{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.12.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceType":"competition","sourceId":154281},{"sourceType":"datasetVersion","sourceId":18956429},{"sourceType":"datasetVersion","sourceId":18229736},{"sourceType":"datasetVersion","sourceId":18839182},{"sourceType":"datasetVersion","sourceId":18757740},{"sourceType":"datasetVersion","sourceId":18715672},{"sourceType":"datasetVersion","sourceId":18673450},{"sourceType":"datasetVersion","sourceId":18716507},{"sourceType":"datasetVersion","sourceId":18706996},{"sourceType":"modelInstanceVersion","sourceId":4533},{"sourceType":"modelInstanceVersion","sourceId":4534}],"dockerImageVersionId":31430,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false},"rsna_optimization":{"official_source_score":0.891,"revision":"v66-v65-parent-legacy-dino-002","source":"pilkwang/rsna-knee-baseline-v1"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Bend the Knee Ensemble\n\nA community pipeline, with one more model added.\n\n## Thank you\n\nThis is built on work other people did first and shared:\n\n- **pilkwang** — twenty trained models that are part of this ensemble, and a\n set of labels read from the reports.\n- **stevenleehans** and **lixin73** — two more sets of labels read from the\n reports, so one reading could be checked against another.\n- **tonylica** — four more trained models that join the ensemble.\n- **marwanmath** — the official RadImageNet ResNet-50 weights.\n- **prvsiyan** — the notebook this was forked from (Apache 2.0). Most of its\n later stages have been removed here.\n- **cf696666** (*fishface*) — for the earliest verified E10/E11 RadImageNet\n machinery, including the four-slot E11 design, and for leaving two findings\n out of the E10 blend.\n- **romantamrazov** — for the fold-rank aggregation idea.\n- **ieshanmeghani** — for isolating the public v15/E10 RadImageNet delta.\n- **sofiaanjenje** — for running and publishing the five trained E11 heads,\n and for the E11 deployment blend used here.\n- **sakhawathossen** and **ranjithragavan07** — for publishing the\n no-extra-pass fold-balanced/smooth DINO aggregation tested here.","metadata":{}},{"cell_type":"markdown","source":"### The added member\n\nThe submission this forks from is a rank mean of twenty **DINOv2** models. Added\nhere is one **DINOv3 ViT-S/16** — self-supervised and pretrained without labels,\nthen fine-tuned on this competition's knee MRI — rank-blended into that\nfamily.\n\nAbove the encoder, each series carries a learned type embedding — plane crossed\nwith fat suppression — added to all of its tokens. The tokens of every series in\na study are then concatenated into one key/value sequence, and twelve learned\nqueries, one per finding, cross-attend over it with multi-head attention. A\nfinding therefore draws evidence from any series in the study at once, rather\nthan from per-series summaries combined afterwards. Each query's output is\nconcatenated with the mean and the max of the per-series CLS embeddings before\nthe classifier. Series a study does not contain are removed by the key-padding\nmask, so nothing is imputed for them.\n\n**RadImageNet** joins the vote in two pinned stages. E10 gives the public v15\nheads a 0.50 rank vote on ten findings while preserving Baker's and Fracture.\nE11 then gives a distinct four-slot, 130 mm RadImageNet family a 0.20 rank\nvote on all twelve findings.\n\nThe audited fold-balanced/smooth DINOv2 reaggregation receives a small\n0.02 rank vote. This preserves 98% of the E10/E11 blend while using the\nindependent aggregation only to resolve close prediction pairs.","metadata":{}},{"cell_type":"code","source":"from __future__ import annotations\nimport re\nimport unicodedata\nTARGETS = ['ACL', 'MCL', 'Medial Meniscus', 'Lateral Meniscus', 'Medial OA', 'Lateral OA', 'PF OA', 'Effusion', 'Synovitis', \"Baker's\", 'Contusion', 'Fracture']\n_PRE = str.maketrans({'ı': 'i', 'İ': 'i', 'I': 'i', 'ß': 'ss', 'đ': 'd', 'Đ': 'd', 'ø': 'o', 'Ø': 'o', 'æ': 'ae', 'Æ': 'ae'})\n\ndef normalize(text: str) -> str:\n if not isinstance(text, str):\n return ''\n text = text.translate(_PRE).lower()\n text = unicodedata.normalize('NFKD', text)\n text = ''.join((ch for ch in text if not unicodedata.combining(ch)))\n text = text.replace('\\xad', '')\n text = re.sub('[_\\\\-/\\\\\\\\]+', ' ', text)\n text = re.sub('[ \\\\t]+', ' ', text)\n return text\n_SENT_SPLIT = re.compile('(?<=[.;!?])\\\\s+|\\\\n+')\n\ndef unwrap(text: str) -> str:\n if not isinstance(text, str):\n return ''\n out = []\n for line in text.split('\\n'):\n s = line.strip()\n if out and out[-1] and (not re.search('[.;:!?>*•]$', out[-1])) and (len(out[-1].split()) >= 4) and s and (not s[:1].isupper()):\n out[-1] = out[-1] + ' ' + s\n else:\n out.append(s)\n return '\\n'.join(out)\n\ndef clauses(text: str):\n norm = normalize(unwrap(text) if FEATURES['unwrap'] else text)\n raw = [c.strip() for c in _SENT_SPLIT.split(norm) if c and c.strip()]\n merged = []\n for i, c in enumerate(raw):\n if c.endswith(':') and len(c.split()) <= 14 and (i + 1 < len(raw)):\n merged.append(c + ' ' + raw[i + 1])\n merged.append(c)\n out = []\n for c in merged:\n out.append(c)\n if len(c.split()) > 25:\n out.extend((p.strip() for p in c.split(',') if len(p.split()) > 2))\n return out\nFEATURES = {'unwrap': True, 'directional_negation': True, 'oa_inherit': True, 'graded_pathology': True, 'synovitis_backoff': True}\n\ndef _rx(*alts: str) -> re.Pattern:\n return re.compile('|'.join(alts))\nPRE_NEG = _rx('\\\\bno\\\\b', '\\\\bnot\\\\b', '\\\\bwithout\\\\b', '\\\\bnegative for\\\\b', '\\\\babsence\\\\b', '\\\\bno evidence\\\\b', '\\\\bfree of\\\\b', '\\\\bnone\\\\b', '\\\\bneither\\\\b', '\\\\bnor\\\\b', '\\\\bsin\\\\b', '\\\\bno hay\\\\b', '\\\\bausencia\\\\b', '\\\\bausentes?\\\\b', '\\\\bno se\\\\b', '\\\\bpas de\\\\b', '\\\\bsans\\\\b', '\\\\baucune?\\\\b', '\\\\bgeen\\\\b', '\\\\bzonder\\\\b', '\\\\bniet\\\\b', '\\\\bkeine?[nmrs]?\\\\b', '\\\\bohne\\\\b', '\\\\bnicht\\\\b', '\\\\bkein\\\\b', '\\\\bnema\\\\b', '\\\\bbez\\\\b', '\\\\bnisu\\\\b', '\\\\bnije\\\\b', '\\\\bδεν\\\\b', '\\\\bχωρις\\\\b', 'ουδεν', '\\\\bουτε\\\\b', '\\\\bбез\\\\b', '\\\\bне\\\\b', 'липсва', '\\\\bняма\\\\b')\nPOST_NEG = _rx('\\\\byok\\\\b', '\\\\byoktur\\\\b', 'izlenmemekte', 'saptanmadi', '\\\\bdegil\\\\b', 'gozlenmemekte', 'mevcut degil', 'eslik etmiyor', '\\\\bizlenmedi\\\\b', 'izlenmemistir', 'saptanmamistir', 'gorulmemistir', '\\\\bnema znakova\\\\b', 'bez znakova')\nNEGATION = _rx(PRE_NEG.pattern, POST_NEG.pattern, '\\\\bunremarkable\\\\b')\nNEG_WINDOW = 90\n\ndef _negated(clause: str, start: int, end: int) -> bool:\n for m in PRE_NEG.finditer(clause):\n if m.end() <= start and start - m.end() <= NEG_WINDOW:\n if not re.search('\\\\b(but|however|ancak|fakat|pero|maar|aber|no i|ali|ωστοσο|αλλα|но)\\\\b', clause[m.end():start]):\n return True\n for m in POST_NEG.finditer(clause):\n if m.start() >= end and m.start() - end <= NEG_WINDOW:\n return True\n return False\nNORMALITY = _rx('\\\\bnormal', '\\\\bintact\\\\b', '\\\\bpreserved\\\\b', '\\\\bwithin normal limits\\\\b', 'limites normales', '\\\\bconservad', '\\\\bintegr', '\\\\bnormales\\\\b', '\\\\bdoga(l|ll)\\\\b', 'korunmus', '\\\\bnormaldir\\\\b', 'olagan', '\\\\buredn', '\\\\bocuvan', '\\\\bodrzan', '\\\\bintakt', '\\\\bprimjeren', '\\\\bodrzanog kontinuiteta', '\\\\bodržan', 'φυσιολογικ', 'ακεραι', 'δεν παρατηρουνται', 'δεν σημειωνονται', 'unauffallig', 'regelrecht', '\\\\bo\\\\.?b\\\\.?\\\\b', 'нормал', 'запазен', 'съхранен', '\\\\bбез особености\\\\b', 'интактн', '\\\\bgaaf\\\\b', '\\\\bnormaal\\\\b')\nNORMAL_PHRASE = _rx('\\\\bsin alteracion', '\\\\bsin cambios\\\\b', '\\\\bsin particularidad', '\\\\bsin hallazgos\\\\b', '\\\\bsin lesion', '\\\\bsin signos de (rotura|lesion)', '\\\\bcontinu[oa]s?\\\\b', '\\\\bcontinuidad conservada\\\\b', '\\\\bno abnormalit', '\\\\bno significant abnormalit', '\\\\bunremarkable\\\\b', '\\\\bno evidence of (tear|injury|abnormalit)', '\\\\bohne auffalligkeit', '\\\\bkein nachweis\\\\b', '\\\\bohne befund\\\\b', '\\\\bgeen afwijking', '\\\\bzonder afwijking', '\\\\bsans anomalie', \"\\\\bpas d[e']anomalie\", '\\\\bbez osobitosti\\\\b', '\\\\bbez znakova (rupture|lezije)\\\\b', '\\\\bbez patoloskih\\\\b', 'χωρις αλλοιωσ', 'χωρις παθολογ', 'δεν παρατηρουνται (αξιολογα|παθολογ)', '\\\\bбез особености\\\\b', '\\\\bбез патологич', '\\\\bбез данни за\\\\b', '\\\\bozel bir ozellik yok', '\\\\bpatolojik bulgu (yok|izlenmemis)')\nUNCERTAIN = _rx('\\\\bpossible\\\\b', '\\\\bprobable\\\\b', '\\\\bsuspicious\\\\b', '\\\\bsuspected?\\\\b', 'cannot (be )?exclude', '\\\\bmay\\\\b', '\\\\bquestionable\\\\b', '\\\\bequivocal\\\\b', '\\\\br/o\\\\b', '\\\\bdd\\\\b', '\\\\blikely\\\\b', '\\\\bsuggest', '\\\\bcompatible with\\\\b', '\\\\bposible\\\\b', 'sin criterios categoricos', '\\\\bdudos', '\\\\bsugier', '\\\\bmuhtemel\\\\b', '\\\\bolasi\\\\b', '\\\\bsupheli\\\\b', '\\\\bizlenim', '\\\\bdusundur', '\\\\bmoguce\\\\b', '\\\\bvjerojatno\\\\b', '\\\\bsumnja\\\\b', '\\\\bmoze odgovarati\\\\b', 'πιθαν', 'υποπτ', '\\\\bmoglich', '\\\\bverdachtig', '\\\\bfraglich', '\\\\bv\\\\.?a\\\\.?\\\\b', '\\\\bwohl\\\\b', '\\\\bвъзможно\\\\b', '\\\\bвероятно\\\\b', 'суспект', '\\\\bmogelijk\\\\b', '\\\\bverdacht\\\\b')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:02.259644Z","iopub.execute_input":"2026-08-17T17:07:02.26058Z","iopub.status.idle":"2026-08-17T17:07:02.292133Z","shell.execute_reply.started":"2026-08-17T17:07:02.260537Z","shell.execute_reply":"2026-08-17T17:07:02.291342Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"TEAR = _rx('\\\\btear', '\\\\btorn\\\\b', '\\\\brupture', '\\\\bdisruption\\\\b', 'discontinuit', '\\\\bavuls', '\\\\bmacerat', '\\\\bbuckethandle\\\\b', 'bucket handle', '\\\\brotura\\\\b', '\\\\broturas\\\\b', '\\\\bruptura', '\\\\bdesgarro', '\\\\broto\\\\b', '\\\\bdechirure', '\\\\bdechire', '\\\\bscheur', '\\\\bruptuur', 'gescheurd', '\\\\briss\\\\b', 'einriss', '\\\\bruptur', 'zerreiss', '\\\\blasion', '\\\\bausriss', '\\\\byirtik', '\\\\byirtig', '\\\\bkopma\\\\b', 'butunluk kaybi', '\\\\brupturu\\\\b', 'devamsizlik', '\\\\brupture\\\\b', '\\\\bdevamliligi secilememis', '\\\\bpuknuce', '\\\\bprekid\\\\b', '\\\\bpukotin', '\\\\bruptur', 'ρηξη', 'ρηξις', 'ρηγμα', 'ασυνεχεια', 'руптура', 'разкъсв', 'разрив', 'скъсв', '\\\\bлезия\\\\b')\nDEGEN = _rx('degenerat', '\\\\bmucoid\\\\b', '\\\\bmyxoid\\\\b', '\\\\bfray', '\\\\bfissur', 'dejeneratif', '\\\\bmukoid\\\\b', 'degenerativn', 'εκφυλ', 'дегенерат', '\\\\bμυξοειδ', '\\\\bμυξωδ', '\\\\bmeniskopat', '\\\\bmeniscopath', '\\\\bmuco ?ide\\\\b', 'aufgefasert', '\\\\bdejenerasyon\\\\b')\nINJURY = _rx('\\\\binjur', '\\\\bsprain', '\\\\blesion', '\\\\blasion', '\\\\bedema\\\\b', '\\\\boedema\\\\b', '\\\\bodem\\\\b', '\\\\bedem\\\\b', '\\\\bοιδημα', '\\\\bодем', '\\\\bедем', '\\\\bstrain\\\\b', '\\\\bhigh signal\\\\b', '\\\\bsignal alteration\\\\b', '\\\\bhiperintens', '\\\\bhyperintens', 'aumento de senal', 'alteracion de senal', 'cambio de senal', '\\\\bsignalanhebung', '\\\\bsignalalteration', 'verhoogd signaal', 'sinyal artis', 'αυξημενο σημα', 'повишен сигнал', '\\\\besguince\\\\b', '\\\\bthicken', '\\\\bzadebljanje\\\\b', '\\\\bverdikking\\\\b', '\\\\bdistenzij', '\\\\blaksite\\\\b', '\\\\blaxity\\\\b', '\\\\bpartial\\\\b', '\\\\bparcijaln', '\\\\bparcial', '\\\\bpartiel', '\\\\bpartiell')\n_GRADE_RX = re.compile('(?:grade|grad|grado|grau|derece|stupnja|stupanj|βαθμ|степен|icrs|outerbridge)[\\\\s:]*(?:grade\\\\s*)?([1-4]|iv|iii|ii|i)\\\\b')\n_ROMAN = {'i': 1, 'ii': 2, 'iii': 3, 'iv': 4}\n\ndef _grade_of(clause: str):\n best = None\n for m in _GRADE_RX.finditer(clause):\n v = m.group(1)\n n = _ROMAN.get(v, None) if not v.isdigit() else int(v)\n if n is not None and (best is None or n > best):\n best = n\n return best\nANAT = {'ACL': _rx('anterior cruciate', '\\\\bacl\\\\b', 'cruzado anterior', '\\\\blca\\\\b', 'croise anterieur', 'voorste kruisband', '\\\\bvkb\\\\b', 'vorderes kreuzband', 'vorderen kreuzband', 'vordere kreuzband', 'on capraz', '\\\\bocb\\\\b', 'anterior capraz', 'prednji krizni', 'prednjeg krizn', 'προσθι[οα][^ ]* χιαστ', 'προσθιου χιαστου', 'χιαστο[^ ]* συνδεσμ', '\\\\bχιαστ\\\\w*', 'предна кръстна', 'предната кръстна', 'предна кръста', 'cruciate ligaments', 'ligamentos cruzados', 'ligaments croises', 'kruisbanden', 'kreuzbander', 'capraz baglar', 'krizn[a-z]* ligament[a-z]*', 'χιαστοι συνδεσμ', 'χιαστων συνδεσμ', 'кръстните връзки', 'кръстни връзки'), 'MCL': _rx('medial collateral', '\\\\bmcl\\\\b', 'tibial collateral', 'colateral medial', 'colateral interno', '\\\\blcm\\\\b', 'collateral medial', 'collateral interne', 'mediale collaterale', 'binnenband', '\\\\b(mediale|laterale) banden\\\\b', '\\\\bcollaterale banden\\\\b', 'innenband', 'mediales? kollateral', '\\\\bic yan bag', 'medial kollateral', '\\\\biyb\\\\b', 'medyal kollateral', 'medijalni kolateraln', 'medijalnog kolateraln', 'εσω πλαγι', 'εσωτερικο πλαγι', '\\\\bπλαγι\\\\w* συνδεσμ', '\\\\bπλαγιοι\\\\b', 'медиален колатерал', 'вътрешна странична', '\\\\bколатерал\\\\w*', '\\\\bcolaterales\\\\b', '\\\\bcollateraux\\\\b', '\\\\bcollateralen\\\\b', '\\\\bkolateralni\\\\b', 'collateral ligaments', 'ligamentos colaterales', 'ligaments collateraux', 'collaterale banden', 'kollateralbander', 'seitenbander', 'yan baglar', 'kolateraln[a-z]* ligament[a-z]*', 'πλαγιοι συνδεσμ', 'πλαγιων συνδεσμ', 'колатерални връзки', 'страничните връзки'), 'Medial Meniscus': _rx('medial meniscus', '\\\\bmm\\\\b(?= tear)', 'medial menisc', 'menisco medial', 'menisco interno', 'menisque medial', 'menisque interne', 'mediale meniscus', 'binnenmeniscus', 'innenmeniskus', 'medialen? meniskus', 'innenmeniskushinterhorn', 'medyal menisk', '\\\\bic menisk', 'medijalni meniskus', 'medijalnog meniskusa', 'medijalnom meniskusu', 'medijaln\\\\w* menisk\\\\w*', '\\\\bmedijalnog meniska\\\\b', 'medijalni menisk', 'εσω μηνισκ', 'μηνισκ[^ ]* του εσω', 'εσω διαμερισμα[^.]{0,40}μηνισκ', 'медиалния менискус', 'медиален менискус', 'вътрешния менискус', 'oba meniska', 'both menisci', 'ambos meniscos', 'beide menisci', 'her iki menisku', 'amfoteroi\\\\w* mhnisk', 'αμφοτερ\\\\w* μηνισκ', 'двата менискуса', 'medial (and|&) lateral menisc'), 'Lateral Meniscus': _rx('lateral meniscus', 'lateral menisc', 'menisco lateral', 'menisco externo', 'menisque lateral', 'menisque externe', 'laterale meniscus', 'buitenmeniscus', 'aussenmeniskus', 'lateralen? meniskus', 'aussenmeniskushinterhorn', 'lateral menisk', '\\\\bdis menisk', 'lateralni meniskus', 'lateralnog meniskusa', 'lateralnom meniskusu', 'lateraln\\\\w* menisk\\\\w*', '\\\\blateralnog meniska\\\\b', 'εξω μηνισκ', 'μηνισκ[^ ]* του εξω', 'εξω διαμερισμα[^.]{0,40}μηνισκ', 'латералния менискус', 'латерален менискус', 'външния менискус', 'oba meniska', 'both menisci', 'ambos meniscos', 'beide menisci', 'her iki menisku', 'αμφοτερ\\\\w* μηνισκ', 'двата менискуса', 'medial (and|&) lateral menisc')}\nOA_EVIDENCE = _rx('osteoarthrit', '\\\\barthros', '\\\\bgonarthros', '\\\\bosteoarthros', 'chondropath', 'chondromalac', 'condropat', 'condromalac', '\\\\bchondros', '\\\\bchondrosis\\\\b', 'chondral (loss|defect|ulcer|thinning|injury|fissur|wear)', 'cartilage (loss|thinning|defect|fissur|wear|damage|heterogeneity|irregularit)', '(loss|thinning|fissur|defect|ulcer|erosion|denudation) of[^.]{0,20}cartilage', 'articular cartilage[^.]{0,30}(loss|thin|fissur|defect|erosion|wear|irregular)', 'osteophyt', 'osteofit', 'osteofyt', 'osteofito', 'osteophyten', 'spurring', 'joint space narrowing', 'pinzamiento articular', 'reduced joint space', 'kikirdak kayb', 'kikirdak incelme', 'kondropati', 'kondral', 'kikirdak dejener', 'eklem aralig\\\\w* daral', 'eklem mesafesi daral', 'kikirdak kalinlig\\\\w* azal', 'kraakbeen', 'gonartrose', 'artrose', '\\\\bknorpel', 'arthrose', 'gonarthrose', 'hrskavic', 'hondromalac', 'artroz', 'osteoartrit', 'artrotsk', 'artrotick', '\\\\boa promjen', '\\\\boa\\\\b', 'degenerativne promjene hrskav', 'χονδρ[^ ]*παθ', 'αρθριτ', 'αρθρωσ', 'οστεοφυτ', 'χονδρομαλακ', 'αρθρικου χονδρου', 'εξαλειψη του αρθρικου χονδρου', 'διαβρωση του αρθρικου χονδρ', 'λεπτυνση[^.]{0,30}χονδρ', 'φθορα[^.]{0,20}χονδρ', 'артроз', 'хондропат', 'остеофит', 'хрущял[^.]{0,40}(изтън|увред|дефект|липс)', 'изтъняване[^.]{0,30}хрущял', 'хондромалац', 'ulcera[s]? condral', 'cartilago[^.]{0,25}(perdida|adelgaz)', 'icrs grade', 'icrs\\\\b', 'outerbridge', '\\\\bdenudation\\\\b', 'denudacij', 'erozivne promjene', '\\\\berosion of[^.]{0,20}cartilage', 'kraakbeenlijden', 'kraakbeenverlies')\nTF_SITE = _rx('compartment', 'compartimento', 'compartiment', 'kompartman', 'kompartiment', 'kompartment', 'odjelj', 'διαμερισμα', 'компартм', '\\\\bотдел', 'femorotibial', 'tibiofemoral', 'femoro tibial', 'femorotibiaal', 'femorotibijaln', 'феморотибиал', '\\\\bft zglob', 'tibiofemoraln', 'condyle', 'condilo', 'kondyl', 'kondil', 'condyl', 'κονδυλ', 'кондил', '\\\\bplateau', '\\\\bplato\\\\b', 'platillo', 'meseta', 'плато', 'tibiaplateau', 'tibijaln\\\\w* plato', 'tibyal plato', 'tibia plato', 'κνημιαι', 'μηριαι', 'weightbearing', 'weightbaring', 'zona de carga', 'dragende deel', 'agirlik tasiyan', '\\\\bfemur\\\\b', '\\\\btibia\\\\b', '\\\\bfemoral\\\\b', '\\\\btibial\\\\b', '\\\\bfemura\\\\b', '\\\\btibije\\\\b', '\\\\bmesarthrio\\\\b', 'μεσαρθριο')\nPF_SITE = _rx('patellofemoral', 'femoropatellar', 'femoropatelar', 'patelofemoral', 'retropatellar', 'retrorotulian', 'trochlea', 'troclea', 'troklea', 'trochlear', 'trohlej', 'τροχιλ', '\\\\bpatella', '\\\\bpatellar', 'rotulian', '\\\\brotula\\\\b', '\\\\bpatele\\\\b', 'patellofemoraal', 'femoropatellair', 'επιγονατιδ', 'μηροεπιγονατιδ', 'пател', 'феморопател', 'anterior compartment', 'compartimento anterior', 'prednj\\\\w* odjeljk', '\\\\bfp zglob', '\\\\bpf zglob', '\\\\bfaset', '\\\\bfacet', 'patellofemoraln')\nSIDE_MEDIAL = _rx('\\\\bmedial\\\\w*', '\\\\bmedyal\\\\w*', '\\\\bmedijaln\\\\w*', '\\\\bmediaal\\\\w*', '\\\\bmediale\\\\w*', '\\\\binterno\\\\b', '\\\\binterna\\\\b', '\\\\binternos\\\\b', '\\\\binterne\\\\b', '\\\\binnen\\\\w*', '\\\\bic\\\\b', '\\\\bunutarnj\\\\w*', '\\\\bεσω\\\\w*', '\\\\bεσωτερικ\\\\w*', '\\\\bмедиал\\\\w*', '\\\\bвътреш\\\\w*', '\\\\bbinnen\\\\w*', '\\\\bmediaal\\\\b', '\\\\bmediales?\\\\b')\nSIDE_LATERAL = _rx('\\\\blateral\\\\w*', '\\\\bexterno\\\\b', '\\\\bexterna\\\\b', '\\\\bexternos\\\\b', '\\\\bexterne\\\\b', '\\\\bdis\\\\b', '\\\\blateraln\\\\w*', '\\\\baussen\\\\w*', '\\\\bbuiten\\\\w*', '\\\\bεξω\\\\w*', '\\\\bεξωτερικ\\\\w*', '\\\\bлатерал\\\\w*', '\\\\bвъншн\\\\w*', '\\\\bvanjsk\\\\w*')\nSIDE_ANTERIOR = _rx('\\\\banterior\\\\w*', '\\\\bant\\\\b', '\\\\bon\\\\b', '\\\\bprednj\\\\w*', '\\\\bvorder\\\\w*', '\\\\bvoorste\\\\b', '\\\\bπροσθι\\\\w*', '\\\\bпредн\\\\w*', '\\\\banteriyor\\\\w*', '\\\\bavant\\\\b', '\\\\banterieur\\\\w*')\nGLOBAL_OA = _rx('tri ?compartment', 'all three compartment', 'global(ised)? (oa|osteoarthrit)', '\\\\bgonarthros', '\\\\bgonartros', '\\\\bgonarthrose', '\\\\bgonartrose', 'gonartro', 'goanrtrot', 'gonartrot', 'osteoarthritis of the knee', 'artrosis (de |)(la )?rodilla', 'knee osteoarthrit', '\\\\bdiz osteoartrit', '\\\\bgonartroz', 'artroza koljena', 'οστεοαρθριτιδα', 'αρθριτιδα του γονατος', 'εκφυλιστικη οστεοαρθριτ', 'артроза на колянната', 'гонартроз', 'degenerative joint disease', '\\\\bdjd\\\\b', 'three compartments', 'compartmens', 'compartments')\nDIRECT = {'Effusion': _rx('\\\\beffusion', 'joint fluid', 'intra ?articular fluid', '\\\\bhydrops\\\\b', '\\\\bhemarthros', '\\\\bhaemarthros', 'derrame articular', '\\\\bderrame\\\\b', 'liquido articular', 'hemartrosis', 'epanchement', 'gewrichtsvocht', '\\\\bvocht\\\\b', 'gewrichtseffusie', 'opzetting van suprapatell', 'gelenkerguss', '\\\\berguss\\\\b', 'gelenksergu', 'gelenksflussigkeit', 'eklem\\\\w* ic\\\\w* sivi', 'efuzyon', 'eklem sivisi', 'eklem mesafesinde sivi', 'sivi (miktari|artisi|birikimi)', 'sivi artis', '\\\\bsivi\\\\b[^.]{0,25}artmis', '\\\\bizljev', '\\\\bizliv', 'zglobn[^ ]* tekucin', '\\\\bhidrops\\\\b', 'αρθρικ[^ ]* υγρ', 'υγρου ενδαρθρικα', 'ενδαρθρικ[^ ]* υγρ', 'ποσοτητα υγρου', 'ενδαρθρικ', 'αρθρικη συλλογη', 'υγρο στην αρθρωση', 'υγρου στην αρθρωση', 'συλλογη υγρου', 'ενθαρθρικ', 'ставен излив', 'излив', 'ставна течност', 'синовиална течност'), 'Synovitis': _rx('synovit', 'sinovit', 'synovial (thickening|proliferation|hypertroph)', 'thicken\\\\w* synovial', 'hypertroph\\\\w* of the synovium', 'synoviale? (verdikking|proliferatie)', 'verdikkingen van (het )?synovium', 'synovialitis', 'synovialis(verdickung|proliferation)', 'reizsynovial', 'sinovijalitis', 'sinovitis', 'zadebljanje sinovij', 'proliferacij\\\\w* sinovij', 'sinovijaln\\\\w* proliferacij', 'υμενιτιδα', 'συνοβιτιδα', 'υμενικ[^ ]* υπερτροφ', 'αρθρικου υμεν', 'παχυνση[^.]{0,20}υμεν', 'υμενα', 'синовит', 'синовиал[^ ]* (задебел|пролифер)', '\\\\bpannus\\\\b', '\\\\bhoffit', 'sinovyal\\\\w* (kalinlas|proliferas)', 'sinovyal hipertrof', '\\\\bartrit\\\\b', '\\\\barthritis\\\\b'), \"Baker's\": _rx('baker', 'popliteal cyst', 'quiste popliteo', 'quistes popliteos', 'kyste poplite', 'popliteale? cyst', 'poplitealzyste', 'bakerzyste', 'popliteal kist', '\\\\bbakerova\\\\b', 'poplitealn[^ ]* cist', 'popliteal\\\\w* cist', 'κυστη baker', 'πολυχωρη συνοβιακη κυστη', 'κυστη του baker', 'συνοβιακη κυστη', 'κυστη τυπου baker', 'киста на бейкър', 'бейкърова киста', 'поплитеална киста', 'бекеров', 'gastrocnemio ?semimembranos', 'gastrocnemius semimembranosus burs'), 'Contusion': _rx('\\\\bcontusion', 'bone bruise', 'bone marrow (o?edema|contusion)', 'marrow o?edema', '\\\\bkontuz', 'medular bone o?edema', 'osseous contusion', 'contusion osea', 'edema oseo', 'edema de medula osea', 'contusiones oseas', 'oedeme osseux', 'contusion osseuse', 'botcontusie', 'botoedeem', 'beenmergoedeem', 'botmergoedeem', 'knochenmarkodem', 'knochenodem', 'knochenmarksodem', 'kontusion', 'kemik kontuzyonu', 'kemik iligi odemi', 'kemik odemi', 'kemik iliginde odem', 'kontuzyonel kemik', 'kemik iligi odemleri', 'kostani edem', 'edem kosti', 'kontuzij', 'kostane srzi[^.]{0,20}edem', 'οστεομυελικ[^ ]* οιδημα', 'οστικο οιδημα', 'μυελικο οιδημα', 'οστικο μωλωπ', 'костномозъчен едем', 'костен едем', 'контузионен', 'костно мозъчен едем'), 'Fracture': _rx('\\\\bfractur', '\\\\bfract\\\\b', '\\\\bfractura', '\\\\bfracturas\\\\b', '\\\\bfractuur', '\\\\bbreuk\\\\b', '\\\\bfraktur', '\\\\bbruch\\\\b', '\\\\bkirik\\\\b', '\\\\bkirigi\\\\b', '\\\\bkiri[kg]\\\\w*', '\\\\bprijelom', 'impresijsk[^ ]* fraktur', 'impaktcij', 'καταγμα', 'καταγματ', 'фрактур', 'счупван', 'фисур', 'insufficiency fracture', 'stress fracture', 'avulsion fracture', 'subchondral fracture', 'subkondral kiri', 'impaction (fracture|injury)', 'osteochondral (fracture|impaction)', '\\\\bsegond\\\\b', 'impactiefractuur', 'subchondrale impression', 'subchondraler? impress')}\nDECOY = {'Fracture': _rx('microfractur', '\\\\bfracture (risk|prophyla)'), \"Baker's\": _rx('meniscal cyst', 'quiste meniscal', 'parameniscal')}\nPAIRED = {'ACL', 'MCL', 'Medial Meniscus', 'Lateral Meniscus'}\nOA_TARGETS = ['Medial OA', 'Lateral OA', 'PF OA']\nPLURAL_MENISCI = _rx('\\\\bmenisci\\\\b', '\\\\bmeniscos\\\\b', '\\\\bmenisques\\\\b', '\\\\bmenisken\\\\b', '\\\\bmeniskusi\\\\b', '\\\\bmenisk\\\\w*ler\\\\b', '\\\\bμηνισκοι\\\\b', '\\\\bμηνισκων\\\\b', '\\\\bменискуси\\\\b', '\\\\bменискусите\\\\b', '\\\\bmenisci\\\\w*\\\\b')\nANY_SIDE = _rx(SIDE_MEDIAL.pattern, SIDE_LATERAL.pattern)\nSTEM_MENISCUS = _rx('menisc\\\\w*', 'menisk\\\\w*', 'μηνισκ\\\\w*', 'мениск\\\\w*')\nSTEM_CRUCIATE = _rx('cruciate', 'cruzado', 'croise', 'kruisband', 'kreuzband', 'capraz bag\\\\w*', 'krizn\\\\w*', 'χιαστ\\\\w*', 'кръстн\\\\w*', '\\\\bacl\\\\b', '\\\\blca\\\\b', '\\\\bvkb\\\\b', '\\\\bocb\\\\b', '\\\\bacb\\\\b')\nSTEM_COLLATERAL = _rx('collateral\\\\w*', 'colateral\\\\w*', 'kollateral\\\\w*', 'collaterale\\\\w*', 'kolateraln\\\\w*', 'yan bag\\\\w*', 'πλαγι\\\\w*', 'колатерал\\\\w*', 'странич\\\\w*', 'innenband\\\\w*', 'binnenband\\\\w*', '\\\\bmcl\\\\b', '\\\\blcm\\\\b', '\\\\biyb\\\\b')\nSTEM_FRACTURE = _rx('fractur\\\\w*', 'fraktur\\\\w*', 'fractuur\\\\w*', '\\\\bfract\\\\b', 'kiri[kgğ]\\\\w*', 'prijelom\\\\w*', 'lom kosti', '\\\\bbreuk\\\\w*', '\\\\bbruch\\\\w*', 'καταγμα\\\\w*', 'καταγματ\\\\w*', 'фрактур\\\\w*', 'счупван\\\\w*', 'fisur\\\\w* (osea|oseas|kost)', 'fissur\\\\w* kost')\nPOSTERIOR_ONLY = _rx('\\\\bpcl\\\\b', '\\\\blcp\\\\b', '\\\\bhkb\\\\b', '\\\\bacb\\\\b', 'posterior cruciate', 'cruzado posterior', 'croise posterieur', 'achterste kruisband', 'hinteres kreuzband', 'arka capraz', 'straznji krizn', 'οπισθι[οα]\\\\w* χιαστ', 'задна кръстн', 'задната кръстн')\nLATERAL_COLL_ONLY = _rx('\\\\blcl\\\\b', '\\\\bfcl\\\\b', 'lateral collateral', 'fibular collateral', 'colateral lateral', 'colateral externo', 'buitenband', 'aussenband', 'dis yan bag', 'lateralni kolateraln', 'εξω πλαγι', 'латерален колатерал')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:02.383775Z","iopub.execute_input":"2026-08-17T17:07:02.384144Z","iopub.status.idle":"2026-08-17T17:07:02.422624Z","shell.execute_reply.started":"2026-08-17T17:07:02.384118Z","shell.execute_reply":"2026-08-17T17:07:02.422003Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def _near(clause: str, stem_rx: re.Pattern, qual_rx: re.Pattern, window: int=55):\n for m in stem_rx.finditer(clause):\n lo = max(0, m.start() - window)\n hi = min(len(clause), m.end() + window)\n if qual_rx.search(clause[lo:hi]):\n return True\n return False\nSTEM_RULES = {'ACL': (STEM_CRUCIATE, SIDE_ANTERIOR), 'MCL': (STEM_COLLATERAL, SIDE_MEDIAL), 'Medial Meniscus': (STEM_MENISCUS, SIDE_MEDIAL), 'Lateral Meniscus': (STEM_MENISCUS, SIDE_LATERAL)}\n\nclass _Matcher:\n\n def __init__(self, phrase_rx, stem=None, side=None, window=55):\n self.phrase_rx = phrase_rx\n self.stem = stem\n self.side = side\n self.window = window\n\n def search(self, clause):\n m = self.phrase_rx.search(clause)\n if m is not None:\n return m\n if self.stem is not None and _near(clause, self.stem, self.side, self.window):\n return self.stem.search(clause)\n return None\nANAT_MATCH = {t: _Matcher(ANAT[t], *STEM_RULES[t]) for t in PAIRED}\nDIRECT_MATCH = {t: _Matcher(_rx(rx.pattern, STEM_FRACTURE.pattern) if t == 'Fracture' else rx) for t, rx in DIRECT.items()}\nSEV_LOW = _rx('\\\\bsmall\\\\b', '\\\\bminimal\\\\b', '\\\\btrace\\\\b', '\\\\bmild\\\\b', '\\\\bslight\\\\b', '\\\\btiny\\\\b', '\\\\bscant\\\\b', '\\\\bdiscrete\\\\b', '\\\\blow ?grade\\\\b', '\\\\bincipient\\\\b', '\\\\bleve\\\\b', '\\\\bminim', '\\\\bpeque', '\\\\bfina\\\\b', '\\\\bfino\\\\b', '\\\\bligero\\\\b', '\\\\bescaso\\\\b', '\\\\bdiscreto\\\\b', '\\\\bhafif\\\\b', '\\\\baz miktarda\\\\b', '\\\\bsilik\\\\b', '\\\\bmanj\\\\w*', '\\\\bblago\\\\b', '\\\\bdiskretn', '\\\\bmalo\\\\b', '\\\\bpocetn', '\\\\bgering', '\\\\bdiskret', '\\\\bkleine?r?\\\\b', '\\\\bwenig\\\\b', '\\\\bzarte?\\\\b', '\\\\bbeperkte?\\\\b', '\\\\bgeringe\\\\b', '\\\\bweinig\\\\b', '\\\\blichte?\\\\b', '\\\\blicht\\\\b', '\\\\bηπι', '\\\\bμικρ', '\\\\bελαχιστ', '\\\\bαρχομεν', '\\\\bминимал', '\\\\bлек', '\\\\bмалк', '\\\\bнеголям')\nSEV_HIGH = _rx('\\\\blarge\\\\b', '\\\\bmarked\\\\b', '\\\\bmassive\\\\b', '\\\\bsevere\\\\b', '\\\\bextensive\\\\b', '\\\\bmoderate\\\\b', '\\\\bgross\\\\b', '\\\\bsignificant\\\\b', '\\\\babundant\\\\b', '\\\\btense\\\\b', '\\\\bcomplete\\\\b', '\\\\bfull ?thickness\\\\b', '\\\\bhigh ?grade\\\\b', '\\\\badvanced\\\\b', '\\\\bmoderad', '\\\\bimportante\\\\b', '\\\\bsevera?\\\\b', '\\\\bmarcad', '\\\\bcuantios', '\\\\bespesor total\\\\b', '\\\\bcompleta?\\\\b', '\\\\bbelirgin\\\\b', '\\\\byaygin\\\\b', '\\\\bileri\\\\b', '\\\\bciddi\\\\b', '\\\\bbol\\\\b', '\\\\bkomplet', '\\\\bopsezan\\\\b', '\\\\bveliki\\\\b', '\\\\bizrazit', '\\\\bznacajn', '\\\\bumjeren', '\\\\buznapredoval', '\\\\bpotpun', '\\\\bkompleksn', '\\\\bausgepragt', '\\\\bdeutlich', '\\\\bmassiv', '\\\\bmassig', '\\\\bgross', '\\\\buitgebreid', '\\\\bgevorderd', '\\\\bveel\\\\b', '\\\\bmatige?\\\\b', '\\\\bvolledig', '\\\\bμετρι', '\\\\bμεγαλ', '\\\\bεκτεταμεν', '\\\\bευμεγεθ', '\\\\bσοβαρ', '\\\\bπληρη', '\\\\bголям', '\\\\bизразен', '\\\\bзначим', '\\\\bумерен', '\\\\bобилен', '\\\\bпълн')\nGRADE_HIGH = re.compile('grade?[ao]?\\\\s*(3|4|iii|iv)\\\\b|icrs grade (iii|iv|3|4)|stupnja iv|stupnja iii|\\\\bgrado (3|4)\\\\b|\\\\bgrad (3|4)\\\\b|\\\\bgrade (3|4)\\\\b')\nDEGENERATIVE_MARROW = _rx('subchondral', 'subcondral', 'subkondral', 'supkondraln', 'subchondraln', 'υποχονδρι', 'υπαρθρικ', 'субхондрал', 'subchondrale?', 'subartikuler', '\\\\bcyst', '\\\\bquist', '\\\\bzyste\\\\b', '\\\\bcistic', 'reactive', 'reactivo', 'degenerative', 'degenerativ', 'reaktiv', '\\\\bcisti\\\\b')\nTRAUMA = _rx('\\\\bbruise\\\\b', '\\\\bcontusion', '\\\\bkontuz', '\\\\btrauma', '\\\\bimpaction\\\\b', '\\\\bpivot shift\\\\b', '\\\\bkissing\\\\b', '\\\\bacute\\\\b', '\\\\bagudo\\\\b', '\\\\bakut', '\\\\bpivot kaymasi\\\\b', '\\\\bcontusion osseuse\\\\b', '\\\\bbone bruise\\\\b', '\\\\bbotcontusie\\\\b', '\\\\bконтузион', '\\\\bμωλωπ', '\\\\bkontuzij', '\\\\bimpaktcij', '\\\\bimpakcij', '\\\\bfall\\\\b', '\\\\binjury\\\\b', '\\\\bimpression\\\\b')\nSYNOVIAL_PROXY = _rx('bursit', 'burzit', '\\\\bbursa\\\\b[^.]{0,30}(fluid|distend|sivi|tekucin|opzetting)', 'suprapatellar (bursitis|effusion|recess)', 'suprapatellar bursa', 'suprapatellar bursada', 'suprapatelarno', 'suprapatellaire recessus', 'hoffa', 'hoffit', 'plica', 'plika', 'πλικα', 'fat pad[^.]{0,20}(edema|oedema)', 'kapsul', 'capsul', 'καψ', 'капсул', '\\\\bpannus\\\\b', '\\\\bsinov', '\\\\bsynov')\n\ndef _polarity(clause: str, span=None) -> str:\n if UNCERTAIN.search(clause):\n return 'uncertain'\n if span is None or not FEATURES['directional_negation']:\n if NEGATION.search(clause):\n return 'negative'\n elif _negated(clause, span[0], span[1]):\n return 'negative'\n if NORMALITY.search(clause):\n if TEAR.search(clause) or GRADE_HIGH.search(clause):\n return 'positive'\n return 'negative'\n return 'positive'\n\ndef _severity(clause: str) -> float:\n high = SEV_HIGH.search(clause) is not None\n low = SEV_LOW.search(clause) is not None\n if high and (not low):\n return 1.0\n if low and (not high):\n return 0.45\n if high and low:\n return 0.8\n return 0.75\n\ndef _grade(n_pos, n_neg, n_unc, best):\n if n_pos or n_unc:\n score = min(0.97, 0.5 + 0.45 * best + 0.015 * min(n_pos, 3))\n conf = min(1.0, 0.55 + 0.15 * n_pos)\n elif n_neg:\n score = max(0.04, 0.2 - 0.04 * n_neg)\n conf = min(0.9, 0.45 + 0.12 * n_neg)\n else:\n score, conf = (0.28, 0.05)\n return (score, conf)\n\ndef _paired_weight(clause: str, meniscus: bool) -> float:\n g = _grade_of(clause) if FEATURES['graded_pathology'] else None\n tear = TEAR.search(clause) is not None\n if meniscus:\n if tear:\n base = 1.0\n elif g is not None:\n base = 0.95 if g >= 3 else 0.3\n elif DEGEN.search(clause):\n base = 0.35\n else:\n base = 0.45\n elif tear:\n base = 1.0\n elif g is not None:\n base = 0.85 if g >= 2 else 0.3\n elif DEGEN.search(clause):\n base = 0.4\n else:\n base = 0.55\n if SEV_HIGH.search(clause) and (not SEV_LOW.search(clause)):\n base = min(1.0, base * 1.2)\n elif SEV_LOW.search(clause) and (not SEV_HIGH.search(clause)):\n base *= 0.7\n return base\n\ndef _score_paired(cls, tgt):\n anat_rx = ANAT_MATCH[tgt]\n path_rx = _rx(TEAR.pattern, DEGEN.pattern, INJURY.pattern)\n meniscus = 'Meniscus' in tgt\n n_pos = n_neg = n_unc = 0\n best = 0.0\n for c in cls:\n hit = anat_rx.search(c)\n if hit is None and meniscus and PLURAL_MENISCI.search(c) and (not ANY_SIDE.search(c)):\n hit = PLURAL_MENISCI.search(c)\n if hit is None:\n continue\n pm = path_rx.search(c)\n if pm is None and _grade_of(c) is None:\n if NORMAL_PHRASE.search(c) or (NORMALITY.search(c) and (not NEGATION.search(c))):\n n_neg += 1\n continue\n span = (pm.start(), pm.end()) if pm is not None else None\n pol = _polarity(c, span)\n if pol == 'positive':\n n_pos += 1\n best = max(best, _paired_weight(c, meniscus))\n elif pol == 'negative':\n n_neg += 1\n else:\n n_unc += 1\n best = max(best, 0.45 * _paired_weight(c, meniscus))\n s, cf = _grade(n_pos, n_neg, n_unc, best)\n return (s, cf, n_pos, n_neg)\n\ndef _score_clauses(cls, anat_rx, path_rx=None, decoy_rx=None, context_penalty=None, context_bonus=None):\n n_pos = n_neg = n_unc = 0\n best = 0.0\n for c in cls:\n m = anat_rx.search(c)\n if not m:\n continue\n if decoy_rx is not None and decoy_rx.search(c):\n continue\n if path_rx is not None and (not path_rx.search(c)):\n if NORMAL_PHRASE.search(c) or (NORMALITY.search(c) and (not NEGATION.search(c))):\n n_neg += 1\n continue\n pol = _polarity(c, (m.start(), m.end()))\n if pol == 'positive':\n n_pos += 1\n w = _severity(c)\n if context_penalty is not None and context_penalty.search(c):\n w *= 0.45\n if context_bonus is not None and context_bonus.search(c):\n w = min(1.0, w * 1.35)\n best = max(best, w)\n elif pol == 'negative':\n n_neg += 1\n else:\n n_unc += 1\n best = max(best, 0.3)\n s, c = _grade(n_pos, n_neg, n_unc, best)\n return (s, c, n_pos, n_neg)\n\ndef _score_oa(cls):\n acc = {t: {'pos': 0, 'neg': 0, 'unc': 0, 'best': 0.0} for t in OA_TARGETS}\n g_pos, g_neg, g_best = (0, 0, 0.0)\n for c in cls:\n m = OA_EVIDENCE.search(c)\n if not m:\n continue\n pol = _polarity(c, (m.start(), m.end()))\n sev = _severity(c)\n tf_med = _near(c, TF_SITE, SIDE_MEDIAL, 45)\n tf_lat = _near(c, TF_SITE, SIDE_LATERAL, 45)\n pf = PF_SITE.search(c) is not None\n hits = []\n if tf_med:\n hits.append('Medial OA')\n if tf_lat:\n hits.append('Lateral OA')\n if pf:\n hits.append('PF OA')\n if not hits:\n if pol == 'positive':\n g_pos += 1\n g_best = max(g_best, sev if GLOBAL_OA.search(c) else sev * 0.7)\n elif pol == 'negative':\n g_neg += 1\n continue\n for t in hits:\n if pol == 'positive':\n acc[t]['pos'] += 1\n acc[t]['best'] = max(acc[t]['best'], sev)\n elif pol == 'negative':\n acc[t]['neg'] += 1\n else:\n acc[t]['unc'] += 1\n acc[t]['best'] = max(acc[t]['best'], 0.3)\n out = {}\n for t in OA_TARGETS:\n a = acc[t]\n pos, neg, unc, best = (a['pos'], a['neg'], a['unc'], a['best'])\n if not (pos or unc) and g_pos and FEATURES['oa_inherit']:\n if neg:\n score, conf = _grade(0, neg, 0, 0.0)\n score = max(score, 0.35)\n conf *= 0.7\n else:\n score, conf = _grade(g_pos, 0, 0, g_best * 0.92)\n conf *= 0.75\n else:\n score, conf = _grade(pos, neg + g_neg, unc, best)\n out[t] = (score, conf, pos, neg)\n return out\n\ndef extract(report: str) -> dict:\n cls = clauses(report)\n out = {}\n for tgt in PAIRED:\n s, c, npos, nneg = _score_paired(cls, tgt)\n out[tgt] = s\n out[tgt + '__conf'] = c\n out[tgt + '__npos'] = npos\n out[tgt + '__nneg'] = nneg\n for tgt, (s, c, npos, nneg) in _score_oa(cls).items():\n out[tgt] = s\n out[tgt + '__conf'] = c\n out[tgt + '__npos'] = npos\n out[tgt + '__nneg'] = nneg\n for tgt in ('Effusion', 'Synovitis', \"Baker's\", 'Contusion', 'Fracture'):\n if tgt == 'Contusion':\n s, c, npos, nneg = _score_clauses(cls, DIRECT_MATCH[tgt], None, DECOY.get(tgt), context_penalty=DEGENERATIVE_MARROW, context_bonus=TRAUMA)\n else:\n s, c, npos, nneg = _score_clauses(cls, DIRECT_MATCH[tgt], None, DECOY.get(tgt))\n out[tgt] = s\n out[tgt + '__conf'] = c\n out[tgt + '__npos'] = npos\n out[tgt + '__nneg'] = nneg\n if FEATURES['synovitis_backoff'] and out['Synovitis__npos'] == 0 and (out['Synovitis__nneg'] == 0):\n proxy = sum((1 for c in cls if SYNOVIAL_PROXY.search(c) and _polarity(c) == 'positive'))\n eff = out['Effusion']\n prior = 0.3 + 0.3 * max(0.0, (eff - 0.5) / 0.45) + 0.06 * min(proxy, 3)\n out['Synovitis'] = min(0.72, prior)\n out['Synovitis__conf'] = 0.18\n return out","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:02.423952Z","iopub.execute_input":"2026-08-17T17:07:02.424303Z","iopub.status.idle":"2026-08-17T17:07:02.46379Z","shell.execute_reply.started":"2026-08-17T17:07:02.42424Z","shell.execute_reply":"2026-08-17T17:07:02.463134Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from __future__ import annotations\nimport os\nfor _v in ('OMP_NUM_THREADS', 'OPENBLAS_NUM_THREADS', 'MKL_NUM_THREADS'):\n os.environ.setdefault(_v, '4')\nimport gc\nimport hashlib\nimport json\nimport re\nimport time\nimport traceback\nimport threading\nfrom concurrent.futures import ThreadPoolExecutor\nfrom pathlib import Path\nimport numpy as np\nimport pandas as pd\nimport pydicom\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\n\ndef _cuda_execution_probe(index):\n dev = torch.device(f'cuda:{index}')\n try:\n major, minor = torch.cuda.get_device_capability(index)\n probe = nn.Conv2d(3, 4, kernel_size=3, padding=1).eval().to(dev)\n with torch.inference_mode():\n out = probe(torch.zeros((1, 3, 16, 16), device=dev))\n if tuple(out.shape) != (1, 4, 16, 16):\n raise RuntimeError(f'unexpected CUDA probe shape {tuple(out.shape)}')\n torch.cuda.synchronize(index)\n print(f'cuda:{index} probe PASS (compute {major}.{minor})')\n del probe, out\n torch.cuda.empty_cache()\n return True\n except Exception as exc:\n print(f'cuda:{index} probe FAIL ({type(exc).__name__}: {exc}); using CPU fallback')\n try:\n torch.cuda.empty_cache()\n except Exception:\n pass\n return False\nDEVS = []\nif torch.cuda.is_available():\n DEVS = [torch.device(f'cuda:{i}') for i in range(torch.cuda.device_count()) if _cuda_execution_probe(i)]\nif not DEVS:\n DEVS = [torch.device('cpu')]\nprint(f'devices: {[str(d) for d in DEVS]}')\nT0 = time.time()\nSEED = 2026\nnp.random.seed(SEED)\ntorch.manual_seed(SEED)\nTARGETS = ['ACL', 'MCL', 'Medial Meniscus', 'Lateral Meniscus', 'Medial OA', 'Lateral OA', 'PF OA', 'Effusion', 'Synovitis', \"Baker's\", 'Contusion', 'Fracture']\nCROP_MM = 130.0\nCACHE_IMG = 336\nGROUP = 3\nN_GROUP_MAX = 1\nCACHE_FRACTION = 0.45\nCACHE_BUDGET_MAX_GB = 24.0\nCACHE_BUDGET_GB = 12.0\nTEST_SHARE = 0.3\nHDR_THREADS = 16\nPIX_THREADS = 12\nORDER_THREADS = 32\nORDER_BUDGET_S = 5400\nRUNS = [{'name': 'r224', 'img': 224}, {'name': 'r336', 'img': 336}]\nEPOCHS = 10\nBATCH_STUDIES = 8\nAUG_ROT_DEG = 8.0\nAUG_SCALE = 0.08\nAUG_SHIFT = 0.05\nAUG_INTENSITY = 0.1\nLAT_MIN_OFFSET_MM = 20.0\nSLICE_BAND = (0.2, 0.8)\nRULES_NATIVE = {'order': 'normal', 'lat': 'centre', 'slot_fallback': False, 'decode_fill': 'nearest'}\nRULES_LEGACY = {'order': 'dominant_axis', 'lat': 'corner_x', 'slot_fallback': True, 'decode_fill': 'zero'}\nRULES = dict(RULES_NATIVE)\nLEGACY_LAT_OFFSET_MM = 5.0\nLR_HEAD = 0.001\nLR_BACKBONE = 8e-06\nUNFREEZE_LAST = 6\nWEIGHT_DECAY = 0.02\nEVAL_BATCH = 8\nTIME_BUDGET = 8.0 * 3600\nSLOTS_RECOVERED = [('SAG_FLUID_FS', 'Sagittal', True, True), ('COR_FLUID_FS', 'Coronal', True, True), ('AX_FLUID_FS', 'Axial', True, True), ('SAG_FLUID_NOFS', 'Sagittal', True, False), ('COR_T1', 'Coronal', False, False), ('SAG_T1', 'Sagittal', False, False)]\nSLOTS_PUBLIC = [('SAG_FLUID', 'Sagittal', None, True), ('COR_FLUID', 'Coronal', None, True), ('AX_FLUID', 'Axial', None, True), ('SAG_STRUCT', 'Sagittal', None, False), ('COR_STRUCT', 'Coronal', None, False), ('AX_STRUCT', 'Axial', None, False)]\nSLOT_SCHEME = os.environ.get('SLOT_SCHEME', 'recovered')\nSLOTS = SLOTS_PUBLIC if SLOT_SCHEME == 'public' else SLOTS_RECOVERED\nN_SLOT = len(SLOTS)\nPOOL_PARTS = {'cls_mean': 2, 'cls_mean_focal': 3}\nSLOT_PRIOR_TABLE = {'ACL': (0, 3, 5), 'MCL': (1, 4), 'Medial Meniscus': (0, 1, 3, 4), 'Lateral Meniscus': (0, 1, 3, 4), 'Medial OA': (1, 4, 5), 'Lateral OA': (1, 4, 5), 'PF OA': (0, 2, 5), 'Effusion': (0, 2), 'Synovitis': (0, 2), \"Baker's\": (0,), 'Contusion': (0, 1, 2), 'Fracture': (0, 1, 2, 4, 5)}\nSLOT_PRIOR_STRENGTH = 0.55\nFATSAT_OPTS = {'FS', 'FATSAT', 'FAT_SAT', 'FSAT'}\n_SEP = re.compile('[_\\\\-.]')\n_FATSAT_RX = re.compile('\\\\bfs\\\\b|fatsat|fat sat|\\\\bstir\\\\b|\\\\bspair\\\\b|\\\\bspir\\\\b|\\\\bwe\\\\b|water excit|\\\\btirm\\\\b|\\\\bsting\\\\b|\\\\bfatsup\\\\b')\n_T1_RX = re.compile('\\\\bt1\\\\b|\\\\bt1w\\\\b')\n_T2_RX = re.compile('\\\\bt2\\\\b|\\\\bt2w\\\\b')\n_PD_RX = re.compile('\\\\bpd\\\\b|\\\\bpdw\\\\b|proton|\\\\bdp\\\\b|dens')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:02.509571Z","iopub.execute_input":"2026-08-17T17:07:02.510118Z","iopub.status.idle":"2026-08-17T17:07:06.651658Z","shell.execute_reply.started":"2026-08-17T17:07:02.510095Z","shell.execute_reply":"2026-08-17T17:07:06.65071Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def log(msg):\n print(f'[{time.time() - T0:7.1f}s] {msg}', flush=True)\n\ndef find_root():\n for c in [Path('/kaggle/input/competitions/rsna-knee-abnormality-detection'), Path('/kaggle/input/rsna-knee-abnormality-detection'), Path('data'), Path('.')]:\n if (c / 'test.csv').is_file() and (c / 'test_series').is_dir():\n return c\n base = Path('/kaggle/input')\n if base.is_dir():\n for depth1 in sorted((p for p in base.iterdir() if p.is_dir())):\n for cand in [depth1] + sorted((p for p in depth1.iterdir() if p.is_dir())):\n if (cand / 'test.csv').is_file():\n return cand\n raise FileNotFoundError(f'competition mount not found (cwd {Path.cwd()}); expected a directory holding test.csv and test_series/')\n\ndef find_dinov2(variant='small'):\n base = Path('/kaggle/input')\n if not base.is_dir():\n return None\n hits = []\n for root, dirs, files in os.walk(base):\n dirs[:] = [d for d in dirs if d not in ('train_series', 'test_series')]\n if 'config.json' in files and 'dinov2' in root.lower():\n hits.append(Path(root))\n for h in hits:\n if variant in str(h).lower():\n return h\n return hits[0] if hits else None\nLABEL_COLS = TARGETS + [t + '__conf' for t in TARGETS]\n\nclass LabelSourceError(RuntimeError):\n pass\n\ndef find_label_table():\n base = Path('/kaggle/input')\n cands = []\n if base.is_dir():\n for root, dirs, files in os.walk(base):\n dirs[:] = [d for d in dirs if d not in ('train_series', 'test_series')]\n cands += [Path(root) / f for f in files if f.startswith('report_labels') and f.endswith('.csv')]\n cands += [p for p in (Path('data/derived/report_labels_v2.csv'),) if p.is_file()]\n for c in cands:\n try:\n head = pd.read_csv(c, nrows=1)\n except Exception:\n continue\n if 'StudyInstanceUID' in head.columns and all((t in head.columns for t in TARGETS)):\n return c\n return None\n\ndef label_mount_attached():\n base = Path('/kaggle/input')\n if not base.is_dir():\n return False\n return any(('label' in p.name.lower() for p in base.iterdir() if p.is_dir()))\n\ndef read_labels(train_df):\n n = len(train_df)\n lab = pd.DataFrame([extract(r) for r in train_df['Report'].fillna('')])\n lab['StudyInstanceUID'] = train_df['StudyInstanceUID'].values\n lab = lab.set_index('StudyInstanceUID')\n src = find_label_table()\n if src is None:\n if label_mount_attached():\n raise LabelSourceError('LABEL SOURCE: a label dataset is mounted but no usable table was found in it. Falling back to the lexicon here would train on the weaker labels and say so only in a log line, so the run stops instead.')\n log(f'LABEL SOURCE: lexicon, {n} studies (no table mounted)')\n return lab\n tab = pd.read_csv(src).set_index('StudyInstanceUID')\n missing = [c for c in LABEL_COLS if c not in tab.columns]\n if missing:\n raise LabelSourceError(f'LABEL SOURCE: {src} is missing {len(missing)} expected columns (first: {missing[0]!r}). Refusing to fall back silently.')\n hit = lab.index.intersection(tab.index)\n if not len(hit):\n raise LabelSourceError(f'LABEL SOURCE: {src} shares no StudyInstanceUID with train.csv.')\n log(f'LABEL SOURCE: {src.name} covers {len(hit)} of {n} studies, lexicon for the remaining {n - len(hit)}')\n lab.loc[hit, LABEL_COLS] = tab.loc[hit, LABEL_COLS].values\n return lab\nROOT = find_root()\nlog(f'input root: {ROOT}')\nIMG = CACHE_IMG\n\ndef available_gb():\n try:\n with open('/proc/meminfo') as fh:\n info = {k.strip(): v for k, v in (l.split(':', 1) for l in fh if ':' in l)}\n return int(info['MemAvailable'].split()[0]) / 1024 ** 2\n except Exception:\n return CACHE_BUDGET_GB / CACHE_FRACTION\n\ndef plan_cache(n_study, n_test=0):\n avail = available_gb()\n budget = min(avail * CACHE_FRACTION, CACHE_BUDGET_MAX_GB)\n n_total = n_study + max(n_test, int(TEST_SHARE * n_study))\n per_slice = n_total * N_SLOT * IMG * IMG\n afford = int(budget * 1024 ** 3 // max(per_slice, 1))\n groups = max(1, min(N_GROUP_MAX, afford // GROUP))\n log(f'memory: {avail:.1f} GB available, {budget:.1f} GB to the cache; sizing for {n_study} train + {n_total - n_study} test studies -> {groups} group(s) of {GROUP} = {groups * GROUP} slices per slot' + (f' (wanted {N_GROUP_MAX})' if groups < N_GROUP_MAX else ''))\n return groups\nN_GROUP = plan_cache(len(pd.read_csv(ROOT / 'train.csv')), len(pd.read_csv(ROOT / 'test.csv')))\nCACHE_SLICES = GROUP * N_GROUP\nlog(f'cache layout: {N_GROUP} groups x {GROUP} slices = {CACHE_SLICES} per slot')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:06.653361Z","iopub.execute_input":"2026-08-17T17:07:06.653676Z","iopub.status.idle":"2026-08-17T17:07:06.831302Z","shell.execute_reply.started":"2026-08-17T17:07:06.653654Z","shell.execute_reply":"2026-08-17T17:07:06.830606Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"HDR_TAGS = ['SeriesDescription', 'SequenceName', 'ScanOptions', 'ScanningSequence', 'RepetitionTime', 'EchoTime', 'Laterality', 'PixelSpacing', 'Rows', 'Columns', 'RescaleSlope', 'RescaleIntercept', 'ImagePositionPatient', 'ImageOrientationPatient']\n\ndef _hdr_vec(s, n):\n if not isinstance(s, str):\n return None\n try:\n v = [float(x) for x in s.split('|')]\n except ValueError:\n return None\n return np.array(v) if len(v) >= n else None\n\ndef side_from_geometry(h):\n cx = {}\n for r in h.itertuples(index=False):\n ipp = _hdr_vec(getattr(r, 'ImagePositionPatient', None), 3)\n iop = _hdr_vec(getattr(r, 'ImageOrientationPatient', None), 6)\n ps = _hdr_vec(getattr(r, 'PixelSpacing', None), 2)\n rows, cols = (getattr(r, 'Rows', None), getattr(r, 'Columns', None))\n if ipp is None or iop is None or ps is None or (not rows) or (not cols):\n continue\n try:\n c = ipp[:3] + iop[:3] * ps[1] * float(cols) / 2 + iop[3:6] * ps[0] * float(rows) / 2\n except (TypeError, ValueError):\n continue\n cx.setdefault(r.StudyInstanceUID, []).append(float(c[0]))\n out = {}\n for st, xs in cx.items():\n m = float(np.median(xs))\n out[st] = None if abs(m) < LAT_MIN_OFFSET_MM else 'R' if m < 0 else 'L'\n return out\n\ndef side_from_corner_x(h):\n out = {}\n for st, g in h.groupby('StudyInstanceUID'):\n xs = []\n for r in g.itertuples(index=False):\n ipp = _hdr_vec(getattr(r, 'ImagePositionPatient', None), 3)\n if ipp is not None and np.isfinite(ipp).all():\n xs.append(float(ipp[0]))\n if not xs:\n out[st] = None\n continue\n x = float(np.median(xs))\n out[st] = None if abs(x) < LEGACY_LAT_OFFSET_MM else 'R' if x < 0 else 'L'\n return out\n\ndef lat_of(h, tag=''):\n geo = side_from_corner_x(h) if RULES['lat'] == 'corner_x' else side_from_geometry(h)\n d, n_tag, n_geo, n_none, n_disagree = ({}, 0, 0, 0, 0)\n for st, g in h.groupby('StudyInstanceUID'):\n v = [str(x).strip().upper() for x in g['Laterality'].dropna()]\n if RULES['lat'] == 'corner_x' and 'ImageLaterality' in g.columns:\n v += [str(x).strip().upper() for x in g['ImageLaterality'].dropna()]\n v = [x[0] for x in v if x and x[0] in ('L', 'R')]\n side = v[0] if v else None\n if side is not None:\n n_tag += 1\n if geo.get(st) is not None and geo[st] != side:\n n_disagree += 1\n else:\n side = geo.get(st)\n n_geo += side is not None\n n_none += side is None\n d[st] = side\n log(f'{tag}laterality: {n_tag} from the tag, {n_geo} from geometry, {n_none} unresolved; tag and geometry disagree on {n_disagree} ({n_disagree / max(n_tag, 1):.1%} of the tagged)')\n return d\n\ndef probe(item):\n split, study, series, path = item\n row = {'split': split, 'StudyInstanceUID': study, 'SeriesInstanceUID': series, 'dir': path}\n try:\n files = sorted((e.name for e in os.scandir(path) if e.name.endswith('.dcm')))\n row['files'] = files\n row['n_slices'] = len(files)\n if not files:\n return row\n ds = pydicom.dcmread(os.path.join(path, files[len(files) // 2]), stop_before_pixels=True, force=True)\n for t in HDR_TAGS:\n v = getattr(ds, t, None)\n if v is None:\n row[t] = None\n elif isinstance(v, (list, tuple)) or type(v).__name__ == 'MultiValue':\n row[t] = '|'.join((str(x) for x in v))\n else:\n row[t] = str(v)\n except Exception as exc:\n row['err'] = str(exc)[:120]\n return row\n\ndef walk(split):\n base = ROOT / split\n items = []\n if not base.is_dir():\n return pd.DataFrame(columns=['split', 'StudyInstanceUID', 'SeriesInstanceUID', 'dir', 'files', 'n_slices'] + HDR_TAGS)\n for study in os.scandir(base):\n if study.is_dir():\n for series in os.scandir(study.path):\n if series.is_dir():\n items.append((split, study.name, series.name, series.path))\n with ThreadPoolExecutor(max_workers=HDR_THREADS) as pool:\n rows = list(pool.map(probe, items))\n return pd.DataFrame(rows)\n\ndef annotate(df):\n desc = df['SeriesDescription'].fillna('') + ' ' + df['SequenceName'].fillna('')\n desc = desc.str.lower().str.replace(_SEP, ' ', regex=True)\n opts = df['ScanOptions'].fillna('').str.upper().str.split('|')\n opts_fs = opts.apply(lambda ts: any((t.strip() in FATSAT_OPTS for t in ts)))\n df['fatsat'] = desc.str.contains(_FATSAT_RX) | opts_fs\n tr = pd.to_numeric(df['RepetitionTime'], errors='coerce')\n te = pd.to_numeric(df['EchoTime'], errors='coerce')\n gre = df['ScanningSequence'].fillna('').str.upper().str.contains('GR')\n t1, t2, pdw = (desc.str.contains(_T1_RX), desc.str.contains(_T2_RX), desc.str.contains(_PD_RX))\n df['weight'] = np.where(t1 & ~t2 & ~pdw, 'T1', np.where(t2 & ~pdw, 'T2', np.where(pdw, 'PD', np.where(gre, 'GRE', np.where(tr < 800, 'T1', np.where(te > 60, 'T2', np.where(tr >= 800, 'PD', 'UNK')))))))\n df['fluid'] = np.isin(df['weight'], ['PD', 'T2'])\n df['px'] = pd.to_numeric(df['PixelSpacing'].fillna('').str.split('|').str[0].replace('', np.nan), errors='coerce')\n return df","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:06.832234Z","iopub.execute_input":"2026-08-17T17:07:06.832557Z","iopub.status.idle":"2026-08-17T17:07:06.865624Z","shell.execute_reply.started":"2026-08-17T17:07:06.832525Z","shell.execute_reply":"2026-08-17T17:07:06.864841Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def pick_slots(series_df, plane_map):\n series_df = series_df.copy()\n series_df['plane'] = series_df['SeriesInstanceUID'].map(plane_map)\n out = {}\n for study, g in series_df.groupby('StudyInstanceUID'):\n chosen = {}\n for name, plane, fluid, fs in SLOTS:\n sel = (g['plane'] == plane) & (g['fatsat'] == fs)\n if fluid is not None:\n sel &= g['fluid'] == fluid\n cand = g[sel]\n if len(cand) == 0 and RULES['slot_fallback'] and (fluid is False):\n cand = g[(g['plane'] == plane) & ~g['fatsat']]\n if len(cand):\n chosen[name] = cand.sort_values('n_slices', ascending=False).iloc[0]\n out[study] = chosen\n return out","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:06.866568Z","iopub.execute_input":"2026-08-17T17:07:06.866877Z","iopub.status.idle":"2026-08-17T17:07:06.88232Z","shell.execute_reply.started":"2026-08-17T17:07:06.866844Z","shell.execute_reply":"2026-08-17T17:07:06.881525Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ORDER_TAGS = [(32, 50), (32, 55), (32, 19)]\nDECODE_FAILED = []\n\ndef cache_tag(rules=None):\n r = dict(RULES if rules is None else rules)\n t = f'{CACHE_IMG}px_{CACHE_SLICES}sl_{int(CROP_MM)}mm_{SLICE_BAND[0]:.2f}-{SLICE_BAND[1]:.2f}'\n if {k: r.get(k, v) for k, v in RULES_NATIVE.items()} != RULES_NATIVE:\n t += '_' + hashlib.md5(json.dumps(r, sort_keys=True).encode()).hexdigest()[:6]\n return t\n\ndef _natural_key(name):\n return tuple((int(x) if x.isdigit() else x.lower() for x in re.split('(\\\\d+)', str(name))))\n\ndef _order_dominant_axis(rec):\n files, d = (rec['files'], rec['dir'])\n rows = []\n for pos, f in enumerate(files):\n ipp = inst = None\n try:\n ds = pydicom.dcmread(os.path.join(d, f), force=True, stop_before_pixels=True, specific_tags=['ImagePositionPatient', 'InstanceNumber'])\n raw = getattr(ds, 'ImagePositionPatient', None)\n if raw is not None and len(raw) >= 3:\n c = np.asarray(raw[:3], dtype=np.float64)\n if np.isfinite(c).all():\n ipp = c\n n = getattr(ds, 'InstanceNumber', None)\n if n is not None:\n inst = float(n)\n except Exception:\n pass\n rows.append((f, ipp, inst, pos))\n placed = [r for r in rows if r[1] is not None]\n need = max(2, int(0.8 * len(rows)))\n if len(placed) >= need:\n xyz = np.stack([r[1] for r in placed])\n axis = int(np.argmax(np.ptp(xyz, axis=0)))\n spare = float(np.nanmedian(xyz[:, axis]))\n rows.sort(key=lambda r: (float(r[1][axis]) if r[1] is not None else spare, r[2] if r[2] is not None else float('inf'), r[3]))\n elif sum((r[2] is not None for r in rows)) >= need:\n rows.sort(key=lambda r: (r[2] if r[2] is not None else float('inf'), r[3]))\n else:\n rows.sort(key=lambda r: _natural_key(r[0]))\n return ([r[0] for r in rows], True)\n\ndef order_slices(rec):\n if RULES['order'] == 'dominant_axis':\n return _order_dominant_axis(rec)\n files, d = (rec['files'], rec['dir'])\n keyed = []\n for f in files:\n k = None\n try:\n ds = pydicom.dcmread(os.path.join(d, f), force=True, stop_before_pixels=True, specific_tags=ORDER_TAGS)\n iop = np.asarray(ds.ImageOrientationPatient, dtype=float)\n ipp = np.asarray(ds.ImagePositionPatient, dtype=float)\n k = float(np.dot(ipp, np.cross(iop[:3], iop[3:])))\n except Exception:\n try:\n k = float(ds.InstanceNumber)\n except Exception:\n k = None\n keyed.append((k, f))\n if any((k is None for k, _ in keyed)):\n return (files, False)\n return ([f for _, f in sorted(keyed, key=lambda t: t[0])], True)\n\ndef read_slot(rec, n_slice=None, out_size=None):\n n_slice = GROUP if n_slice is None else n_slice\n out_size = IMG if out_size is None else out_size\n files, d, px = (rec.get('ordered') or rec['files'], rec['dir'], rec['px'])\n n = len(files)\n if n == 0:\n return None\n lo, hi = (int(SLICE_BAND[0] * (n - 1)), int(SLICE_BAND[1] * (n - 1)))\n idx = np.unique(np.linspace(lo, hi, n_slice).astype(int)) if hi > lo else np.array([n // 2])\n while len(idx) < n_slice:\n idx = np.append(idx, idx[-1])\n planes = []\n for i in idx[:n_slice]:\n try:\n ds = pydicom.dcmread(os.path.join(d, files[int(i)]), force=True)\n a = ds.pixel_array.astype(np.float32)\n sl = float(getattr(ds, 'RescaleSlope', 1) or 1)\n ic = float(getattr(ds, 'RescaleIntercept', 0) or 0)\n a = a * sl + ic\n except Exception:\n a = None\n planes.append(a)\n got = [k for k, p in enumerate(planes) if p is not None]\n if RULES['decode_fill'] == 'zero':\n if not got:\n DECODE_FAILED.append(rec.get('SeriesInstanceUID', d))\n planes = [np.zeros((out_size, out_size), np.float32) if p is None else p for p in planes]\n got = list(range(len(planes)))\n if not got:\n DECODE_FAILED.append(rec.get('SeriesInstanceUID', d))\n return None\n if len(got) < len(planes):\n DECODE_FAILED.append(rec.get('SeriesInstanceUID', d))\n for k, p in enumerate(planes):\n if p is None:\n planes[k] = planes[min(got, key=lambda j: abs(j - k))]\n shp = planes[0].shape\n planes = [p if p.shape == shp else np.zeros(shp, np.float32) for p in planes]\n vol = np.stack(planes)\n if px and np.isfinite(px) and (px > 0):\n want = int(round(CROP_MM / px))\n h, w = shp\n if 16 < want < min(h, w):\n cy, cx = (h // 2, w // 2)\n half = want // 2\n vol = vol[:, max(0, cy - half):cy + half, max(0, cx - half):cx + half]\n lo_v, hi_v = np.percentile(vol, [1, 99])\n vol = np.clip((vol - lo_v) / max(hi_v - lo_v, 1e-06), 0, 1)\n t = torch.from_numpy(np.ascontiguousarray(vol)).unsqueeze(0)\n t = F.interpolate(t, size=(out_size, out_size), mode='bilinear', align_corners=False)\n return (t.squeeze(0) * 255).round().clamp(0, 255).to(torch.uint8)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:06.884429Z","iopub.execute_input":"2026-08-17T17:07:06.88482Z","iopub.status.idle":"2026-08-17T17:07:06.908746Z","shell.execute_reply.started":"2026-08-17T17:07:06.884764Z","shell.execute_reply":"2026-08-17T17:07:06.90799Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def normalise_laterality(img, plane, lat):\n if lat != 'R':\n return img\n if plane in ('Coronal', 'Axial'):\n return torch.flip(img, dims=[-1])\n return torch.flip(img, dims=[0])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:06.909659Z","iopub.execute_input":"2026-08-17T17:07:06.909938Z","iopub.status.idle":"2026-08-17T17:07:06.923828Z","shell.execute_reply.started":"2026-08-17T17:07:06.909917Z","shell.execute_reply":"2026-08-17T17:07:06.923319Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ORDER_CACHE = os.environ.get('RSNA_ORDER_CACHE') or None\n\ndef build_cache(slot_map, plane_map, lat_map, tag):\n studies = sorted(slot_map)\n sidx = {s: i for i, s in enumerate(studies)}\n cache = np.zeros((len(studies), N_SLOT, CACHE_SLICES, IMG, IMG), np.uint8)\n mask = np.zeros((len(studies), N_SLOT), np.float32)\n log(f'{tag}: cache {cache.shape} = {cache.nbytes / 1024 ** 3:.1f} GB')\n jobs = [(st, k, plane, slot_map[st][name]) for st in studies for k, (name, plane, _, _) in enumerate(SLOTS) if name in slot_map[st]]\n n_job = len(jobs)\n t_ord = time.time()\n n_slice_total = sum((len(j[3]['files']) for j in jobs))\n log(f'{tag}: ordering {len(jobs)} slot-series ({n_slice_total} slice headers)')\n ok = done = 0\n CHUNK_O = 1024\n seen = {}\n if ORDER_CACHE and Path(ORDER_CACHE).is_file():\n try:\n import json as _json\n seen = _json.loads(Path(ORDER_CACHE).read_text())\n except (OSError, ValueError):\n seen = {}\n hit = 0\n for _, _, _, rec in jobs:\n e = seen.get(rec['SeriesInstanceUID'])\n if e and len(e['files']) == len(rec['files']):\n rec['ordered'] = e['files']\n ok += int(e['good'])\n hit += 1\n jobs = [j for j in jobs if 'ordered' not in j[3]]\n log(f'{tag}: {hit} slot-series ordered from {ORDER_CACHE}, {len(jobs)} to read')\n with ThreadPoolExecutor(max_workers=ORDER_THREADS) as pool:\n for c0 in range(0, len(jobs), CHUNK_O):\n block = jobs[c0:c0 + CHUNK_O]\n for (_, _, _, rec), (files, good) in zip(block, pool.map(lambda j: order_slices(j[3]), block)):\n rec['ordered'] = files\n ok += int(good)\n done += 1\n if ORDER_CACHE:\n seen[rec['SeriesInstanceUID']] = {'files': files, 'good': bool(good)}\n budget = min(ORDER_BUDGET_S, max(60.0, (TIME_BUDGET - (time.time() - T0)) * 0.35))\n if time.time() - t_ord > budget:\n log(f'{tag}: ordering budget spent at {done}/{len(jobs)}; the rest keep file order')\n break\n if ORDER_CACHE and done:\n import json as _json\n _t = Path(ORDER_CACHE).with_suffix('.tmp')\n _t.write_text(_json.dumps(seen))\n _t.replace(Path(ORDER_CACHE))\n log(f'{tag}: ordered {ok}/{n_job} by geometry ({n_job - ok} kept arbitrary) in {time.time() - t_ord:.0f}s')\n jobs = [(st, k, plane, slot_map[st][name]) for st in studies for k, (name, plane, _, _) in enumerate(SLOTS) if name in slot_map[st]]\n log(f'{tag}: decoding {len(jobs)} slot-series')\n n_failed_before = len(DECODE_FAILED)\n CHUNK = 512\n done = 0\n with ThreadPoolExecutor(max_workers=PIX_THREADS) as pool:\n for c0 in range(0, len(jobs), CHUNK):\n block = jobs[c0:c0 + CHUNK]\n for (st, k, plane, _), img in zip(block, pool.map(lambda j: read_slot(j[3], CACHE_SLICES, IMG), block)):\n done += 1\n if img is None:\n continue\n cache[sidx[st], k] = normalise_laterality(img, plane, lat_map.get(st)).numpy()\n mask[sidx[st], k] = 1.0\n if done % 4096 < CHUNK:\n log(f' {tag} {done}/{len(jobs)}')\n if time.time() - T0 > TIME_BUDGET:\n log(f' {tag}: time budget reached during decode')\n break\n n_failed = len(DECODE_FAILED) - n_failed_before\n log(f'{tag}: {int(mask.sum())}/{len(jobs)} slots filled' + (f'; {n_failed} series had a slice that would not decode' if n_failed else ''))\n gc.collect()\n return (studies, cache, mask)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:06.924627Z","iopub.execute_input":"2026-08-17T17:07:06.924797Z","iopub.status.idle":"2026-08-17T17:07:06.940788Z","shell.execute_reply.started":"2026-08-17T17:07:06.92478Z","shell.execute_reply":"2026-08-17T17:07:06.940035Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class SlotHead(nn.Module):\n\n def __init__(self, dim, n_slot, n_out, hidden=256, p=0.2, prior=False):\n super().__init__()\n self.proj = nn.Sequential(nn.LayerNorm(dim), nn.Linear(dim, hidden), nn.GELU())\n self.slot_emb = nn.Parameter(torch.randn(n_slot, hidden) * 0.02)\n self.query = nn.Parameter(torch.randn(n_out, hidden) * 0.02)\n self.drop = nn.Dropout(p)\n self.out = nn.Linear(hidden, n_out)\n self.hidden = hidden\n p_ = torch.zeros(n_out, n_slot)\n if prior and n_slot == len(SLOTS) and (n_out == len(TARGETS)):\n for t, slots in SLOT_PRIOR_TABLE.items():\n if t in TARGETS:\n p_[TARGETS.index(t), list(slots)] = SLOT_PRIOR_STRENGTH\n self.prior = prior\n if prior:\n self.register_buffer('slot_prior', p_)\n\n def forward(self, x, mask):\n h = self.proj(x) + self.slot_emb\n att = torch.einsum('bsh,oh->bos', h, self.query) / self.hidden ** 0.5\n if self.prior:\n att = att + self.slot_prior.unsqueeze(0)\n att = att.masked_fill(mask.unsqueeze(1) < 0.5, -10000.0).softmax(-1)\n ctx = self.drop(torch.einsum('bos,bsh->boh', att, h))\n return (ctx * self.out.weight.unsqueeze(0)).sum(-1) + self.out.bias","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:06.941799Z","iopub.execute_input":"2026-08-17T17:07:06.94215Z","iopub.status.idle":"2026-08-17T17:07:06.957618Z","shell.execute_reply.started":"2026-08-17T17:07:06.942118Z","shell.execute_reply":"2026-08-17T17:07:06.95695Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class Model(nn.Module):\n\n def __init__(self, backbone, dim, pool='cls_mean', prior=False):\n super().__init__()\n self.backbone = backbone\n self.pool = pool\n self.head = SlotHead(dim * POOL_PARTS[pool], N_SLOT, len(TARGETS), prior=prior)\n self.register_buffer('mean', torch.tensor([0.485, 0.456, 0.406]).view(1, 3, 1, 1))\n self.register_buffer('std', torch.tensor([0.229, 0.224, 0.225]).view(1, 3, 1, 1))\n\n def forward(self, imgs, mask, img_size=None):\n B, S = imgs.shape[:2]\n x = imgs.reshape(B * S, *imgs.shape[2:]).float().div_(255.0)\n if img_size is not None and img_size != x.shape[-1]:\n x = F.interpolate(x, size=(img_size, img_size), mode='bilinear', align_corners=False)\n x = (x - self.mean) / self.std\n out = self.backbone(pixel_values=x).last_hidden_state\n patch = out[:, 1:]\n parts = [out[:, 0], patch.mean(1)]\n if self.pool == 'cls_mean_focal':\n k = max(1, patch.shape[1] // 8)\n parts.append(patch.topk(k, dim=1).values.mean(1))\n feat = torch.cat(parts, dim=1).reshape(B, S, -1)\n return self.head(feat, mask)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:06.958563Z","iopub.execute_input":"2026-08-17T17:07:06.958827Z","iopub.status.idle":"2026-08-17T17:07:06.975318Z","shell.execute_reply.started":"2026-08-17T17:07:06.958807Z","shell.execute_reply":"2026-08-17T17:07:06.974545Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def build_model(unfreeze_last, source=None, variant='small', pool='cls_mean', prior=False):\n from transformers import AutoModel\n p = source if source is not None else find_dinov2(variant)\n if p is None:\n raise FileNotFoundError('DINOv2 weights not attached')\n bb = AutoModel.from_pretrained(str(p))\n n_layer = len(bb.encoder.layer)\n for prm in bb.parameters():\n prm.requires_grad = False\n for blk in bb.encoder.layer[max(0, n_layer - unfreeze_last):]:\n for prm in blk.parameters():\n prm.requires_grad = True\n for prm in bb.layernorm.parameters():\n prm.requires_grad = True\n dim = bb.config.hidden_size\n trainable = sum((p.numel() for p in bb.parameters() if p.requires_grad))\n log(f'backbone: {n_layer} blocks, last {unfreeze_last} trainable ({trainable / 1000000.0:.1f}M params), feature dim {dim * POOL_PARTS[pool]}')\n return Model(bb, dim, pool=pool, prior=prior)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:06.976126Z","iopub.execute_input":"2026-08-17T17:07:06.976439Z","iopub.status.idle":"2026-08-17T17:07:06.990886Z","shell.execute_reply.started":"2026-08-17T17:07:06.976419Z","shell.execute_reply":"2026-08-17T17:07:06.990191Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"FINGERPRINT_TOL = 0.002\n\ndef fingerprint(model, dev, img_size, n_slot=None, group=None, seed=None):\n n_slot = N_SLOT if n_slot is None else n_slot\n group = GROUP if group is None else group\n seed = SEED if seed is None else seed\n g = torch.Generator().manual_seed(seed)\n imgs = torch.randint(0, 256, (2, n_slot, group, img_size, img_size), generator=g, dtype=torch.uint8).to(dev)\n mask = torch.ones(2, n_slot, device=dev)\n mask[1, -1] = 0.0\n was_training = model.training\n model.eval()\n with torch.no_grad():\n out = model(imgs, mask, img_size).float().cpu().numpy()\n if was_training:\n model.train()\n return out\n\ndef check_fingerprint(model, dev, img_size, expected, tol=FINGERPRINT_TOL, tag=''):\n got = fingerprint(model, dev, img_size)\n exp = np.asarray(expected, np.float32)\n if got.shape != exp.shape:\n raise WeightsError(f'{tag}fingerprint shape {got.shape} != stored {exp.shape}: the architecture is not the one these weights were fitted to')\n d = float(np.abs(got - exp).max())\n if d > tol:\n raise WeightsError(f'{tag}fingerprint differs by {d:.4g} (tolerance {tol:g}). The weights load but do not compute what they computed when fitted - preprocessing, resolution or architecture has moved between the two runs.')\n log(f'{tag}fingerprint matches within {d:.2g}')\n return d\n\nclass WeightsError(RuntimeError):\n pass\n\ndef find_weights(name='manifest.json'):\n import json\n base = Path('/kaggle/input')\n if not base.is_dir():\n return None\n for root, dirs, files in os.walk(base):\n dirs[:] = [d for d in dirs if d not in ('train_series', 'test_series')]\n if name not in files:\n continue\n try:\n man = json.loads((Path(root) / name).read_text())\n except (OSError, ValueError):\n continue\n if isinstance(man.get('members'), list) and man['members']:\n missing = [m['file'] for m in man['members'] if not (Path(root) / m['file']).is_file()]\n if missing:\n raise WeightsError(f\"{root} holds a manifest listing {len(man['members'])} members but {len(missing)} of their files are absent (first {missing[0]!r})\")\n return Path(root)\n return None\nTTA_OVERLAP = True\nTTA_POOL = 'prob'\nPUBLIC_FRONTIER_TARGET_POOL = {'Fracture': 'max', 'Contusion': 'max', 'Medial Meniscus': 'max', 'Lateral Meniscus': 'max', 'ACL': 'top2', 'MCL': 'top2', \"Baker's\": 'max'}\nTTA_TARGET_POOL = {**PUBLIC_FRONTIER_TARGET_POOL, 'Synovitis': 'original_mean'}\n# No-extra-pass diversity branch: smooth focal pooling is evaluated from\n# the same no-jitter public-member windows already used by the parent.\nLEGACY_FOLD_SOFTPOOL_BETA = {\n 'ACL': 6.0, 'MCL': 6.0,\n 'Medial Meniscus': 8.0, 'Lateral Meniscus': 8.0,\n \"Baker's\": 8.0, 'Contusion': 8.0, 'Fracture': 10.0,\n}\nLEGACY_FOLD_SOFTPOOL_ALPHA = {\n 'ACL': 0.20, 'MCL': 0.20,\n 'Medial Meniscus': 0.25, 'Lateral Meniscus': 0.25,\n \"Baker's\": 0.20, 'Contusion': 0.20, 'Fracture': 0.15,\n}\nLEGACY_MEMBER_WEIGHT_BY_TARGET = {'Lateral Meniscus': 15.0, 'Medial OA': 2.5, 'Lateral OA': 15.0, 'Contusion': 5.0}\n\ndef window_starts(n_slice, group, overlap=None):\n overlap = TTA_OVERLAP if overlap is None else overlap\n if overlap and n_slice >= group:\n return list(range(n_slice - group + 1))\n return [g * group for g in range(max(n_slice // group, 1))]\n\ndef apply_target_window_pool(values, probs, logits, original_probs, mapping, target_idx):\n for target, mode in mapping.items():\n j = target_idx[target]\n if mode == 'max':\n values[:, j] = probs[:, :, j].max(0).values\n elif mode == 'mean':\n values[:, j] = probs[:, :, j].mean(0)\n elif mode == 'logit_mean':\n values[:, j] = torch.sigmoid(logits[:, :, j].mean(0))\n elif mode == 'original_mean':\n values[:, j] = original_probs[:, :, j].mean(0)\n elif mode in ('top2', 'top3'):\n k = min(int(mode[3:]), probs.shape[0])\n values[:, j] = probs[:, :, j].topk(k, dim=0).values.mean(0)\n else:\n raise ValueError(f'unknown TTA pooling mode for {target}: {mode}')\n return values\n\ndef legacy_fold_soft_window_pool(original_probs, target_idx):\n values = original_probs.mean(0).clone()\n for target, beta in LEGACY_FOLD_SOFTPOOL_BETA.items():\n j = target_idx[target]\n x = original_probs[:, :, j]\n weight = torch.softmax(float(beta) * x, dim=0)\n values[:, j] = (weight * x).sum(0)\n return values\n\n@torch.no_grad()\ndef predict_member(model, cache, mask, idx, dev, img_size, group=None, pool=None, starts=None, jitter=False, jitter_seed=SEED, return_public_frontier=False):\n group = GROUP if group is None else group\n pool = TTA_POOL if pool is None else pool\n starts = window_starts(cache.shape[2], group) if starts is None else list(starts)\n if not starts:\n raise ValueError('predict_member was given no windows to average over')\n target_idx = {t: j for j, t in enumerate(TARGETS)}\n unknown = (set(TTA_TARGET_POOL) | set(PUBLIC_FRONTIER_TARGET_POOL)) - set(target_idx)\n if unknown:\n raise ValueError(f'unknown target(s) in TTA_TARGET_POOL: {unknown}')\n jitter_gen = torch.Generator(device=dev)\n jitter_gen.manual_seed(int(jitter_seed) % (2 ** 63 - 1))\n model.eval()\n out, public_frontier_out, public_soft_out = ([], [], [])\n for b in range(0, len(idx), EVAL_BATCH):\n sel = idx[b:b + EVAL_BATCH]\n m = torch.from_numpy(mask[sel]).to(dev)\n win_probs, win_logits, win_original_probs = ([], [], [])\n for st in starts:\n rows = torch.from_numpy(np.ascontiguousarray(cache[sel, :, st:st + group])).to(dev)\n views = [rows] + ([augment(rows, generator=jitter_gen)] if jitter else [])\n view_probs, view_logits = ([], [])\n for view in views:\n with torch.autocast('cuda', enabled=dev.type == 'cuda'):\n z = model(view, m, img_size).float()\n view_logits.append(z)\n view_probs.append(torch.sigmoid(z))\n win_logits.append(torch.stack(view_logits).mean(0))\n win_probs.append(torch.stack(view_probs).mean(0))\n win_original_probs.append(view_probs[0])\n probs = torch.stack(win_probs)\n logits = torch.stack(win_logits)\n original_probs = torch.stack(win_original_probs)\n v = torch.sigmoid(logits.mean(0)) if pool == 'logit' else probs.mean(0)\n v = apply_target_window_pool(v, probs, logits, original_probs, TTA_TARGET_POOL, target_idx)\n out.append(v.cpu().numpy())\n if return_public_frontier:\n public_v = apply_target_window_pool(original_probs.mean(0), original_probs, logits, original_probs, PUBLIC_FRONTIER_TARGET_POOL, target_idx)\n public_frontier_out.append(public_v.cpu().numpy())\n public_soft = legacy_fold_soft_window_pool(original_probs, target_idx)\n public_soft_out.append(public_soft.cpu().numpy())\n primary = np.concatenate(out) if out else np.zeros((0, len(TARGETS)), np.float32)\n if not return_public_frontier:\n return primary\n public_frontier = np.concatenate(public_frontier_out) if public_frontier_out else np.zeros((0, len(TARGETS)), np.float32)\n public_soft = np.concatenate(public_soft_out) if public_soft_out else np.zeros((0, len(TARGETS)), np.float32)\n return (primary, public_frontier, public_soft)\nBUILD_LOCK = threading.Lock()\nSTATE_LOCK = threading.Lock()\nLEGACY_BUNDLE_FILE = 'rsna_20260807_v1.pt'\nLEGACY_WEIGHT = 0.5\n\ndef find_legacy_bundle():\n base = Path('/kaggle/input')\n if not base.is_dir():\n return None\n for root, dirs, files in os.walk(base):\n dirs[:] = [d for d in dirs if d not in ('train_series', 'test_series')]\n if LEGACY_BUNDLE_FILE in files:\n return Path(root) / LEGACY_BUNDLE_FILE\n return None\n\ndef legacy_group_members():\n p = find_legacy_bundle()\n if p is None:\n log('no legacy bundle attached; blending skipped')\n return {}\n try:\n b = torch.load(p, map_location='cpu', weights_only=False)\n folds = b.get('fold_states') or []\n b_slots = [tuple(s)[0] for s in b.get('slots', SLOTS)]\n if list(b.get('targets', TARGETS)) != TARGETS or b_slots != [s[0] for s in SLOTS]:\n log(f'legacy bundle {p.name}: target/slot contract differs; blending skipped')\n return {}\n gr, n_gr = (int(b.get('group', 3)), int(b.get('n_group', 3)))\n variant = str(b.get('model_variant', 'dinov2-small')).split('-')[-1]\n key = json.dumps({'img': int(b.get('img', 224)), 'group': gr, 'slices': gr * n_gr, 'crop_mm': 160.0, 'band': [0.2, 0.8], 'rules': RULES_LEGACY, 'slots': [s[0] for s in SLOTS]}, sort_keys=True)\n ms = [{'id': f\"legacy-f{f.get('fold', k)}\", 'fold': f.get('fold', k), 'state': f['state_dict'], 'holdout': None, 'weight': LEGACY_WEIGHT, 'target_weight': [LEGACY_MEMBER_WEIGHT_BY_TARGET.get(t, 0.0) for t in TARGETS], 'pixel_group': key, 'config': {'unfreeze_last': 6, 'variant': 'base' if variant == 'base' else 'small', 'pool': 'cls_mean_focal', 'prior': True}} for k, f in enumerate(folds)]\n if ms:\n active = sorted(set(LEGACY_MEMBER_WEIGHT_BY_TARGET.values()))\n log(f'legacy bundle {p.name}: {len(ms)} fold(s) join with target-specific per-member weights {active}')\n return {key: ms} if ms else {}\n except Exception as exc:\n log(f'legacy bundle unusable ({type(exc).__name__}: {exc}); blending skipped')\n return {}\n\ndef _run_member(path, m, dev, Cte, Mte, idx, starts, jitter):\n t0 = time.time()\n with BUILD_LOCK:\n if 'state' in m:\n state, fp = (m['state'], None)\n else:\n ck = torch.load(Path(path) / m['file'], map_location='cpu', weights_only=False)\n state, fp = (ck['model'], ck.get('fingerprint'))\n model = build_model(int(m['config']['unfreeze_last']), variant=m['config']['variant'], pool=m['config'].get('pool', 'cls_mean'), prior=bool(m['config'].get('prior', False))).to(dev)\n model.load_state_dict(state)\n if fp is not None:\n check_fingerprint(model, dev, IMG, fp, tag=f\"{m['id']}: \")\n else:\n log(f\" {m['id']}: no stored fingerprint (legacy bundle) -- accepted at reduced weight\")\n t_ready = time.time()\n jitter_seed = SEED + int(hashlib.sha256(str(m['id']).encode()).hexdigest()[:8], 16)\n public_member = 'state' not in m\n predicted = predict_member(model, Cte, Mte, idx, dev, IMG, starts=starts, jitter=jitter, jitter_seed=jitter_seed, return_public_frontier=public_member)\n if public_member:\n p, public_p, public_soft = predicted\n else:\n p, public_p, public_soft = (predicted, None, None)\n t_done = time.time()\n del model, state\n gc.collect()\n if dev.type == 'cuda':\n with torch.cuda.device(dev):\n torch.cuda.empty_cache()\n passes = len(starts) * (2 if jitter else 1)\n return (p, public_p, public_soft, (t_ready - t0, (t_done - t_ready) / max(passes, 1)))\n\ndef _combine(per_member):\n all_ids = sorted({s for m in per_member for s in m['ids']})\n pos = {s: i for i, s in enumerate(all_ids)}\n acc = np.zeros((len(all_ids), len(TARGETS)), np.float64)\n tot = np.zeros(len(TARGETS), np.float64)\n for m in per_member:\n target_weight = m.get('target_weight')\n w = np.asarray(target_weight if target_weight is not None else [float(m.get('weight', 1.0))] * len(TARGETS), dtype=np.float64)\n if w.shape != (len(TARGETS),) or np.any(w < 0):\n raise ValueError(f\"invalid target weights for {m.get('id')}: {w}\")\n r = pd.DataFrame(m['pred']).rank(pct=True).to_numpy()\n acc[[pos[s] for s in m['ids']]] += r * w[None, :]\n tot += w\n if np.any(tot <= 0):\n raise ValueError(f'at least one target has no ensemble vote: {tot}')\n return (all_ids, acc / tot[None, :])\n\ndef combine_public_members_by_fold(per_member, pred_key='pred'):\n # Raw-average the four members within each fold, rank each fold,\n # then give all five folds equal weight.\n all_ids = sorted({study for member in per_member for study in member['ids']})\n position = {study: i for i, study in enumerate(all_ids)}\n groups = {}\n for i, member in enumerate(per_member):\n fold = member.get('fold')\n key = f'fold_{fold}' if fold is not None else f'member_{i}'\n groups.setdefault(key, []).append(member)\n fold_ranks, diagnostics = ([], [])\n for key, members_in_fold in sorted(groups.items()):\n matrices = []\n for member in members_in_fold:\n values = np.full((len(all_ids), len(TARGETS)), np.nan, np.float64)\n values[[position[study] for study in member['ids']]] = np.asarray(member[pred_key], np.float64)\n if np.isnan(values).any():\n raise WeightsError(f\"{member.get('id')}: incomplete {pred_key} coverage\")\n matrices.append(values)\n raw_fold_mean = np.mean(matrices, axis=0)\n fold_ranks.append(pd.DataFrame(raw_fold_mean).rank(method='average', pct=True).to_numpy(np.float64))\n diagnostics.append({'ensemble_group': key, 'members': len(members_in_fold)})\n if len(fold_ranks) != 5:\n raise WeightsError(f'legacy branch requires five folds, found {len(fold_ranks)}')\n return all_ids, np.mean(fold_ranks, axis=0), pd.DataFrame(diagnostics)\n\ndef blend_legacy_frontier_and_soft(frontier_rank, soft_rank):\n output = np.asarray(frontier_rank, np.float64).copy()\n for j, target in enumerate(TARGETS):\n alpha = float(LEGACY_FOLD_SOFTPOOL_ALPHA.get(target, 0.0))\n if alpha:\n output[:, j] = (1.0 - alpha) * frontier_rank[:, j] + alpha * soft_rank[:, j]\n return output\n\ndef infer_from_package(path, dev=None):\n man = json.loads((Path(path) / 'manifest.json').read_text())\n members = man['members']\n log(f'weights package: {len(members)} member(s) from {path}; {len(DEVS)} device(s)')\n test_df = pd.read_csv(ROOT / 'test.csv')\n test_series = pd.read_csv(ROOT / 'test_series.csv')\n plane_map = dict(zip(test_series['SeriesInstanceUID'], test_series['Anatomical_Plane']))\n hte = annotate(walk('test_series'))\n log(f'test header pass: {len(hte)} series')\n groups = {}\n for m in members:\n groups.setdefault(m['pixel_group'], []).append(m)\n groups.update(legacy_group_members())\n per_member, public_frontier_members = ([], [])\n est = {'fixed': None, 'win': None}\n\n def bank(m, ids, pred, starts, jitter, public_pred=None, public_soft=None):\n if float(np.std(pred)) < 1e-09:\n log(f\" {m['id']}: degenerate predictions; not banked\")\n return\n with STATE_LOCK:\n per_member.append({'id': m['id'], 'fold': m.get('fold'), 'ids': ids, 'pred': pred, 'weight': m.get('weight', 1.0), 'target_weight': m.get('target_weight'), 'holdout': m.get('holdout')})\n if public_pred is not None and len(starts) == len(starts_full):\n if float(np.std(public_pred)) < 1e-09:\n raise WeightsError(f\"{m['id']}: degenerate public-frontier prediction\")\n public_frontier_members.append({'id': m['id'], 'fold': m.get('fold'), 'ids': ids, 'pred': public_pred, 'soft_pred': public_soft})\n elif public_pred is not None:\n log(f\" {m['id']}: public-frontier vote omitted because only {len(starts)} / {len(starts_full)} windows completed\")\n all_ids, acc = _combine(per_member)\n write_submission(acc, all_ids, test_df, 'submission.csv')\n log(f\" banked {m['id']} fold {m.get('fold', '?')} ({len(starts)} window(s){(', jitter' if jitter else '')}); submission.csv = weighted rank mean of {len(per_member)} member(s)\")\n for gi, (key, gm) in enumerate(groups.items(), 1):\n cfg = json.loads(key)\n adopt_config_globals(cfg)\n log(f\"decode group {gi}/{len(groups)}: {cfg['img']}px x {cfg['slices']} slices, crop {cfg['crop_mm']} mm -> {len(gm)} member(s)\")\n st_te, Cte, Mte = build_cache(pick_slots(hte, plane_map), plane_map, lat_of(hte, 'test '), f'test g{gi}')\n idx = np.arange(len(st_te))\n starts_full = window_starts(Cte.shape[2], GROUP)\n pending = sorted(gm, key=lambda m: -(m.get('holdout') or 0))\n left_after = sum((len(g) for j, (_, g) in enumerate(groups.items(), 1) if j > gi))\n\n def pop_next():\n with STATE_LOCK:\n if not pending:\n return (None, None, False)\n left = TIME_BUDGET - (time.time() - T0)\n remaining = len(pending) + left_after\n slots_left = -(-remaining // len(DEVS))\n starts, jit = (starts_full, False)\n if est['fixed'] is not None and est['win'] is not None:\n afford = max(left * 0.9, 0.0)\n room = afford / max(slots_left, 1)\n if est['fixed'] + est['win'] > room:\n log(f' {left / 60:.0f} min left: surrendering {len(pending)} member(s); not one more fits')\n pending.clear()\n return (None, None, False)\n jit = est['fixed'] + 2 * len(starts_full) * est['win'] <= room * 0.6\n per_win = est['win'] * (2 if jit else 1)\n n_win = int((room - est['fixed']) / per_win) if per_win > 0 else len(starts_full)\n n_win = max(1, min(len(starts_full), n_win))\n if n_win < len(starts_full):\n mid = (len(starts_full) - n_win) // 2\n starts = starts_full[mid:mid + n_win]\n return (pending.pop(0), starts, jit)\n\n def worker(dev):\n others = [d for d in DEVS if d is not dev]\n while True:\n m, starts, jit = pop_next()\n if m is None:\n return\n for attempt, d in enumerate([dev] + others[:1]):\n try:\n p, public_p, public_soft, (fs, ws) = _run_member(path, m, d, Cte, Mte, idx, starts, jit)\n with STATE_LOCK:\n est['fixed'], est['win'] = (fs, ws)\n bank(m, st_te, p, starts, jit, public_p, public_soft)\n break\n except Exception as exc:\n log(f\" MEMBER {m['id']} failed on {d} ({type(exc).__name__}: {exc}); \" + ('retrying on peer device' if attempt == 0 and others else 'dropped -- costs one vote, not the run'))\n if d.type == 'cuda':\n with torch.cuda.device(d):\n torch.cuda.empty_cache()\n threads = [threading.Thread(target=worker, args=(d,)) for d in DEVS]\n for t in threads:\n t.start()\n for t in threads:\n t.join()\n del Cte, Mte\n gc.collect()\n if not per_member:\n raise WeightsError('no member produced predictions; submission stays at 0.5')\n all_ids, acc = _combine(per_member)\n sub = write_submission(acc, all_ids, test_df, 'submission.csv')\n log(f'final submission.csv = weighted rank mean of {len(per_member)} member(s); {sub.shape}; nulls {int(sub[TARGETS].isna().sum().sum())}')\n if len(public_frontier_members) == len(members):\n frontier_ids, frontier_acc = _combine(public_frontier_members)\n frontier_sub = write_submission(frontier_acc, frontier_ids, test_df, 'submission_public_0899.csv')\n log(f'submission_public_0899.csv = exact no-jitter public-frontier rank mean of {len(public_frontier_members)} member(s); {frontier_sub.shape}; nulls {int(frontier_sub[TARGETS].isna().sum().sum())}')\n fold_ids, fold_frontier, fold_diagnostics = combine_public_members_by_fold(public_frontier_members, 'pred')\n soft_ids, fold_soft, _ = combine_public_members_by_fold(public_frontier_members, 'soft_pred')\n if fold_ids != soft_ids:\n raise WeightsError('legacy hard/soft study order mismatch')\n legacy_prediction = blend_legacy_frontier_and_soft(fold_frontier, fold_soft)\n legacy_sub = write_submission(legacy_prediction, fold_ids, test_df, 'submission_legacy_fold_blend.csv')\n fold_diagnostics.to_csv('legacy_fold_diagnostics.csv', index=False)\n log(f'legacy DINO aggregation written from five folds; {legacy_sub.shape}')\n else:\n log(f'public-frontier fallback not emitted: {len(public_frontier_members)} / {len(members)} required public members completed')\n return sub\n\ndef adopt_config_globals(cfg):\n global IMG, CACHE_IMG, GROUP, CACHE_SLICES, N_GROUP, CROP_MM, SLICE_BAND, RULES\n CACHE_IMG = IMG = int(cfg['img'])\n GROUP = int(cfg['group'])\n CACHE_SLICES = int(cfg['slices'])\n N_GROUP = max(CACHE_SLICES // GROUP, 1)\n CROP_MM = float(cfg['crop_mm'])\n SLICE_BAND = tuple((float(x) for x in cfg['band']))\n rules = cfg.get('rules') or RULES_NATIVE\n unknown = {k: v for k, v in rules.items() if k not in RULES_NATIVE or v not in (RULES_NATIVE[k], RULES_LEGACY[k])}\n if unknown:\n raise WeightsError(f'the members record pixel rules this pipeline cannot reproduce: {unknown}')\n RULES = {**RULES_NATIVE, **rules}\n if [s[0] for s in SLOTS] != list(cfg['slots']):\n raise WeightsError(f\"the members were fitted on slots {cfg['slots']} and this pipeline defines {[s[0] for s in SLOTS]}; a weight would be read against the wrong slot\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:06.992162Z","iopub.execute_input":"2026-08-17T17:07:06.992924Z","iopub.status.idle":"2026-08-17T17:07:07.056033Z","shell.execute_reply.started":"2026-08-17T17:07:06.992898Z","shell.execute_reply":"2026-08-17T17:07:07.055318Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def take_group(cache_rows, g):\n return cache_rows[:, :, g * GROUP:(g + 1) * GROUP]\n\ndef augment(imgs, generator=None):\n lead = imgs.shape[:-3]\n x = imgs.reshape(-1, *imgs.shape[-3:]).float()\n n, dev = (x.shape[0], x.device)\n rot = (torch.rand(n, device=dev, generator=generator) - 0.5) * 2 * (AUG_ROT_DEG * np.pi / 180)\n sc = 1.0 + torch.rand(n, device=dev, generator=generator) * AUG_SCALE\n tx = (torch.rand(n, device=dev, generator=generator) - 0.5) * 2 * AUG_SHIFT\n ty = (torch.rand(n, device=dev, generator=generator) - 0.5) * 2 * AUG_SHIFT\n cos, sin = (torch.cos(rot) / sc, torch.sin(rot) / sc)\n theta = torch.zeros(n, 2, 3, device=dev, dtype=torch.float32)\n theta[:, 0, 0], theta[:, 0, 1], theta[:, 0, 2] = (cos, -sin, tx)\n theta[:, 1, 0], theta[:, 1, 1], theta[:, 1, 2] = (sin, cos, ty)\n grid = F.affine_grid(theta, x.shape, align_corners=False)\n x = F.grid_sample(x, grid, mode='bilinear', padding_mode='border', align_corners=False)\n scale = 1.0 + (torch.rand(n, 1, 1, 1, device=dev, generator=generator) - 0.5) * 2 * AUG_INTENSITY\n x = (x * scale).clamp(0, 255)\n return x.reshape(*lead, *x.shape[-3:]).to(imgs.dtype)\n\n@torch.no_grad()\ndef predict(model, cache, mask, idx, dev, img_size=None):\n model.eval()\n out = []\n for b in range(0, len(idx), EVAL_BATCH):\n sel = idx[b:b + EVAL_BATCH]\n m = torch.from_numpy(mask[sel]).to(dev)\n acc = None\n for g in range(N_GROUP):\n rows = torch.from_numpy(np.ascontiguousarray(cache[sel, :, g * GROUP:(g + 1) * GROUP])).to(dev)\n with torch.autocast('cuda', enabled=dev.type == 'cuda'):\n z = model(rows, m, img_size).float()\n acc = z if acc is None else acc + z\n out.append(torch.sigmoid(acc / N_GROUP).cpu().numpy())\n return np.concatenate(out) if out else np.zeros((0, len(TARGETS)), np.float32)\n\ndef macro_auc(y, p):\n from sklearn.metrics import roc_auc_score\n return float(np.nanmean([roc_auc_score(y[:, j], p[:, j]) if len(set(y[:, j])) > 1 else np.nan for j in range(y.shape[1])]))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:07.056964Z","iopub.execute_input":"2026-08-17T17:07:07.05766Z","iopub.status.idle":"2026-08-17T17:07:07.074232Z","shell.execute_reply.started":"2026-08-17T17:07:07.057638Z","shell.execute_reply":"2026-08-17T17:07:07.073566Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import math\nimport cv2\nTARGET_FAMILIES = ['acl', 'mcl', 'medial_meniscus', 'lateral_meniscus', 'medial_oa', 'lateral_oa', 'pf_oa', 'effusion', 'synovitis', 'baker', 'contusion', 'fracture']\nGROUP_NAMES = ['ligament', 'meniscus', 'oa', 'inflammation', 'bone', 'other']\n\ndef target_group_id(family):\n if family in {'acl', 'mcl'}:\n return 0\n if family in {'medial_meniscus', 'lateral_meniscus'}:\n return 1\n if family in {'medial_oa', 'lateral_oa', 'pf_oa'}:\n return 2\n if family in {'effusion', 'synovitis', 'baker'}:\n return 3\n if family in {'contusion', 'fracture'}:\n return 4\n return 5\nTARGET_GROUP_IDS = torch.tensor([target_group_id(f) for f in TARGET_FAMILIES], dtype=torch.long)\n\nclass RTAHMIL(nn.Module):\n\n def __init__(self, in_dim, hidden_dim, n_targets, n_slots, n_slices, dropout, series_dropout):\n super().__init__()\n self.n_targets = n_targets\n self.n_slots = n_slots\n self.n_slices = n_slices\n self.series_dropout = float(series_dropout)\n self.input_proj = nn.Sequential(nn.LayerNorm(in_dim), nn.Linear(in_dim, hidden_dim), nn.GELU(), nn.Dropout(dropout))\n self.slice_pos_emb = nn.Parameter(torch.randn(n_slices, hidden_dim) / math.sqrt(hidden_dim))\n slice_layer = nn.TransformerEncoderLayer(d_model=hidden_dim, nhead=8, dim_feedforward=hidden_dim * 4, dropout=dropout, activation='gelu', batch_first=True, norm_first=True)\n self.slice_encoder = nn.TransformerEncoder(slice_layer, num_layers=1)\n self.series_query = nn.Parameter(torch.randn(1, 1, hidden_dim) / math.sqrt(hidden_dim))\n self.series_pool = nn.MultiheadAttention(hidden_dim, num_heads=8, dropout=dropout, batch_first=True)\n self.slot_emb = nn.Embedding(n_slots, hidden_dim)\n self.plane_emb = nn.Embedding(3, hidden_dim)\n self.sequence_emb = nn.Embedding(2, hidden_dim)\n study_layer = nn.TransformerEncoderLayer(d_model=hidden_dim, nhead=8, dim_feedforward=hidden_dim * 4, dropout=dropout, activation='gelu', batch_first=True, norm_first=True)\n self.study_encoder = nn.TransformerEncoder(study_layer, num_layers=2)\n self.target_queries = nn.Parameter(torch.randn(n_targets, hidden_dim) / math.sqrt(hidden_dim))\n self.group_emb = nn.Embedding(len(GROUP_NAMES), hidden_dim)\n self.target_cross_attn = nn.MultiheadAttention(hidden_dim, num_heads=8, dropout=dropout, batch_first=True)\n self.target_fuse = nn.Sequential(nn.Linear(hidden_dim * 2, hidden_dim), nn.GELU(), nn.Dropout(dropout))\n self.target_heads = nn.ModuleList([nn.Sequential(nn.LayerNorm(hidden_dim), nn.Linear(hidden_dim, hidden_dim // 2), nn.GELU(), nn.Dropout(dropout), nn.Linear(hidden_dim // 2, 1)) for _ in range(n_targets)])\n slot_plane = [0, 0, 1, 1, 2, 2]\n slot_sequence = [0, 1, 0, 1, 0, 1]\n self.register_buffer('slot_plane_ids', torch.tensor(slot_plane, dtype=torch.long), persistent=False)\n self.register_buffer('slot_sequence_ids', torch.tensor(slot_sequence, dtype=torch.long), persistent=False)\n self.register_buffer('target_group_ids', TARGET_GROUP_IDS, persistent=False)\n\n def stochastic_slot_mask(self, mask):\n if not self.training or self.series_dropout <= 0:\n return mask\n keep = torch.rand(mask.shape, device=mask.device) > self.series_dropout\n new_mask = mask & keep\n all_missing = (~new_mask).all(dim=1)\n if all_missing.any():\n for row in torch.where(all_missing)[0]:\n valid = torch.where(mask[row])[0]\n if len(valid) > 0:\n new_mask[row, valid[0]] = True\n return new_mask\n\n def forward(self, x, slot_mask):\n B, S, K, _ = x.shape\n z = self.input_proj(x)\n z = z + self.slice_pos_emb[None, None, :K, :]\n z = z.reshape(B * S, K, -1)\n z = self.slice_encoder(z)\n q = self.series_query.expand(B * S, -1, -1)\n series_token, _ = self.series_pool(q, z, z, need_weights=False)\n series_token = series_token[:, 0].reshape(B, S, -1)\n slot_ids = torch.arange(S, device=x.device)\n plane_ids = self.slot_plane_ids[:S]\n seq_ids = self.slot_sequence_ids[:S]\n series_token = series_token + self.slot_emb(slot_ids)[None, :, :] + 0.35 * self.plane_emb(plane_ids)[None, :, :] + 0.35 * self.sequence_emb(seq_ids)[None, :, :]\n effective_mask = self.stochastic_slot_mask(slot_mask)\n no_valid_slot = (~effective_mask).all(dim=1)\n if no_valid_slot.any():\n effective_mask = effective_mask.clone()\n series_token = series_token.clone()\n effective_mask[no_valid_slot, 0] = True\n series_token[no_valid_slot, 0] = 0.0\n series_token = self.study_encoder(series_token, src_key_padding_mask=~effective_mask)\n denom = effective_mask.sum(dim=1, keepdim=True).clamp_min(1).to(series_token.dtype)\n study_global = (series_token * effective_mask.unsqueeze(-1)).sum(dim=1) / denom\n target_q = self.target_queries + 0.25 * self.group_emb(self.target_group_ids)\n target_q = target_q.unsqueeze(0).expand(B, -1, -1)\n target_context, _ = self.target_cross_attn(target_q, series_token, series_token, key_padding_mask=~effective_mask, need_weights=False)\n global_expand = study_global.unsqueeze(1).expand(-1, self.n_targets, -1)\n fused = self.target_fuse(torch.cat([target_context, global_expand], dim=-1))\n logits = []\n for j, head in enumerate(self.target_heads):\n logits.append(head(fused[:, j]))\n return torch.cat(logits, dim=1)\n'Runtime helpers embedded into the V26 Kaggle notebook.\\n\\nThe exact RTAHMIL class from the public report-teacher notebook is prepended by the\\ncandidate builder. This file contains only hidden-test feature extraction, checkpoint\\ninference, and the fail-safe Synovitis blend.\\n'\nRT_START_CUTOFF_S = 5.9 * 3600\nRT_DEADLINE_S = 7.1 * 3600\nRT_IMG_SIZE = 336\nRT_TARGET_SPACING = 0.42\nRT_SLICES = 7\nRT_SYN_WEIGHT = 0.75\nRT_SEEDS = (2026, 3407)\n\ndef _rt_find_checkpoint_dir():\n root = Path('/kaggle/input')\n required = [f'rta_final_seed{seed}_fold{fold}.pth' for seed in RT_SEEDS for fold in range(4)]\n for first in required[:1]:\n for hit in root.glob(f'*/{first}'):\n parent = hit.parent\n if all(((parent / name).is_file() for name in required)):\n return parent\n raise FileNotFoundError('the complete eight-checkpoint report-teacher package is absent')\n\ndef _rt_find_dino_base():\n direct = [Path('/kaggle/input/dinov2/pytorch/base/1'), Path('/kaggle/input/models/metaresearch/dinov2/pytorch/base/1')]\n for path in direct:\n if (path / 'config.json').is_file():\n return path\n for top in Path('/kaggle/input').iterdir():\n if not top.is_dir() or 'dino' not in top.name.lower():\n continue\n for config in top.glob('**/config.json'):\n try:\n if 'dinov2' in config.read_text(errors='ignore').lower():\n model_type = json.loads(config.read_text()).get('model_type', '')\n if model_type == 'dinov2' and 'base' in str(config.parent).lower():\n return config.parent\n except Exception:\n continue\n raise FileNotFoundError('offline DINOv2-base model is absent')\n\ndef _rt_binary_flag(value):\n if pd.isna(value):\n return 0\n if isinstance(value, str):\n return int(value.strip().lower() in {'1', 'true', 'yes', 'y'})\n try:\n return int(float(value) > 0)\n except Exception:\n return 0\n\ndef _rt_plane_id(value):\n text = str(value).lower()\n if 'sag' in text:\n return 0\n if 'cor' in text:\n return 1\n if 'axi' in text or 'trans' in text or 'tra' == text.strip():\n return 2\n return 3\n\ndef _rt_assign_slots(series_df):\n x = series_df.copy()\n x['StudyInstanceUID'] = x['StudyInstanceUID'].astype(str)\n x['SeriesInstanceUID'] = x['SeriesInstanceUID'].astype(str)\n x['_plane_id'] = x['Anatomical_Plane'].map(_rt_plane_id)\n fluid = x['Fluid_Sensitive'].map(_rt_binary_flag)\n fat = x['Fat_Suppression'].map(_rt_binary_flag)\n x['_fluid_like'] = np.maximum(fluid.astype(int), fat.astype(int))\n slot_defs = ((0, 0), (0, 1), (1, 0), (1, 1), (2, 0), (2, 1))\n lookup = {}\n for study_uid, group in x.groupby('StudyInstanceUID', sort=False):\n group = group.sort_values(['SeriesInstanceUID']).copy()\n used = set()\n for slot_id, (plane, fluid_like) in enumerate(slot_defs):\n desired = group[(group['_plane_id'] == plane) & (group['_fluid_like'] == fluid_like) & ~group['SeriesInstanceUID'].isin(used)]\n if len(desired) == 0:\n desired = group[(group['_plane_id'] == plane) & ~group['SeriesInstanceUID'].isin(used)]\n if len(desired) == 0:\n continue\n series_uid = str(desired.iloc[0]['SeriesInstanceUID'])\n used.add(series_uid)\n lookup[str(study_uid), slot_id] = series_uid\n return lookup\n\ndef _rt_locate_series_dir(study_uid, series_uid):\n canonical = ROOT / 'test_series'\n candidates = (canonical / str(series_uid), canonical / str(study_uid) / str(series_uid), ROOT / 'test' / str(study_uid) / str(series_uid), ROOT / 'test_images' / str(study_uid) / str(series_uid), ROOT / 'test_dicom' / str(study_uid) / str(series_uid), ROOT / 'test_dicoms' / str(study_uid) / str(series_uid), ROOT / 'images' / 'test' / str(study_uid) / str(series_uid))\n for path in candidates:\n if path.is_dir():\n return path\n raise FileNotFoundError(f'report-teacher series missing: study={study_uid}, series={series_uid}')\n\ndef _rt_sorted_dicom_files(series_dir):\n files = list(Path(series_dir).glob('*.dcm'))\n if not files:\n files = [path for path in Path(series_dir).iterdir() if path.is_file()]\n if not files:\n raise FileNotFoundError(f'no DICOM files in {series_dir}')\n simple_numeric = [path.stem.isdigit() and len(path.stem) <= 8 for path in files]\n if np.mean(simple_numeric) >= 0.9:\n number_re = re.compile('(\\\\d+)')\n\n def key(path):\n matches = number_re.findall(path.stem)\n return int(matches[-1]) if matches else 10 ** 12\n return sorted(files, key=key)\n keyed = []\n for index, path in enumerate(files):\n try:\n ds = pydicom.dcmread(str(path), stop_before_pixels=True, force=True)\n if hasattr(ds, 'ImagePositionPatient') and len(ds.ImagePositionPatient) >= 3:\n key = float(ds.ImagePositionPatient[2])\n else:\n key = float(getattr(ds, 'InstanceNumber', index))\n except Exception:\n key = float(index)\n keyed.append((key, path))\n return [path for _, path in sorted(keyed, key=lambda pair: pair[0])]\n\ndef _rt_robust_uint8(array):\n array = np.asarray(array, dtype=np.float32)\n finite = np.isfinite(array)\n if not finite.any():\n return np.zeros(array.shape, dtype=np.uint8)\n values = array[finite]\n lo, hi = np.percentile(values, [1.0, 99.0])\n if hi <= lo:\n lo, hi = (float(values.min()), float(values.max()) + 1e-06)\n array = np.clip(array, lo, hi)\n array = (array - lo) / max(hi - lo, 1e-06)\n return np.clip(array * 255.0, 0, 255).astype(np.uint8)\n\ndef _rt_center_crop_or_pad(image):\n height, width = image.shape[:2]\n pad_y, pad_x = (max(0, RT_IMG_SIZE - height), max(0, RT_IMG_SIZE - width))\n if pad_y or pad_x:\n top, left = (pad_y // 2, pad_x // 2)\n image = cv2.copyMakeBorder(image, top, pad_y - top, left, pad_x - left, borderType=cv2.BORDER_CONSTANT, value=0)\n height, width = image.shape[:2]\n y0, x0 = (max(0, (height - RT_IMG_SIZE) // 2), max(0, (width - RT_IMG_SIZE) // 2))\n return image[y0:y0 + RT_IMG_SIZE, x0:x0 + RT_IMG_SIZE]\n\ndef _rt_read_dicom(path):\n ds = pydicom.dcmread(str(path), force=True)\n array = ds.pixel_array.astype(np.float32)\n slope = float(getattr(ds, 'RescaleSlope', 1.0) or 1.0)\n intercept = float(getattr(ds, 'RescaleIntercept', 0.0) or 0.0)\n image = _rt_robust_uint8(array * slope + intercept)\n if str(getattr(ds, 'PhotometricInterpretation', '')).upper() == 'MONOCHROME1':\n image = 255 - image\n spacing = getattr(ds, 'PixelSpacing', None)\n if spacing is not None and len(spacing) >= 2:\n try:\n scale_y = np.clip(float(spacing[0]) / RT_TARGET_SPACING, 0.4, 3.0)\n scale_x = np.clip(float(spacing[1]) / RT_TARGET_SPACING, 0.4, 3.0)\n new_h = max(32, int(round(image.shape[0] * scale_y)))\n new_w = max(32, int(round(image.shape[1] * scale_x)))\n image = cv2.resize(image, (new_w, new_h), interpolation=cv2.INTER_LINEAR)\n return _rt_center_crop_or_pad(image)\n except Exception:\n pass\n return cv2.resize(image, (RT_IMG_SIZE, RT_IMG_SIZE), interpolation=cv2.INTER_AREA)\n\ndef _rt_load_series_25d(study_uid, series_uid):\n files = _rt_sorted_dicom_files(_rt_locate_series_dir(study_uid, series_uid))\n quantiles = np.array([0.08, 0.23, 0.38, 0.5, 0.62, 0.77, 0.92], np.float32)\n centers = np.zeros(RT_SLICES, np.int64) if len(files) <= 1 else np.round(quantiles * (len(files) - 1)).astype(np.int64)\n centers = np.clip(centers, 0, len(files) - 1)\n views = []\n for center in centers:\n channels = []\n for index in (max(0, center - 1), center, min(len(files) - 1, center + 1)):\n try:\n channels.append(_rt_read_dicom(files[index]))\n except Exception:\n channels.append(np.zeros((RT_IMG_SIZE, RT_IMG_SIZE), dtype=np.uint8))\n views.append(np.stack(channels, axis=-1))\n return np.stack(views, axis=0)\n\ndef _rt_try_attached_visible_features(checkpoint_dir, expected_uids):\n uid_path = checkpoint_dir / 'rta_final_test_uids.txt'\n feature_path = checkpoint_dir / 'rta_final_test_features.npy'\n mask_path = checkpoint_dir / 'rta_final_test_slot_mask.npy'\n if not (uid_path.is_file() and feature_path.is_file() and mask_path.is_file()):\n return None\n if uid_path.read_text().splitlines() != list(expected_uids):\n return None\n features = np.load(feature_path, mmap_mode='r')\n mask = np.load(mask_path, mmap_mode='r')\n if features.shape[:3] != (len(expected_uids), 6, 7) or mask.shape != (len(expected_uids), 6):\n return None\n log('report-teacher: exact attached visible-test features reused')\n return (features, mask)\n\ndef _rt_extract_features(test_df, series_df, checkpoint_dir, dev):\n from transformers import AutoModel\n expected_uids = test_df['StudyInstanceUID'].astype(str).tolist()\n attached = _rt_try_attached_visible_features(checkpoint_dir, expected_uids)\n if attached is not None:\n return attached\n if time.time() - T0 > RT_START_CUTOFF_S:\n raise TimeoutError('insufficient runtime reserve for report-teacher feature extraction')\n dino_dir = _rt_find_dino_base()\n log(f'report-teacher: DINOv2 base from {dino_dir}')\n dino = AutoModel.from_pretrained(str(dino_dir), local_files_only=True).eval().to(dev)\n for parameter in dino.parameters():\n parameter.requires_grad_(False)\n dino_dim = int(dino.config.hidden_size)\n if dino_dim != 768:\n raise AssertionError(f'expected DINOv2-base hidden size 768, got {dino_dim}')\n mean = torch.tensor([0.485, 0.456, 0.406]).view(1, 3, 1, 1)\n std = torch.tensor([0.229, 0.224, 0.225]).view(1, 3, 1, 1)\n slot_lookup = _rt_assign_slots(series_df)\n features = np.zeros((len(expected_uids), 6, RT_SLICES, dino_dim * 2), np.float16)\n slot_mask = np.zeros((len(expected_uids), 6), bool)\n\n @torch.inference_mode()\n def encode(images):\n tensor = torch.from_numpy(images).permute(0, 3, 1, 2).float() / 255.0\n tensor = (tensor - mean) / std\n parts = []\n for start in range(0, len(tensor), 8):\n batch = tensor[start:start + 8].to(dev, non_blocking=True)\n with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=dev.type == 'cuda'):\n output = dino(pixel_values=batch, interpolate_pos_encoding=True)\n tokens = output.last_hidden_state\n part = torch.cat((tokens[:, 0], tokens[:, 1:].mean(dim=1)), dim=-1)\n parts.append(part.float().cpu())\n return torch.cat(parts, dim=0).numpy().astype(np.float32)\n for row_index, study_uid in enumerate(expected_uids):\n if time.time() - T0 > RT_DEADLINE_S:\n raise TimeoutError('report-teacher deadline reached before submission overwrite')\n jobs = [(slot_id, slot_lookup[study_uid, slot_id]) for slot_id in range(6) if (study_uid, slot_id) in slot_lookup]\n\n def load_job(job):\n slot_id, series_uid = job\n return (slot_id, _rt_load_series_25d(study_uid, series_uid))\n if jobs:\n with ThreadPoolExecutor(max_workers=4) as executor:\n loaded = list(executor.map(load_job, jobs))\n encoded = encode(np.concatenate([views for _, views in loaded], axis=0))\n cursor = 0\n for slot_id, views in loaded:\n count = len(views)\n features[row_index, slot_id] = encoded[cursor:cursor + count].astype(np.float16)\n slot_mask[row_index, slot_id] = True\n cursor += count\n if row_index == 0 or (row_index + 1) % 100 == 0 or row_index + 1 == len(expected_uids):\n log(f'report-teacher features {row_index + 1}/{len(expected_uids)}')\n if dev.type == 'cuda' and (row_index + 1) % 100 == 0:\n torch.cuda.empty_cache()\n del dino\n gc.collect()\n if dev.type == 'cuda':\n torch.cuda.empty_cache()\n return (features, slot_mask)\n\n@torch.inference_mode()\ndef _rt_predict_checkpoints(features, slot_mask, checkpoint_dir, dev):\n syn_index = TARGETS.index('Synovitis')\n seed_predictions = []\n for seed in RT_SEEDS:\n seed_prediction = np.zeros(len(features), np.float32)\n for fold in range(4):\n if time.time() - T0 > RT_DEADLINE_S:\n raise TimeoutError('report-teacher deadline reached during checkpoint ensemble')\n path = checkpoint_dir / f'rta_final_seed{seed}_fold{fold}.pth'\n checkpoint = torch.load(path, map_location='cpu', weights_only=False)\n if checkpoint.get('targets') != TARGETS:\n raise AssertionError(f'target order mismatch in {path.name}')\n cfg = checkpoint['cfg']\n model = RTAHMIL(in_dim=int(checkpoint['slice_feat_dim']), hidden_dim=int(cfg['hidden_dim']), n_targets=len(TARGETS), n_slots=int(cfg['n_slots']), n_slices=int(cfg['slices_per_series']), dropout=float(cfg['dropout']), series_dropout=float(cfg['series_dropout']))\n model.load_state_dict(checkpoint['state_dict'], strict=True)\n model.eval().to(dev)\n fold_prediction = []\n for start in range(0, len(features), 48):\n x = torch.from_numpy(np.asarray(features[start:start + 48])).float().to(dev)\n mask = torch.from_numpy(np.asarray(slot_mask[start:start + 48])).bool().to(dev)\n with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=dev.type == 'cuda'):\n logits = model(x, mask)\n fold_prediction.append(torch.sigmoid(logits[:, syn_index]).float().cpu().numpy())\n seed_prediction += np.concatenate(fold_prediction) / 4.0\n del model, checkpoint\n gc.collect()\n if dev.type == 'cuda':\n torch.cuda.empty_cache()\n seed_predictions.append(seed_prediction)\n return np.mean(np.stack(seed_predictions, axis=0), axis=0)\n\ndef _rt_blend_synovitis(primary, teacher_synovitis, teacher_uids):\n result = primary.copy()\n primary_uids = result['StudyInstanceUID'].astype(str)\n teacher = pd.Series(np.asarray(teacher_synovitis, dtype=np.float64), index=pd.Index([str(uid) for uid in teacher_uids], name='StudyInstanceUID'))\n if teacher.index.has_duplicates or set(primary_uids) != set(teacher.index):\n raise AssertionError('report-teacher and primary StudyInstanceUID sets differ')\n teacher = teacher.reindex(primary_uids.values)\n if not np.isfinite(teacher.values).all():\n raise AssertionError('non-finite report-teacher prediction')\n base_rank = result['Synovitis'].rank(pct=True).to_numpy(np.float64)\n teacher_rank = teacher.rank(pct=True).to_numpy(np.float64)\n result['Synovitis'] = (1.0 - RT_SYN_WEIGHT) * base_rank + RT_SYN_WEIGHT * teacher_rank\n return result\n\ndef run_report_teacher_synovitis_specialist():\n if time.time() - T0 > RT_START_CUTOFF_S:\n log('report-teacher skipped: the primary ensemble used its runtime reserve')\n return False\n checkpoint_dir = _rt_find_checkpoint_dir()\n primary_path = Path('submission.csv')\n primary = pd.read_csv(primary_path, dtype={'StudyInstanceUID': str})\n if primary.columns.tolist() != ['StudyInstanceUID'] + TARGETS:\n raise AssertionError('primary submission schema mismatch')\n test_df = pd.read_csv(ROOT / 'test.csv', dtype={'StudyInstanceUID': str})\n series_df = pd.read_csv(ROOT / 'test_series.csv', dtype={'StudyInstanceUID': str, 'SeriesInstanceUID': str})\n expected_uids = test_df['StudyInstanceUID'].astype(str).tolist()\n dev = DEVS[0]\n features, slot_mask = _rt_extract_features(test_df, series_df, checkpoint_dir, dev)\n teacher_synovitis = _rt_predict_checkpoints(features, slot_mask, checkpoint_dir, dev)\n result = _rt_blend_synovitis(primary, teacher_synovitis, expected_uids)\n untouched = [target for target in TARGETS if target != 'Synovitis']\n if not result[untouched].equals(primary[untouched]):\n raise AssertionError('report-teacher changed a non-Synovitis target')\n if result.shape != primary.shape or not np.isfinite(result[TARGETS].to_numpy()).all():\n raise AssertionError('invalid report-teacher blend')\n temp_path = Path('submission_v26_synovitis.tmp.csv')\n result.to_csv(temp_path, index=False)\n reread = pd.read_csv(temp_path)\n if reread.shape != primary.shape or not np.isfinite(reread[TARGETS].to_numpy()).all():\n raise AssertionError('serialized report-teacher blend is invalid')\n temp_path.replace(primary_path)\n log('report-teacher complete: 0.75 Synovitis rank blend; all other targets preserved')\n return True","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:07.075383Z","iopub.execute_input":"2026-08-17T17:07:07.075628Z","iopub.status.idle":"2026-08-17T17:07:07.405491Z","shell.execute_reply.started":"2026-08-17T17:07:07.075609Z","shell.execute_reply":"2026-08-17T17:07:07.404693Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import base64\nimport gc\nimport hashlib\nimport io\nimport json\nimport math\nimport os\nimport random\nimport time\nimport zlib\nfrom concurrent.futures import ThreadPoolExecutor\nfrom functools import lru_cache\nfrom pathlib import Path\nimport cv2\nimport joblib\nimport numpy as np\nimport pandas as pd\nimport pydicom\nfrom scipy.stats import rankdata\nfrom sklearn.ensemble import ExtraTreesClassifier, HistGradientBoostingClassifier\nfrom sklearn.decomposition import PCA\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import StandardScaler\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom transformers import AutoModel\nHYB_PREFIX = 'v8_hybrid_dino224_6slot_5pos_radiomics'\nHYB_EXPECTED_TRAIN_ID_SHA256 = '21c1944bd15c3397290f0816de614ad4153f62e84c4bfb0e4d6147ac72084af8'\nHYB_TEACHER_PAYLOAD = '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'\nHYB_START_CUTOFF_S = 7.2 * 3600\nHYB_DEADLINE_S = 8.72 * 3600\nHYB_IMG_SIZE = 224\nHYB_N_POSITIONS = 5\nHYB_N_SLOTS = 6\nHYB_SLOT_META_DIM = 8\nHYB_STUDY_META_DIM = 13\nHYB_RAD_DIM = 14\nHYB_RAD_AGG_DIM = 56\nHYB_SEEDS = (20260809, 20260810, 20260811, 20260814, 20260815, 20260816, 20260817, 20260818)\nHYB_LM_FAMILY_WEIGHTS = (0.5227272727272728, 0.27272727272727276, 0.20454545454545456, 0.0)\nHYB_FAMILIES = ('lr', 'et', 'hgb', 'exact_lr')\nHYB_FAMILY_WEIGHTS = (0.46, 0.24, 0.18, 0.12)\nHYB_LR_CS = (0.015, 0.05, 0.16, 0.5)\nHYB_EXACT_LR_CS = (0.01, 0.03, 0.1, 0.3)\nHYB_TARGET = 'Lateral Meniscus'\nHYB_OA_TARGET = 'Lateral OA'\nHYB_OA_SEEDS = (20260809, 20260810, 20260811, 20260812, 20260813, 20260814, 20260815, 20260816, 20260817, 20260818)\nHYB_OA_FAMILY_WEIGHTS = (0.5227272727272728, 0.27272727272727276, 0.20454545454545456, 0.0)\nHYB_PLANES = ('Sagittal', 'Coronal', 'Axial')\nHYB_CONTRASTS = ('Fluid', 'Structural')\nHYB_SLOT_NAMES = tuple((f'{plane}_{contrast}' for plane in HYB_PLANES for contrast in HYB_CONTRASTS))\n\ndef _hyb_required_cache_names():\n names = []\n for split in ('train', 'test'):\n stem = f'{split}_{HYB_PREFIX}_'\n names.extend((stem + suffix for suffix in ('slot_features.npy', 'slot_mask.npy', 'slot_meta.npy', 'radiomics.npy', 'study_meta.npy', 'sex.npy', 'ids.npy')))\n names.append(f'{HYB_PREFIX}_ipca_192.joblib')\n return names\n\ndef _hyb_find_cache_dir():\n local = globals().get('HYB_LOCAL_CACHE_DIR')\n candidates = []\n if local:\n candidates.append(Path(local))\n root = Path('/kaggle/input')\n if root.is_dir():\n marker = f'train_{HYB_PREFIX}_slot_features.npy'\n candidates.extend((hit.parent for hit in root.glob(f'*/{marker}')))\n candidates.extend((hit.parent for hit in root.glob(f'*/*/{marker}')))\n required = _hyb_required_cache_names()\n for path in candidates:\n if all(((path / name).is_file() for name in required)):\n return path\n raise FileNotFoundError('the complete public hybrid feature/PCA cache is absent')\n\ndef _hyb_find_dino_small():\n preferred = (Path('/kaggle/input/models/metaresearch/dinov2/pytorch/small/1'), Path('/kaggle/input/dinov2/pytorch/small/1'), Path('/kaggle/input/dinov2-small/pytorch/small/1'))\n for path in preferred:\n if (path / 'config.json').is_file():\n return path\n for top in Path('/kaggle/input').glob('*'):\n if not top.is_dir() or 'dino' not in top.name.lower():\n continue\n for config_path in top.glob('**/config.json'):\n try:\n cfg = json.loads(config_path.read_text())\n if cfg.get('model_type') == 'dinov2' and int(cfg.get('hidden_size', -1)) == 384:\n return config_path.parent\n except Exception:\n continue\n raise FileNotFoundError('offline DINOv2-small model is absent')\n\ndef _hyb_numeric(value, default=0.0):\n try:\n value = float(value)\n return value if np.isfinite(value) else default\n except Exception:\n return default\n\ndef _hyb_sex_to_id(row):\n value = str(row.get('PatientSex', '')).strip().lower()\n if value.startswith('m'):\n return 1\n if value.startswith('f'):\n return 2\n return 0\n\ndef _hyb_choose_series(part, contrast, used_ids):\n if len(part) == 0:\n return None\n fluid = part['Fluid_Sensitive'].fillna(0).astype(float)\n fat = part['Fat_Suppression'].fillna(0).astype(float)\n if contrast == 'Fluid':\n score = 4.0 * fluid + 2.0 * fat\n else:\n score = 3.5 * (1.0 - fluid) + 1.5 * (1.0 - fat)\n ordered = part.assign(_slot_score=score).sort_values('_slot_score', ascending=False)\n for _, row in ordered.iterrows():\n series_id = str(row['SeriesInstanceUID'])\n if series_id not in used_ids:\n return row\n return ordered.iloc[0]\n\ndef _hyb_build_slots(series_df):\n slots, study_meta = ({}, {})\n for study_id, rows in series_df.groupby('StudyInstanceUID', sort=False):\n study_id = str(study_id)\n selected, meta = ({}, [])\n plane_lower = rows['Anatomical_Plane'].astype(str).str.lower()\n for plane in HYB_PLANES:\n part = rows[plane_lower == plane.lower()]\n count = len(part)\n fluid_mean = part['Fluid_Sensitive'].fillna(0).astype(float).mean() if count else 0.0\n fat_mean = part['Fat_Suppression'].fillna(0).astype(float).mean() if count else 0.0\n meta.extend([np.log1p(count) / 3.0, fluid_mean, fat_mean])\n used = set()\n for contrast in HYB_CONTRASTS:\n row = _hyb_choose_series(part, contrast, used)\n if row is None:\n continue\n sid = str(row['SeriesInstanceUID'])\n used.add(sid)\n selected[f'{plane}_{contrast}'] = {'series_id': sid, 'contrast': contrast, 'fluid': _hyb_numeric(row.get('Fluid_Sensitive', 0)), 'fat': _hyb_numeric(row.get('Fat_Suppression', 0))}\n total = len(rows)\n meta.extend([np.log1p(total) / 4.0, rows['Fluid_Sensitive'].fillna(0).astype(float).mean() if total else 0.0, rows['Fat_Suppression'].fillna(0).astype(float).mean() if total else 0.0, rows['SeriesInstanceUID'].nunique() / 12.0 if total else 0.0])\n slots[study_id] = selected\n study_meta[study_id] = np.asarray(meta, dtype=np.float32)\n return (slots, study_meta)\n\ndef _hyb_locate_series_dir(study_uid, series_uid):\n candidates = (ROOT / 'test_series' / str(study_uid) / str(series_uid), ROOT / 'test_series' / str(series_uid), ROOT / 'test' / str(study_uid) / str(series_uid), ROOT / 'test_images' / str(study_uid) / str(series_uid), ROOT / 'test_dicom' / str(study_uid) / str(series_uid), ROOT / 'test_dicoms' / str(study_uid) / str(series_uid), ROOT / 'images' / 'test' / str(study_uid) / str(series_uid))\n for path in candidates:\n if path.is_dir():\n return path\n raise FileNotFoundError(f'hybrid series missing: study={study_uid}, series={series_uid}')\n\ndef _hyb_read_header(path):\n try:\n return pydicom.dcmread(str(path), stop_before_pixels=True, force=True)\n except Exception:\n return None\n\ndef _hyb_header_position(ds):\n if ds is None:\n return None\n try:\n ipp = np.asarray([float(x) for x in ds.ImagePositionPatient], dtype=np.float64)\n iop = np.asarray([float(x) for x in ds.ImageOrientationPatient], dtype=np.float64)\n return float(np.dot(ipp, np.cross(iop[:3], iop[3:])))\n except Exception:\n pass\n for name in ('SliceLocation', 'InstanceNumber'):\n try:\n return float(getattr(ds, name))\n except Exception:\n continue\n return None\n\n@lru_cache(maxsize=8192)\ndef _hyb_ordered_files(folder_str):\n files = sorted(Path(folder_str).glob('*.dcm'))\n if not files:\n files = sorted((path for path in Path(folder_str).iterdir() if path.is_file()))\n keyed, ok = ([], 0)\n for fallback, path in enumerate(files):\n key = _hyb_header_position(_hyb_read_header(path))\n if key is None:\n key = fallback\n else:\n ok += 1\n keyed.append((key, str(path)))\n if ok >= max(3, len(files) // 3):\n keyed.sort(key=lambda pair: pair[0])\n return tuple((path for _, path in keyed))\n\ndef _hyb_spacing(ds):\n spacing_x = spacing_y = thickness = 0.0\n try:\n ps = [float(x) for x in ds.PixelSpacing]\n spacing_y, spacing_x = (ps[0], ps[1])\n except Exception:\n pass\n for name in ('SliceThickness', 'SpacingBetweenSlices'):\n try:\n thickness = float(getattr(ds, name))\n break\n except Exception:\n continue\n return (spacing_x, spacing_y, thickness)\n\ndef _hyb_read_pixel(path):\n ds = pydicom.dcmread(str(path), force=True)\n array = ds.pixel_array.astype(np.float32)\n array = array * _hyb_numeric(getattr(ds, 'RescaleSlope', 1.0), 1.0)\n array += _hyb_numeric(getattr(ds, 'RescaleIntercept', 0.0), 0.0)\n if str(getattr(ds, 'PhotometricInterpretation', '')).upper() == 'MONOCHROME1':\n array = array.max() - array\n return (array, ds)\n\ndef _hyb_robust_uint8(stack):\n stack = np.asarray(stack, dtype=np.float32)\n finite = stack[np.isfinite(stack)]\n if finite.size == 0:\n return np.zeros(stack.shape, dtype=np.uint8)\n low, high = np.percentile(finite, [1.0, 99.4])\n if high <= low:\n low, high = (float(finite.min()), float(finite.max()))\n if high <= low:\n return np.zeros(stack.shape, dtype=np.uint8)\n return (255.0 * np.clip((stack - low) / (high - low), 0.0, 1.0)).astype(np.uint8)\n\ndef _hyb_crop_foreground(image):\n gray = image.max(axis=2)\n mask = gray > max(8, np.percentile(gray, 55) * 0.18)\n if mask.sum() < 64:\n return image\n ys, xs = np.where(mask)\n y0, y1, x0, x1 = (int(ys.min()), int(ys.max()) + 1, int(xs.min()), int(xs.max()) + 1)\n pad_y, pad_x = (int(0.08 * (y1 - y0 + 1)), int(0.08 * (x1 - x0 + 1)))\n y0, y1 = (max(0, y0 - pad_y), min(image.shape[0], y1 + pad_y))\n x0, x1 = (max(0, x0 - pad_x), min(image.shape[1], x1 + pad_x))\n if y1 - y0 < 32 or x1 - x0 < 32:\n return image\n return image[y0:y1, x0:x1]\n\ndef _hyb_resize(image):\n return cv2.resize(image, (HYB_IMG_SIZE, HYB_IMG_SIZE), interpolation=cv2.INTER_AREA)\n\ndef _hyb_view_radiomics(image):\n gray = image.astype(np.float32).mean(axis=2) / 255.0\n height, width = gray.shape\n q = np.percentile(gray, [1, 5, 10, 25, 50, 75, 90, 95, 99])\n center = gray[height // 4:3 * height // 4, width // 4:3 * width // 4]\n gy, gx = np.gradient(gray)\n grad = np.sqrt(gx * gx + gy * gy)\n foreground = gray > 0.08\n return np.asarray([gray.mean(), gray.std(), q[0], q[2], q[4], q[6], q[8], center.mean(), center.std(), grad.mean(), grad.std(), foreground.mean(), gray[foreground].mean() if foreground.any() else 0.0, gray[foreground].std() if foreground.any() else 0.0], dtype=np.float32)\n\ndef _hyb_make_view(paths):\n arrays, first_ds = ([], None)\n for path in paths:\n try:\n array, ds = _hyb_read_pixel(path)\n first_ds = ds if first_ds is None else first_ds\n arrays.append(array)\n except Exception:\n return (None, np.zeros(HYB_RAD_DIM, np.float32), (0.0, 0.0, 0.0))\n image = np.transpose(_hyb_robust_uint8(np.stack(arrays)), (1, 2, 0))\n image = _hyb_resize(_hyb_crop_foreground(image))\n return (np.transpose(image, (2, 0, 1)), _hyb_view_radiomics(image), _hyb_spacing(first_ds) if first_ds is not None else (0.0, 0.0, 0.0))\n\ndef _hyb_sampled_triplets(study_uid, series_uid):\n files = list(_hyb_ordered_files(str(_hyb_locate_series_dir(study_uid, series_uid))))\n if not files:\n return ([], 0)\n centers = np.round(np.linspace(0.08 * (len(files) - 1), 0.92 * (len(files) - 1), HYB_N_POSITIONS)).astype(int)\n centers = np.clip(centers, 0, len(files) - 1)\n return ([[files[max(0, center - 1)], files[center], files[min(len(files) - 1, center + 1)]] for center in centers], len(files))\n\ndef _hyb_load_study(row, slots, study_meta):\n study_uid = str(row['StudyInstanceUID'])\n images = np.zeros((6, 5, 3, 224, 224), np.uint8)\n view_mask = np.zeros((6, 5), bool)\n slot_meta = np.zeros((6, 8), np.float32)\n radiomics = np.zeros((6, 56), np.float32)\n selected = slots.get(study_uid, {})\n for slot_index, slot_name in enumerate(HYB_SLOT_NAMES):\n info = selected.get(slot_name)\n if info is None:\n continue\n triplets, n_files = _hyb_sampled_triplets(study_uid, info['series_id'])\n rad_values, spacings = ([], [])\n for pos_index, paths in enumerate(triplets[:5]):\n image, rad, spacing = _hyb_make_view(paths)\n if image is None:\n continue\n images[slot_index, pos_index] = image\n view_mask[slot_index, pos_index] = True\n rad_values.append(rad)\n spacings.append(spacing)\n if rad_values:\n rad_array = np.stack(rad_values).astype(np.float32)\n radiomics[slot_index] = np.concatenate([rad_array.mean(0), rad_array.std(0), rad_array.min(0), rad_array.max(0)])\n spacing_mean = np.asarray(spacings, np.float32).mean(0)\n else:\n spacing_mean = np.zeros(3, np.float32)\n slot_meta[slot_index] = np.asarray([info['fluid'], info['fat'], float(info['contrast'] == 'Structural'), np.log1p(n_files) / 6.0, float(view_mask[slot_index].mean()), spacing_mean[0] / 2.5 if spacing_mean[0] else 0.0, spacing_mean[1] / 2.5 if spacing_mean[1] else 0.0, spacing_mean[2] / 8.0 if spacing_mean[2] else 0.0], np.float32)\n return (images, view_mask, slot_meta, radiomics, study_meta.get(study_uid, np.zeros(13, np.float32)), _hyb_sex_to_id(row), study_uid)\n\nclass _HybridDinoEncoder(nn.Module):\n\n def __init__(self, backbone):\n super().__init__()\n self.backbone = backbone\n\n def forward(self, pixel_values):\n tokens = self.backbone(pixel_values=pixel_values).last_hidden_state\n patches = tokens[:, 1:]\n return torch.cat([F.normalize(tokens[:, 0], dim=1), F.normalize(patches.mean(dim=1), dim=1), F.normalize(patches.amax(dim=1), dim=1)], dim=1)\n\ndef _hyb_load_cached_split(cache_dir, split):\n stem = f'{split}_{HYB_PREFIX}_'\n return tuple((np.load(cache_dir / (stem + suffix), mmap_mode=None if suffix == 'ids.npy' else 'r', allow_pickle=suffix == 'ids.npy') for suffix in ('slot_features.npy', 'slot_mask.npy', 'slot_meta.npy', 'radiomics.npy', 'study_meta.npy', 'sex.npy', 'ids.npy')))\n\ndef _hyb_extract_test_bundle(test_df, series_df, cache_dir, dev):\n expected_uids = test_df['StudyInstanceUID'].astype(str).to_numpy()\n cached = _hyb_load_cached_split(cache_dir, 'test')\n if np.array_equal(np.asarray(cached[-1]).astype(str), expected_uids):\n log('hybrid: exact attached visible-test features reused')\n return cached\n if time.time() - T0 > HYB_START_CUTOFF_S:\n raise TimeoutError('insufficient runtime reserve for hybrid feature extraction')\n slots, study_meta = _hyb_build_slots(series_df)\n backbone = AutoModel.from_pretrained(str(_hyb_find_dino_small()), local_files_only=True, trust_remote_code=False)\n if int(backbone.config.hidden_size) != 384:\n raise AssertionError('the hybrid specialist requires DINOv2-small hidden size 384')\n model = _HybridDinoEncoder(backbone).eval().to(dev)\n for parameter in model.parameters():\n parameter.requires_grad_(False)\n mean = torch.tensor([0.485, 0.456, 0.406], device=dev).view(1, 3, 1, 1)\n std = torch.tensor([0.229, 0.224, 0.225], device=dev).view(1, 3, 1, 1)\n\n @torch.inference_mode()\n def encode(images):\n outputs = []\n for start in range(0, len(images), 64):\n batch = images[start:start + 64].to(dev, non_blocking=True).float().div_(255.0)\n batch = (batch - mean) / std\n with torch.autocast('cuda', dtype=torch.float16, enabled=dev.type == 'cuda'):\n outputs.append(model(batch).float().cpu())\n return torch.cat(outputs, dim=0)\n n = len(test_df)\n features = np.zeros((n, 6, 3456), np.float16)\n masks = np.zeros((n, 6), bool)\n slot_meta_array = np.zeros((n, 6, 8), np.float16)\n radiomics_array = np.zeros((n, 6, 56), np.float16)\n study_meta_array = np.zeros((n, 13), np.float16)\n sexes = np.zeros(n, np.int8)\n ids = expected_uids.astype(object)\n\n def safe_load(index):\n try:\n return _hyb_load_study(test_df.iloc[index], slots, study_meta)\n except Exception as exc:\n uid = str(test_df.iloc[index]['StudyInstanceUID'])\n log(f'hybrid study decode failed safely: {uid}: {exc}')\n return (np.zeros((6, 5, 3, 224, 224), np.uint8), np.zeros((6, 5), bool), np.zeros((6, 8), np.float32), np.zeros((6, 56), np.float32), np.zeros(13, np.float32), 0, uid)\n workers = max(1, min(8, os.cpu_count() or 8))\n with ThreadPoolExecutor(max_workers=workers) as executor:\n for start in range(0, n, 6):\n if time.time() - T0 > HYB_DEADLINE_S:\n raise TimeoutError('hybrid deadline reached during feature extraction')\n stop = min(start + 6, n)\n items = list(executor.map(safe_load, range(start, stop)))\n image_batch = torch.from_numpy(np.stack([item[0] for item in items]))\n view_mask = torch.from_numpy(np.stack([item[1] for item in items]))\n valid = view_mask.reshape(-1)\n view_features = torch.zeros(len(items) * 30, 1152, dtype=torch.float32)\n if valid.any():\n flat_images = image_batch.reshape(-1, 3, 224, 224)\n view_features[valid] = encode(flat_images[valid])\n view_features = view_features.reshape(len(items), 6, 5, 1152)\n aggregate = torch.zeros(len(items), 6, 3456, dtype=torch.float32)\n slot_mask = view_mask.any(dim=2)\n for batch_index in range(len(items)):\n for slot_index in range(6):\n present = view_mask[batch_index, slot_index]\n if present.any():\n values = view_features[batch_index, slot_index, present]\n aggregate[batch_index, slot_index] = torch.cat([values.mean(0), values.amax(0), values.std(0, unbiased=False)])\n features[start:stop] = aggregate.numpy().astype(np.float16)\n masks[start:stop] = slot_mask.numpy()\n slot_meta_array[start:stop] = np.stack([item[2] for item in items]).astype(np.float16)\n radiomics_array[start:stop] = np.stack([item[3] for item in items]).astype(np.float16)\n study_meta_array[start:stop] = np.stack([item[4] for item in items]).astype(np.float16)\n sexes[start:stop] = np.asarray([item[5] for item in items], np.int8)\n if start == 0 or stop % 100 == 0 or stop == n:\n log(f'hybrid features {stop}/{n}')\n del model, backbone\n gc.collect()\n if dev.type == 'cuda':\n torch.cuda.empty_cache()\n return (features, masks, slot_meta_array, radiomics_array, study_meta_array, sexes, ids)\n\ndef _hyb_align_bundle(bundle, expected_uids):\n ids = np.asarray(bundle[-1]).astype(str)\n expected_uids = np.asarray(expected_uids).astype(str)\n if np.array_equal(ids, expected_uids):\n return bundle\n if len(set(ids)) != len(ids) or set(ids) != set(expected_uids):\n raise AssertionError('hybrid cache StudyInstanceUID set mismatch')\n positions = {uid: index for index, uid in enumerate(ids)}\n order = np.asarray([positions[uid] for uid in expected_uids], dtype=int)\n return tuple((np.asarray(array)[order] for array in bundle[:-1])) + (expected_uids,)\n\ndef _hyb_transform(bundle, pca):\n features, masks, slot_meta, radiomics, study_meta, sex, _ = bundle\n n = len(features)\n result = np.zeros((n, 6, 192), np.float32)\n for start in range(0, n, 96):\n stop = min(start + 96, n)\n block = np.asarray(features[start:stop], np.float32)\n block_mask = np.asarray(masks[start:stop]).reshape(-1).astype(bool)\n flat = block.reshape(-1, block.shape[-1])\n transformed = np.zeros((len(flat), 192), np.float32)\n if block_mask.any():\n transformed[block_mask] = pca.transform(flat[block_mask]).astype(np.float32)\n result[start:stop] = transformed.reshape(stop - start, 6, 192)\n sex_onehot = np.eye(3, dtype=np.float32)[np.asarray(sex, dtype=int).clip(0, 2)]\n matrix = np.concatenate([result.reshape(n, -1), np.asarray(masks, np.float32), np.asarray(slot_meta, np.float32).reshape(n, -1), np.asarray(radiomics, np.float32).reshape(n, -1), np.asarray(study_meta, np.float32), sex_onehot], axis=1)\n matrix = np.nan_to_num(matrix, nan=0.0, posinf=0.0, neginf=0.0)\n if matrix.shape != (n, 1558):\n raise AssertionError(f'unexpected hybrid matrix shape {matrix.shape}')\n return matrix.astype(np.float32)\n\ndef _hyb_rank(values, denominator_offset=0.0):\n values = np.asarray(values, np.float64)\n if len(values) <= 1 or np.ptp(values) < 1e-12:\n return np.full(len(values), 0.5, np.float64)\n return rankdata(values, method='average') / (len(values) + denominator_offset)\n\ndef _hyb_payload():\n raw = zlib.decompress(base64.b64decode(HYB_TEACHER_PAYLOAD.encode('ascii')))\n with np.load(io.BytesIO(raw), allow_pickle=False) as payload:\n return {name: payload[name].astype(np.float32) for name in payload.files}\n\ndef _hyb_select_top(indices, scores, labels, class_value, cap=2200):\n keep = indices[labels == class_value]\n if len(keep) <= cap:\n return keep\n keep_scores = scores[labels == class_value]\n return keep[np.argsort(-keep_scores)[:cap]]\n\ndef _hyb_training_arrays(pseudo_y, pseudo_conf, exact_mask, exact_y):\n exact_idx = np.flatnonzero(exact_mask)\n pseudo_pool = ~exact_mask\n confidence = np.clip(pseudo_conf, 0.0, 1.0)\n candidates = np.flatnonzero(pseudo_pool & (confidence >= 0.2))\n candidate_labels = (pseudo_y[candidates] >= 0.5).astype(int)\n pos = _hyb_select_top(candidates, confidence[candidates], candidate_labels, 1)\n neg = _hyb_select_top(candidates, confidence[candidates], candidate_labels, 0)\n pseudo_idx = np.concatenate([pos, neg]).astype(int)\n pseudo_labels = (pseudo_y[pseudo_idx] >= 0.5).astype(int)\n pseudo_weight = 0.18 + 1.15 * np.power(np.clip(confidence[pseudo_idx], 0, 1), 1.4)\n fit_idx = np.concatenate([exact_idx, pseudo_idx]).astype(int)\n fit_y = np.concatenate([exact_y[exact_idx].astype(int), pseudo_labels]).astype(int)\n fit_weight = np.concatenate([np.full(len(exact_idx), 7.0, np.float32), pseudo_weight.astype(np.float32)])\n return (fit_idx, fit_y, fit_weight, exact_idx, exact_y[exact_idx].astype(int))\n\ndef _hyb_fit_lr(x_fit, y_fit, x_test, weights, cs, seed):\n predictions = []\n for index, c_value in enumerate(cs):\n model = LogisticRegression(C=c_value, solver='liblinear', class_weight='balanced', max_iter=3000, random_state=seed + 31 * index)\n model.fit(x_fit, y_fit, sample_weight=weights)\n predictions.append(model.predict_proba(x_test)[:, 1])\n return np.mean(predictions, axis=0).astype(np.float32)\n\ndef _hyb_fit_family(family, x_train, fit_idx, fit_y, fit_weight, x_test, seed):\n if time.time() - T0 > HYB_DEADLINE_S:\n raise TimeoutError('hybrid deadline reached during model fitting')\n if family == 'lr':\n return _hyb_fit_lr(x_train[fit_idx], fit_y, x_test, fit_weight, HYB_LR_CS, seed)\n if family == 'exact_lr':\n return _hyb_fit_lr(x_train[fit_idx], fit_y, x_test, fit_weight, HYB_EXACT_LR_CS, seed)\n if family == 'et':\n model = ExtraTreesClassifier(n_estimators=420, max_features='sqrt', min_samples_leaf=4, min_samples_split=8, bootstrap=False, class_weight='balanced', random_state=seed, n_jobs=-1)\n elif family == 'hgb':\n model = HistGradientBoostingClassifier(learning_rate=0.035, max_iter=180, max_leaf_nodes=15, min_samples_leaf=18, l2_regularization=0.25, early_stopping=True, validation_fraction=0.15, random_state=seed)\n else:\n raise ValueError(f'unknown hybrid family {family}')\n model.fit(x_train[fit_idx], fit_y, sample_weight=fit_weight)\n return model.predict_proba(x_test)[:, 1].astype(np.float32)\n\ndef _hyb_teacher_arm(x_train, x_test, pseudo_y, pseudo_conf, exact_mask, exact_y, exact_lr):\n fit_idx, fit_y, fit_weight, _, _ = _hyb_training_arrays(pseudo_y, pseudo_conf, exact_mask, exact_y)\n predictions = {}\n for family in ('lr', 'et', 'hgb'):\n seed_predictions = []\n for seed in HYB_SEEDS:\n model_seed = seed + 101 * TARGETS.index(HYB_TARGET) + len(family)\n seed_predictions.append(_hyb_fit_family(family, x_train, fit_idx, fit_y, fit_weight, x_test, model_seed))\n predictions[family] = np.mean(np.stack(seed_predictions), axis=0)\n predictions['exact_lr'] = exact_lr\n weighted_rank = np.zeros(len(x_test), np.float64)\n weighted_prob = np.zeros(len(x_test), np.float64)\n for weight, family in zip(HYB_FAMILY_WEIGHTS, HYB_FAMILIES):\n pred = np.clip(predictions[family], 1e-05, 1.0 - 1e-05)\n weighted_rank += weight * _hyb_rank(pred, denominator_offset=1.0)\n weighted_prob += weight * pred\n return 0.9 * weighted_rank + 0.1 * weighted_prob\n\ndef run_hybrid_lm_and_lateral_oa_specialists():\n if time.time() - T0 > HYB_START_CUTOFF_S:\n log('hybrid skipped: insufficient runtime reserve')\n return False\n cache_dir = _hyb_find_cache_dir()\n primary_path = Path('submission.csv')\n primary = pd.read_csv(primary_path, dtype={'StudyInstanceUID': str})\n train_df = pd.read_csv(ROOT / 'train.csv', dtype={'StudyInstanceUID': str})\n test_df = pd.read_csv(ROOT / 'test.csv', dtype={'StudyInstanceUID': str})\n series_df = pd.read_csv(ROOT / 'test_series.csv', dtype={'StudyInstanceUID': str, 'SeriesInstanceUID': str})\n if primary.columns.tolist() != ['StudyInstanceUID'] + TARGETS:\n raise AssertionError('primary submission schema mismatch')\n train_uids = train_df['StudyInstanceUID'].astype(str).to_numpy()\n uid_hash = hashlib.sha256('\\n'.join(train_uids).encode()).hexdigest()\n if uid_hash != HYB_EXPECTED_TRAIN_ID_SHA256:\n raise AssertionError('competition train StudyInstanceUID order drifted')\n test_uids = test_df['StudyInstanceUID'].astype(str).to_numpy()\n dev = DEVS[0]\n train_bundle = _hyb_align_bundle(_hyb_load_cached_split(cache_dir, 'train'), train_uids)\n test_bundle = _hyb_align_bundle(_hyb_extract_test_bundle(test_df, series_df, cache_dir, dev), test_uids)\n pca = joblib.load(cache_dir / f'{HYB_PREFIX}_ipca_192.joblib')\n x_train_raw = _hyb_transform(train_bundle, pca)\n x_test_raw = _hyb_transform(test_bundle, pca)\n joint = np.concatenate([x_train_raw, x_test_raw], axis=0)\n mean = joint.mean(axis=0, dtype=np.float64).astype(np.float32)\n scale = joint.std(axis=0, dtype=np.float64).astype(np.float32)\n scale[scale < 1e-05] = 1.0\n x_train = ((x_train_raw - mean) / scale).astype(np.float32)\n x_test = ((x_test_raw - mean) / scale).astype(np.float32)\n payload = _hyb_payload()\n if any((len(payload[name]) != len(train_df) for name in payload)):\n raise AssertionError('embedded hybrid teacher length mismatch')\n\n def fit_target(target_name, pseudo_y, pseudo_conf, seeds):\n exact_mask = train_df[target_name].notna().to_numpy()\n exact_y = np.nan_to_num(train_df[target_name].to_numpy(np.float32), nan=0.0)\n exact_idx = np.flatnonzero(exact_mask)\n exact_labels = exact_y[exact_idx].astype(int)\n exact_predictions = []\n for seed in seeds:\n model_seed = seed + 101 * TARGETS.index(target_name) + len('exact_lr')\n exact_predictions.append(_hyb_fit_family('exact_lr', x_train, exact_idx, exact_labels, np.full(len(exact_idx), 3.0, np.float32), x_test, model_seed))\n exact_lr = np.mean(np.stack(exact_predictions), axis=0)\n fit_idx, fit_y, fit_weight, _, _ = _hyb_training_arrays(pseudo_y, pseudo_conf, exact_mask, exact_y)\n predictions = {}\n for family in ('lr', 'et', 'hgb'):\n seed_predictions = []\n for seed in seeds:\n model_seed = seed + 101 * TARGETS.index(target_name) + len(family)\n seed_predictions.append(_hyb_fit_family(family, x_train, fit_idx, fit_y, fit_weight, x_test, model_seed))\n predictions[family] = np.mean(np.stack(seed_predictions), axis=0)\n predictions['exact_lr'] = exact_lr\n weighted_rank = np.zeros(len(x_test), np.float64)\n weighted_prob = np.zeros(len(x_test), np.float64)\n family_weights = HYB_LM_FAMILY_WEIGHTS if target_name == HYB_TARGET else HYB_OA_FAMILY_WEIGHTS\n for weight, family in zip(family_weights, HYB_FAMILIES):\n pred = np.clip(predictions[family], 1e-05, 1.0 - 1e-05)\n weighted_rank += weight * _hyb_rank(pred, denominator_offset=1.0)\n weighted_prob += weight * pred\n return 0.9 * weighted_rank + 0.1 * weighted_prob\n lm_consensus = fit_target(HYB_TARGET, payload['lm_consensus_y'], payload['lm_consensus_conf'], HYB_SEEDS)\n lm_pilkwang = fit_target(HYB_TARGET, payload['lm_pilkwang_y'], payload['lm_pilkwang_conf'], HYB_SEEDS)\n lm_teacher_rank = 1.0 * _hyb_rank(lm_consensus) + 0.0 * _hyb_rank(lm_pilkwang)\n oa_pilkwang = fit_target(HYB_OA_TARGET, payload['oa_pilkwang_y'], payload['oa_pilkwang_conf'], HYB_OA_SEEDS)\n oa_teacher_rank = _hyb_rank(oa_pilkwang)\n train_mean = x_train_raw.mean(axis=0, dtype=np.float64).astype(np.float32)\n train_scale = x_train_raw.std(axis=0, dtype=np.float64).astype(np.float32)\n train_scale[train_scale < 1e-05] = 1.0\n x_train_pca = ((x_train_raw - train_mean) / train_scale).astype(np.float32)\n x_test_pca = ((x_test_raw - train_mean) / train_scale).astype(np.float32)\n pca_specs = {HYB_TARGET: (128, 0.1), 'Synovitis': (32, 1.0)}\n pca_predictions = {target: [] for target in pca_specs}\n for pca_seed in (20260809, 20260819, 20260829, 20260839):\n decomposition = PCA(n_components=128, whiten=True, svd_solver='randomized', n_oversamples=20, random_state=pca_seed)\n train_embedding = decomposition.fit_transform(x_train_pca)\n test_embedding = decomposition.transform(x_test_pca)\n for target_name, (dimensions, c_value) in pca_specs.items():\n exact_mask = train_df[target_name].notna().to_numpy()\n exact_labels = train_df.loc[exact_mask, target_name].to_numpy(int)\n if int(exact_mask.sum()) != 58 or set(np.unique(exact_labels)) != {0, 1}:\n raise AssertionError(f'unexpected exact-label support for {target_name}')\n model = make_pipeline(StandardScaler(), LogisticRegression(C=c_value, solver='liblinear', class_weight='balanced', max_iter=5000, random_state=pca_seed))\n model.fit(train_embedding[exact_mask, :dimensions], exact_labels)\n pca_predictions[target_name].append(model.predict_proba(test_embedding[:, :dimensions])[:, 1])\n pca_predictions = {target: np.mean(np.stack(predictions), axis=0) for target, predictions in pca_predictions.items()}\n result = primary.copy()\n primary_uids = result['StudyInstanceUID'].astype(str)\n if set(primary_uids) != set(test_uids):\n raise AssertionError('hybrid and primary StudyInstanceUID sets differ')\n lm_by_uid = pd.Series(lm_teacher_rank, index=test_uids).reindex(primary_uids.values)\n oa_by_uid = pd.Series(oa_teacher_rank, index=test_uids).reindex(primary_uids.values)\n lm_pca_by_uid = pd.Series(_hyb_rank(pca_predictions[HYB_TARGET]), index=test_uids).reindex(primary_uids.values)\n syn_pca_by_uid = pd.Series(_hyb_rank(pca_predictions['Synovitis']), index=test_uids).reindex(primary_uids.values)\n lm_base_rank = result[HYB_TARGET].rank(pct=True).to_numpy(np.float64)\n oa_base_rank = result[HYB_OA_TARGET].rank(pct=True).to_numpy(np.float64)\n syn_base_rank = result['Synovitis'].rank(pct=True).to_numpy(np.float64)\n result[HYB_TARGET] = 0.125 * lm_base_rank + 0.5 * lm_by_uid.to_numpy(np.float64) + 0.375 * lm_pca_by_uid.to_numpy(np.float64)\n result[HYB_OA_TARGET] = 0.125 * oa_base_rank + 0.875 * oa_by_uid.to_numpy(np.float64)\n result['Synovitis'] = 0.75 * syn_base_rank + 0.25 * syn_pca_by_uid.to_numpy(np.float64)\n changed = {HYB_TARGET, HYB_OA_TARGET, 'Synovitis'}\n untouched = [target for target in TARGETS if target not in changed]\n if not result[untouched].equals(primary[untouched]):\n raise AssertionError('hybrid changed an unevaluated target')\n if result.shape != primary.shape or not np.isfinite(result[TARGETS].to_numpy()).all():\n raise AssertionError('invalid hybrid blend')\n temp_path = Path('submission_v34_hybrid.tmp.csv')\n result.to_csv(temp_path, index=False)\n reread = pd.read_csv(temp_path)\n if reread.shape != primary.shape or not np.isfinite(reread[TARGETS].to_numpy()).all():\n raise AssertionError('serialized hybrid blend is invalid')\n temp_path.replace(primary_path)\n log('hybrid complete: LM 0.125 base / 0.500 consensus / 0.375 PCA; Lateral OA 0.125 base / 0.875 Pilkwang; Synovitis 0.75 base / 0.25 PCA; nine other targets preserved')\n return True","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:07.407904Z","iopub.execute_input":"2026-08-17T17:07:07.408604Z","iopub.status.idle":"2026-08-17T17:07:26.648981Z","shell.execute_reply.started":"2026-08-17T17:07:07.408579Z","shell.execute_reply":"2026-08-17T17:07:26.648434Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def write_submission(pred, studies, test_df, path):\n sub = pd.DataFrame(pd.DataFrame(pred).rank(pct=True).values, columns=TARGETS)\n sub.insert(0, 'StudyInstanceUID', studies)\n sub = test_df[['StudyInstanceUID']].merge(sub, on='StudyInstanceUID', how='left')\n sub[TARGETS] = sub[TARGETS].fillna(0.5)\n sub.to_csv(path, index=False)\n return sub\n\ndef write_benchmark_submission():\n t = pd.read_csv(ROOT / 'test.csv')\n for c in TARGETS:\n t[c] = 0.5\n t.to_csv('submission.csv', index=False)\n\ndef _v37_validate_submission(path, test_df, tag):\n path = Path(path)\n frame = pd.read_csv(path)\n expected = ['StudyInstanceUID'] + TARGETS\n if list(frame.columns) != expected:\n raise ValueError(f'{tag}: columns differ from the competition contract')\n if len(frame) != len(test_df) or not frame['StudyInstanceUID'].is_unique:\n raise ValueError(f'{tag}: row count or StudyInstanceUID uniqueness failed')\n if set(frame['StudyInstanceUID'].astype(str)) != set(test_df['StudyInstanceUID'].astype(str)):\n raise ValueError(f'{tag}: StudyInstanceUID set differs from test.csv')\n values = frame[TARGETS].to_numpy(np.float64)\n if not np.isfinite(values).all():\n raise ValueError(f'{tag}: non-finite prediction')\n return test_df[['StudyInstanceUID']].merge(frame, on='StudyInstanceUID', how='left')\n\ndef _v37_find_yash_submission():\n candidates = []\n local = globals().get('YASH_LOCAL_SOURCE_DIR')\n if local:\n candidates.append(Path(local) / 'submission.csv')\n root = Path('/kaggle/input')\n candidates.append(root / 'rsna-knee-infer-v1' / 'submission.csv')\n if root.is_dir():\n candidates.extend((meta.parent / 'submission.csv' for meta in root.glob('**/infer_meta.json')))\n seen = set()\n for path in candidates:\n key = str(path)\n if key in seen or not path.is_file():\n continue\n seen.add(key)\n meta_path = path.with_name('infer_meta.json')\n if meta_path.is_file():\n meta = json.loads(meta_path.read_text())\n if int(meta.get('errors', -1)) != 0:\n raise ValueError(f\"Yash source reports {meta.get('errors')} inference errors\")\n return path\n raise FileNotFoundError('the attached yashbishnoi98/rsna-knee-infer-v1 output is absent')\n\ndef run_yash_public_ensemble():\n import shutil\n test_df = pd.read_csv(ROOT / 'test.csv')\n native_path = Path('submission.csv')\n public_path = Path('submission_public_0899.csv')\n native = _v37_validate_submission(native_path, test_df, 'native V36')\n public = _v37_validate_submission(public_path, test_df, 'public DINO family')\n yash_path = _v37_find_yash_submission()\n yash = _v37_validate_submission(yash_path, test_df, 'Yash public image family')\n meta_path = yash_path.with_name('infer_meta.json')\n if meta_path.is_file():\n meta = json.loads(meta_path.read_text())\n if int(meta.get('studies', -1)) != len(test_df):\n raise ValueError('Yash source study count differs from test.csv')\n shutil.copyfile(native_path, 'submission_native_v36.csv')\n shutil.copyfile(yash_path, 'submission_yash_reference.csv')\n yr = yash[TARGETS].rank(pct=True).to_numpy(np.float64)\n dr = public[TARGETS].rank(pct=True).to_numpy(np.float64)\n blend = 0.55 * yr + 0.45 * dr\n result = test_df[['StudyInstanceUID']].copy()\n result[TARGETS] = blend\n if result.shape != yash.shape or not np.isfinite(result[TARGETS].to_numpy()).all():\n raise AssertionError('invalid Yash/DINO rank blend')\n candidate_path = Path('submission_yash_dino_rankblend.csv')\n result.to_csv(candidate_path, index=False)\n reread = _v37_validate_submission(candidate_path, test_df, 'Yash/DINO rank blend')\n changed = sum((tuple(reread[target].rank(method='first')) != tuple(yash[target].rank(method='first')) for target in TARGETS))\n if changed == 0:\n raise AssertionError('Yash/DINO blend is rank-identical to its Yash parent')\n temp_path = Path('submission_v37_yash_dino.tmp.csv')\n reread.to_csv(temp_path, index=False)\n temp_path.replace(native_path)\n log(f'Yash public family banked; V37 primary = 0.55 Yash / 0.45 public DINO rank blend ({changed} target orderings differ from Yash); exact Yash and native V36 outputs retained')\n return True\n\ndef main():\n write_benchmark_submission()\n pkg = find_weights()\n if pkg is not None:\n dev = DEVS[0]\n infer_from_package(pkg, dev)\n try:\n test_df = pd.read_csv(ROOT / 'test.csv')\n native_path = Path('submission.csv')\n public_path = Path('submission_public_0899.csv')\n native = _v37_validate_submission(native_path, test_df, 'native 24-member')\n public = _v37_validate_submission(public_path, test_df, 'public DINO frontier')\n native.to_csv('submission_native_v38.csv', index=False)\n public.to_csv(native_path, index=False)\n promoted = _v37_validate_submission(native_path, test_df, 'V40 primary')\n if not promoted.equals(public):\n raise AssertionError('V40 serialization differs from validated public frontier')\n log('V40 primary = exact no-jitter public-frontier target pooling; native 24-member output retained')\n except Exception as public_frontier_error:\n log(f'public-frontier promotion skipped safely: {public_frontier_error}')\n traceback.print_exc()\n log('done')\n return\n read_labels(pd.read_csv(ROOT / 'train.csv', usecols=['StudyInstanceUID', 'Report']))\n test_df = pd.read_csv(ROOT / 'test.csv')\n test_series = pd.read_csv(ROOT / 'test_series.csv')\n train_df = pd.read_csv(ROOT / 'train.csv')\n train_series = pd.read_csv(ROOT / 'train_series.csv')\n log(f'train {train_df.shape} test {test_df.shape}')\n both = pd.concat([train_series, test_series])\n plane_map = dict(zip(both['SeriesInstanceUID'], both['Anatomical_Plane']))\n log('header pass: test')\n hte = annotate(walk('test_series'))\n log(f' {len(hte)} test series')\n log('header pass: train')\n htr = annotate(walk('train_series'))\n log(f' {len(htr)} train series')\n slots_te, slots_tr = (pick_slots(hte, plane_map), pick_slots(htr, plane_map))\n cov = pd.Series([len(v) for v in slots_tr.values()]).describe()\n log(f\"train slots per study: mean {cov['mean']:.2f} min {cov['min']:.0f} max {cov['max']:.0f}\")\n st_tr, Ctr, Mtr = build_cache(slots_tr, plane_map, lat_of(htr, 'train '), 'train')\n st_te, Cte, Mte = build_cache(slots_te, plane_map, lat_of(hte, 'test '), 'test')\n t_lab = time.time()\n lab = read_labels(train_df)\n log(f'derived labels for {len(lab)} studies in {time.time() - t_lab:.1f}s')\n gold = train_df.set_index('StudyInstanceUID')[TARGETS]\n gold = gold[gold.notna().all(axis=1)]\n Y = np.zeros((len(st_tr), len(TARGETS)), np.float32)\n W = np.zeros_like(Y)\n for i, st in enumerate(st_tr):\n if st in gold.index:\n Y[i], W[i] = (gold.loc[st].values, 3.0)\n elif st in lab.index:\n r = lab.loc[st]\n Y[i] = r[TARGETS].values\n W[i] = 0.25 + 0.75 * r[[t + '__conf' for t in TARGETS]].values\n keep = np.where(W.sum(1) > 0)[0]\n log(f'supervised {len(keep)} of {len(st_tr)} studies (annotated {len(gold)})')\n import hashlib\n rep = train_df.set_index('StudyInstanceUID')['Report'].fillna('')\n grp = np.array([int(hashlib.md5(rep.get(s, s).encode()).hexdigest()[:8], 16) % 5 for s in st_tr])\n va = np.array([i for i in keep if grp[i] == 0])\n tr = np.array([i for i in keep if grp[i] != 0])\n if len(va) == 0 or len(tr) < BATCH_STUDIES:\n cut = max(1, len(keep) // 5)\n va, tr = (keep[:cut], keep[cut:])\n log(f'train {len(tr)} / holdout {len(va)} studies')\n gpos = {s: i for i, s in enumerate(st_tr)}\n va_set = set(va.tolist())\n gi = np.array([gpos[s] for s in gold.index if s in gpos and gpos[s] in va_set])\n gold_y = gold.loc[[st_tr[i] for i in gi]].values.astype(int) if len(gi) else None\n yv = (Y[va] > 0.5).astype(int)\n log(f'annotation check: {len(gi)} of {len(gold)} annotated studies are in the holdout')\n dev = DEVS[0]\n results, test_preds = ({}, {})\n for cfg in RUNS:\n pitch = CROP_MM / cfg['img']\n log(f\"=== {cfg['name']}: {cfg['img']} px, {pitch:.3f} mm/pixel, {pitch * 14:.2f} mm per patch token ===\")\n torch.manual_seed(SEED)\n model = build_model(UNFREEZE_LAST).to(dev)\n opt = torch.optim.AdamW([{'params': [p for p in model.backbone.parameters() if p.requires_grad], 'lr': LR_BACKBONE}, {'params': model.head.parameters(), 'lr': LR_HEAD}], weight_decay=WEIGHT_DECAY)\n steps = max(EPOCHS * (len(tr) // BATCH_STUDIES), 1)\n sched = torch.optim.lr_scheduler.OneCycleLR(opt, max_lr=[LR_BACKBONE, LR_HEAD], total_steps=steps, pct_start=0.15)\n scaler = torch.amp.GradScaler('cuda', enabled=dev.type == 'cuda')\n best, best_state, best_annot = (-1.0, None, float('nan'))\n for ep in range(EPOCHS):\n model.train()\n perm = np.random.permutation(tr)\n tot, nstep = (0.0, 0)\n for b in range(0, len(perm) - BATCH_STUDIES + 1, BATCH_STUDIES):\n sel = perm[b:b + BATCH_STUDIES]\n rows = torch.from_numpy(Ctr[sel]).to(dev)\n g = int(torch.randint(N_GROUP, (1,)).item())\n imgs = augment(take_group(rows, g))\n m = torch.from_numpy(Mtr[sel]).to(dev)\n y = torch.from_numpy(Y[sel]).to(dev)\n w = torch.from_numpy(W[sel]).to(dev)\n with torch.autocast('cuda', enabled=dev.type == 'cuda'):\n loss = (F.binary_cross_entropy_with_logits(model(imgs, m, cfg['img']), y, reduction='none') * w).mean()\n opt.zero_grad(set_to_none=True)\n scaler.scale(loss).backward()\n scaler.step(opt)\n scaler.update()\n sched.step()\n tot += loss.item()\n nstep += 1\n pv = predict(model, Ctr, Mtr, va, dev, cfg['img'])\n d = macro_auc(yv, pv)\n g_auc = float('nan')\n if gold_y is not None and len(gi):\n g_auc = macro_auc(gold_y, predict(model, Ctr, Mtr, gi, dev, cfg['img']))\n log(f' epoch {ep + 1}/{EPOCHS} loss {tot / max(nstep, 1):.4f} holdout {d:.4f} annot(n={len(gi)}) {g_auc:.4f}')\n if d > best:\n best, best_annot = (d, g_auc)\n best_state = {k: v.detach().cpu().clone() for k, v in model.state_dict().items()}\n if time.time() - T0 > TIME_BUDGET:\n log(' time budget reached')\n break\n if best_state is not None:\n model.load_state_dict(best_state)\n results[cfg['name']] = (best, best_annot)\n test_preds[cfg['name']] = predict(model, Cte, Mte, np.arange(len(st_te)), dev, cfg['img'])\n log(f\" {cfg['name']}: best holdout {best:.4f} (annot {best_annot:.4f})\")\n del model, opt, sched, scaler, best_state\n gc.collect()\n if dev.type == 'cuda':\n torch.cuda.empty_cache()\n log('---- summary ----')\n for n, (d, g_auc) in results.items():\n log(f' {n:12s} holdout {d:.4f} annot {g_auc:.4f}')\n pick = max(results, key=lambda k: results[k][0])\n log(f'best on the holdout: {pick} ({results[pick][0]:.4f})')\n for name, pred in test_preds.items():\n sub = write_submission(pred, st_te, test_df, f'submission_{name}.csv')\n log(f' submission_{name}.csv {sub.shape}; nulls {int(sub[TARGETS].isna().sum().sum())}')\n ens = np.mean([pd.DataFrame(p).rank(pct=True).values for p in test_preds.values()], axis=0)\n write_submission(ens, st_te, test_df, 'submission_rankmean.csv')\n log(f' submission_rankmean.csv (rank mean of {len(test_preds)})')\n sub = write_submission(test_preds[pick], st_te, test_df, 'submission.csv')\n log(f'submission.csv = {pick}; {sub.shape}; nulls {int(sub[TARGETS].isna().sum().sum())}')\n print(sub.head().to_string())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:26.649917Z","iopub.execute_input":"2026-08-17T17:07:26.650429Z","iopub.status.idle":"2026-08-17T17:07:26.685503Z","shell.execute_reply.started":"2026-08-17T17:07:26.650395Z","shell.execute_reply":"2026-08-17T17:07:26.684772Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"try:\n main()\nexcept LabelSourceError:\n traceback.print_exc()\n raise\nexcept Exception:\n traceback.print_exc()\n t = pd.read_csv(find_root() / 'test.csv')\n for c in TARGETS:\n t[c] = 0.5\n t.to_csv('submission.csv', index=False)\n print('wrote fallback submission.csv')\nlog('done')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:07:26.686618Z","iopub.execute_input":"2026-08-17T17:07:26.686923Z","iopub.status.idle":"2026-08-17T17:08:11.961308Z","shell.execute_reply.started":"2026-08-17T17:07:26.686886Z","shell.execute_reply":"2026-08-17T17:08:11.960499Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"_A5_SAVED = dict(globals())\nimport gc, os, time, warnings\nfrom concurrent.futures import ProcessPoolExecutor, as_completed\nfrom pathlib import Path\nimport cv2\nimport numpy as np\nimport pandas as pd\nimport pydicom\nimport timm\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nwarnings.filterwarnings('ignore')\ncv2.setNumThreads(1)\nCROP_MM = 130.0\nSIZE = 336\nSLICE_BAND = (0.12, 0.88)\nN_SLICE = 16\nINTENSITY = 'slice'\nSLOTS = [('Sagittal', 1), ('Sagittal', 0), ('Coronal', 1), ('Coronal', 0), ('Axial', 1), ('Axial', 0)]\nN_SLOT = len(SLOTS)\nLABELS = ['ACL', 'MCL', 'Medial Meniscus', 'Lateral Meniscus', 'Medial OA', 'Lateral OA', 'PF OA', 'Effusion', 'Synovitis', \"Baker's\", 'Contusion', 'Fracture']\n\ndef _find_dir(*names):\n root = Path('/kaggle/input')\n cand = []\n for n in names:\n cand += [root / n, root / 'competitions' / n, root / 'datasets' / n]\n for parent in (root / 'datasets', root / 'competitions', root):\n if parent.is_dir():\n try:\n cand += [d / n for d in parent.iterdir() if d.is_dir()]\n except OSError:\n pass\n for p in cand:\n if p.is_dir():\n return p\n return None\nCOMP = _find_dir('rsna-knee-abnormality-detection')\nCKPT = _find_dir('knee-mri-fold-weights')\nassert COMP is not None, 'competition data not attached'\nassert CKPT is not None, 'fold weights not attached'\nassert (COMP / 'sample_submission.csv').exists(), f'no competition data at {COMP}'\nassert list(CKPT.glob('*_f*.pt')), f'no checkpoints at {CKPT}'\nDEV = 'cuda' if torch.cuda.is_available() else 'cpu'\nprint(f'competition : {COMP}')\nprint(f'checkpoints : {CKPT}')\nprint(f'device : {DEV}')\nfor i in range(torch.cuda.device_count() if DEV == 'cuda' else 0):\n cc = torch.cuda.get_device_capability(i)\n print(f' gpu{i} : {torch.cuda.get_device_name(i)} sm_{cc[0]}{cc[1]}, {torch.cuda.get_device_properties(i).total_memory / 2 ** 30:.0f} GiB, native bf16={cc >= (8, 0)}')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:08:11.962399Z","iopub.execute_input":"2026-08-17T17:08:11.96275Z","iopub.status.idle":"2026-08-17T17:08:15.505958Z","shell.execute_reply.started":"2026-08-17T17:08:11.96271Z","shell.execute_reply":"2026-08-17T17:08:15.505319Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"SERIES_ROOT = COMP / 'test_series'\nif not SERIES_ROOT.exists():\n SERIES_ROOT = COMP / 'train_series'\nprint('series root:', SERIES_ROOT)\n\ndef ordered_files(sdir, cap=64):\n keyed = []\n for f in sdir.glob('*.dcm'):\n try:\n ds = pydicom.dcmread(str(f), stop_before_pixels=True)\n keyed.append((int(ds.InstanceNumber), str(f)))\n except Exception:\n continue\n if len(keyed) >= cap * 4:\n break\n return [f for _, f in sorted(keyed)]\n\ndef series_side(path):\n try:\n return float(pydicom.dcmread(path, stop_before_pixels=True).ImagePositionPatient[0])\n except Exception:\n return 0.0\n\ndef read_crop(path):\n try:\n ds = pydicom.dcmread(path)\n arr = ds.pixel_array.astype(np.float32)\n except Exception:\n return None\n try:\n ps = float(ds.PixelSpacing[0])\n except Exception:\n ps = CROP_MM / max(arr.shape)\n half = int(round(CROP_MM / ps / 2))\n cy, cx = (arr.shape[0] // 2, arr.shape[1] // 2)\n y0, y1 = (max(0, cy - half), min(arr.shape[0], cy + half))\n x0, x1 = (max(0, cx - half), min(arr.shape[1], cx + half))\n crop = arr[y0:y1, x0:x1]\n return None if crop.size == 0 else crop\n\ndef window(crop, lo, hi, flip):\n c = np.clip((crop - lo) / max(hi - lo, 1e-06), 0, 1)\n img = cv2.resize(c, (SIZE, SIZE), interpolation=cv2.INTER_AREA)\n return img[:, ::-1].copy() if flip else img\n\ndef render(path, flip):\n crop = read_crop(path)\n if crop is None:\n return None\n lo, hi = np.percentile(crop[::4, ::4], [1, 99])\n return window(crop, lo, hi, flip)\n\ndef build_study(args):\n idx, study, recs = args\n out = np.zeros((N_SLOT, N_SLICE, SIZE, SIZE), np.uint8)\n mask = np.zeros(N_SLOT, np.uint8)\n rows = pd.DataFrame(recs)\n if len(rows):\n for s_i, (plane, fs) in enumerate(SLOTS):\n sub = rows[(rows.Anatomical_Plane == plane) & (rows.Fat_Suppression == fs)]\n if sub.empty:\n continue\n files = ordered_files(SERIES_ROOT / study / sub.iloc[0].SeriesInstanceUID)\n if not files:\n continue\n flip = plane != 'Sagittal' and series_side(files[0]) < 0\n lo, hi = SLICE_BAND\n i0 = int(round(lo * (len(files) - 1)))\n i1 = int(round(hi * (len(files) - 1)))\n avail = list(range(i0, i1 + 1))\n if len(avail) >= N_SLICE:\n picks = [avail[int(round(t))] for t in np.linspace(0, len(avail) - 1, N_SLICE)]\n off = 0\n else:\n picks, off = (avail, (N_SLICE - len(avail)) // 2)\n if INTENSITY == 'series':\n crops = [read_crop(files[p]) for p in picks]\n got = [x for x in crops if x is not None]\n if got:\n samp = np.concatenate([x[::4, ::4].ravel() for x in got])\n lo_, hi_ = np.percentile(samp, [1, 99])\n for c, x in enumerate(crops):\n if x is None:\n x = read_crop(files[min(len(files) - 1, picks[c] + 1)])\n if x is not None:\n out[s_i, off + c] = (window(x, lo_, hi_, flip) * 255).astype(np.uint8)\n else:\n for c, p in enumerate(picks):\n img = render(files[p], flip)\n if img is None:\n img = render(files[min(len(files) - 1, p + 1)], flip)\n if img is not None:\n out[s_i, off + c] = (img * 255).astype(np.uint8)\n mask[s_i] = len(picks)\n return (idx, out, mask)\nsub_df = pd.read_csv(COMP / 'sample_submission.csv')\nser_csv = pd.read_csv(COMP / 'test_series.csv')\nif not (COMP / 'test_series').exists():\n ser_csv = pd.read_csv(COMP / 'train_series.csv')\nser_csv = ser_csv.loc[:, ~ser_csv.columns.duplicated()]\nstudies = sub_df.StudyInstanceUID.tolist()\nby = {s: g.to_dict('records') for s, g in ser_csv[ser_csv.StudyInstanceUID.isin(set(studies))].groupby('StudyInstanceUID')}\nprint(f'{len(studies):,} test studies, {len(by):,} with series metadata')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:08:15.506801Z","iopub.execute_input":"2026-08-17T17:08:15.507339Z","iopub.status.idle":"2026-08-17T17:08:15.546206Z","shell.execute_reply.started":"2026-08-17T17:08:15.507307Z","shell.execute_reply":"2026-08-17T17:08:15.545576Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"N_SLOT_TYPES, MASK_IDX = (6, 0)\n\ndef segment_softmax(scores, sidx, B):\n T, K = scores.shape\n idx = sidx.unsqueeze(1).expand(-1, K)\n m = torch.full((B, K), float('-inf'), device=scores.device, dtype=scores.dtype)\n m = m.scatter_reduce(0, idx, scores, reduce='amax', include_self=True)\n e = (scores - m[sidx]).exp()\n s = torch.zeros(B, K, device=scores.device, dtype=scores.dtype).index_add_(0, sidx, e)\n return e / s[sidx].clamp(min=1e-06)\n\nclass MeanMaxPool(nn.Module):\n\n def forward(self, f, sidx, B, slot=None, return_attn=False):\n D = f.shape[1]\n cnt = torch.zeros(B, device=f.device, dtype=f.dtype).index_add_(0, sidx, torch.ones(f.shape[0], device=f.device, dtype=f.dtype))\n mean = torch.zeros(B, D, device=f.device, dtype=f.dtype).index_add_(0, sidx, f)\n mean = mean / cnt.clamp(min=1).unsqueeze(1)\n mx = torch.full((B, D), -10000.0, device=f.device, dtype=f.dtype)\n mx = mx.scatter_reduce(0, sidx.unsqueeze(1).expand(-1, D), f, reduce='amax', include_self=True)\n return (torch.cat([mean, mx], 1), None)\n\nclass LabelAttentionPool(nn.Module):\n\n def __init__(self, d, n_labels=12, n_heads=4, slot_bias=True):\n super().__init__()\n self.d, self.k, self.h = (d, n_labels, n_heads)\n self.q = nn.Parameter(torch.randn(n_labels, d) * 0.02)\n self.key, self.val = (nn.Linear(d, d), nn.Linear(d, d))\n self.slot_bias = nn.Parameter(torch.zeros(n_labels, N_SLOT_TYPES + 1)) if slot_bias else None\n\n def forward(self, f, sidx, B, slot=None, return_attn=False):\n scores = self.key(f) @ self.q.t() / self.d ** 0.5\n if self.slot_bias is not None and slot is not None:\n scores = scores + self.slot_bias.t()[slot]\n a = segment_softmax(scores, sidx, B)\n out = torch.zeros(B, self.k, self.d, device=f.device, dtype=f.dtype)\n out = out.index_add_(0, sidx, a.unsqueeze(-1) * self.val(f).unsqueeze(1))\n return (out, a)\n\nclass TokenXAttnPool(nn.Module):\n\n def __init__(self, d, n_labels=12, n_heads=6, dropout=0.2):\n super().__init__()\n self.d, self.k = (d, n_labels)\n self.q = nn.Parameter(torch.randn(n_labels, d) * 0.02)\n self.slot_emb = nn.Embedding(N_SLOT_TYPES + 1, d, padding_idx=0)\n self.kv_norm = nn.LayerNorm(d)\n self.attn = nn.MultiheadAttention(d, n_heads, dropout=dropout, batch_first=True)\n\n def forward(self, tok, sidx, B, slot=None, return_attn=False):\n T, N, D = tok.shape\n cnt = torch.bincount(sidx, minlength=B)\n S = int(cnt.max().item())\n starts = torch.cumsum(cnt, 0) - cnt\n pos = torch.arange(T, device=tok.device) - starts[sidx]\n kv = tok + self.slot_emb(slot).unsqueeze(1)\n pad = tok.new_zeros(B, S, N, D)\n pad[sidx, pos] = kv\n keep = torch.zeros(B, S, dtype=torch.bool, device=tok.device)\n keep[sidx, pos] = True\n kpm = ~keep.repeat_interleave(N, dim=1)\n pad = self.kv_norm(pad.reshape(B, S * N, D))\n q = self.q.unsqueeze(0).expand(B, -1, -1)\n att, w = self.attn(q, pad, pad, key_padding_mask=kpm, need_weights=return_attn, average_attn_weights=True)\n cls = tok[:, 0]\n mean = torch.zeros(B, D, device=tok.device, dtype=tok.dtype).index_add_(0, sidx, cls) / cnt.clamp(min=1).unsqueeze(1)\n mx = torch.full((B, D), -10000.0, device=tok.device, dtype=tok.dtype)\n mx = mx.scatter_reduce(0, sidx.unsqueeze(1).expand(-1, D), cls, reduce='amax', include_self=True)\n base = torch.cat([mean, mx], 1).unsqueeze(1).expand(-1, self.k, -1)\n return (torch.cat([att, base], -1), w)\n\nclass ViTSlotToken(nn.Module):\n\n def __init__(self, vit, n_cat, dim=None):\n super().__init__()\n self.vit = vit\n d = dim or vit.embed_dim\n self.tok = nn.Embedding(n_cat + 1, d, padding_idx=MASK_IDX)\n self.num_features = vit.num_features\n self._orig_prefix = getattr(vit, 'num_prefix_tokens', 1)\n vit.num_prefix_tokens = self._orig_prefix + 1\n for blk in vit.blocks:\n a = getattr(blk, 'attn', None)\n if a is not None and hasattr(a, 'num_prefix_tokens'):\n a.num_prefix_tokens = a.num_prefix_tokens + 1\n\n @staticmethod\n def _maybe(mod, x):\n return x if mod is None else mod(x)\n\n def forward_features(self, x, cat):\n v = self.vit\n x = v.patch_embed(x)\n pos = v._pos_embed(x)\n rope = None\n if isinstance(pos, tuple):\n x, rope = pos\n else:\n x = pos\n x = self._maybe(getattr(v, 'patch_drop', None), x)\n x = self._maybe(getattr(v, 'norm_pre', None), x)\n npt = self._orig_prefix\n tok = self.tok(cat).unsqueeze(1)\n x = torch.cat([x[:, :npt], tok, x[:, npt:]], dim=1)\n if rope is not None:\n if getattr(v, 'rope_mixed', False):\n for i, blk in enumerate(v.blocks):\n x = blk(x, rope=rope[i])\n else:\n for blk in v.blocks:\n x = blk(x, rope=rope)\n else:\n x = v.blocks(x)\n return v.norm(x)\n\n def forward_head(self, x, pre_logits=True):\n return self.vit.forward_head(x, pre_logits=pre_logits)\nIMAGENET_MEAN = (0.485, 0.456, 0.406)\nIMAGENET_STD = (0.229, 0.224, 0.225)\n\nclass _GatedDepthBlock(nn.Module):\n\n def __init__(self, n_slice, dropout=0.0, ls_init=0.1):\n super().__init__()\n self.norm = nn.GroupNorm(1, n_slice)\n self.v = nn.Conv2d(n_slice, n_slice, 1)\n self.g = nn.Conv2d(n_slice, n_slice, 1)\n self.out = nn.Conv2d(n_slice, n_slice, 1)\n self.gamma = nn.Parameter(torch.full((n_slice, 1, 1), ls_init))\n self.drop = nn.Dropout2d(dropout) if dropout else nn.Identity()\n\n def forward(self, x):\n z = self.norm(x)\n return x + self.gamma * self.drop(self.out(self.v(z) * F.silu(self.g(z))))\n\nclass DepthCompress(nn.Module):\n\n def __init__(self, n_slice=16, out_ch=3, depth=1, dropout=0.0, ls_init=0.1, imagenet=True, proj_noise=0.25):\n super().__init__()\n self.imagenet = imagenet\n self.blocks = nn.ModuleList([_GatedDepthBlock(n_slice, dropout, ls_init) for _ in range(depth)])\n self.proj = nn.Conv2d(n_slice, out_ch, 1, bias=True)\n if imagenet:\n self.register_buffer('mu', torch.tensor(IMAGENET_MEAN).view(1, -1, 1, 1))\n self.register_buffer('sd', torch.tensor(IMAGENET_STD).view(1, -1, 1, 1))\n\n def forward(self, x):\n keep = (x.amax(dim=1, keepdim=True) > 0).to(x.dtype)\n z = x\n for b in self.blocks:\n z = b(z)\n z = self.proj(z)\n if self.imagenet:\n z = (z - self.mu.to(z.dtype)) / self.sd.to(z.dtype)\n return z * keep\nN_PLANE, N_CONTRAST = (3, 2)\n_PLANE_OF = lambda s: torch.clamp(s - 1, 0, 5) // 2\n_CONTRAST_OF = lambda s: torch.clamp(s - 1, 0, 5) % 2\n\nclass SlotDepthMixer(nn.Module):\n\n def __init__(self, n_slice=16, ksize=5, alpha_max=0.25):\n super().__init__()\n self.n_slice, self.ksize, self.r = (n_slice, ksize, ksize // 2)\n self.alpha_max = alpha_max\n b = torch.tensor([1.0, 4.0, 6.0, 4.0, 1.0])\n self.register_buffer('base', b.log()[self.r:])\n n_u = self.r + 1\n self.shared = nn.Parameter(torch.zeros(n_u))\n self.plane_k = nn.Parameter(torch.zeros(N_PLANE, n_u))\n self.contrast_k = nn.Parameter(torch.zeros(N_CONTRAST, n_u))\n self.g0 = nn.Parameter(torch.zeros(()))\n self.gate_p = nn.Parameter(torch.zeros(N_PLANE))\n self.gate_c = nn.Parameter(torch.zeros(N_CONTRAST))\n idx = torch.arange(n_slice)\n self.register_buffer('off', idx[None, :] - idx[:, None])\n\n def kernel(self, slot):\n p, c = (_PLANE_OF(slot), _CONTRAST_OF(slot))\n half = self.base + self.shared + self.plane_k[p] + self.contrast_k[c]\n full = torch.cat([half.flip(-1)[..., :self.r], half], dim=-1)\n return F.softmax(full, dim=-1)\n\n def alpha(self, slot):\n p, c = (_PLANE_OF(slot), _CONTRAST_OF(slot))\n return self.alpha_max * torch.tanh(self.g0 + self.gate_p[p] + self.gate_c[c])\n\n def forward(self, x, slot, vmask):\n T, S, H, W = x.shape\n if vmask is None:\n raise ValueError('stem=mixer requires the padding mask')\n k = self.kernel(slot)\n v = vmask.to(k.dtype)\n d = self.off + self.r\n inb = (d >= 0) & (d < self.ksize)\n kk = k[:, d.clamp(0, self.ksize - 1)] * inb\n M = kk * v[:, None, :]\n den = M.sum(-1, keepdim=True)\n eye = torch.eye(S, device=x.device, dtype=M.dtype).expand(T, S, S)\n ok = (den > 1e-06) & v[:, :, None].bool()\n M = torch.where(ok, M / den.clamp(min=1e-06), eye)\n a = self.alpha(slot)[:, None, None]\n Aop = ((1.0 - a) * eye + a * M).to(x.dtype)\n if x.is_contiguous(memory_format=torch.channels_last) and (not x.is_contiguous()):\n y = torch.bmm(x.permute(0, 2, 3, 1).reshape(T, H * W, S), Aop.transpose(1, 2))\n return y.reshape(T, H, W, S).permute(0, 3, 1, 2)\n return torch.bmm(Aop, x.reshape(T, S, H * W)).reshape(T, S, H, W)\n\ndef _seg_mean_max(v, sidx, B):\n D = v.shape[1]\n cnt = torch.zeros(B, device=v.device, dtype=v.dtype).index_add_(0, sidx, torch.ones(v.shape[0], device=v.device, dtype=v.dtype))\n mean = torch.zeros(B, D, device=v.device, dtype=v.dtype).index_add_(0, sidx, v)\n mean = mean / cnt.clamp(min=1).unsqueeze(1)\n mx = torch.full((B, D), -10000.0, device=v.device, dtype=v.dtype)\n mx = mx.scatter_reduce(0, sidx.unsqueeze(1).expand(-1, D), v, reduce='amax', include_self=True)\n return torch.cat([mean, mx], 1)\n\ndef _pad_kv(x, sidx, B, norm):\n T, P, D = x.shape\n cnt = torch.bincount(sidx, minlength=B)\n S = int(cnt.max().item())\n starts = torch.cumsum(cnt, 0) - cnt\n pos = torch.arange(T, device=x.device) - starts[sidx]\n pad = x.new_zeros(B, S, P, D)\n pad[sidx, pos] = x\n keep = torch.zeros(B, S, dtype=torch.bool, device=x.device)\n keep[sidx, pos] = True\n return (norm(pad.reshape(B, S * P, D)), ~keep.repeat_interleave(P, dim=1))\n\nclass _GatedDelta(nn.Module):\n\n def __init__(self, d, n_labels, n_heads, dropout):\n super().__init__()\n self.q = nn.Parameter(torch.randn(n_labels, d) * 0.02)\n self.kv_norm = nn.LayerNorm(d)\n self.attn = nn.MultiheadAttention(d, n_heads, dropout=dropout, batch_first=True)\n self.d_norm = nn.LayerNorm(d)\n self.dw = nn.Parameter(torch.randn(n_labels, d) * (1.0 / d ** 0.5))\n self.db = nn.Parameter(torch.zeros(n_labels))\n self.gate = nn.Parameter(torch.zeros(n_labels))\n\n def delta(self, pat, sidx, B, return_attn):\n kv, kpm = _pad_kv(pat, sidx, B, self.kv_norm)\n q = self.q.unsqueeze(0).expand(B, -1, -1)\n att, w = self.attn(q, kv, kv, key_padding_mask=kpm, need_weights=return_attn, average_attn_weights=True)\n return ((self.d_norm(att) * self.dw).sum(-1) + self.db, w)\n\nclass TokenResidualPool(_GatedDelta):\n\n def __init__(self, d, n_labels=12, n_heads=6, pe=64, dropout=0.2):\n super().__init__(d, n_labels, n_heads, dropout)\n self.base = nn.Sequential(nn.LayerNorm(2 * d + pe), nn.Dropout(dropout), nn.Linear(2 * d + pe, n_labels))\n\n def forward(self, tok, slot, sidx, B, pres, return_attn=False):\n base = self.base(torch.cat([_seg_mean_max(tok[:, 1:].mean(1), sidx, B), pres], 1))\n d_, w = self.delta(tok[:, 1:], sidx, B, return_attn)\n return (base + self.gate * d_, w)\n\nclass CodexResidualPool(_GatedDelta):\n\n def __init__(self, d, n_labels=12, n_heads=6, pe=64, dropout=0.2):\n super().__init__(d, n_labels, n_heads, dropout)\n self.base = nn.Sequential(nn.LayerNorm(2 * d + pe), nn.Dropout(dropout), nn.Linear(2 * d + pe, n_labels))\n\n def forward(self, tok, slot, sidx, B, pres, return_attn=False):\n base = self.base(torch.cat([_seg_mean_max(tok[:, 0], sidx, B), pres], 1))\n d_, w = self.delta(tok[:, 1:], sidx, B, return_attn)\n return (base + self.gate * d_, w)\n\nclass ClsAddPool(nn.Module):\n\n def __init__(self, d, n_labels=12, pe=64, dropout=0.2):\n super().__init__()\n self.net = nn.Sequential(nn.LayerNorm(4 * d + pe), nn.Dropout(dropout), nn.Linear(4 * d + pe, n_labels))\n\n def forward(self, tok, slot, sidx, B, pres, return_attn=False):\n return (self.net(torch.cat([_seg_mean_max(tok[:, 1:].mean(1), sidx, B), _seg_mean_max(tok[:, 0], sidx, B), pres], 1)), None)\n\nclass Readout(nn.Module):\n\n def __init__(self, pool, d, n_labels=12, pe=64):\n super().__init__()\n self.pool_kind, self.k = (pool, n_labels)\n self.pres_emb = nn.Embedding(N_SLOT_TYPES + 1, pe, padding_idx=0)\n if pool in ('xres', 'clsadd', 'xcodex'):\n self.pool = {'xres': TokenResidualPool, 'clsadd': ClsAddPool, 'xcodex': CodexResidualPool}[pool](d, n_labels, pe=pe)\n elif pool in ('attn', 'xattn'):\n if pool == 'xattn':\n self.pool = TokenXAttnPool(d, n_labels)\n wd = 3 * d + pe\n else:\n self.pool = LabelAttentionPool(d, n_labels)\n wd = d + pe\n self.norm = nn.LayerNorm(wd)\n self.w = nn.Parameter(torch.randn(n_labels, wd) * (1.0 / wd ** 0.5))\n self.b = nn.Parameter(torch.zeros(n_labels))\n else:\n self.pool = MeanMaxPool()\n self.net = nn.Sequential(nn.LayerNorm(2 * d + pe), nn.Dropout(0.2), nn.Linear(2 * d + pe, n_labels))\n self.drop = nn.Dropout(0.2)\n\n def forward(self, f, slot, sidx, B, return_attn=False):\n pe = self.pres_emb(slot)\n pres = torch.zeros(B, pe.shape[1], device=f.device, dtype=f.dtype).index_add_(0, sidx, pe)\n if self.pool_kind in ('xres', 'clsadd', 'xcodex'):\n return self.pool(f, slot, sidx, B, pres)[0]\n pooled, attn = self.pool(f, sidx, B, slot=slot, return_attn=return_attn)\n if self.pool_kind in ('attn', 'xattn'):\n x = torch.cat([pooled, pres.unsqueeze(1).expand(-1, self.k, -1)], -1)\n x = self.drop(self.norm(x))\n return (x * self.w).sum(-1) + self.b\n return self.net(torch.cat([pooled, pres], 1))\n\nclass Net(nn.Module):\n\n def __init__(self, enc, cond, n_meta=0, pool='mean_max', stem='native', n_slice=16):\n super().__init__()\n self.enc, self.cond = (enc, cond)\n self.compress = DepthCompress(n_slice, 3) if stem == 'compress' else None\n self.mixer = SlotDepthMixer(n_slice) if stem == 'mixer' else None\n self.tokens = pool in ('xattn', 'xres', 'clsadd', 'xcodex')\n D = enc.num_features\n self.meta_mlp = nn.Sequential(nn.LayerNorm(n_meta), nn.Linear(n_meta, 128), nn.GELU(), nn.Linear(128, D)) if n_meta > 0 else None\n self.readout = Readout(pool, D)\n if cond == 'post':\n self.slot_emb = nn.Embedding(N_SLOT_TYPES + 1, D, padding_idx=MASK_IDX)\n\n def forward(self, im, slot, smeta, sidx, B, vm=None):\n if self.mixer is not None:\n im = self.mixer(im, slot, vm)\n if self.compress is not None:\n im = self.compress(im)\n f = self.enc.forward_features(im, slot) if self.cond == 'token' else self.enc.forward_features(im)\n if self.tokens:\n inner = getattr(self.enc, 'vit', self.enc)\n orig = getattr(self.enc, '_orig_prefix', getattr(inner, 'num_prefix_tokens', 1))\n f = torch.cat([f[:, :1], f[:, orig:]], 1)\n else:\n f = self.enc.forward_head(f, pre_logits=True)\n if f.dim() > 2:\n f = f.flatten(1)\n ex = (lambda v: v.unsqueeze(1)) if self.tokens else lambda v: v\n if self.cond == 'post':\n f = f + ex(self.slot_emb(slot))\n if self.meta_mlp is not None and smeta.shape[1] > 0:\n mt = self.meta_mlp(smeta)\n f = torch.cat([f, mt.unsqueeze(1)], 1) if self.tokens else f + mt\n return self.readout(f, slot, sidx, B)\nmodels = []\nfor ckpt_path in sorted(CKPT.glob('*_f*.pt')):\n z = torch.load(ckpt_path, map_location='cpu', weights_only=False)\n cfg = z['cfg']\n _stem = cfg.get('stem', 'native')\n _in = 3 if _stem == 'compress' else cfg.get('n_slice', 16)\n enc = timm.create_model(cfg['backbone'], pretrained=False, num_classes=0, in_chans=_in, **{'img_size': cfg['img']} if 'vit_' in cfg['backbone'] else {})\n if cfg['cond'] == 'token':\n enc = ViTSlotToken(enc, N_SLOT_TYPES)\n m = Net(enc, cfg['cond'], cfg.get('n_meta', 0), cfg['pool'], stem=_stem, n_slice=cfg.get('n_slice', 16))\n missing, unexpected = m.load_state_dict(z['state_dict'], strict=False)\n assert not [k for k in missing if not k.startswith('enc.')], f'missing {missing[:5]}'\n assert not unexpected, f'unexpected {unexpected[:5]}'\n models.append(m.eval())\n print(f\"loaded {ckpt_path.name} fold {z['fold']} {cfg['backbone']} pool={cfg['pool']} meta={cfg['meta']}\")\nCFG = cfg\nassert CFG.get('n_meta', 0) == 0, f\"checkpoint expects {CFG['n_meta']} metadata features -- build slot_meta for the TEST studies and pass it to predict() before submitting\"\nprint(f\"\\n{len(models)} fold models ready | input norm: {CFG.get('norm', 'none')}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:08:15.547307Z","iopub.execute_input":"2026-08-17T17:08:15.5478Z","iopub.status.idle":"2026-08-17T17:08:21.742339Z","shell.execute_reply.started":"2026-08-17T17:08:15.547777Z","shell.execute_reply":"2026-08-17T17:08:21.741599Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"AMP_PREF = 'bf16'\n\ndef amp_for(dev):\n if not str(dev).startswith('cuda'):\n return (torch.float32, False)\n cc = torch.cuda.get_device_capability(dev)\n if AMP_PREF == 'bf16':\n return (torch.bfloat16, True)\n if AMP_PREF == 'fp16':\n return (torch.float16, True)\n if AMP_PREF == 'fp32':\n return (torch.float32, False)\n return (torch.bfloat16 if cc >= (8, 0) else torch.float16, True)\nAMP_DT, AMP_ON = amp_for(DEV)\nWORKERS = max(1, min(4, os.cpu_count() or 4))\nCHUNK = 48\nMICRO = 8\nmodels = [m.to(DEV).eval() for m in models]\nprint(f\"device {DEV} | amp {str(AMP_DT).split('.')[-1]} (on={AMP_ON}) | workers {WORKERS} | chunk {CHUNK} | micro {MICRO}\")\n\ndef _norm_(im):\n k = CFG.get('norm', 'none')\n if k == 'zscore':\n m = (im > 0).float()\n n = m.sum(dim=(1, 2, 3), keepdim=True).clamp(min=1.0)\n mu = (im * m).sum(dim=(1, 2, 3), keepdim=True) / n\n var = (((im - mu) * m) ** 2).sum(dim=(1, 2, 3), keepdim=True) / n\n return (im - mu) / (var.sqrt() + 1e-06) * m\n if k == 'imagenet':\n m = (im > 0).float()\n return (im - 0.485) / 0.229 * m\n return im\n\n@torch.no_grad()\ndef _micro(images, masks):\n dev = DEV\n ims, slots, sidx, vms = ([], [], [], [])\n for b in range(len(masks)):\n present = np.nonzero(masks[b] > 0)[0]\n if len(present) == 0:\n continue\n blk = images[b][present]\n ims.append(torch.from_numpy(blk))\n vms.append(torch.from_numpy(blk.reshape(blk.shape[0], blk.shape[1], -1).max(2) > 0))\n slots.append(torch.from_numpy(present + 1).long())\n sidx.append(torch.full((len(present),), b, dtype=torch.long))\n out = np.full((len(models), len(masks), len(LABELS)), np.nan, np.float32)\n if not ims:\n return out\n im = _norm_(torch.cat(ims).to(dev, non_blocking=True).float().div_(255.0))\n sl = torch.cat(slots).to(dev)\n si = torch.cat(sidx).to(dev)\n vm = torch.cat(vms).to(dev)\n sm = torch.zeros(len(sl), CFG.get('n_meta', 0), device=dev)\n per = torch.zeros(len(models), len(masks), len(LABELS), device=dev, dtype=torch.float32)\n with torch.autocast('cuda' if str(dev).startswith('cuda') else 'cpu', dtype=AMP_DT, enabled=AMP_ON):\n for fold_index, model in enumerate(models):\n per[fold_index] = torch.sigmoid(\n model(im, sl, sm, si, len(masks), vm=vm).float()\n )\n got = per.cpu().numpy()\n keep = np.array([(masks[b] > 0).any() for b in range(len(masks))])\n out[:, keep] = got[:, keep]\n return out\n\ndef predict(images, masks):\n out = np.full((len(models), len(masks), len(LABELS)), np.nan, np.float32)\n for a in range(0, len(masks), MICRO):\n b = min(a + MICRO, len(masks))\n out[:, a:b] = _micro(images[a:b], masks[a:b])\n return out\n\n# Macro ROC-AUC depends on ordering, so combine fold orderings rather\n# than allowing a fold's probability scale to dominate the mean.\npreds = np.full((len(models), len(studies), len(LABELS)), np.nan, np.float32)\nt0, done = (time.time(), 0)\nwith ProcessPoolExecutor(max_workers=WORKERS) as ex:\n for c0 in range(0, len(studies), CHUNK):\n block = studies[c0:c0 + CHUNK]\n imgs = np.zeros((len(block), N_SLOT, N_SLICE, SIZE, SIZE), np.uint8)\n msks = np.zeros((len(block), N_SLOT), np.uint8)\n futs = [ex.submit(build_study, (i, s, by.get(s, []))) for i, s in enumerate(block)]\n for f in as_completed(futs):\n try:\n i, a, k = f.result()\n imgs[i], msks[i] = (a, k)\n except Exception as e:\n print(f' study failed: {type(e).__name__}: {e}')\n preds[:, c0:c0 + len(block)] = predict(imgs, msks)\n done += len(block)\n el = time.time() - t0\n print(f' {done:,}/{len(studies):,} {el / 60:.1f}m eta {el / done * (len(studies) - done) / 60:.1f}m', flush=True)\n del imgs, msks\n gc.collect()\nprint(f'\\ninference done in {(time.time() - t0) / 60:.1f} min')\nA5_W = 0.45\nA5_LABELS = list(LABELS)\n_a5_ok = np.isfinite(preds).all(axis=(0, 2))\n_a5_rank_mean = np.zeros((len(studies), len(LABELS)), np.float64)\nfor fold_index in range(preds.shape[0]):\n fold = preds[fold_index][_a5_ok]\n ordinal = fold.argsort(0).argsort(0).astype(np.float64)\n _a5_rank_mean[_a5_ok] += ordinal / max(len(fold) - 1, 1)\n_a5_rank_mean /= preds.shape[0]\n_a5_rank_mean[~_a5_ok] = np.nan\nA5_PREDS = dict(zip(\n sub_df['StudyInstanceUID'].astype(str), _a5_rank_mean.astype(np.float32)\n))\nfor _a5k, _a5v in _A5_SAVED.items():\n globals()[_a5k] = _a5v\ndel _A5_SAVED, _a5k, _a5v","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:08:21.74345Z","iopub.execute_input":"2026-08-17T17:08:21.743824Z","iopub.status.idle":"2026-08-17T17:08:25.414614Z","shell.execute_reply.started":"2026-08-17T17:08:21.743801Z","shell.execute_reply":"2026-08-17T17:08:25.413878Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"_a5_sub = pd.read_csv('/kaggle/working/submission.csv',\n dtype={'StudyInstanceUID': str})\nassert _a5_sub.columns.tolist()[1:] == A5_LABELS, 'submission schema drift'\nif A5_W > 0:\n _a5_ours = np.stack([A5_PREDS[_u]\n for _u in _a5_sub['StudyInstanceUID'].astype(str)])\n _a5_base_rank = _a5_sub[A5_LABELS].rank(method='average', pct=True)\n _a5_ours_rank = pd.DataFrame(_a5_ours, columns=A5_LABELS,\n index=_a5_sub.index).rank(method='average', pct=True)\n _a5_sub[A5_LABELS] = (1.0 - A5_W) * _a5_base_rank + A5_W * _a5_ours_rank\n assert np.isfinite(_a5_sub[A5_LABELS].to_numpy()).all()\n _a5_sub.to_csv('/kaggle/working/submission.csv', index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:08:25.415629Z","iopub.execute_input":"2026-08-17T17:08:25.415951Z","iopub.status.idle":"2026-08-17T17:08:25.431237Z","shell.execute_reply.started":"2026-08-17T17:08:25.415926Z","shell.execute_reply":"2026-08-17T17:08:25.430498Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Surgical V50 -> winning-frontier-v2 delta.\n#\n# Stage E10 gives the pinned public-v15 RadImageNet family a 0.50 rank vote on\n# ten findings, preserving Baker's and Fracture from the DINO parent. Stage E11\n# then gives a pinned, pixel-diverse RadImageNet family a 0.15 rank vote on all\n# twelve findings. A final 0.05 rank vote comes from a fold-balanced/smooth\n# aggregation of the same 20 DINOv2 forward passes.\nfrom __future__ import annotations\n\nimport contextlib as _rad_contextlib\nimport gc as _rad_gc\nimport hashlib as _rad_hashlib\nimport json as _rad_json\nimport os as _rad_os\nimport re as _rad_re\nimport time as _rad_time\nfrom concurrent.futures import ThreadPoolExecutor as _RadThreadPool\nfrom pathlib import Path as _RadPath\n\nimport numpy as _rad_np\nimport pandas as _rad_pd\nimport pydicom as _rad_pydicom\nimport torch as _rad_torch\nimport torch.nn as _rad_nn\nimport torch.nn.functional as _rad_F\nfrom torchvision.models import resnet50 as _rad_resnet50\n\n_RAD_LABELS = [\n 'ACL', 'MCL', 'Medial Meniscus', 'Lateral Meniscus', 'Medial OA',\n 'Lateral OA', 'PF OA', 'Effusion', 'Synovitis', \"Baker's\",\n 'Contusion', 'Fracture',\n]\n_RAD_ALPHA = 0.50\n_RAD_EXCLUDE = (\"Baker's\", 'Fracture')\n_RAD_HEADS_SHA256 = '54f657826b3458a7ba3d462e198ba380732f2b136246182312704929874a9a2c'\n_RAD_ENCODER_SHA256 = '08629f7e7bd3e29b8ee9522ca3f65ce4d010a7ddf74f0ea3c7e3f3d0bbab0734'\n_RAD_E11_HEADS_SHA256 = 'df98518d0a8f7cc506b4b806da03c3fca18c8f8f743e813c5401759b45e0f1fe'\n_RAD_E11_ALPHA = 0.20\n_RAD_LEGACY_DINO_ALPHA = 0.02\n_RAD_TOKEN_DIM, _RAD_HEAD_DIM = 2048, 512\n\n_RAD_E11_SLOTS = [\n ('SAG_NOFS', 'Sagittal', None, False),\n ('COR_NOFS', 'Coronal', None, False),\n ('AX_NOFS', 'Axial', None, False),\n ('SAG_FS', 'Sagittal', None, True),\n]\n_RAD_E11_CROP_MM = 130.0\n_RAD_E11_CACHE_SLICES = 8\n_RAD_E11_IMG = 224\n\n# Our independently trained five-fold family. Its preprocessing and estimator\n# are preserved from V35: native DICOM geometry/fat-sat handling and a mean of\n# per-fold percentile ranks (rather than v15's rank of the probability mean).\n_OUR_PLANES = ('Sagittal', 'Coronal', 'Axial')\n_OUR_N_SLOT, _OUR_N_SLICE, _OUR_IMG = 3, 8, 224\n_OUR_SLICE_BAND = (0.12, 0.88)\n_OUR_FOLD_SHA256 = '1301603a060226c47c96be54d4c3618fee41f2e97f8f82d8f77a752819ffb7e3'\n_OUR_CONFIG_HASH = '794a44d95a0ebb7096f17daa5a06dc191ec16c4d0835e69ac1868e82a7eb05dd'\n_OUR_HEAD_SHA256 = {\n 'rad_head_f0.pt': '0c92b27578e139cc35071a3f72ddd4e1a66106761225a7e011f076f37eb7051d',\n 'rad_head_f1.pt': 'c29e60a99982d8dfb933a276f51c8b3a7d2e849649ed27a09affa822405fbd17',\n 'rad_head_f2.pt': '40328ac7d72ca281e7e04438643100e99eb87fbe1e2b51965350b1a73a7b57ab',\n 'rad_head_f3.pt': '6538a5faa92b61705727a14bd98c5ddce2989028dd8cccb261c47b2066fa5efa',\n 'rad_head_f4.pt': '5bd126d68ddadd479a0eab6f0cdb17603060614a7eb14402e5b9945f651107af',\n}\n_OUR_FATSAT_OPTIONS = {'FS', 'FATSAT', 'FAT_SAT', 'FSAT'}\n_OUR_FATSAT_PATTERN = _rad_re.compile(\n r'\\bfs\\b|fatsat|fat sat|\\bstir\\b|\\bspair\\b|\\bspir\\b|\\bwe\\b|'\n r'water excit|\\btirm\\b|\\bsting\\b|\\bfatsup\\b'\n)\n\n# Exact V40/E10 test representation: three fat-suppressed planes, eight\n# acquired slices per plane, full frame, legacy ordering/laterality/fill.\nSLOTS = [\n ('SAG_FS', 'Sagittal', None, True),\n ('COR_FS', 'Coronal', None, True),\n ('AX_FS', 'Axial', None, True),\n]\nN_SLOT = len(SLOTS)\nCACHE_SLICES = 8\nIMG = CACHE_IMG = 224\nCROP_MM = 10_000.0\nSLICE_BAND = (0.12, 0.88)\nRULES = dict(RULES_LEGACY)\nTIME_BUDGET = 8.72 * 3600\n\n\ndef _rad_log(message):\n print(f'[Rad-dual5] {message}', flush=True)\n\n\ndef _rad_sha256(path, chunk=8 << 20):\n digest = _rad_hashlib.sha256()\n with open(path, 'rb') as handle:\n for block in iter(lambda: handle.read(chunk), b''):\n digest.update(block)\n return digest.hexdigest()\n\n\ndef _rad_find_file(name, expected_sha=None, explicit_env=None):\n if explicit_env and _rad_os.environ.get(explicit_env):\n candidates = [_RadPath(_rad_os.environ[explicit_env])]\n else:\n candidates = []\n base = _RadPath('/kaggle/input')\n if base.is_dir():\n for root, dirs, files in _rad_os.walk(base):\n dirs[:] = [d for d in dirs if d not in ('train_series', 'test_series')]\n if name in files:\n candidates.append(_RadPath(root) / name)\n if not candidates:\n raise FileNotFoundError(f'V36 missing input artifact {name}')\n for path in candidates:\n if expected_sha is None or _rad_sha256(path) == expected_sha:\n return path\n raise RuntimeError(f'V36 found {name}, but no copy has the required SHA-256')\n\n\ndef _ours_find_head_dir():\n override = _rad_os.environ.get('RSNA_RAD_HEAD_DIR')\n roots = [_RadPath(override)] if override else []\n if not roots:\n base = _RadPath('/kaggle/input')\n if base.is_dir():\n for root, dirs, files in _rad_os.walk(base):\n # Never traverse the competition's DICOM trees while locating a\n # tiny attached model manifest.\n dirs[:] = [d for d in dirs if d not in ('train_series', 'test_series')]\n if 'rad_heads_manifest.json' in files:\n roots.append(_RadPath(root))\n for root in roots:\n manifest_path = root / 'rad_heads_manifest.json'\n if not manifest_path.is_file():\n continue\n manifest = _rad_json.loads(manifest_path.read_text())\n if manifest.get('artifact_type') != 'rsna-radimagenet-foldsv1-heads':\n continue\n if manifest.get('fold_sha256') != _OUR_FOLD_SHA256:\n raise RuntimeError('our Rad head manifest fold hash drift')\n if manifest.get('config_hash') != _OUR_CONFIG_HASH:\n raise RuntimeError('our Rad head manifest config hash drift')\n if manifest.get('labels') != _RAD_LABELS:\n raise RuntimeError('our Rad head manifest label order drift')\n return root, manifest\n raise FileNotFoundError('our five-fold RadImageNet head dataset is not attached')\n\n\ndef _ours_vector(value, length):\n try:\n result = _rad_np.asarray([float(item) for item in value], dtype=_rad_np.float64)\n except Exception:\n return None\n if len(result) < length or not _rad_np.isfinite(result[:length]).all():\n return None\n return result\n\n\ndef _ours_dicom_files(directory):\n return sorted(_RadPath(directory).glob('*.dcm'), key=lambda path: path.name)\n\n\ndef _ours_header(path):\n tags = [\n 'ImagePositionPatient', 'ImageOrientationPatient', 'InstanceNumber',\n 'Laterality', 'PixelSpacing', 'Rows', 'Columns', 'SeriesDescription',\n 'SequenceName', 'ScanOptions',\n ]\n try:\n return _rad_pydicom.dcmread(\n str(path), stop_before_pixels=True, force=True, specific_tags=tags\n )\n except Exception:\n return None\n\n\ndef _ours_image_center_x(ds):\n if ds is None:\n return None\n ipp = _ours_vector(getattr(ds, 'ImagePositionPatient', None), 3)\n iop = _ours_vector(getattr(ds, 'ImageOrientationPatient', None), 6)\n spacing = _ours_vector(getattr(ds, 'PixelSpacing', None), 2)\n try:\n rows, cols = float(ds.Rows), float(ds.Columns)\n except Exception:\n return None\n if ipp is None or iop is None or spacing is None:\n return None\n center = (\n ipp[:3]\n + iop[:3] * spacing[1] * cols / 2.0\n + iop[3:6] * spacing[0] * rows / 2.0\n )\n return float(center[0])\n\n\ndef _ours_is_fatsat(ds):\n if ds is None:\n return False\n description = (\n f\"{getattr(ds, 'SeriesDescription', '') or ''} \"\n f\"{getattr(ds, 'SequenceName', '') or ''}\"\n ).lower()\n description = _rad_re.sub(r'[_\\-.]', ' ', description)\n options = getattr(ds, 'ScanOptions', None)\n if options is None:\n tokens = []\n elif isinstance(options, str):\n tokens = _rad_re.split(r'[|\\\\]', options)\n else:\n try:\n tokens = list(options)\n except TypeError:\n tokens = [options]\n option_match = any(\n str(token).strip().upper() in _OUR_FATSAT_OPTIONS for token in tokens\n )\n return bool(_OUR_FATSAT_PATTERN.search(description) or option_match)\n\n\ndef _ours_inspect_series(job):\n study, series, plane, directory = job\n files = _ours_dicom_files(directory)\n ds = _ours_header(files[len(files) // 2]) if files else None\n laterality = str(getattr(ds, 'Laterality', '') or '').strip().upper()[:1]\n laterality = laterality if laterality in ('L', 'R') else None\n return {\n 'study': study,\n 'series': series,\n 'plane': plane,\n 'directory': str(directory),\n 'n_files': len(files),\n 'fatsat': _ours_is_fatsat(ds),\n 'laterality': laterality,\n 'center_x': _ours_image_center_x(ds),\n }\n\n\ndef _ours_select_series(comp, studies):\n table = _rad_pd.read_csv(\n comp / 'test_series.csv',\n dtype={'StudyInstanceUID': str, 'SeriesInstanceUID': str},\n )\n table = table[table['StudyInstanceUID'].isin(studies)]\n root = comp / 'test_series'\n jobs = [\n (\n str(row.StudyInstanceUID),\n str(row.SeriesInstanceUID),\n str(row.Anatomical_Plane),\n root / str(row.StudyInstanceUID) / str(row.SeriesInstanceUID),\n )\n for row in table.itertuples(index=False)\n ]\n workers = max(1, min(16, _rad_os.cpu_count() or 1))\n with _RadThreadPool(max_workers=workers) as pool:\n inspected = list(pool.map(_ours_inspect_series, jobs))\n selected = {uid: [None] * _OUR_N_SLOT for uid in studies}\n tags = {uid: [] for uid in studies}\n centers = {uid: [] for uid in studies}\n for record in inspected:\n uid = record['study']\n if record['laterality']:\n tags[uid].append(record['laterality'])\n if record['center_x'] is not None:\n centers[uid].append(record['center_x'])\n if not record['fatsat'] or record['plane'] not in _OUR_PLANES:\n continue\n slot = _OUR_PLANES.index(record['plane'])\n current = selected[uid][slot]\n if current is None or record['n_files'] > current['n_files']:\n selected[uid][slot] = record\n sides = {}\n for uid in studies:\n if tags[uid]:\n sides[uid] = tags[uid][0]\n elif centers[uid]:\n middle = float(_rad_np.median(centers[uid]))\n sides[uid] = None if abs(middle) < 20.0 else ('R' if middle < 0 else 'L')\n else:\n sides[uid] = None\n return selected, sides\n\n\ndef _ours_order_files(directory):\n files = _ours_dicom_files(directory)\n rows = []\n for path in files:\n ds = _ours_header(path)\n key = None\n if ds is not None:\n ipp = _ours_vector(getattr(ds, 'ImagePositionPatient', None), 3)\n iop = _ours_vector(getattr(ds, 'ImageOrientationPatient', None), 6)\n if ipp is not None and iop is not None:\n key = float(_rad_np.dot(ipp[:3], _rad_np.cross(iop[:3], iop[3:6])))\n if key is None:\n try:\n key = float(ds.InstanceNumber)\n except Exception:\n pass\n rows.append((key, path))\n # Preserve the native training rule: if any position is unavailable, use\n # filename order for the entire series rather than mixing order systems.\n if any(key is None for key, _ in rows):\n return files\n return [path for _, path in sorted(rows, key=lambda item: item[0])]\n\n\ndef _ours_sample_indices(length):\n if length <= 0:\n return _rad_np.zeros(0, dtype=_rad_np.int64)\n lo = int(_OUR_SLICE_BAND[0] * (length - 1))\n hi = int(_OUR_SLICE_BAND[1] * (length - 1))\n if hi > lo:\n indices = _rad_np.unique(\n _rad_np.linspace(lo, hi, _OUR_N_SLICE).astype(_rad_np.int64)\n )\n else:\n indices = _rad_np.array([length // 2], dtype=_rad_np.int64)\n while len(indices) < _OUR_N_SLICE:\n indices = _rad_np.append(indices, indices[-1])\n return indices[:_OUR_N_SLICE]\n\n\ndef _ours_read_series(record):\n files = _ours_order_files(record['directory'])\n indices = _ours_sample_indices(len(files))\n if not len(indices):\n return None\n images = []\n for index in indices:\n try:\n ds = _rad_pydicom.dcmread(str(files[int(index)]), force=True)\n image = ds.pixel_array.astype(_rad_np.float32)\n image = image * float(getattr(ds, 'RescaleSlope', 1) or 1)\n image = image + float(getattr(ds, 'RescaleIntercept', 0) or 0)\n except Exception:\n image = None\n images.append(image)\n valid = [index for index, image in enumerate(images) if image is not None]\n if not valid:\n return None\n for index, image in enumerate(images):\n if image is None:\n images[index] = images[min(valid, key=lambda other: abs(other - index))]\n shape = images[0].shape\n images = [\n image if image.shape == shape else _rad_np.zeros(shape, _rad_np.float32)\n for image in images\n ]\n volume = _rad_np.stack(images).astype(_rad_np.float32, copy=False)\n lo, hi = _rad_np.percentile(volume, [1.0, 99.0])\n volume = _rad_np.clip((volume - lo) / max(float(hi - lo), 1e-6), 0.0, 1.0)\n tensor = _rad_torch.from_numpy(_rad_np.ascontiguousarray(volume)).unsqueeze(0)\n resized = _rad_F.interpolate(\n tensor, size=(_OUR_IMG, _OUR_IMG), mode='bilinear', align_corners=False\n ).squeeze(0)\n return resized.mul(255).round().clamp(0, 255).to(_rad_torch.uint8).numpy()\n\n\ndef _ours_build_study(job):\n index, uid, records, side = job\n output = _rad_np.zeros(\n (_OUR_N_SLOT, _OUR_N_SLICE, _OUR_IMG, _OUR_IMG), _rad_np.uint8\n )\n mask = _rad_np.zeros(_OUR_N_SLOT, _rad_np.uint8)\n for slot, record in enumerate(records):\n if record is None:\n continue\n image = _ours_read_series(record)\n if image is None:\n continue\n if side == 'R':\n image = (\n image[::-1].copy()\n if record['plane'] == 'Sagittal'\n else image[:, :, ::-1].copy()\n )\n output[slot] = image\n mask[slot] = 1\n return index, uid, output, mask\n\n\nclass _RadEncoder(_rad_nn.Module):\n def __init__(self):\n super().__init__()\n self.backbone = _rad_nn.Sequential(\n *list(_rad_resnet50(weights=None).children())[:-2]\n )\n\n def forward(self, image):\n return self.backbone(image).mean(dim=(2, 3))\n\n\nclass _RadHead(_rad_nn.Module):\n def __init__(self):\n super().__init__()\n self.project = _rad_nn.Sequential(\n _rad_nn.LayerNorm(_RAD_TOKEN_DIM),\n _rad_nn.Linear(_RAD_TOKEN_DIM, _RAD_HEAD_DIM),\n _rad_nn.GELU(),\n )\n self.plane = _rad_nn.Parameter(_rad_torch.randn(N_SLOT, _RAD_HEAD_DIM) * .01)\n self.position = _rad_nn.Parameter(_rad_torch.randn(CACHE_SLICES, _RAD_HEAD_DIM) * .01)\n self.query = _rad_nn.Parameter(_rad_torch.randn(len(_RAD_LABELS), _RAD_HEAD_DIM) * .02)\n self.attn = _rad_nn.MultiheadAttention(\n _RAD_HEAD_DIM, 8, dropout=.10, batch_first=True\n )\n self.fuse = _rad_nn.Sequential(\n _rad_nn.LayerNorm(_RAD_HEAD_DIM * 4),\n _rad_nn.Linear(_RAD_HEAD_DIM * 4, _RAD_HEAD_DIM),\n _rad_nn.GELU(),\n _rad_nn.Dropout(.15),\n )\n self.weight = _rad_nn.Parameter(\n _rad_torch.randn(len(_RAD_LABELS), _RAD_HEAD_DIM) * .02\n )\n self.bias = _rad_nn.Parameter(_rad_torch.zeros(len(_RAD_LABELS)))\n\n def forward(self, feature, mask):\n token = self.project(feature.float())\n token = token.view(len(token), N_SLOT, CACHE_SLICES, _RAD_HEAD_DIM)\n token = token + self.plane[None, :, None] + self.position[None, None]\n token = token.flatten(1, 2)\n key_padding = mask <= 0\n all_empty = key_padding.all(1)\n if all_empty.any():\n key_padding = key_padding.clone()\n key_padding[all_empty, 0] = False\n query = self.query.unsqueeze(0).expand(len(token), -1, -1)\n attended = query + self.attn(\n query, token, token, key_padding_mask=key_padding, need_weights=False\n )[0]\n denominator = mask.sum(1, keepdim=True).clamp_min(1).unsqueeze(-1)\n mean = (token * mask.unsqueeze(-1)).sum(1, keepdim=True) / denominator\n mean = mean.expand(-1, len(_RAD_LABELS), -1)\n fused = self.fuse(_rad_torch.cat(\n [attended, mean, _rad_torch.abs(attended - mean), attended * mean], dim=-1\n ))\n return (fused * self.weight.unsqueeze(0)).sum(-1) + self.bias\n\n\ndef _rad_load_models(device):\n encoder_path = _rad_find_file(\n 'ResNet50.pt', _RAD_ENCODER_SHA256, explicit_env='RSNA_RAD_WEIGHT_PATH'\n )\n encoder = _RadEncoder()\n encoder.load_state_dict(\n _rad_torch.load(encoder_path, map_location='cpu', weights_only=True), strict=True\n )\n if sum(parameter.numel() for parameter in encoder.parameters()) != 23_508_032:\n raise RuntimeError('V36 RadImageNet encoder parameter-count drift')\n encoder.eval().to(device)\n for parameter in encoder.parameters():\n parameter.requires_grad_(False)\n if device.type == 'cuda' and _rad_torch.cuda.device_count() > 1:\n encoder = _rad_nn.DataParallel(\n encoder, device_ids=list(range(_rad_torch.cuda.device_count()))\n )\n\n heads_path = _rad_find_file('v52_radimagenet_heads.pt', _RAD_HEADS_SHA256)\n payload = _rad_torch.load(heads_path, map_location='cpu', weights_only=True)\n expected = {\n 'version': 'v52-radimagenet-resnet50-official-1',\n 'targets': _RAD_LABELS,\n 'encoder_sha256': _RAD_ENCODER_SHA256,\n 'encoder_source_commit': '0ce16f7375db4236e646829d1eca61cdb4282133',\n 'img': 224,\n 'slices_per_plane': 8,\n 'feature': 'global_average_pool',\n }\n for key, value in expected.items():\n if payload.get(key) != value:\n raise RuntimeError(f'V36 v15 head contract drift for {key}')\n folds = payload.get('folds')\n if not isinstance(folds, list) or len(folds) != 5:\n raise RuntimeError('V36 requires all five public v15 heads')\n if sorted(int(record.get('fold', -1)) for record in folds) != list(range(5)):\n raise RuntimeError('V36 public v15 fold identity drift')\n heads = []\n for record in folds:\n head = _RadHead().to(device).eval()\n head.load_state_dict(record['state_dict'], strict=True)\n heads.append(head)\n return encoder, heads, str(encoder_path), str(heads_path)\n\n\ndef _ours_load_heads(device):\n if (_OUR_N_SLOT, _OUR_N_SLICE) != (N_SLOT, CACHE_SLICES):\n raise RuntimeError('public and native Rad head tensor shapes diverged')\n head_dir, manifest = _ours_find_head_dir()\n heads = []\n observed_heads = {}\n for fold in range(5):\n name = f'rad_head_f{fold}.pt'\n path = head_dir / name\n if not path.is_file():\n raise FileNotFoundError(path)\n observed = _rad_sha256(path)\n if observed != _OUR_HEAD_SHA256[name]:\n raise RuntimeError(f'our Rad head SHA-256 drift for {name}')\n if manifest['heads'][name]['sha256'] != observed:\n raise RuntimeError(f'our Rad manifest/checkpoint mismatch for {name}')\n checkpoint = _rad_torch.load(path, map_location='cpu', weights_only=False)\n config = checkpoint.get('config', {})\n if checkpoint.get('fold') != fold:\n raise RuntimeError(f'our Rad checkpoint fold drift for fold {fold}')\n if checkpoint.get('config_hash') != _OUR_CONFIG_HASH:\n raise RuntimeError(f'our Rad checkpoint config hash drift for fold {fold}')\n if config.get('gold_override') is not False:\n raise RuntimeError(f'our Rad checkpoint gold policy drift for fold {fold}')\n if config.get('target_mode') != 'public3':\n raise RuntimeError(f'our Rad checkpoint target mode drift for fold {fold}')\n if config.get('folds', {}).get('sha256') != _OUR_FOLD_SHA256:\n raise RuntimeError(f'our Rad checkpoint fold contract drift for fold {fold}')\n head = _RadHead().to(device).eval()\n head.load_state_dict(checkpoint['state_dict'], strict=True)\n heads.append(head)\n observed_heads[name] = observed\n return heads, str(head_dir), observed_heads\n\n\n@_rad_torch.inference_mode()\ndef _rad_encode(encoder, pixels, slot_mask, device):\n n, slots, slices, height, width = pixels.shape\n features = _rad_np.zeros(\n (n, slots * slices, _RAD_TOKEN_DIM), _rad_np.float16\n )\n token_mask = _rad_np.repeat(slot_mask[:, :, None], slices, axis=2).reshape(n, -1)\n valid = _rad_np.flatnonzero(token_mask.reshape(-1) > 0)\n flat = pixels.reshape(-1, height, width)\n batch = 192 if device.type == 'cuda' and _rad_torch.cuda.device_count() > 1 else (\n 96 if device.type == 'cuda' else 8\n )\n for start in range(0, len(valid), batch):\n indices = valid[start:start + batch]\n image = _rad_torch.from_numpy(flat[indices]).to(device).float().div_(127.5).sub_(1.0)\n image = image.unsqueeze(1).expand(-1, 3, -1, -1).contiguous()\n amp = (_rad_torch.autocast('cuda')\n if device.type == 'cuda' else _rad_contextlib.nullcontext())\n with amp:\n feature = encoder(image)\n values = feature.float().cpu().numpy()\n if not _rad_np.isfinite(values).all():\n raise RuntimeError('V36 non-finite RadImageNet feature')\n features.reshape(-1, _RAD_TOKEN_DIM)[indices] = values.astype(_rad_np.float16)\n return features, token_mask.astype(_rad_np.float32)\n\n\n@_rad_torch.inference_mode()\ndef _rad_predict_head(head, features, masks, device, batch=64):\n predictions = []\n for start in range(0, len(features), batch):\n image = _rad_torch.from_numpy(features[start:start + batch]).to(device)\n mask = _rad_torch.from_numpy(masks[start:start + batch]).to(device)\n amp = (_rad_torch.autocast('cuda')\n if device.type == 'cuda' else _rad_contextlib.nullcontext())\n with amp:\n predictions.append(_rad_torch.sigmoid(head(image, mask)).float().cpu())\n return _rad_torch.cat(predictions).numpy()\n\n\n@_rad_torch.inference_mode()\ndef _ours_encode_block(encoder, pixels, slot_mask, device):\n n = len(pixels)\n features = _rad_np.zeros(\n (n, _OUR_N_SLOT * _OUR_N_SLICE, _RAD_TOKEN_DIM), _rad_np.float16\n )\n token_mask = _rad_np.repeat(\n slot_mask[:, :, None], _OUR_N_SLICE, axis=2\n ).reshape(n, -1)\n valid = _rad_np.flatnonzero(token_mask.reshape(-1) > 0)\n flat = pixels.reshape(-1, _OUR_IMG, _OUR_IMG)\n # Preserve the native five-fold encoder batch/precision contract.\n batch = 96 if device.type == 'cuda' else 8\n for start in range(0, len(valid), batch):\n indices = valid[start:start + batch]\n image = _rad_torch.from_numpy(flat[indices]).to(device).float().div_(127.5).sub_(1.0)\n image = image.unsqueeze(1).expand(-1, 3, -1, -1).contiguous()\n amp = (\n _rad_torch.autocast('cuda', dtype=_rad_torch.float16)\n if device.type == 'cuda'\n else _rad_contextlib.nullcontext()\n )\n with amp:\n feature = encoder(image)\n values = feature.float().cpu().numpy()\n if not _rad_np.isfinite(values).all():\n raise RuntimeError('our Rad family produced non-finite encoder features')\n features.reshape(-1, _RAD_TOKEN_DIM)[indices] = values.astype(_rad_np.float16)\n return features, token_mask.astype(_rad_np.float32)\n\n\n@_rad_torch.inference_mode()\ndef _ours_predict_heads(heads, features, masks, device):\n feature = _rad_torch.from_numpy(features).to(device)\n mask = _rad_torch.from_numpy(masks).to(device)\n # These heads were selected/rescored without head autocast; keep that path.\n return [\n _rad_torch.sigmoid(head(feature, mask)).cpu().numpy()\n for head in heads\n ]\n\n\ndef _rad_rank_columns(values):\n return _rad_pd.DataFrame(\n _rad_np.asarray(values, dtype=_rad_np.float64)\n ).rank(method='average', pct=True).to_numpy(_rad_np.float64)\n\n\ndef _rad_validate(frame, expected_ids):\n if frame.columns.tolist() != ['StudyInstanceUID', *_RAD_LABELS]:\n raise RuntimeError('V36 submission schema drift')\n ids = frame['StudyInstanceUID'].astype(str).tolist()\n if ids != list(map(str, expected_ids)) or len(ids) != len(set(ids)):\n raise RuntimeError('V36 submission study identity/order drift')\n values = frame[_RAD_LABELS].to_numpy(_rad_np.float64)\n if not _rad_np.isfinite(values).all() or values.min() < 0 or values.max() > 1:\n raise RuntimeError('V36 invalid submission values')\n\n\ndef _rad_main():\n started = _rad_time.time()\n work = _RadPath(_rad_os.environ.get('RSNA_RAD_OUTPUT_DIR', '/kaggle/working'))\n primary = work / 'submission.csv'\n if not primary.is_file():\n raise FileNotFoundError('V37 requires the completed DINO parent submission.csv')\n test = _rad_pd.read_csv(ROOT / 'test.csv', dtype={'StudyInstanceUID': str})\n expected_ids = test['StudyInstanceUID'].astype(str).tolist()\n baseline = _rad_pd.read_csv(primary, dtype={'StudyInstanceUID': str})\n _rad_validate(baseline, expected_ids)\n\n device = _rad_torch.device('cuda:0' if _rad_torch.cuda.is_available() else 'cpu')\n if device.type != 'cuda':\n raise RuntimeError('V37 RadImageNet inference requires CUDA')\n encoder, public_heads, encoder_path, public_heads_path = _rad_load_models(device)\n\n # Family 1: public v15/E10 legacy pixels. Keep this path bit-for-bit as in\n # V36, including rank(mean(fold probability)).\n test_series = _rad_pd.read_csv(\n ROOT / 'test_series.csv',\n dtype={'StudyInstanceUID': str, 'SeriesInstanceUID': str},\n )\n plane = dict(zip(test_series.SeriesInstanceUID, test_series.Anatomical_Plane))\n headers = annotate(walk('test_series'))\n studies, pixels, slot_mask = build_cache(\n pick_slots(headers, plane), plane, lat_of(headers, 'test-e10 '), 'test-e10'\n )\n by_uid = {str(uid): index for index, uid in enumerate(studies)}\n missing = [uid for uid in expected_ids if uid not in by_uid]\n if missing:\n raise RuntimeError(f'{len(missing)} test studies absent from public-v15 cache')\n order = _rad_np.asarray([by_uid[uid] for uid in expected_ids], dtype=_rad_np.int64)\n pixels, slot_mask = pixels[order], slot_mask[order]\n token_count = int(\n _rad_np.repeat(slot_mask[:, :, None], CACHE_SLICES, axis=2).sum()\n )\n if token_count < int(0.85 * len(test) * N_SLOT * CACHE_SLICES):\n raise RuntimeError(f'insufficient acquired public-v15 test slices: {token_count}')\n\n features, token_mask = _rad_encode(encoder, pixels, slot_mask, device)\n del pixels, slot_mask, headers\n _rad_gc.collect()\n public_fold_predictions = [\n _rad_predict_head(head, features, token_mask, device)\n for head in public_heads\n ]\n if len(public_fold_predictions) != 5:\n raise RuntimeError('V37 inference did not use all five public v15 heads')\n\n # V40 ranks the probability mean of the five v15 heads (not mean-fold-rank).\n public_probability = _rad_np.mean(_rad_np.stack(public_fold_predictions), axis=0)\n public_rank = _rad_rank_columns(public_probability)\n del public_heads, public_fold_predictions, public_probability, features, token_mask\n _rad_gc.collect()\n _rad_torch.cuda.empty_cache()\n _rad_log(\n f'public v15 family complete with its legacy pixels ({public_heads_path})'\n )\n\n # E10: exactly the winning v2's public-v15 0.50 vote. The two excluded\n # findings remain the raw parent values, matching the audited deployment.\n baseline_rank = _rad_rank_columns(baseline[_RAD_LABELS].to_numpy())\n candidate = baseline.copy()\n for index, target in enumerate(_RAD_LABELS):\n if target not in _RAD_EXCLUDE:\n candidate[target] = (\n (1.0 - _RAD_ALPHA) * baseline_rank[:, index]\n + _RAD_ALPHA * public_rank[:, index]\n )\n for target in _RAD_EXCLUDE:\n if not _rad_np.array_equal(\n candidate[target].to_numpy(), baseline[target].to_numpy()\n ):\n raise RuntimeError(f'E10 failed to preserve raw parent values for {target}')\n _rad_validate(candidate, expected_ids)\n e10_path = work / 'submission_e10_v2.csv'\n candidate.to_csv(e10_path, index=False)\n _rad_log(\n f'E10 complete: 0.50*rank(parent)+0.50*rank(public-v15); '\n f'preserved raw={list(_RAD_EXCLUDE)}'\n )\n\n # E11: a genuinely different pixel view—three non-fat-suppressed planes and\n # one sagittal fat-suppressed anchor at a 130 mm crop. The serialized bundle\n # and all five folds are pinned before they can affect submission.csv.\n globals().update(\n SLOTS=list(_RAD_E11_SLOTS),\n N_SLOT=len(_RAD_E11_SLOTS),\n CACHE_SLICES=int(_RAD_E11_CACHE_SLICES),\n IMG=int(_RAD_E11_IMG),\n CACHE_IMG=int(_RAD_E11_IMG),\n CROP_MM=float(_RAD_E11_CROP_MM),\n RULES=dict(RULES_LEGACY),\n )\n e11_path = _rad_find_file('v52_e11_heads.pt', _RAD_E11_HEADS_SHA256)\n e11_payload = _rad_torch.load(\n e11_path, map_location='cpu', weights_only=False\n )\n e11_expected = {\n 'version': 'e11-radimagenet-resnet50-diverse-1',\n 'targets': _RAD_LABELS,\n 'encoder_sha256': _RAD_ENCODER_SHA256,\n 'slots': [list(slot) for slot in _RAD_E11_SLOTS],\n 'crop_mm': _RAD_E11_CROP_MM,\n 'img': _RAD_E11_IMG,\n 'slices_per_plane': _RAD_E11_CACHE_SLICES,\n 'feature': 'global_average_pool',\n }\n for key, value in e11_expected.items():\n if e11_payload.get(key) != value:\n raise RuntimeError(f'E11 head contract drift for {key}')\n e11_folds = e11_payload.get('folds')\n if not isinstance(e11_folds, list) or len(e11_folds) != 5:\n raise RuntimeError('E11 requires all five pinned heads')\n if sorted(int(record.get('fold', -1)) for record in e11_folds) != list(range(5)):\n raise RuntimeError('E11 fold identity drift')\n e11_heads = []\n for record in e11_folds:\n head = _RadHead().to(device).eval()\n head.load_state_dict(record['state_dict'], strict=True)\n e11_heads.append(head)\n\n headers = annotate(walk('test_series'))\n studies, pixels, slot_mask = build_cache(\n pick_slots(headers, plane), plane, lat_of(headers, 'test-e11 '), 'test-e11'\n )\n by_uid = {str(uid): index for index, uid in enumerate(studies)}\n missing = [uid for uid in expected_ids if uid not in by_uid]\n if missing:\n raise RuntimeError(f'{len(missing)} test studies absent from E11 cache')\n order = _rad_np.asarray([by_uid[uid] for uid in expected_ids], dtype=_rad_np.int64)\n pixels, slot_mask = pixels[order], slot_mask[order]\n e11_token_count = int(\n _rad_np.repeat(slot_mask[:, :, None], CACHE_SLICES, axis=2).sum()\n )\n if e11_token_count < int(0.55 * len(test) * N_SLOT * CACHE_SLICES):\n raise RuntimeError(f'insufficient acquired E11 test slices: {e11_token_count}')\n features, token_mask = _rad_encode(encoder, pixels, slot_mask, device)\n del pixels, slot_mask, headers\n _rad_gc.collect()\n e11_predictions = [\n _rad_predict_head(head, features, token_mask, device)\n for head in e11_heads\n ]\n if len(e11_predictions) != 5:\n raise RuntimeError('E11 inference did not use all five pinned heads')\n e11_probability = _rad_np.mean(_rad_np.stack(e11_predictions), axis=0)\n if (\n e11_probability.shape != (len(test), len(_RAD_LABELS))\n or not _rad_np.isfinite(e11_probability).all()\n ):\n raise RuntimeError(f'invalid E11 prediction shape/value: {e11_probability.shape}')\n\n # Re-rank the already-blended E10 table, then apply E11 to all twelve\n # findings while preserving the audited two-stage rank geometry.\n e10_rank = _rad_rank_columns(candidate[_RAD_LABELS].to_numpy())\n e11_rank = _rad_rank_columns(e11_probability)\n final = candidate.copy()\n for index, target in enumerate(_RAD_LABELS):\n final[target] = (\n (1.0 - _RAD_E11_ALPHA) * e10_rank[:, index]\n + _RAD_E11_ALPHA * e11_rank[:, index]\n )\n _rad_validate(final, expected_ids)\n\n # Preserve 98% of the audited E10/E11 result and let the existing\n # fold-balanced DINO aggregation resolve only close prediction pairs.\n legacy_path = work / 'submission_legacy_fold_blend.csv'\n if not legacy_path.is_file():\n raise FileNotFoundError('V60 requires submission_legacy_fold_blend.csv')\n legacy = _rad_pd.read_csv(legacy_path, dtype={'StudyInstanceUID': str})\n _rad_validate(legacy, expected_ids)\n e10_e11_rank = _rad_rank_columns(final[_RAD_LABELS].to_numpy())\n legacy_rank = _rad_rank_columns(legacy[_RAD_LABELS].to_numpy())\n for index, target in enumerate(_RAD_LABELS):\n final[target] = (\n (1.0 - _RAD_LEGACY_DINO_ALPHA) * e10_e11_rank[:, index]\n + _RAD_LEGACY_DINO_ALPHA * legacy_rank[:, index]\n )\n _rad_validate(final, expected_ids)\n temporary = primary.with_suffix('.csv.tmp')\n final.to_csv(temporary, index=False)\n _rad_os.replace(temporary, primary)\n\n receipt = {\n 'recipe': 'v50-parent -> public-v15 E10@0.50 -> diverse E11@0.20 -> legacy-DINO@0.02',\n 'e10_alpha': _RAD_ALPHA,\n 'e10_preserved_targets': list(_RAD_EXCLUDE),\n 'e11_alpha': _RAD_E11_ALPHA,\n 'legacy_dino_alpha': _RAD_LEGACY_DINO_ALPHA,\n 'legacy_dino_estimator': 'mean raw within fold -> rank fold -> mean five folds; focal soft-window correction',\n 'public_heads_sha256': _RAD_HEADS_SHA256,\n 'e11_heads_sha256': _RAD_E11_HEADS_SHA256,\n 'encoder_sha256': _RAD_ENCODER_SHA256,\n 'test_studies': len(expected_ids),\n 'e10_tokens': token_count,\n 'e11_tokens': e11_token_count,\n 'submission_sha256': _rad_sha256(primary),\n }\n (work / 'v50_v2_repro_receipt.json').write_text(\n _rad_json.dumps(receipt, indent=2, sort_keys=True) + '\\n'\n )\n del encoder, e11_heads, e11_predictions, features, token_mask\n _rad_gc.collect()\n _rad_torch.cuda.empty_cache()\n _rad_log(\n f'V66 complete: 0.98*rank(E10/E11)+0.02*rank(legacy-DINO) on all 12; '\n f'v15={public_heads_path}; e11={e11_path}; encoder={encoder_path}; '\n f'elapsed={(_rad_time.time()-started)/60:.1f}m'\n )\n\n\n_rad_main()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-17T17:08:25.43272Z","iopub.execute_input":"2026-08-17T17:08:25.433032Z","iopub.status.idle":"2026-08-17T17:08:33.991339Z","shell.execute_reply.started":"2026-08-17T17:08:25.43301Z","shell.execute_reply":"2026-08-17T17:08:33.990751Z"}},"outputs":[],"execution_count":null}]}