{ "id": 598235, "title": "Should I use dicom metadata for training or even preprocessing?", "url": "/competitions/rsna-intracranial-aneurysm-detection/discussion/598235", "author_name": "Bhavesh Solanki", "post_date": "2025-08-09T13:02:36.314000", "votes": -2, "comment_count": 2, "views": 0, "content": "

I am having really hard time understanding DiCom files i have collected some metadata that looked important, here it is:

\n

StudyInstanceUID
\n1.2.826.0.1.3680043.8.498.26875275827756142632463662271305814995 1441
\n1.2.826.0.1.3680043.8.498.95823759726018881810909243809398453285 1331
\n1.2.826.0.1.3680043.8.498.54090196673781955332780103653722908665 1314
\n1.2.826.0.1.3680043.8.498.96493458432292738336891549465693531362 1311
\n1.2.826.0.1.3680043.8.498.90287698646889729761534522929777327309 1291
\n …
\n1.2.826.0.1.3680043.8.498.10034385894802321175291320093789615030 1
\n1.2.826.0.1.3680043.8.498.95814811312894040378383764209574694874 1
\n1.2.826.0.1.3680043.8.498.11035097333885684808818474949068969433 1
\n1.2.826.0.1.3680043.8.498.11819620448760534150797658408275744970 1
\n1.2.826.0.1.3680043.8.498.28835161805054693497036672217352479293 1
\nName: count, Length: 4405, dtype: int64
\n0

\n
\n

SeriesInstanceUID
\n1.2.826.0.1.3680043.8.498.69955588258737419513349554116268560350 1441
\n1.2.826.0.1.3680043.8.498.91165535256035309178395737877979649687 1331
\n1.2.826.0.1.3680043.8.498.13224525180219586797860545856267800837 1314
\n1.2.826.0.1.3680043.8.498.21982310536273258320808209774087969721 1311
\n1.2.826.0.1.3680043.8.498.10487456545489144263441234750888574208 1291
\n …
\n1.2.826.0.1.3680043.8.498.13001629435974764211403087597568806527 1
\n1.2.826.0.1.3680043.8.498.57295451550670979695930636846746586334 1
\n1.2.826.0.1.3680043.8.498.10035782880104673269567641444954004745 1
\n1.2.826.0.1.3680043.8.498.99804081131933373817667779922320327920 1
\n1.2.826.0.1.3680043.8.498.12731166731428722510842096480704381330 1
\nName: count, Length: 4405, dtype: int64
\n0

\n
\n

SOPInstanceUID
\n1.2.826.0.1.3680043.8.498.99869751254453760418974589018088745528 1
\n1.2.826.0.1.3680043.8.498.10124807242473374136099471315028464450 1
\n1.2.826.0.1.3680043.8.498.10138383895715496920719014209752366343 1
\n1.2.826.0.1.3680043.8.498.10163629202066490350525656863994550563 1
\n1.2.826.0.1.3680043.8.498.10168500191766317056991929548420609601 1
\n ..
\n1.2.826.0.1.3680043.8.498.10676452078924881901296423855445745451 1
\n1.2.826.0.1.3680043.8.498.10539829370105743308434271256984603393 1
\n1.2.826.0.1.3680043.8.498.10517225444888619475163956382223622124 1
\n1.2.826.0.1.3680043.8.498.10486211606858414516699231337500956997 1
\n1.2.826.0.1.3680043.8.498.10402291067741894444758238077775726419 1
\nName: count, Length: 1012263, dtype: int64
\n0

\n
\n

PatientID
\na187f7ca-a4b 1441
\n742ae8a7-46a 1331
\n91da1b43-b68 1314
\nc67b7d42-a40 1311
\nb9d2cf45-355 1291
\n …
\n83cce436-3f8 1
\n92d0f734-a93 1
\n9719ade7-b2f 1
\nd270d272-398 1
\ne707a832-8ad 1
\nName: count, Length: 4405, dtype: int64
\n0

\n
\n

PatientAge_x
\n065Y 75876
\n060Y 71155
\n070Y 68604
\n050Y 59791
\n055Y 57759
\n …
\n081Y 168
\n029Y 107
\n043Y 71
\n089Y 56
\n71Y 54
\nName: count, Length: 123, dtype: int64
\n250902

\n
\n

PatientSex_x
\nF 425066
\nM 231096
\nO 106744
\nName: count, dtype: int64
\n249357

\n
\n

PatientWeight
\n70.000000 14604
\n60.000000 10522
\n65.000000 10427
\n0.000000 8967
\n75.000000 8689
\n …
\n131.543000 30
\n65.770000 27
\n63.049339 26
\n90.718474 26
\n79.378665 25
\nName: count, Length: 546, dtype: int64
\n686701

\n
\n

PatientSize
\n1.600000 13441
\n1.700000 9158
\n1.650000 8487
\n1.753000 6298
\n1.676000 5826
\n …
\n1.905004 95
\n1.530000 42
\n1.867000 34
\n1.499000 34
\n1.574803 2
\nName: count, Length: 118, dtype: int64
\n804172

\n
\n

EthnicGroup
\nNON-HISPANIC 17659
\nHISPANIC 16911
\nU 14541
\nNot Hispanic/Lat 12321
\n4 10670
\nHispanic/Latino 2544
\nUnknown/Informat 1913
\nUNKNOWN 902
\n4.0 714
\n1 675
\nAS 523
\nO 167
\nWHT 158
\nUNK 154
\nName: count, dtype: int64
\n932411

\n
\n

SmokingStatus
\nUNKNOWN 65455
\nName: count, dtype: int64
\n946808

\n
\n

Modality_x
\nCT 737104
\nMR 275159
\nName: count, dtype: int64
\n0

\n
\n

StudyDescription
\nCTA HEAD AND NECK 57142
\nCT HEAD+NECK ANGIOGRAM 55580
\nCT ANGIOGRAM HEAD AND NECK WITH CONTRAST 49225
\nCT ANGIO BRAIN/NECK FOR STROKE (INC 3D POST-PROCESSING AND PERF) 29164
\nCTA HEAD W IV CONT 28601
\n …
\nMri tolgoin fast tulburtei 10
\nMri tolgoin fast 9
\nBrain+ce 5
\nTolgoi mri 4
\nBrain Fast 1
\nName: count, Length: 240, dtype: int64
\n221657

\n
\n

SeriesDescription
\nCTA HEAD & NECK, iDose (3) 50260
\nAneurysm 23784
\nVOL ANGIO 0.625 21430
\nCTA STROKE 20528
\nTOF_3D_multi-slab 19377
\n …
\nCTA 3.0 Sag-MIP.Ref CE 16
\nCor T1 3MM +C 15
\nScout 4
\nMPR AUXILIARY IMAGES 2
\nSurview 1
\nName: count, Length: 673, dtype: int64
\n164282

\n
\n

BodyPartExamined
\nHEAD 342806
\nBRAIN 93343
\nCAROTID 71140
\nCT ANGIO BRAIN A 46008
\nNECK 40804
\n …
\nCERERAL_ANGIO 90
\nINTRACRANIAL 84
\nINTRACRANIAL _AN 78
\nICA_ANGIO 68
\nCEREBRAL_ANGIO_B 31
\nName: count, Length: 72, dtype: int64
\n204146

\n
\n

MRAcquisitionType
\n3D 246772
\n2D 28237
\nName: count, dtype: int64
\n737254

\n
\n

AngioFlag
\nN 123370
\nY 117874
\nName: count, dtype: int64
\n771019

\n
\n

Rows
\n512 865952
\n768 27515
\n384 24899
\n256 24643
\n320 11183
\n …
\n460 1
\n644 1
\n645 1
\n393 1
\n484 1
\nName: count, Length: 82, dtype: int64
\n0

\n
\n

Columns
\n512 862779
\n696 22165
\n256 19295
\n1024 9791
\n576 7293
\n …
\n592 22
\n180 22
\n700 20
\n820 4
\n484 1
\nName: count, Length: 113, dtype: int64
\n0

\n
\n

PixelSpacing
\n['0.488281', '0.488281'] 67168
\n['0.48828125', '0.48828125'] 43021
\n['0.390625', '0.390625'] 36904
\n['0.4297', '0.4297'] 36310
\n['0.3515625', '0.3515625'] 20809
\n …
\n['0.507000', '0.507000'] 1
\n['1.44523566', '1.44523566'] 1
\n['0.53346076', '0.53346076'] 1
\n['0.469104', '0.469104'] 1
\n['0.4707030058', '0.4707030058'] 1
\nName: count, Length: 718, dtype: int64
\n322

\n
\n

SliceThickness
\n1.000000 225072
\n0.625000 197324
\n0.800000 168692
\n0.500000 157516
\n0.600000 36635
\n …
\n250.000000 1
\n0.416016 1
\n0.523438 1
\n2.824218 1
\n400.000000 1
\nName: count, Length: 90, dtype: int64
\n324

\n
\n

SpacingBetweenSlices
\n0.400 152448
\n0.625 111197
\n0.500 105657
\n0.600 33375
\n5.000 27422
\n …
\n6.800 26
\n5.750 26
\n6.650 24
\n3.480 22
\n10.000 4
\nName: count, Length: 158, dtype: int64
\n378370

\n
\n

ImagePositionPatient
\n['-125.000', '-125.000', '30.000'] 29
\n['-125.000', '-125.000', '75.000'] 29
\n['-125.000', '-125.000', '90.000'] 29
\n['-125.000', '-125.000', '80.000'] 29
\n['-125.000', '-125.000', '50.000'] 29
\n ..
\n['-125.775390625', '-284.775390625', '-116.7'] 1
\n['-125.775390625', '-284.775390625', '-86.7'] 1
\n['-125.775390625', '-284.775390625', '-157.7'] 1
\n['-125.775390625', '-284.775390625', '-39.7'] 1
\n['-83.825987640163', '-79.552251907846', '32.460949707916'] 1
\nName: count, Length: 972942, dtype: int64
\n322

\n
\n

ImageOrientationPatient
\n['1', '0', '0', '0', '1', '0'] 422008
\n['1.000000', '0.000000', '0.000000', '0.000000', '1.000000', '0.000000'] 202978
\n['1.00000', '0.00000', '0.00000', '0.00000', '1.00000', '0.00000'] 100489
\n['1.0000000000000', '-0.0000000000000', '0.0000000000000', '-0.0000000000000', '1.0000000000000', '0.0000000000000'] 3406
\n['1', '4.897e-012', '0', '-4.897e-012', '1', '0'] 2390
\n …
\n['0.998483', '-0.0550422', '0.00157649', '0.0550447', '0.998483', '-0.00162843'] 1
\n['0.9996548543674', '-0.0219687717646', '0.0144064293556', '0.0236181093021', '0.9916703962528', '-0.1266175742493'] 1
\n['0.9996548543674', '-0.0219687717646', '0.0144064293556', '0.0236181084898', '0.9916703968281', '-0.1266175698949'] 1
\n['0.9996548541801', '-0.0219687717605', '0.0144064423575', '0.0236181084769', '0.9916703962838', '-0.1266175741603'] 1
\n['0.9996548526570', '-0.0219688410851', '0.0144064423356', '0.0236181085028', '0.9916703973724', '-0.1266175656296'] 1
\nName: count, Length: 7146, dtype: int64
\n322

\n
\n

RepetitionTime
\n21.00 36962
\n22.00 29177
\n24.00 28532
\n25.00 17976
\n23.00 13280
\n …
\n3740.00 18
\n4110.00 18
\n4838.00 18
\n3166.67 15
\n504.00 15
\nName: count, Length: 675, dtype: int64
\n737426

\n
\n

EchoTime
\n7.000 32985
\n3.500 14148
\n3.420 13662
\n2.600 11034
\n3.690 10617
\n …
\n106.888 18
\n104.780 16
\n107.756 16
\n8.448 15
\n98.560 15
\nName: count, Length: 483, dtype: int64
\n737426

\n
\n

FlipAngle
\n20.0 58101
\n18.0 48056
\n25.0 43693
\n15.0 37237
\n8.0 17464
\n …
\n149.0 34
\n83.0 33
\n143.0 32
\n147.0 30
\n136.0 25
\nName: count, Length: 67, dtype: int64
\n737426

\n
\n

MagneticFieldStrength
\n3.000 140546
\n1.500 133146
\n1.160 414
\n1.494 118
\n15000.000 30
\nName: count, dtype: int64
\n738009

\n
\n

Manufacturer
\nGE MEDICAL SYSTEMS 296228
\nSIEMENS 287794
\nPhilips 188968
\nTOSHIBA 125034
\nSiemens Healthineers 81118
\nSiemens 9889
\nCanon Medical Systems 7547
\nPhilips Medical Systems 6456
\nPhilips Healthcare 4091
\nCANON_MEC 3401
\nTOSHIBA_MEC 905
\nSiemens HealthCare GmbH 416
\nHitachi, Ltd. 414
\nIntelerad Medical Systems 2
\nName: count, dtype: int64
\n0

\n
\n

ManufacturerModelName
\niCT 256 115027
\nSOMATOM Force 84840
\nLightSpeed VCT 81292
\nAquilion ONE 59157
\nAquilion PRIME 44548
\n …
\nSIGNA EXCITE 64
\nIntera 52
\nMAGNETOM_ESSENZA 43
\nGENESIS_SIGNA 30
\nInteleViewer 2
\nName: count, Length: 95, dtype: int64
\n0

\n
\n

ScanningSequence
\nGR 219363
\nSE 30299
\n['GR', 'IR'] 20319
\nRM 3374
\n['RM', 'IR'] 1124
\n['SE', 'IR'] 316
\nIR 42
\nName: count, dtype: int64
\n737426

\n
\n

BitsAllocated
\n16 1012263
\nName: count, dtype: int64
\n0

\n
\n

BitsStored
\n16 1004687
\n12 7576
\nName: count, dtype: int64
\n0

\n
\n

PixelRepresentation
\n1 1004685
\n0 7578
\nName: count, dtype: int64
\n0

\n
\n

WindowCenter
\n40 172648
\n['40', '40'] 94997
\n['80', '250'] 77818
\n['60', '60'] 61490
\n50 42141
\n …
\n216.52 1
\n301.05 1
\n250.33 1
\n235.77 1
\n188.1 1
\nName: count, Length: 14094, dtype: int64
\n322

\n
\n

WindowWidth
\n400 99881
\n['400', '400'] 84714
\n450 83446
\n['700', '500'] 77818
\n['360', '360'] 59762
\n …
\n491.74 1
\n432.09 1
\n13080 1
\n12174 1
\n15472 1
\nName: count, Length: 19219, dtype: int64
\n322

\n
\n

RescaleIntercept
\n-1024.0 239113
\n 0.0 144736
\n-8192.0 8271
\n-10240.0 7373
\nName: count, dtype: int64
\n612770

\n
\n

RescaleSlope
\n1.0 392120
\n10.0 7373
\nName: count, dtype: int64
\n612770

\n
\n

NumberOfFrames
\n1.0 781
\n150.0 150
\n25.0 47
\n23.0 45
\n24.0 27
\n26.0 12
\n27.0 10
\n31.0 8
\n22.0 3
\n160.0 3
\n32.0 3
\n30.0 2
\n29.0 2
\n180.0 2
\n33.0 2
\n35.0 1
\n28.0 1
\n165.0 1
\n21.0 1
\n34.0 1
\n170.0 1
\nName: count, dtype: int64
\n1011160

\n
\n

PatientAge_y
\n68 33293
\n65 30064
\n64 28034
\n63 27531
\n62 27358
\n …
\n19 2656
\n18 2598
\n29 2338
\n24 2075
\n22 1874
\nName: count, Length: 72, dtype: int64
\n0

\n
\n

PatientSex_y
\nFemale 671965
\nMale 340298
\nName: count, dtype: int64
\n0

\n
\n

Modality_y
\nCTA 737316
\nMRA 197219
\nMRI T1post 47326
\nMRI T2 30402
\nName: count, dtype: int64
\n0

\n
\n

Left Infraclinoid Internal Carotid Artery
\n0 992853
\n1 19410
\nName: count, dtype: int64
\n0

\n
\n

Right Infraclinoid Internal Carotid Artery
\n0 984188
\n1 28075
\nName: count, dtype: int64
\n0

\n
\n

Left Supraclinoid Internal Carotid Artery
\n0 932705
\n1 79558
\nName: count, dtype: int64
\n0

\n
\n

Right Supraclinoid Internal Carotid Artery
\n0 949258
\n1 63005
\nName: count, dtype: int64
\n0

\n
\n

Left Middle Cerebral Artery
\n0 953095
\n1 59168
\nName: count, dtype: int64
\n0

\n
\n

Right Middle Cerebral Artery
\n0 931520
\n1 80743
\nName: count, dtype: int64
\n0

\n
\n

Anterior Communicating Artery
\n0 911791
\n1 100472
\nName: count, dtype: int64
\n0

\n
\n

Left Anterior Cerebral Artery
\n0 998233
\n1 14030
\nName: count, dtype: int64
\n0

\n
\n

Right Anterior Cerebral Artery
\n0 996858
\n1 15405
\nName: count, dtype: int64
\n0

\n
\n

Left Posterior Communicating Artery
\n0 982884
\n1 29379
\nName: count, dtype: int64
\n0

\n
\n

Right Posterior Communicating Artery
\n0 980764
\n1 31499
\nName: count, dtype: int64
\n0

\n
\n

Basilar Tip
\n0 980775
\n1 31488
\nName: count, dtype: int64
\n0

\n
\n

Other Posterior Circulation
\n0 981191
\n1 31072
\nName: count, dtype: int64
\n0

\n
\n

Aneurysm Present
\n0 531662
\n1 480601
\nName: count, dtype: int64
\n0

\n
\n

I am confused should i use it for training model or preprocessing like will this data always be their like 'Rows',
\n 'Columns',
\n 'PixelSpacing',
\n 'SliceThickness',
\n 'SpacingBetweenSlices',
\n 'ImagePositionPatient',
\n 'ImageOrientationPatient',
\nthese and other can be used to do some preprocessing should i use them, and other stuff like demographic data be used for model training should i use that?? cause I am afraid that these feature may not always be their or be under different name

\n

If anyone has any clarity please help, would really appericite it

", "messages": [ { "id": 3267311, "postDate": "2025-08-10T22:19:49.320Z", "content": "

Its up to you whether or not you want to use header metadata in your model; however, keep in mind that we have limited the available header metadata in the test set (please see this post).

\n

Pretty much all of the allowed header metadata tags in the test set are required for image geometry/intensity etc and do not have any particular relevance to the patient. For me personally, I do not think there are any test set header metadata variables that will be strong (or even weak) predictors of aneurysm presence and location. This is by design, as we want the algorithms to be image focused.

\n

So in short, you can use the limited test-set header metadata in your model if you want, but I don't think it will be very useful.

", "rawMarkdown": "Its up to you whether or not you want to use header metadata in your model; however, keep in mind that we have limited the available header metadata in the test set (please see [this post](https://www.kaggle.com/code/ryanholbrook/rsna-aneurysm-detection-demo-submission)). \n\nPretty much all of the allowed header metadata tags in the test set are required for image geometry/intensity etc and do not have any particular relevance to the patient. For me personally, I do not think there are any test set header metadata variables that will be strong (or even weak) predictors of aneurysm presence and location. This is by design, as we want the algorithms to be image focused.\n\nSo in short, you can use the limited test-set header metadata in your model if you want, but I don't think it will be very useful.", "votes": 1, "replies": [ { "id": 3270114, "postDate": "2025-08-15T18:18:53.640Z", "content": "

make sense thankyou

", "rawMarkdown": "make sense thankyou " } ] }, { "id": 3266635, "postDate": "2025-08-09T13:02:36.313Z", "content": "

I am having really hard time understanding DiCom files i have collected some metadata that looked important, here it is:

\n

StudyInstanceUID
\n1.2.826.0.1.3680043.8.498.26875275827756142632463662271305814995 1441
\n1.2.826.0.1.3680043.8.498.95823759726018881810909243809398453285 1331
\n1.2.826.0.1.3680043.8.498.54090196673781955332780103653722908665 1314
\n1.2.826.0.1.3680043.8.498.96493458432292738336891549465693531362 1311
\n1.2.826.0.1.3680043.8.498.90287698646889729761534522929777327309 1291
\n …
\n1.2.826.0.1.3680043.8.498.10034385894802321175291320093789615030 1
\n1.2.826.0.1.3680043.8.498.95814811312894040378383764209574694874 1
\n1.2.826.0.1.3680043.8.498.11035097333885684808818474949068969433 1
\n1.2.826.0.1.3680043.8.498.11819620448760534150797658408275744970 1
\n1.2.826.0.1.3680043.8.498.28835161805054693497036672217352479293 1
\nName: count, Length: 4405, dtype: int64
\n0

\n
\n

SeriesInstanceUID
\n1.2.826.0.1.3680043.8.498.69955588258737419513349554116268560350 1441
\n1.2.826.0.1.3680043.8.498.91165535256035309178395737877979649687 1331
\n1.2.826.0.1.3680043.8.498.13224525180219586797860545856267800837 1314
\n1.2.826.0.1.3680043.8.498.21982310536273258320808209774087969721 1311
\n1.2.826.0.1.3680043.8.498.10487456545489144263441234750888574208 1291
\n …
\n1.2.826.0.1.3680043.8.498.13001629435974764211403087597568806527 1
\n1.2.826.0.1.3680043.8.498.57295451550670979695930636846746586334 1
\n1.2.826.0.1.3680043.8.498.10035782880104673269567641444954004745 1
\n1.2.826.0.1.3680043.8.498.99804081131933373817667779922320327920 1
\n1.2.826.0.1.3680043.8.498.12731166731428722510842096480704381330 1
\nName: count, Length: 4405, dtype: int64
\n0

\n
\n

SOPInstanceUID
\n1.2.826.0.1.3680043.8.498.99869751254453760418974589018088745528 1
\n1.2.826.0.1.3680043.8.498.10124807242473374136099471315028464450 1
\n1.2.826.0.1.3680043.8.498.10138383895715496920719014209752366343 1
\n1.2.826.0.1.3680043.8.498.10163629202066490350525656863994550563 1
\n1.2.826.0.1.3680043.8.498.10168500191766317056991929548420609601 1
\n ..
\n1.2.826.0.1.3680043.8.498.10676452078924881901296423855445745451 1
\n1.2.826.0.1.3680043.8.498.10539829370105743308434271256984603393 1
\n1.2.826.0.1.3680043.8.498.10517225444888619475163956382223622124 1
\n1.2.826.0.1.3680043.8.498.10486211606858414516699231337500956997 1
\n1.2.826.0.1.3680043.8.498.10402291067741894444758238077775726419 1
\nName: count, Length: 1012263, dtype: int64
\n0

\n
\n

PatientID
\na187f7ca-a4b 1441
\n742ae8a7-46a 1331
\n91da1b43-b68 1314
\nc67b7d42-a40 1311
\nb9d2cf45-355 1291
\n …
\n83cce436-3f8 1
\n92d0f734-a93 1
\n9719ade7-b2f 1
\nd270d272-398 1
\ne707a832-8ad 1
\nName: count, Length: 4405, dtype: int64
\n0

\n
\n

PatientAge_x
\n065Y 75876
\n060Y 71155
\n070Y 68604
\n050Y 59791
\n055Y 57759
\n …
\n081Y 168
\n029Y 107
\n043Y 71
\n089Y 56
\n71Y 54
\nName: count, Length: 123, dtype: int64
\n250902

\n
\n

PatientSex_x
\nF 425066
\nM 231096
\nO 106744
\nName: count, dtype: int64
\n249357

\n
\n

PatientWeight
\n70.000000 14604
\n60.000000 10522
\n65.000000 10427
\n0.000000 8967
\n75.000000 8689
\n …
\n131.543000 30
\n65.770000 27
\n63.049339 26
\n90.718474 26
\n79.378665 25
\nName: count, Length: 546, dtype: int64
\n686701

\n
\n

PatientSize
\n1.600000 13441
\n1.700000 9158
\n1.650000 8487
\n1.753000 6298
\n1.676000 5826
\n …
\n1.905004 95
\n1.530000 42
\n1.867000 34
\n1.499000 34
\n1.574803 2
\nName: count, Length: 118, dtype: int64
\n804172

\n
\n

EthnicGroup
\nNON-HISPANIC 17659
\nHISPANIC 16911
\nU 14541
\nNot Hispanic/Lat 12321
\n4 10670
\nHispanic/Latino 2544
\nUnknown/Informat 1913
\nUNKNOWN 902
\n4.0 714
\n1 675
\nAS 523
\nO 167
\nWHT 158
\nUNK 154
\nName: count, dtype: int64
\n932411

\n
\n

SmokingStatus
\nUNKNOWN 65455
\nName: count, dtype: int64
\n946808

\n
\n

Modality_x
\nCT 737104
\nMR 275159
\nName: count, dtype: int64
\n0

\n
\n

StudyDescription
\nCTA HEAD AND NECK 57142
\nCT HEAD+NECK ANGIOGRAM 55580
\nCT ANGIOGRAM HEAD AND NECK WITH CONTRAST 49225
\nCT ANGIO BRAIN/NECK FOR STROKE (INC 3D POST-PROCESSING AND PERF) 29164
\nCTA HEAD W IV CONT 28601
\n …
\nMri tolgoin fast tulburtei 10
\nMri tolgoin fast 9
\nBrain+ce 5
\nTolgoi mri 4
\nBrain Fast 1
\nName: count, Length: 240, dtype: int64
\n221657

\n
\n

SeriesDescription
\nCTA HEAD & NECK, iDose (3) 50260
\nAneurysm 23784
\nVOL ANGIO 0.625 21430
\nCTA STROKE 20528
\nTOF_3D_multi-slab 19377
\n …
\nCTA 3.0 Sag-MIP.Ref CE 16
\nCor T1 3MM +C 15
\nScout 4
\nMPR AUXILIARY IMAGES 2
\nSurview 1
\nName: count, Length: 673, dtype: int64
\n164282

\n
\n

BodyPartExamined
\nHEAD 342806
\nBRAIN 93343
\nCAROTID 71140
\nCT ANGIO BRAIN A 46008
\nNECK 40804
\n …
\nCERERAL_ANGIO 90
\nINTRACRANIAL 84
\nINTRACRANIAL _AN 78
\nICA_ANGIO 68
\nCEREBRAL_ANGIO_B 31
\nName: count, Length: 72, dtype: int64
\n204146

\n
\n

MRAcquisitionType
\n3D 246772
\n2D 28237
\nName: count, dtype: int64
\n737254

\n
\n

AngioFlag
\nN 123370
\nY 117874
\nName: count, dtype: int64
\n771019

\n
\n

Rows
\n512 865952
\n768 27515
\n384 24899
\n256 24643
\n320 11183
\n …
\n460 1
\n644 1
\n645 1
\n393 1
\n484 1
\nName: count, Length: 82, dtype: int64
\n0

\n
\n

Columns
\n512 862779
\n696 22165
\n256 19295
\n1024 9791
\n576 7293
\n …
\n592 22
\n180 22
\n700 20
\n820 4
\n484 1
\nName: count, Length: 113, dtype: int64
\n0

\n
\n

PixelSpacing
\n['0.488281', '0.488281'] 67168
\n['0.48828125', '0.48828125'] 43021
\n['0.390625', '0.390625'] 36904
\n['0.4297', '0.4297'] 36310
\n['0.3515625', '0.3515625'] 20809
\n …
\n['0.507000', '0.507000'] 1
\n['1.44523566', '1.44523566'] 1
\n['0.53346076', '0.53346076'] 1
\n['0.469104', '0.469104'] 1
\n['0.4707030058', '0.4707030058'] 1
\nName: count, Length: 718, dtype: int64
\n322

\n
\n

SliceThickness
\n1.000000 225072
\n0.625000 197324
\n0.800000 168692
\n0.500000 157516
\n0.600000 36635
\n …
\n250.000000 1
\n0.416016 1
\n0.523438 1
\n2.824218 1
\n400.000000 1
\nName: count, Length: 90, dtype: int64
\n324

\n
\n

SpacingBetweenSlices
\n0.400 152448
\n0.625 111197
\n0.500 105657
\n0.600 33375
\n5.000 27422
\n …
\n6.800 26
\n5.750 26
\n6.650 24
\n3.480 22
\n10.000 4
\nName: count, Length: 158, dtype: int64
\n378370

\n
\n

ImagePositionPatient
\n['-125.000', '-125.000', '30.000'] 29
\n['-125.000', '-125.000', '75.000'] 29
\n['-125.000', '-125.000', '90.000'] 29
\n['-125.000', '-125.000', '80.000'] 29
\n['-125.000', '-125.000', '50.000'] 29
\n ..
\n['-125.775390625', '-284.775390625', '-116.7'] 1
\n['-125.775390625', '-284.775390625', '-86.7'] 1
\n['-125.775390625', '-284.775390625', '-157.7'] 1
\n['-125.775390625', '-284.775390625', '-39.7'] 1
\n['-83.825987640163', '-79.552251907846', '32.460949707916'] 1
\nName: count, Length: 972942, dtype: int64
\n322

\n
\n

ImageOrientationPatient
\n['1', '0', '0', '0', '1', '0'] 422008
\n['1.000000', '0.000000', '0.000000', '0.000000', '1.000000', '0.000000'] 202978
\n['1.00000', '0.00000', '0.00000', '0.00000', '1.00000', '0.00000'] 100489
\n['1.0000000000000', '-0.0000000000000', '0.0000000000000', '-0.0000000000000', '1.0000000000000', '0.0000000000000'] 3406
\n['1', '4.897e-012', '0', '-4.897e-012', '1', '0'] 2390
\n …
\n['0.998483', '-0.0550422', '0.00157649', '0.0550447', '0.998483', '-0.00162843'] 1
\n['0.9996548543674', '-0.0219687717646', '0.0144064293556', '0.0236181093021', '0.9916703962528', '-0.1266175742493'] 1
\n['0.9996548543674', '-0.0219687717646', '0.0144064293556', '0.0236181084898', '0.9916703968281', '-0.1266175698949'] 1
\n['0.9996548541801', '-0.0219687717605', '0.0144064423575', '0.0236181084769', '0.9916703962838', '-0.1266175741603'] 1
\n['0.9996548526570', '-0.0219688410851', '0.0144064423356', '0.0236181085028', '0.9916703973724', '-0.1266175656296'] 1
\nName: count, Length: 7146, dtype: int64
\n322

\n
\n

RepetitionTime
\n21.00 36962
\n22.00 29177
\n24.00 28532
\n25.00 17976
\n23.00 13280
\n …
\n3740.00 18
\n4110.00 18
\n4838.00 18
\n3166.67 15
\n504.00 15
\nName: count, Length: 675, dtype: int64
\n737426

\n
\n

EchoTime
\n7.000 32985
\n3.500 14148
\n3.420 13662
\n2.600 11034
\n3.690 10617
\n …
\n106.888 18
\n104.780 16
\n107.756 16
\n8.448 15
\n98.560 15
\nName: count, Length: 483, dtype: int64
\n737426

\n
\n

FlipAngle
\n20.0 58101
\n18.0 48056
\n25.0 43693
\n15.0 37237
\n8.0 17464
\n …
\n149.0 34
\n83.0 33
\n143.0 32
\n147.0 30
\n136.0 25
\nName: count, Length: 67, dtype: int64
\n737426

\n
\n

MagneticFieldStrength
\n3.000 140546
\n1.500 133146
\n1.160 414
\n1.494 118
\n15000.000 30
\nName: count, dtype: int64
\n738009

\n
\n

Manufacturer
\nGE MEDICAL SYSTEMS 296228
\nSIEMENS 287794
\nPhilips 188968
\nTOSHIBA 125034
\nSiemens Healthineers 81118
\nSiemens 9889
\nCanon Medical Systems 7547
\nPhilips Medical Systems 6456
\nPhilips Healthcare 4091
\nCANON_MEC 3401
\nTOSHIBA_MEC 905
\nSiemens HealthCare GmbH 416
\nHitachi, Ltd. 414
\nIntelerad Medical Systems 2
\nName: count, dtype: int64
\n0

\n
\n

ManufacturerModelName
\niCT 256 115027
\nSOMATOM Force 84840
\nLightSpeed VCT 81292
\nAquilion ONE 59157
\nAquilion PRIME 44548
\n …
\nSIGNA EXCITE 64
\nIntera 52
\nMAGNETOM_ESSENZA 43
\nGENESIS_SIGNA 30
\nInteleViewer 2
\nName: count, Length: 95, dtype: int64
\n0

\n
\n

ScanningSequence
\nGR 219363
\nSE 30299
\n['GR', 'IR'] 20319
\nRM 3374
\n['RM', 'IR'] 1124
\n['SE', 'IR'] 316
\nIR 42
\nName: count, dtype: int64
\n737426

\n
\n

BitsAllocated
\n16 1012263
\nName: count, dtype: int64
\n0

\n
\n

BitsStored
\n16 1004687
\n12 7576
\nName: count, dtype: int64
\n0

\n
\n

PixelRepresentation
\n1 1004685
\n0 7578
\nName: count, dtype: int64
\n0

\n
\n

WindowCenter
\n40 172648
\n['40', '40'] 94997
\n['80', '250'] 77818
\n['60', '60'] 61490
\n50 42141
\n …
\n216.52 1
\n301.05 1
\n250.33 1
\n235.77 1
\n188.1 1
\nName: count, Length: 14094, dtype: int64
\n322

\n
\n

WindowWidth
\n400 99881
\n['400', '400'] 84714
\n450 83446
\n['700', '500'] 77818
\n['360', '360'] 59762
\n …
\n491.74 1
\n432.09 1
\n13080 1
\n12174 1
\n15472 1
\nName: count, Length: 19219, dtype: int64
\n322

\n
\n

RescaleIntercept
\n-1024.0 239113
\n 0.0 144736
\n-8192.0 8271
\n-10240.0 7373
\nName: count, dtype: int64
\n612770

\n
\n

RescaleSlope
\n1.0 392120
\n10.0 7373
\nName: count, dtype: int64
\n612770

\n
\n

NumberOfFrames
\n1.0 781
\n150.0 150
\n25.0 47
\n23.0 45
\n24.0 27
\n26.0 12
\n27.0 10
\n31.0 8
\n22.0 3
\n160.0 3
\n32.0 3
\n30.0 2
\n29.0 2
\n180.0 2
\n33.0 2
\n35.0 1
\n28.0 1
\n165.0 1
\n21.0 1
\n34.0 1
\n170.0 1
\nName: count, dtype: int64
\n1011160

\n
\n

PatientAge_y
\n68 33293
\n65 30064
\n64 28034
\n63 27531
\n62 27358
\n …
\n19 2656
\n18 2598
\n29 2338
\n24 2075
\n22 1874
\nName: count, Length: 72, dtype: int64
\n0

\n
\n

PatientSex_y
\nFemale 671965
\nMale 340298
\nName: count, dtype: int64
\n0

\n
\n

Modality_y
\nCTA 737316
\nMRA 197219
\nMRI T1post 47326
\nMRI T2 30402
\nName: count, dtype: int64
\n0

\n
\n

Left Infraclinoid Internal Carotid Artery
\n0 992853
\n1 19410
\nName: count, dtype: int64
\n0

\n
\n

Right Infraclinoid Internal Carotid Artery
\n0 984188
\n1 28075
\nName: count, dtype: int64
\n0

\n
\n

Left Supraclinoid Internal Carotid Artery
\n0 932705
\n1 79558
\nName: count, dtype: int64
\n0

\n
\n

Right Supraclinoid Internal Carotid Artery
\n0 949258
\n1 63005
\nName: count, dtype: int64
\n0

\n
\n

Left Middle Cerebral Artery
\n0 953095
\n1 59168
\nName: count, dtype: int64
\n0

\n
\n

Right Middle Cerebral Artery
\n0 931520
\n1 80743
\nName: count, dtype: int64
\n0

\n
\n

Anterior Communicating Artery
\n0 911791
\n1 100472
\nName: count, dtype: int64
\n0

\n
\n

Left Anterior Cerebral Artery
\n0 998233
\n1 14030
\nName: count, dtype: int64
\n0

\n
\n

Right Anterior Cerebral Artery
\n0 996858
\n1 15405
\nName: count, dtype: int64
\n0

\n
\n

Left Posterior Communicating Artery
\n0 982884
\n1 29379
\nName: count, dtype: int64
\n0

\n
\n

Right Posterior Communicating Artery
\n0 980764
\n1 31499
\nName: count, dtype: int64
\n0

\n
\n

Basilar Tip
\n0 980775
\n1 31488
\nName: count, dtype: int64
\n0

\n
\n

Other Posterior Circulation
\n0 981191
\n1 31072
\nName: count, dtype: int64
\n0

\n
\n

Aneurysm Present
\n0 531662
\n1 480601
\nName: count, dtype: int64
\n0

\n
\n

I am confused should i use it for training model or preprocessing like will this data always be their like 'Rows',
\n 'Columns',
\n 'PixelSpacing',
\n 'SliceThickness',
\n 'SpacingBetweenSlices',
\n 'ImagePositionPatient',
\n 'ImageOrientationPatient',
\nthese and other can be used to do some preprocessing should i use them, and other stuff like demographic data be used for model training should i use that?? cause I am afraid that these feature may not always be their or be under different name

\n

If anyone has any clarity please help, would really appericite it

", "rawMarkdown": "I am having really hard time understanding DiCom files i have collected some metadata that looked important, here it is:\n\nStudyInstanceUID\n1.2.826.0.1.3680043.8.498.26875275827756142632463662271305814995 1441\n1.2.826.0.1.3680043.8.498.95823759726018881810909243809398453285 1331\n1.2.826.0.1.3680043.8.498.54090196673781955332780103653722908665 1314\n1.2.826.0.1.3680043.8.498.96493458432292738336891549465693531362 1311\n1.2.826.0.1.3680043.8.498.90287698646889729761534522929777327309 1291\n ... \n1.2.826.0.1.3680043.8.498.10034385894802321175291320093789615030 1\n1.2.826.0.1.3680043.8.498.95814811312894040378383764209574694874 1\n1.2.826.0.1.3680043.8.498.11035097333885684808818474949068969433 1\n1.2.826.0.1.3680043.8.498.11819620448760534150797658408275744970 1\n1.2.826.0.1.3680043.8.498.28835161805054693497036672217352479293 1\nName: count, Length: 4405, dtype: int64\n0\n**************************************************\nSeriesInstanceUID\n1.2.826.0.1.3680043.8.498.69955588258737419513349554116268560350 1441\n1.2.826.0.1.3680043.8.498.91165535256035309178395737877979649687 1331\n1.2.826.0.1.3680043.8.498.13224525180219586797860545856267800837 1314\n1.2.826.0.1.3680043.8.498.21982310536273258320808209774087969721 1311\n1.2.826.0.1.3680043.8.498.10487456545489144263441234750888574208 1291\n ... \n1.2.826.0.1.3680043.8.498.13001629435974764211403087597568806527 1\n1.2.826.0.1.3680043.8.498.57295451550670979695930636846746586334 1\n1.2.826.0.1.3680043.8.498.10035782880104673269567641444954004745 1\n1.2.826.0.1.3680043.8.498.99804081131933373817667779922320327920 1\n1.2.826.0.1.3680043.8.498.12731166731428722510842096480704381330 1\nName: count, Length: 4405, dtype: int64\n0\n**************************************************\nSOPInstanceUID\n1.2.826.0.1.3680043.8.498.99869751254453760418974589018088745528 1\n1.2.826.0.1.3680043.8.498.10124807242473374136099471315028464450 1\n1.2.826.0.1.3680043.8.498.10138383895715496920719014209752366343 1\n1.2.826.0.1.3680043.8.498.10163629202066490350525656863994550563 1\n1.2.826.0.1.3680043.8.498.10168500191766317056991929548420609601 1\n ..\n1.2.826.0.1.3680043.8.498.10676452078924881901296423855445745451 1\n1.2.826.0.1.3680043.8.498.10539829370105743308434271256984603393 1\n1.2.826.0.1.3680043.8.498.10517225444888619475163956382223622124 1\n1.2.826.0.1.3680043.8.498.10486211606858414516699231337500956997 1\n1.2.826.0.1.3680043.8.498.10402291067741894444758238077775726419 1\nName: count, Length: 1012263, dtype: int64\n0\n**************************************************\nPatientID\na187f7ca-a4b 1441\n742ae8a7-46a 1331\n91da1b43-b68 1314\nc67b7d42-a40 1311\nb9d2cf45-355 1291\n ... \n83cce436-3f8 1\n92d0f734-a93 1\n9719ade7-b2f 1\nd270d272-398 1\ne707a832-8ad 1\nName: count, Length: 4405, dtype: int64\n0\n**************************************************\nPatientAge_x\n065Y 75876\n060Y 71155\n070Y 68604\n050Y 59791\n055Y 57759\n ... \n081Y 168\n029Y 107\n043Y 71\n089Y 56\n71Y 54\nName: count, Length: 123, dtype: int64\n250902\n**************************************************\nPatientSex_x\nF 425066\nM 231096\nO 106744\nName: count, dtype: int64\n249357\n**************************************************\nPatientWeight\n70.000000 14604\n60.000000 10522\n65.000000 10427\n0.000000 8967\n75.000000 8689\n ... \n131.543000 30\n65.770000 27\n63.049339 26\n90.718474 26\n79.378665 25\nName: count, Length: 546, dtype: int64\n686701\n**************************************************\nPatientSize\n1.600000 13441\n1.700000 9158\n1.650000 8487\n1.753000 6298\n1.676000 5826\n ... \n1.905004 95\n1.530000 42\n1.867000 34\n1.499000 34\n1.574803 2\nName: count, Length: 118, dtype: int64\n804172\n**************************************************\nEthnicGroup\nNON-HISPANIC 17659\nHISPANIC 16911\nU 14541\nNot Hispanic/Lat 12321\n4 10670\nHispanic/Latino 2544\nUnknown/Informat 1913\nUNKNOWN 902\n4.0 714\n1 675\nAS 523\nO 167\nWHT 158\nUNK 154\nName: count, dtype: int64\n932411\n**************************************************\nSmokingStatus\nUNKNOWN 65455\nName: count, dtype: int64\n946808\n**************************************************\nModality_x\nCT 737104\nMR 275159\nName: count, dtype: int64\n0\n**************************************************\nStudyDescription\nCTA HEAD AND NECK 57142\nCT HEAD+NECK ANGIOGRAM 55580\nCT ANGIOGRAM HEAD AND NECK WITH CONTRAST 49225\nCT ANGIO BRAIN/NECK FOR STROKE (INC 3D POST-PROCESSING AND PERF) 29164\nCTA HEAD W IV CONT 28601\n ... \nMri tolgoin fast tulburtei 10\nMri tolgoin fast 9\nBrain+ce 5\nTolgoi mri 4\nBrain Fast 1\nName: count, Length: 240, dtype: int64\n221657\n**************************************************\nSeriesDescription\nCTA HEAD & NECK, iDose (3) 50260\nAneurysm 23784\nVOL ANGIO 0.625 21430\nCTA STROKE 20528\nTOF_3D_multi-slab 19377\n ... \nCTA 3.0 Sag-MIP.Ref CE 16\nCor T1 3MM +C 15\nScout 4\nMPR AUXILIARY IMAGES 2\nSurview 1\nName: count, Length: 673, dtype: int64\n164282\n**************************************************\nBodyPartExamined\nHEAD 342806\nBRAIN 93343\nCAROTID 71140\nCT ANGIO BRAIN A 46008\nNECK 40804\n ... \nCERERAL_ANGIO 90\nINTRACRANIAL 84\nINTRACRANIAL _AN 78\nICA_ANGIO 68\nCEREBRAL_ANGIO_B 31\nName: count, Length: 72, dtype: int64\n204146\n**************************************************\nMRAcquisitionType\n3D 246772\n2D 28237\nName: count, dtype: int64\n737254\n**************************************************\nAngioFlag\nN 123370\nY 117874\nName: count, dtype: int64\n771019\n**************************************************\nRows\n512 865952\n768 27515\n384 24899\n256 24643\n320 11183\n ... \n460 1\n644 1\n645 1\n393 1\n484 1\nName: count, Length: 82, dtype: int64\n0\n**************************************************\nColumns\n512 862779\n696 22165\n256 19295\n1024 9791\n576 7293\n ... \n592 22\n180 22\n700 20\n820 4\n484 1\nName: count, Length: 113, dtype: int64\n0\n**************************************************\nPixelSpacing\n['0.488281', '0.488281'] 67168\n['0.48828125', '0.48828125'] 43021\n['0.390625', '0.390625'] 36904\n['0.4297', '0.4297'] 36310\n['0.3515625', '0.3515625'] 20809\n ... \n['0.507000', '0.507000'] 1\n['1.44523566', '1.44523566'] 1\n['0.53346076', '0.53346076'] 1\n['0.469104', '0.469104'] 1\n['0.4707030058', '0.4707030058'] 1\nName: count, Length: 718, dtype: int64\n322\n**************************************************\nSliceThickness\n1.000000 225072\n0.625000 197324\n0.800000 168692\n0.500000 157516\n0.600000 36635\n ... \n250.000000 1\n0.416016 1\n0.523438 1\n2.824218 1\n400.000000 1\nName: count, Length: 90, dtype: int64\n324\n**************************************************\nSpacingBetweenSlices\n0.400 152448\n0.625 111197\n0.500 105657\n0.600 33375\n5.000 27422\n ... \n6.800 26\n5.750 26\n6.650 24\n3.480 22\n10.000 4\nName: count, Length: 158, dtype: int64\n378370\n**************************************************\nImagePositionPatient\n['-125.000', '-125.000', '30.000'] 29\n['-125.000', '-125.000', '75.000'] 29\n['-125.000', '-125.000', '90.000'] 29\n['-125.000', '-125.000', '80.000'] 29\n['-125.000', '-125.000', '50.000'] 29\n ..\n['-125.775390625', '-284.775390625', '-116.7'] 1\n['-125.775390625', '-284.775390625', '-86.7'] 1\n['-125.775390625', '-284.775390625', '-157.7'] 1\n['-125.775390625', '-284.775390625', '-39.7'] 1\n['-83.825987640163', '-79.552251907846', '32.460949707916'] 1\nName: count, Length: 972942, dtype: int64\n322\n**************************************************\nImageOrientationPatient\n['1', '0', '0', '0', '1', '0'] 422008\n['1.000000', '0.000000', '0.000000', '0.000000', '1.000000', '0.000000'] 202978\n['1.00000', '0.00000', '0.00000', '0.00000', '1.00000', '0.00000'] 100489\n['1.0000000000000', '-0.0000000000000', '0.0000000000000', '-0.0000000000000', '1.0000000000000', '0.0000000000000'] 3406\n['1', '4.897e-012', '0', '-4.897e-012', '1', '0'] 2390\n ... \n['0.998483', '-0.0550422', '0.00157649', '0.0550447', '0.998483', '-0.00162843'] 1\n['0.9996548543674', '-0.0219687717646', '0.0144064293556', '0.0236181093021', '0.9916703962528', '-0.1266175742493'] 1\n['0.9996548543674', '-0.0219687717646', '0.0144064293556', '0.0236181084898', '0.9916703968281', '-0.1266175698949'] 1\n['0.9996548541801', '-0.0219687717605', '0.0144064423575', '0.0236181084769', '0.9916703962838', '-0.1266175741603'] 1\n['0.9996548526570', '-0.0219688410851', '0.0144064423356', '0.0236181085028', '0.9916703973724', '-0.1266175656296'] 1\nName: count, Length: 7146, dtype: int64\n322\n**************************************************\nRepetitionTime\n21.00 36962\n22.00 29177\n24.00 28532\n25.00 17976\n23.00 13280\n ... \n3740.00 18\n4110.00 18\n4838.00 18\n3166.67 15\n504.00 15\nName: count, Length: 675, dtype: int64\n737426\n**************************************************\nEchoTime\n7.000 32985\n3.500 14148\n3.420 13662\n2.600 11034\n3.690 10617\n ... \n106.888 18\n104.780 16\n107.756 16\n8.448 15\n98.560 15\nName: count, Length: 483, dtype: int64\n737426\n**************************************************\nFlipAngle\n20.0 58101\n18.0 48056\n25.0 43693\n15.0 37237\n8.0 17464\n ... \n149.0 34\n83.0 33\n143.0 32\n147.0 30\n136.0 25\nName: count, Length: 67, dtype: int64\n737426\n**************************************************\nMagneticFieldStrength\n3.000 140546\n1.500 133146\n1.160 414\n1.494 118\n15000.000 30\nName: count, dtype: int64\n738009\n**************************************************\nManufacturer\nGE MEDICAL SYSTEMS 296228\nSIEMENS 287794\nPhilips 188968\nTOSHIBA 125034\nSiemens Healthineers 81118\nSiemens 9889\nCanon Medical Systems 7547\nPhilips Medical Systems 6456\nPhilips Healthcare 4091\nCANON_MEC 3401\nTOSHIBA_MEC 905\nSiemens HealthCare GmbH 416\nHitachi, Ltd. 414\nIntelerad Medical Systems 2\nName: count, dtype: int64\n0\n**************************************************\nManufacturerModelName\niCT 256 115027\nSOMATOM Force 84840\nLightSpeed VCT 81292\nAquilion ONE 59157\nAquilion PRIME 44548\n ... \nSIGNA EXCITE 64\nIntera 52\nMAGNETOM_ESSENZA 43\nGENESIS_SIGNA 30\nInteleViewer 2\nName: count, Length: 95, dtype: int64\n0\n**************************************************\nScanningSequence\nGR 219363\nSE 30299\n['GR', 'IR'] 20319\nRM 3374\n['RM', 'IR'] 1124\n['SE', 'IR'] 316\nIR 42\nName: count, dtype: int64\n737426\n**************************************************\nBitsAllocated\n16 1012263\nName: count, dtype: int64\n0\n**************************************************\nBitsStored\n16 1004687\n12 7576\nName: count, dtype: int64\n0\n**************************************************\nPixelRepresentation\n1 1004685\n0 7578\nName: count, dtype: int64\n0\n**************************************************\nWindowCenter\n40 172648\n['40', '40'] 94997\n['80', '250'] 77818\n['60', '60'] 61490\n50 42141\n ... \n216.52 1\n301.05 1\n250.33 1\n235.77 1\n188.1 1\nName: count, Length: 14094, dtype: int64\n322\n**************************************************\nWindowWidth\n400 99881\n['400', '400'] 84714\n450 83446\n['700', '500'] 77818\n['360', '360'] 59762\n ... \n491.74 1\n432.09 1\n13080 1\n12174 1\n15472 1\nName: count, Length: 19219, dtype: int64\n322\n**************************************************\nRescaleIntercept\n-1024.0 239113\n 0.0 144736\n-8192.0 8271\n-10240.0 7373\nName: count, dtype: int64\n612770\n**************************************************\nRescaleSlope\n1.0 392120\n10.0 7373\nName: count, dtype: int64\n612770\n**************************************************\nNumberOfFrames\n1.0 781\n150.0 150\n25.0 47\n23.0 45\n24.0 27\n26.0 12\n27.0 10\n31.0 8\n22.0 3\n160.0 3\n32.0 3\n30.0 2\n29.0 2\n180.0 2\n33.0 2\n35.0 1\n28.0 1\n165.0 1\n21.0 1\n34.0 1\n170.0 1\nName: count, dtype: int64\n1011160\n**************************************************\nPatientAge_y\n68 33293\n65 30064\n64 28034\n63 27531\n62 27358\n ... \n19 2656\n18 2598\n29 2338\n24 2075\n22 1874\nName: count, Length: 72, dtype: int64\n0\n**************************************************\nPatientSex_y\nFemale 671965\nMale 340298\nName: count, dtype: int64\n0\n**************************************************\nModality_y\nCTA 737316\nMRA 197219\nMRI T1post 47326\nMRI T2 30402\nName: count, dtype: int64\n0\n**************************************************\nLeft Infraclinoid Internal Carotid Artery\n0 992853\n1 19410\nName: count, dtype: int64\n0\n**************************************************\nRight Infraclinoid Internal Carotid Artery\n0 984188\n1 28075\nName: count, dtype: int64\n0\n**************************************************\nLeft Supraclinoid Internal Carotid Artery\n0 932705\n1 79558\nName: count, dtype: int64\n0\n**************************************************\nRight Supraclinoid Internal Carotid Artery\n0 949258\n1 63005\nName: count, dtype: int64\n0\n**************************************************\nLeft Middle Cerebral Artery\n0 953095\n1 59168\nName: count, dtype: int64\n0\n**************************************************\nRight Middle Cerebral Artery\n0 931520\n1 80743\nName: count, dtype: int64\n0\n**************************************************\nAnterior Communicating Artery\n0 911791\n1 100472\nName: count, dtype: int64\n0\n**************************************************\nLeft Anterior Cerebral Artery\n0 998233\n1 14030\nName: count, dtype: int64\n0\n**************************************************\nRight Anterior Cerebral Artery\n0 996858\n1 15405\nName: count, dtype: int64\n0\n**************************************************\nLeft Posterior Communicating Artery\n0 982884\n1 29379\nName: count, dtype: int64\n0\n**************************************************\nRight Posterior Communicating Artery\n0 980764\n1 31499\nName: count, dtype: int64\n0\n**************************************************\nBasilar Tip\n0 980775\n1 31488\nName: count, dtype: int64\n0\n**************************************************\nOther Posterior Circulation\n0 981191\n1 31072\nName: count, dtype: int64\n0\n**************************************************\nAneurysm Present\n0 531662\n1 480601\nName: count, dtype: int64\n0\n**************************************************\n\n\nI am confused should i use it for training model or preprocessing like will this data always be their like 'Rows',\n 'Columns',\n 'PixelSpacing',\n 'SliceThickness',\n 'SpacingBetweenSlices',\n 'ImagePositionPatient',\n 'ImageOrientationPatient',\nthese and other can be used to do some preprocessing should i use them, and other stuff like demographic data be used for model training should i use that?? cause I am afraid that these feature may not always be their or be under different name\n\nIf anyone has any clarity please help, would really appericite it \n", "votes": -2 } ], "comments": [ { "id": 3267311, "author_name": "Evan Calabrese", "author_url": "", "post_date": "2025-08-10T22:19:49.320000", "content": "

Its up to you whether or not you want to use header metadata in your model; however, keep in mind that we have limited the available header metadata in the test set (please see this post).

\n

Pretty much all of the allowed header metadata tags in the test set are required for image geometry/intensity etc and do not have any particular relevance to the patient. For me personally, I do not think there are any test set header metadata variables that will be strong (or even weak) predictors of aneurysm presence and location. This is by design, as we want the algorithms to be image focused.

\n

So in short, you can use the limited test-set header metadata in your model if you want, but I don't think it will be very useful.

", "votes": 1, "replies": [ { "id": 3270114, "author_name": "Bhavesh Solanki", "author_url": "", "post_date": "2025-08-15T18:18:53.640000", "content": "

make sense thankyou

", "votes": 0, "replies": [] } ] } ], "raw_markdown_by_id": { "3267311": "Its up to you whether or not you want to use header metadata in your model; however, keep in mind that we have limited the available header metadata in the test set (please see [this post](https://www.kaggle.com/code/ryanholbrook/rsna-aneurysm-detection-demo-submission)). \n\nPretty much all of the allowed header metadata tags in the test set are required for image geometry/intensity etc and do not have any particular relevance to the patient. For me personally, I do not think there are any test set header metadata variables that will be strong (or even weak) predictors of aneurysm presence and location. This is by design, as we want the algorithms to be image focused.\n\nSo in short, you can use the limited test-set header metadata in your model if you want, but I don't think it will be very useful.", "3266635": "I am having really hard time understanding DiCom files i have collected some metadata that looked important, here it is:\n\nStudyInstanceUID\n1.2.826.0.1.3680043.8.498.26875275827756142632463662271305814995 1441\n1.2.826.0.1.3680043.8.498.95823759726018881810909243809398453285 1331\n1.2.826.0.1.3680043.8.498.54090196673781955332780103653722908665 1314\n1.2.826.0.1.3680043.8.498.96493458432292738336891549465693531362 1311\n1.2.826.0.1.3680043.8.498.90287698646889729761534522929777327309 1291\n ... \n1.2.826.0.1.3680043.8.498.10034385894802321175291320093789615030 1\n1.2.826.0.1.3680043.8.498.95814811312894040378383764209574694874 1\n1.2.826.0.1.3680043.8.498.11035097333885684808818474949068969433 1\n1.2.826.0.1.3680043.8.498.11819620448760534150797658408275744970 1\n1.2.826.0.1.3680043.8.498.28835161805054693497036672217352479293 1\nName: count, Length: 4405, dtype: int64\n0\n**************************************************\nSeriesInstanceUID\n1.2.826.0.1.3680043.8.498.69955588258737419513349554116268560350 1441\n1.2.826.0.1.3680043.8.498.91165535256035309178395737877979649687 1331\n1.2.826.0.1.3680043.8.498.13224525180219586797860545856267800837 1314\n1.2.826.0.1.3680043.8.498.21982310536273258320808209774087969721 1311\n1.2.826.0.1.3680043.8.498.10487456545489144263441234750888574208 1291\n ... \n1.2.826.0.1.3680043.8.498.13001629435974764211403087597568806527 1\n1.2.826.0.1.3680043.8.498.57295451550670979695930636846746586334 1\n1.2.826.0.1.3680043.8.498.10035782880104673269567641444954004745 1\n1.2.826.0.1.3680043.8.498.99804081131933373817667779922320327920 1\n1.2.826.0.1.3680043.8.498.12731166731428722510842096480704381330 1\nName: count, Length: 4405, dtype: int64\n0\n**************************************************\nSOPInstanceUID\n1.2.826.0.1.3680043.8.498.99869751254453760418974589018088745528 1\n1.2.826.0.1.3680043.8.498.10124807242473374136099471315028464450 1\n1.2.826.0.1.3680043.8.498.10138383895715496920719014209752366343 1\n1.2.826.0.1.3680043.8.498.10163629202066490350525656863994550563 1\n1.2.826.0.1.3680043.8.498.10168500191766317056991929548420609601 1\n ..\n1.2.826.0.1.3680043.8.498.10676452078924881901296423855445745451 1\n1.2.826.0.1.3680043.8.498.10539829370105743308434271256984603393 1\n1.2.826.0.1.3680043.8.498.10517225444888619475163956382223622124 1\n1.2.826.0.1.3680043.8.498.10486211606858414516699231337500956997 1\n1.2.826.0.1.3680043.8.498.10402291067741894444758238077775726419 1\nName: count, Length: 1012263, dtype: int64\n0\n**************************************************\nPatientID\na187f7ca-a4b 1441\n742ae8a7-46a 1331\n91da1b43-b68 1314\nc67b7d42-a40 1311\nb9d2cf45-355 1291\n ... \n83cce436-3f8 1\n92d0f734-a93 1\n9719ade7-b2f 1\nd270d272-398 1\ne707a832-8ad 1\nName: count, Length: 4405, dtype: int64\n0\n**************************************************\nPatientAge_x\n065Y 75876\n060Y 71155\n070Y 68604\n050Y 59791\n055Y 57759\n ... \n081Y 168\n029Y 107\n043Y 71\n089Y 56\n71Y 54\nName: count, Length: 123, dtype: int64\n250902\n**************************************************\nPatientSex_x\nF 425066\nM 231096\nO 106744\nName: count, dtype: int64\n249357\n**************************************************\nPatientWeight\n70.000000 14604\n60.000000 10522\n65.000000 10427\n0.000000 8967\n75.000000 8689\n ... \n131.543000 30\n65.770000 27\n63.049339 26\n90.718474 26\n79.378665 25\nName: count, Length: 546, dtype: int64\n686701\n**************************************************\nPatientSize\n1.600000 13441\n1.700000 9158\n1.650000 8487\n1.753000 6298\n1.676000 5826\n ... \n1.905004 95\n1.530000 42\n1.867000 34\n1.499000 34\n1.574803 2\nName: count, Length: 118, dtype: int64\n804172\n**************************************************\nEthnicGroup\nNON-HISPANIC 17659\nHISPANIC 16911\nU 14541\nNot Hispanic/Lat 12321\n4 10670\nHispanic/Latino 2544\nUnknown/Informat 1913\nUNKNOWN 902\n4.0 714\n1 675\nAS 523\nO 167\nWHT 158\nUNK 154\nName: count, dtype: int64\n932411\n**************************************************\nSmokingStatus\nUNKNOWN 65455\nName: count, dtype: int64\n946808\n**************************************************\nModality_x\nCT 737104\nMR 275159\nName: count, dtype: int64\n0\n**************************************************\nStudyDescription\nCTA HEAD AND NECK 57142\nCT HEAD+NECK ANGIOGRAM 55580\nCT ANGIOGRAM HEAD AND NECK WITH CONTRAST 49225\nCT ANGIO BRAIN/NECK FOR STROKE (INC 3D POST-PROCESSING AND PERF) 29164\nCTA HEAD W IV CONT 28601\n ... \nMri tolgoin fast tulburtei 10\nMri tolgoin fast 9\nBrain+ce 5\nTolgoi mri 4\nBrain Fast 1\nName: count, Length: 240, dtype: int64\n221657\n**************************************************\nSeriesDescription\nCTA HEAD & NECK, iDose (3) 50260\nAneurysm 23784\nVOL ANGIO 0.625 21430\nCTA STROKE 20528\nTOF_3D_multi-slab 19377\n ... \nCTA 3.0 Sag-MIP.Ref CE 16\nCor T1 3MM +C 15\nScout 4\nMPR AUXILIARY IMAGES 2\nSurview 1\nName: count, Length: 673, dtype: int64\n164282\n**************************************************\nBodyPartExamined\nHEAD 342806\nBRAIN 93343\nCAROTID 71140\nCT ANGIO BRAIN A 46008\nNECK 40804\n ... \nCERERAL_ANGIO 90\nINTRACRANIAL 84\nINTRACRANIAL _AN 78\nICA_ANGIO 68\nCEREBRAL_ANGIO_B 31\nName: count, Length: 72, dtype: int64\n204146\n**************************************************\nMRAcquisitionType\n3D 246772\n2D 28237\nName: count, dtype: int64\n737254\n**************************************************\nAngioFlag\nN 123370\nY 117874\nName: count, dtype: int64\n771019\n**************************************************\nRows\n512 865952\n768 27515\n384 24899\n256 24643\n320 11183\n ... \n460 1\n644 1\n645 1\n393 1\n484 1\nName: count, Length: 82, dtype: int64\n0\n**************************************************\nColumns\n512 862779\n696 22165\n256 19295\n1024 9791\n576 7293\n ... \n592 22\n180 22\n700 20\n820 4\n484 1\nName: count, Length: 113, dtype: int64\n0\n**************************************************\nPixelSpacing\n['0.488281', '0.488281'] 67168\n['0.48828125', '0.48828125'] 43021\n['0.390625', '0.390625'] 36904\n['0.4297', '0.4297'] 36310\n['0.3515625', '0.3515625'] 20809\n ... \n['0.507000', '0.507000'] 1\n['1.44523566', '1.44523566'] 1\n['0.53346076', '0.53346076'] 1\n['0.469104', '0.469104'] 1\n['0.4707030058', '0.4707030058'] 1\nName: count, Length: 718, dtype: int64\n322\n**************************************************\nSliceThickness\n1.000000 225072\n0.625000 197324\n0.800000 168692\n0.500000 157516\n0.600000 36635\n ... \n250.000000 1\n0.416016 1\n0.523438 1\n2.824218 1\n400.000000 1\nName: count, Length: 90, dtype: int64\n324\n**************************************************\nSpacingBetweenSlices\n0.400 152448\n0.625 111197\n0.500 105657\n0.600 33375\n5.000 27422\n ... \n6.800 26\n5.750 26\n6.650 24\n3.480 22\n10.000 4\nName: count, Length: 158, dtype: int64\n378370\n**************************************************\nImagePositionPatient\n['-125.000', '-125.000', '30.000'] 29\n['-125.000', '-125.000', '75.000'] 29\n['-125.000', '-125.000', '90.000'] 29\n['-125.000', '-125.000', '80.000'] 29\n['-125.000', '-125.000', '50.000'] 29\n ..\n['-125.775390625', '-284.775390625', '-116.7'] 1\n['-125.775390625', '-284.775390625', '-86.7'] 1\n['-125.775390625', '-284.775390625', '-157.7'] 1\n['-125.775390625', '-284.775390625', '-39.7'] 1\n['-83.825987640163', '-79.552251907846', '32.460949707916'] 1\nName: count, Length: 972942, dtype: int64\n322\n**************************************************\nImageOrientationPatient\n['1', '0', '0', '0', '1', '0'] 422008\n['1.000000', '0.000000', '0.000000', '0.000000', '1.000000', '0.000000'] 202978\n['1.00000', '0.00000', '0.00000', '0.00000', '1.00000', '0.00000'] 100489\n['1.0000000000000', '-0.0000000000000', '0.0000000000000', '-0.0000000000000', '1.0000000000000', '0.0000000000000'] 3406\n['1', '4.897e-012', '0', '-4.897e-012', '1', '0'] 2390\n ... \n['0.998483', '-0.0550422', '0.00157649', '0.0550447', '0.998483', '-0.00162843'] 1\n['0.9996548543674', '-0.0219687717646', '0.0144064293556', '0.0236181093021', '0.9916703962528', '-0.1266175742493'] 1\n['0.9996548543674', '-0.0219687717646', '0.0144064293556', '0.0236181084898', '0.9916703968281', '-0.1266175698949'] 1\n['0.9996548541801', '-0.0219687717605', '0.0144064423575', '0.0236181084769', '0.9916703962838', '-0.1266175741603'] 1\n['0.9996548526570', '-0.0219688410851', '0.0144064423356', '0.0236181085028', '0.9916703973724', '-0.1266175656296'] 1\nName: count, Length: 7146, dtype: int64\n322\n**************************************************\nRepetitionTime\n21.00 36962\n22.00 29177\n24.00 28532\n25.00 17976\n23.00 13280\n ... \n3740.00 18\n4110.00 18\n4838.00 18\n3166.67 15\n504.00 15\nName: count, Length: 675, dtype: int64\n737426\n**************************************************\nEchoTime\n7.000 32985\n3.500 14148\n3.420 13662\n2.600 11034\n3.690 10617\n ... \n106.888 18\n104.780 16\n107.756 16\n8.448 15\n98.560 15\nName: count, Length: 483, dtype: int64\n737426\n**************************************************\nFlipAngle\n20.0 58101\n18.0 48056\n25.0 43693\n15.0 37237\n8.0 17464\n ... \n149.0 34\n83.0 33\n143.0 32\n147.0 30\n136.0 25\nName: count, Length: 67, dtype: int64\n737426\n**************************************************\nMagneticFieldStrength\n3.000 140546\n1.500 133146\n1.160 414\n1.494 118\n15000.000 30\nName: count, dtype: int64\n738009\n**************************************************\nManufacturer\nGE MEDICAL SYSTEMS 296228\nSIEMENS 287794\nPhilips 188968\nTOSHIBA 125034\nSiemens Healthineers 81118\nSiemens 9889\nCanon Medical Systems 7547\nPhilips Medical Systems 6456\nPhilips Healthcare 4091\nCANON_MEC 3401\nTOSHIBA_MEC 905\nSiemens HealthCare GmbH 416\nHitachi, Ltd. 414\nIntelerad Medical Systems 2\nName: count, dtype: int64\n0\n**************************************************\nManufacturerModelName\niCT 256 115027\nSOMATOM Force 84840\nLightSpeed VCT 81292\nAquilion ONE 59157\nAquilion PRIME 44548\n ... \nSIGNA EXCITE 64\nIntera 52\nMAGNETOM_ESSENZA 43\nGENESIS_SIGNA 30\nInteleViewer 2\nName: count, Length: 95, dtype: int64\n0\n**************************************************\nScanningSequence\nGR 219363\nSE 30299\n['GR', 'IR'] 20319\nRM 3374\n['RM', 'IR'] 1124\n['SE', 'IR'] 316\nIR 42\nName: count, dtype: int64\n737426\n**************************************************\nBitsAllocated\n16 1012263\nName: count, dtype: int64\n0\n**************************************************\nBitsStored\n16 1004687\n12 7576\nName: count, dtype: int64\n0\n**************************************************\nPixelRepresentation\n1 1004685\n0 7578\nName: count, dtype: int64\n0\n**************************************************\nWindowCenter\n40 172648\n['40', '40'] 94997\n['80', '250'] 77818\n['60', '60'] 61490\n50 42141\n ... \n216.52 1\n301.05 1\n250.33 1\n235.77 1\n188.1 1\nName: count, Length: 14094, dtype: int64\n322\n**************************************************\nWindowWidth\n400 99881\n['400', '400'] 84714\n450 83446\n['700', '500'] 77818\n['360', '360'] 59762\n ... \n491.74 1\n432.09 1\n13080 1\n12174 1\n15472 1\nName: count, Length: 19219, dtype: int64\n322\n**************************************************\nRescaleIntercept\n-1024.0 239113\n 0.0 144736\n-8192.0 8271\n-10240.0 7373\nName: count, dtype: int64\n612770\n**************************************************\nRescaleSlope\n1.0 392120\n10.0 7373\nName: count, dtype: int64\n612770\n**************************************************\nNumberOfFrames\n1.0 781\n150.0 150\n25.0 47\n23.0 45\n24.0 27\n26.0 12\n27.0 10\n31.0 8\n22.0 3\n160.0 3\n32.0 3\n30.0 2\n29.0 2\n180.0 2\n33.0 2\n35.0 1\n28.0 1\n165.0 1\n21.0 1\n34.0 1\n170.0 1\nName: count, dtype: int64\n1011160\n**************************************************\nPatientAge_y\n68 33293\n65 30064\n64 28034\n63 27531\n62 27358\n ... \n19 2656\n18 2598\n29 2338\n24 2075\n22 1874\nName: count, Length: 72, dtype: int64\n0\n**************************************************\nPatientSex_y\nFemale 671965\nMale 340298\nName: count, dtype: int64\n0\n**************************************************\nModality_y\nCTA 737316\nMRA 197219\nMRI T1post 47326\nMRI T2 30402\nName: count, dtype: int64\n0\n**************************************************\nLeft Infraclinoid Internal Carotid Artery\n0 992853\n1 19410\nName: count, dtype: int64\n0\n**************************************************\nRight Infraclinoid Internal Carotid Artery\n0 984188\n1 28075\nName: count, dtype: int64\n0\n**************************************************\nLeft Supraclinoid Internal Carotid Artery\n0 932705\n1 79558\nName: count, dtype: int64\n0\n**************************************************\nRight Supraclinoid Internal Carotid Artery\n0 949258\n1 63005\nName: count, dtype: int64\n0\n**************************************************\nLeft Middle Cerebral Artery\n0 953095\n1 59168\nName: count, dtype: int64\n0\n**************************************************\nRight Middle Cerebral Artery\n0 931520\n1 80743\nName: count, dtype: int64\n0\n**************************************************\nAnterior Communicating Artery\n0 911791\n1 100472\nName: count, dtype: int64\n0\n**************************************************\nLeft Anterior Cerebral Artery\n0 998233\n1 14030\nName: count, dtype: int64\n0\n**************************************************\nRight Anterior Cerebral Artery\n0 996858\n1 15405\nName: count, dtype: int64\n0\n**************************************************\nLeft Posterior Communicating Artery\n0 982884\n1 29379\nName: count, dtype: int64\n0\n**************************************************\nRight Posterior Communicating Artery\n0 980764\n1 31499\nName: count, dtype: int64\n0\n**************************************************\nBasilar Tip\n0 980775\n1 31488\nName: count, dtype: int64\n0\n**************************************************\nOther Posterior Circulation\n0 981191\n1 31072\nName: count, dtype: int64\n0\n**************************************************\nAneurysm Present\n0 531662\n1 480601\nName: count, dtype: int64\n0\n**************************************************\n\n\nI am confused should i use it for training model or preprocessing like will this data always be their like 'Rows',\n 'Columns',\n 'PixelSpacing',\n 'SliceThickness',\n 'SpacingBetweenSlices',\n 'ImagePositionPatient',\n 'ImageOrientationPatient',\nthese and other can be used to do some preprocessing should i use them, and other stuff like demographic data be used for model training should i use that?? cause I am afraid that these feature may not always be their or be under different name\n\nIf anyone has any clarity please help, would really appericite it \n" } }