{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceType":"competition","sourceId":24800,"datasetId":1042002,"databundleVersionId":1831594}],"dockerImageVersionId":31286,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\n\n# Kaggle dataset path\nBASE_PATH = \"/kaggle/input/vinbigdata-chest-xray-abnormalities-detection\"\nTRAIN_DICOM_PATH = os.path.join(BASE_PATH, \"train\")\nCSV_PATH = os.path.join(BASE_PATH, \"train.csv\")\n\n# Working directory\nWORK_PATH = \"/kaggle/working/CliniScan\"\nIMAGE_SAVE_PATH = os.path.join(WORK_PATH, \"images\")\nLABEL_SAVE_PATH = os.path.join(WORK_PATH, \"labels\")\n\nos.makedirs(IMAGE_SAVE_PATH, exist_ok=True)\nos.makedirs(LABEL_SAVE_PATH, exist_ok=True)\n\nprint(\"Working directory created.\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-01T09:11:30.178195Z","iopub.execute_input":"2026-03-01T09:11:30.178554Z","iopub.status.idle":"2026-03-01T09:11:30.194275Z","shell.execute_reply.started":"2026-03-01T09:11:30.178525Z","shell.execute_reply":"2026-03-01T09:11:30.193119Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Convert DICOM to JPG¶","metadata":{}},{"cell_type":"code","source":"import pydicom\nimport cv2\nimport numpy as np\nfrom tqdm import tqdm\n\nimage_ids = [f.replace(\".dicom\", \"\") for f in os.listdir(TRAIN_DICOM_PATH)]\n\nfor image_id in tqdm(image_ids):\n    \n    dicom_path = os.path.join(TRAIN_DICOM_PATH, image_id + \".dicom\")\n    save_path = os.path.join(IMAGE_SAVE_PATH, image_id + \".jpg\")\n    \n    try:\n        dicom = pydicom.dcmread(dicom_path)\n        image = dicom.pixel_array.astype(np.float32)\n        \n        # Normalize to 0–255\n        image = (image - image.min()) / (image.max() - image.min())\n        image = (image * 255).astype(np.uint8)\n        \n        # Resize to 1024×1024\n        image = cv2.resize(image, (1024, 1024))\n        \n        # Save as JPG\n        cv2.imwrite(save_path, image, [cv2.IMWRITE_JPEG_QUALITY, 95])\n        \n    except Exception as e:\n        print(\"Error:\", image_id)\n\nprint(\"DICOM → JPG conversion completed.\")","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}