{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"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\n#for 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\n\nimport pydicom\nfrom pathlib import Path\nimport cv2\nfrom PIL import Image\nfrom matplotlib import pyplot as plt\n\ndef dicom_file_to_ary(path):\n    dicom = pydicom.dcmread(path)\n    data = dicom.pixel_array\n       \n    data = (data - data.min()) / (data.max() - data.min())\n    \n    if dicom.PhotometricInterpretation == \"MONOCHROME1\":\n        data = 1 - data\n        \n    data = cv2.resize(data, RESIZE_TO)\n    data = (data * 255).astype(np.uint8)\n    return data\n\nRESIZE_TO = (512, 512)\n\n\n#directories = list(Path('/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/12.dcm').iterdir())\n\n\n\ndef process_Image(image_path):\n    processed_ary = dicom_file_to_ary(image_path)\n        \n    return processed_ary\n\n\ndef process_directory(directory_path):\n    parent_directory = str(directory_path).split('/')[-1]\n    !mkdir -p train_images_processed_cv2_{RESIZE_TO[0]}/{parent_directory}\n    \n    for sub_dir_path in directory_path.iterdir():\n        #print(sub_dir_path)\n        for image_path in sub_dir_path.iterdir():\n            processed_ary = dicom_file_to_ary(image_path)\n        \n            cv2.imwrite(\n                f'train_images_processed_cv2_{RESIZE_TO[0]}/{parent_directory}/{image_path.stem}.png',\n                processed_ary)\n        \n        \n        \nimg_path =Path('/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/10004/21057/1029.dcm')      \nimg = process_Image(img_path)\n\n\n\ndirectories = list(Path('/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images').iterdir())\n\n\nimport multiprocessing as mp\n\nwith mp.Pool(64) as p:\n    p.map(process_directory, directories)\n\nplt.imshow(img)\n\n\n\n\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]}]}