{"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":"markdown","source":"## Training notebook - https://www.kaggle.com/hijest/rsna-miccai-2dcnn-training","metadata":{}},{"cell_type":"code","source":"import os\nimport json\nimport glob\nimport random\nimport collections\n\nimport numpy as np\nimport pandas as pd\nimport pydicom\nfrom pydicom.pixel_data_handlers.util import apply_voi_lut\nimport cv2\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport random\nfrom tqdm.notebook import tqdm\n\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom sklearn.metrics import roc_auc_score\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras import layers","metadata":{"execution":{"iopub.status.busy":"2022-06-16T14:11:43.294144Z","iopub.execute_input":"2022-06-16T14:11:43.294648Z","iopub.status.idle":"2022-06-16T14:11:48.969130Z","shell.execute_reply.started":"2022-06-16T14:11:43.294563Z","shell.execute_reply":"2022-06-16T14:11:48.968387Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef Laplacian(data):\n    \n    if data is None:\n        return -1\n    \n    kernel = np.array(([1, 1, 1],\n                       [1, -8, 1],\n                      [1, 1, 1]), dtype=\"float32\")\n    kernel1 = np.array(([0, -1, 0],\n                       [-1, 5, -1],\n                        [0, -1, 0]), dtype=\"float32\")\n  \n    result = cv2.filter2D(data, -1, kernel)\n    result1 = cv2.filter2D(data, -1, kernel1)\n        \n    \n#     fig = plt.figure(figsize=(12,8))\n#     ax1 = plt.subplot(1,2,1)\n#     ax1.imshow(data, cmap=\"gray\")\n#     ax1.set_title(f\"Original image shape = {result.shape}\")\n#     ax2 = plt.subplot(1,2,2)\n#     ax2.imshow(result1, cmap=\"gray\")\n#     ax2.set_title(f\"Preproc image shape = {result1.shape}\")\n#     plt.show()\n    \n    return result1","metadata":{"execution":{"iopub.status.busy":"2022-06-16T14:11:48.970870Z","iopub.execute_input":"2022-06-16T14:11:48.971143Z","iopub.status.idle":"2022-06-16T14:11:48.979637Z","shell.execute_reply.started":"2022-06-16T14:11:48.971109Z","shell.execute_reply":"2022-06-16T14:11:48.978754Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"TYPES = [\"FLAIR\", \"T1w\", \"T2w\", \"T1wCE\"]\nWHITE_THRESHOLD = 10 # out of 255\nEXCLUDE = [109, 123, 709]\n\n\ntrain_df = pd.read_csv(\"../input/rsna-miccai-brain-tumor-radiogenomic-classification/train_labels.csv\")\ntest_df = pd.read_csv('../input/rsna-miccai-brain-tumor-radiogenomic-classification/sample_submission.csv')\ntrain_df = train_df[~train_df.BraTS21ID.isin(EXCLUDE)]\nSCALE = .8\ndef load_dicom(path, size = 224):\n    ''' \n    Reads a DICOM image, standardizes so that the pixel values are between 0 and 1, then rescales to 0 and 255\n    \n    Note super sure if this kind of scaling is appropriate, but everyone seems to do it. \n    '''\n    \n    dicom = pydicom.read_file(path)\n    data = dicom.pixel_array\n    if np.max(data) != 0:\n        data = data / np.max(data)\n    data = (data * 255).astype(np.uint8)\n    return cv2.resize(data, (size, size))\n    \n\ndef get_all_image_paths(brats21id, image_type, folder='train'): \n    '''\n    Returns an arry of all the images of a particular type for a particular patient ID\n    '''\n    assert(image_type in TYPES)\n    \n    patient_path = os.path.join(\n        \"../input/rsna-miccai-brain-tumor-radiogenomic-classification/%s/\" % folder, \n        str(brats21id).zfill(5),\n    )\n\n    paths = sorted(\n        glob.glob(os.path.join(patient_path, image_type, \"*\")), \n        key=lambda x: int(x[:-4].split(\"-\")[-1]),\n    )\n    \n    num_images = len(paths)\n    \n    start = int(num_images * 0.25)\n    end = int(num_images * 0.75)\n\n    interval = 3\n    \n    if num_images < 10: \n        interval = 1\n    \n    return np.array(paths[start:end:interval])\n\ndef get_all_images(brats21id, image_type, folder='train', size=225):\n    return [load_dicom(path,size) for path in get_all_image_paths(brats21id, image_type, folder)]\nIMAGE_SIZE = 128\n\ndef get_all_data_for_train(image_type):\n    global train_df\n    \n    X = []\n    y = []\n    train_ids = []\n\n    for i in tqdm(train_df.index):\n        x = train_df.loc[i]\n        images = get_all_images(int(x['BraTS21ID']), image_type, 'train', IMAGE_SIZE)\n        label = x['MGMT_value']\n\n        X += images\n        y += [label] * len(images)\n        train_ids += [int(x['BraTS21ID'])] * len(images)\n        assert(len(X) == len(y))\n    return np.array(X), np.array(y), np.array(train_ids)\n\ndef get_all_data_for_test(image_type):\n    global test_df\n    \n    X = []\n    test_ids = []\n\n    for i in tqdm(test_df.index):\n        x = test_df.loc[i]\n        images = get_all_images(int(x['BraTS21ID']), image_type, 'test', IMAGE_SIZE)\n        X += images\n        test_ids += [int(x['BraTS21ID'])] * len(images)\n\n    return np.array(X), np.array(test_ids)\n\nX_test, testidt = get_all_data_for_test('FLAIR')\n\ndef convert_to_rgb(array):\n    array = array.reshape((-1, 128, 128, 1))\n    return np.stack([array, array, array], axis=2).reshape((-1, 128, 128, 3))\n\nX_test = convert_to_rgb(X_test)","metadata":{"execution":{"iopub.status.busy":"2022-06-16T14:11:48.981451Z","iopub.execute_input":"2022-06-16T14:11:48.982105Z","iopub.status.idle":"2022-06-16T14:12:12.021096Z","shell.execute_reply.started":"2022-06-16T14:11:48.982045Z","shell.execute_reply":"2022-06-16T14:12:12.020328Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file_path= '../input/newmodel/best_model_new.h5'","metadata":{"execution":{"iopub.status.busy":"2022-06-16T14:12:12.023172Z","iopub.execute_input":"2022-06-16T14:12:12.023510Z","iopub.status.idle":"2022-06-16T14:12:12.027296Z","shell.execute_reply.started":"2022-06-16T14:12:12.023472Z","shell.execute_reply":"2022-06-16T14:12:12.026618Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_best = tf.keras.models.load_model(filepath=file_path)","metadata":{"execution":{"iopub.status.busy":"2022-06-16T14:12:12.028515Z","iopub.execute_input":"2022-06-16T14:12:12.028938Z","iopub.status.idle":"2022-06-16T14:12:15.444344Z","shell.execute_reply.started":"2022-06-16T14:12:12.028903Z","shell.execute_reply":"2022-06-16T14:12:15.443031Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample = pd.read_csv('../input/rsna-miccai-brain-tumor-radiogenomic-classification/sample_submission.csv')\n\ny_pred = model_best.predict(X_test)\n\npred = np.argmax(y_pred, axis=1)\n\nresult=pd.DataFrame(testidt)\nresult[1]=pred\n\nresult.columns=['BraTS21ID','MGMT_value']\nresult2 = result.groupby('BraTS21ID',as_index=False).mean()\nresult2['BraTS21ID'] = sample['BraTS21ID']\n# result2['MGMT_value'] = result2['MGMT_value'].apply(lambda x:round(x*10)/10)\nresult2.to_csv('submission.csv',index=False)\nresult2","metadata":{"execution":{"iopub.status.busy":"2022-06-16T14:12:15.445547Z","iopub.status.idle":"2022-06-16T14:12:15.446585Z","shell.execute_reply.started":"2022-06-16T14:12:15.446305Z","shell.execute_reply":"2022-06-16T14:12:15.446330Z"},"trusted":true},"execution_count":null,"outputs":[]}]}