{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":71549,"databundleVersionId":8561470,"sourceType":"competition"},{"sourceId":67743,"sourceType":"modelInstanceVersion","modelInstanceId":56480}],"dockerImageVersionId":30733,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## Import Libraries","metadata":{}},{"cell_type":"code","source":"import os\nimport gc\nimport sys\nimport cv2\nimport math, random\nimport numpy as np\nimport pandas as pd\nimport glob\nfrom tqdm import tqdm\nfrom sklearn.model_selection import KFold\n\nfrom collections import OrderedDict\n\nimport torch\nimport torch.nn.functional as F\nfrom torch import nn\nfrom torch.utils.data import DataLoader, Dataset\nfrom torch.optim import AdamW\n\nimport timm\nfrom timm.utils import ModelEmaV2\nfrom transformers import get_cosine_schedule_with_warmup\n\nimport albumentations as A\n\nimport re\nimport pydicom","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:10.295028Z","iopub.execute_input":"2024-07-11T13:15:10.29538Z","iopub.status.idle":"2024-07-11T13:15:18.374691Z","shell.execute_reply.started":"2024-07-11T13:15:10.295351Z","shell.execute_reply":"2024-07-11T13:15:18.373652Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Config","metadata":{}},{"cell_type":"code","source":"rd = '/kaggle/input/rsna-2024-lumbar-spine-degenerative-classification'\nOUTPUT_DIR = f'/kaggle/input/spine-degenerative-classification/pytorch/densenet201-10-fold/1'\n\nN_WORKERS = os.cpu_count()\nUSE_AMP = True\nSEED = 8620\n\nIMG_SIZE = [512, 512]\nIN_CHANS = 30\nN_LABELS = 25\nN_CLASSES = 3 * N_LABELS\n\nMODEL_NAME = \"densenet201\"\n\nBATCH_SIZE = 1\n\ndevice = torch.device('cuda:0') if torch.cuda.is_available() else torch.device('cpu')\ndevice","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:18.376259Z","iopub.execute_input":"2024-07-11T13:15:18.376706Z","iopub.status.idle":"2024-07-11T13:15:18.434128Z","shell.execute_reply.started":"2024-07-11T13:15:18.376679Z","shell.execute_reply":"2024-07-11T13:15:18.432981Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv(f'{rd}/test_series_descriptions.csv')\ndf.head()\nstudy_ids = list(df['study_id'].unique())\nsample_sub = pd.read_csv(f'{rd}/sample_submission.csv')\nLABELS = list(sample_sub.columns[1:])\nCONDITIONS = [\n    'spinal_canal_stenosis',\n    'left_neural_foraminal_narrowing',\n    'right_neural_foraminal_narrowing',\n    'left_subarticular_stenosis',\n    'right_subarticular_stenosis'\n]\n\nLEVELS = [\n    'l1_l2',\n    'l2_l3',\n    'l3_l4',\n    'l4_l5',\n    'l5_s1',\n]","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:18.439518Z","iopub.execute_input":"2024-07-11T13:15:18.439781Z","iopub.status.idle":"2024-07-11T13:15:18.462989Z","shell.execute_reply.started":"2024-07-11T13:15:18.439757Z","shell.execute_reply":"2024-07-11T13:15:18.462295Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def atoi(text):\n    return int(text) if text.isdigit() else text\n\n\ndef natural_keys(text):\n    return [ atoi(c) for c in re.split(r'(\\d+)', text) ]","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:18.464189Z","iopub.execute_input":"2024-07-11T13:15:18.464523Z","iopub.status.idle":"2024-07-11T13:15:18.47008Z","shell.execute_reply.started":"2024-07-11T13:15:18.464485Z","shell.execute_reply":"2024-07-11T13:15:18.46925Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Define Dataset","metadata":{}},{"cell_type":"code","source":"class RSNA24TestDataset(Dataset):\n    def __init__(self, df, study_ids, phase='test', transform=None):\n        self.df = df\n        self.study_ids = study_ids\n        self.transform = transform\n        self.phase = phase\n\n    def __len__(self):\n        return len(self.study_ids)\n\n    def get_img_paths(self, study_id, series_desc):\n        pdf = self.df[self.df['study_id'] == study_id]\n        pdf_ = pdf[pdf['series_description'] == series_desc]\n        allimgs = []\n        for i, row in pdf_.iterrows():\n            pimgs = glob.glob(f'{rd}/test_images/{study_id}/{row[\"series_id\"]}/*.dcm')\n            pimgs = sorted(pimgs, key=natural_keys)\n            allimgs.extend(pimgs)\n\n        return allimgs\n\n    def read_dcm_ret_arr(self, src_path):\n        dicom_data = pydicom.dcmread(src_path)\n        image = dicom_data.pixel_array\n        image = (image - image.min()) / (image.max() - image.min() + 1e-6) * 255\n        img = cv2.resize(image, (IMG_SIZE[0], IMG_SIZE[1]), interpolation=cv2.INTER_CUBIC)\n        assert img.shape == (IMG_SIZE[0], IMG_SIZE[1])\n        return img\n\n    def __getitem__(self, idx):\n        x = np.zeros((IMG_SIZE[0], IMG_SIZE[1], IN_CHANS), dtype=np.uint8)\n        st_id = self.study_ids[idx]\n\n        # Sagittal T1\n        allimgs_st1 = self.get_img_paths(st_id, 'Sagittal T1')\n        if len(allimgs_st1) == 0:\n            print(st_id, ': Sagittal T1, has no images')\n\n        else:\n            step = len(allimgs_st1) / 10.0\n            st = len(allimgs_st1) / 2.0 - 4.0 * step\n            end = len(allimgs_st1) + 0.0001\n            for j, i in enumerate(np.arange(st, end, step)):\n                try:\n                    ind2 = max(0, int((i - 0.5001).round()))\n                    img = self.read_dcm_ret_arr(allimgs_st1[ind2])\n                    x[..., j] = img.astype(np.uint8)\n                except:\n                    print(f'failed to load on {st_id}, Sagittal T1')\n                    pass\n\n        # Sagittal T2/STIR\n        allimgs_st2 = self.get_img_paths(st_id, 'Sagittal T2/STIR')\n        if len(allimgs_st2) == 0:\n            print(st_id, ': Sagittal T2/STIR, has no images')\n\n        else:\n            step = len(allimgs_st2) / 10.0\n            st = len(allimgs_st2) / 2.0 - 4.0 * step\n            end = len(allimgs_st2) + 0.0001\n            for j, i in enumerate(np.arange(st, end, step)):\n                try:\n                    ind2 = max(0, int((i - 0.5001).round()))\n                    img = self.read_dcm_ret_arr(allimgs_st2[ind2])\n                    x[..., j + 10] = img.astype(np.uint8)\n                except:\n                    print(f'failed to load on {st_id}, Sagittal T2/STIR')\n                    pass\n\n        # Axial T2\n        allimgs_at2 = self.get_img_paths(st_id, 'Axial T2')\n        if len(allimgs_at2) == 0:\n            print(st_id, ': Axial T2, has no images')\n\n        else:\n            step = len(allimgs_at2) / 10.0\n            st = len(allimgs_at2) / 2.0 - 4.0 * step\n            end = len(allimgs_at2) + 0.0001\n\n            for j, i in enumerate(np.arange(st, end, step)):\n                try:\n                    ind2 = max(0, int((i - 0.5001).round()))\n                    img = self.read_dcm_ret_arr(allimgs_at2[ind2])\n                    x[..., j + 20] = img.astype(np.uint8)\n                except:\n                    print(f'failed to load on {st_id}, Axial T2')\n                    pass\n\n        if self.transform is not None:\n            x = self.transform(image=x)['image']\n\n        x = x.transpose(2, 0, 1)\n\n        return x, str(st_id)","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:18.47156Z","iopub.execute_input":"2024-07-11T13:15:18.471815Z","iopub.status.idle":"2024-07-11T13:15:18.493152Z","shell.execute_reply.started":"2024-07-11T13:15:18.471792Z","shell.execute_reply":"2024-07-11T13:15:18.492375Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"transforms_test = A.Compose([\n    A.Resize(IMG_SIZE[0], IMG_SIZE[1]),\n    A.Normalize(mean=0.5, std=0.5)\n])\ntest_ds = RSNA24TestDataset(df, study_ids, transform=transforms_test)\ntest_dl = DataLoader(\n    test_ds,\n    batch_size=1,\n    shuffle=False,\n    num_workers=N_WORKERS,\n    pin_memory=True,\n    drop_last=False\n)","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:18.494453Z","iopub.execute_input":"2024-07-11T13:15:18.495015Z","iopub.status.idle":"2024-07-11T13:15:18.504305Z","shell.execute_reply.started":"2024-07-11T13:15:18.494983Z","shell.execute_reply":"2024-07-11T13:15:18.503448Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Define Model","metadata":{}},{"cell_type":"code","source":"class RSNA24Model(nn.Module):\n    def __init__(self, model_name, in_c=30, n_classes=75, pretrained=True, features_only=False):\n        super().__init__()\n        self.model = timm.create_model(\n            model_name,\n            pretrained=pretrained,\n            features_only=features_only,\n            in_chans=in_c,\n            num_classes=n_classes,\n            global_pool='avg'\n        )\n\n    def forward(self, x):\n        y = self.model(x)\n        return y","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:18.505506Z","iopub.execute_input":"2024-07-11T13:15:18.506079Z","iopub.status.idle":"2024-07-11T13:15:18.513969Z","shell.execute_reply.started":"2024-07-11T13:15:18.506048Z","shell.execute_reply":"2024-07-11T13:15:18.513133Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Load Models","metadata":{}},{"cell_type":"code","source":"models = []\nCKPT_PATHS = glob.glob(OUTPUT_DIR + '/best_wll_model_fold-*.pt')\nCKPT_PATHS = sorted(CKPT_PATHS)\n\nfor i, cp in enumerate(CKPT_PATHS):\n    print(f'loading {cp}...')\n    model = RSNA24Model(MODEL_NAME, IN_CHANS, N_CLASSES, pretrained=False)\n    model.load_state_dict(torch.load(cp))\n    model.eval()\n    model.half()\n    model.to(device)\n    models.append(model)","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:18.515338Z","iopub.execute_input":"2024-07-11T13:15:18.515814Z","iopub.status.idle":"2024-07-11T13:15:34.527692Z","shell.execute_reply.started":"2024-07-11T13:15:18.515761Z","shell.execute_reply":"2024-07-11T13:15:34.52691Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Inference","metadata":{}},{"cell_type":"code","source":"autocast = torch.cuda.amp.autocast(enabled=USE_AMP, dtype=torch.half)\ny_preds = []\nrow_names = []\n\nwith tqdm(test_dl, leave=True) as pbar:\n    with torch.no_grad():\n        for idx, (x, si) in enumerate(pbar):\n            x = x.to(device)\n            pred_per_study = np.zeros((25, 3))\n\n            for cond in CONDITIONS:\n                for level in LEVELS:\n                    row_names.append(si[0] + '_' + cond + '_' + level)\n\n            with autocast:\n                for m in models:\n                    y = m(x)[0]\n                    for col in range(N_LABELS):\n                        pred = y[col * 3:col * 3 + 3]\n                        y_pred = pred.float().softmax(0).cpu().numpy()\n                        pred_per_study[col] += y_pred / len(models)\n                y_preds.append(pred_per_study)","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:34.530288Z","iopub.execute_input":"2024-07-11T13:15:34.530574Z","iopub.status.idle":"2024-07-11T13:15:37.753437Z","shell.execute_reply.started":"2024-07-11T13:15:34.530549Z","shell.execute_reply":"2024-07-11T13:15:37.752464Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Make Submission","metadata":{}},{"cell_type":"code","source":"y_preds = np.concatenate(y_preds, axis=0)\nsub = pd.DataFrame()\nsub['row_id'] = row_names\nsub[LABELS] = y_preds","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:37.754882Z","iopub.execute_input":"2024-07-11T13:15:37.755205Z","iopub.status.idle":"2024-07-11T13:15:37.769765Z","shell.execute_reply.started":"2024-07-11T13:15:37.755177Z","shell.execute_reply":"2024-07-11T13:15:37.768735Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub.to_csv('submission.csv', index=False)\npd.read_csv('submission.csv').head()","metadata":{"execution":{"iopub.status.busy":"2024-07-11T13:15:37.771022Z","iopub.execute_input":"2024-07-11T13:15:37.771362Z","iopub.status.idle":"2024-07-11T13:15:37.799079Z","shell.execute_reply.started":"2024-07-11T13:15:37.771336Z","shell.execute_reply":"2024-07-11T13:15:37.798127Z"},"trusted":true},"execution_count":null,"outputs":[]}]}