{"cells":[{"metadata":{},"cell_type":"markdown","source":"# 1. Importing Libraries and packages"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\n\nimport os\nimport gc\nimport time\nfrom IPython.display import clear_output\n\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Dense, Dropout, Conv2D\n\nfrom tensorflow.keras.models import load_model\nfrom tensorflow.keras.callbacks import ModelCheckpoint as MC\nfrom tensorflow.keras import backend as K\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Detect hardware, return appropriate distribution strategy\ntry:\n    # TPU detection. No parameters necessary if TPU_NAME environment variable is\n    # set: this is always the case on Kaggle.\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    # Default distribution strategy in Tensorflow. Works on CPU and single GPU.\n    strategy = tf.distribute.get_strategy()\n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 2. Loading the Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"root = '/kaggle/input/rsna-str-pulmonary-embolism-detection'\nfor item in os.listdir(root):\n    path = os.path.join(root, item)\n    if os.path.isfile(path):\n        print(path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Loading Training Data ...\")\ntrain = pd.read_csv(\"/kaggle/input/rsna-str-pulmonary-embolism-detection/train.csv\")\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Loading Testing Data...\")\ntest = pd.read_csv(\"/kaggle/input/rsna-str-pulmonary-embolism-detection/test.csv\")\nprint(test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\" Loading Sample Output ...\")\nss = pd.read_csv(\"../input/rsna-str-pulmonary-embolism-detection/sample_submission.csv\")\nprint(ss.shape)\nss.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 3. Checking Targets and input images"},{"metadata":{"trusted":true},"cell_type":"code","source":"ids = ss.id\ncounter = [1 for _ in range(10)]\nmapper = []\nfor i in ids:\n    n = '_'.join(i.split('_')[1:])\n    if n not in mapper:\n        mapper.append(n)\n    else:\n        counter[mapper.index(n)] +=1\nprint(\"List of keys: \")\nprint(mapper, sep = '\\n')\nprint()\nprint(\"Count of items per key: \")\nprint(counter)\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import vtk\nfrom vtk.util import numpy_support\nimport cv2\n\nreader = vtk.vtkDICOMImageReader()\ndef get_img(path):\n    reader.SetFileName(path)\n    reader.Update()\n    _extent = reader.GetDataExtent()\n    ConstPixelDims = [_extent[1]-_extent[0]+1, _extent[3]-_extent[2]+1, _extent[5]-_extent[4]+1]\n    ConstPixelSpacing = reader.GetPixelSpacing()\n    imageData = reader.GetOutput()\n    pointData = imageData.GetPointData()\n    arrayData = pointData.GetArray(0)\n    ArrayDicom = numpy_support.vtk_to_numpy(arrayData)\n    ArrayDicom = ArrayDicom.reshape(ConstPixelDims, order = 'F')\n    ArrayDicom = cv2.resize(ArrayDicom, (512, 512))\n    return ArrayDicom","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Let's load a dcom file and view it\n\nfpath = \"../input/rsna-str-pulmonary-embolism-detection/train/0003b3d648eb/d2b2960c2bbf/00ac73cfc372.dcm\"\nds = get_img(fpath)\n\nimport matplotlib.pyplot as plt\n\n# Convert dcom file to 8 bit color\n\nfunc = lambda x: int((2**15 + x)*(255/2**16))\nint16_to_uint8 = np.vectorize(func)\n\ndef show_dicom_images(dcom):\n    f, ax = plt.subplots(1, 2, figsize=(16, 20))\n    data_row_img = int16_to_uint8(ds)\n    ax[0].imshow(data_row_img, cmap=plt.cm.bone)\n    ax[1].imshow(ds, cmap=plt.cm.bone)\n    \n    ax[0].axis(\"off\")\n    ax[0].set_title('8-bit DICOM Image')\n    ax[1].axis('off')\n    ax[1].set_title('16-bit DICOM Image')\n    plt.show()\n\nshow_dicom_images(ds)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 4. Building the model"},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Dense, Dropout, Conv2D\n\nwith strategy.scope():\n    \n    inputs = Input((512, 512, 3))\n    #x = Conv2D(3, (1, 1), activation='relu')(inputs)\n    base_model = keras.applications.Xception(\n        include_top=False,\n        weights=\"imagenet\"\n    )\n\n    base_model.trainable = False\n\n    outputs = base_model(inputs, training=False)\n    outputs = keras.layers.GlobalAveragePooling2D()(outputs)\n    outputs = Dropout(0.25)(outputs)\n    outputs = Dense(1024, activation='relu')(outputs)\n    outputs = Dense(256, activation='relu')(outputs)\n    outputs = Dense(64, activation='relu')(outputs)\n    ppoi = Dense(1, activation='sigmoid', name='pe_present_on_image')(outputs)\n    rlrg1 = Dense(1, activation='sigmoid', name='rv_lv_ratio_gte_1')(outputs)\n    rlrl1 = Dense(1, activation='sigmoid', name='rv_lv_ratio_lt_1')(outputs) \n    lspe = Dense(1, activation='sigmoid', name='leftsided_pe')(outputs)\n    cpe = Dense(1, activation='sigmoid', name='chronic_pe')(outputs)\n    rspe = Dense(1, activation='sigmoid', name='rightsided_pe')(outputs)\n    aacpe = Dense(1, activation='sigmoid', name='acute_and_chronic_pe')(outputs)\n    cnpe = Dense(1, activation='sigmoid', name='central_pe')(outputs)\n    indt = Dense(1, activation='sigmoid', name='indeterminate')(outputs)\n\n    model = Model(inputs=inputs, outputs={'pe_present_on_image':ppoi,\n                                          'rv_lv_ratio_gte_1':rlrg1,\n                                          'rv_lv_ratio_lt_1':rlrl1,\n                                          'leftsided_pe':lspe,\n                                          'chronic_pe':cpe,\n                                          'rightsided_pe':rspe,\n                                          'acute_and_chronic_pe':aacpe,\n                                          'central_pe':cnpe,\n                                          'indeterminate':indt})\n\n    opt = keras.optimizers.Adam(lr=0.001)\n\n    model.compile(optimizer=opt,\n                  loss='binary_crossentropy',\n                  metrics=['accuracy'])\n\n    model.summary()\n    model.save('pe_detection_model.h5')\n    del model\nK.clear_session()\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 5. Training the model"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Image Generator\n\ndef convert_to_rgb(array):\n    array = array.reshape((512, 512, 1))\n    return np.stack([array, array, array], axis=2).reshape((512, 512, 3))\n    \ndef custom_dcom_image_generator(batch_size, dataset, test=False, debug=False):\n    \n    fnames = dataset[['StudyInstanceUID', 'SeriesInstanceUID', 'SOPInstanceUID']]\n    \n    if not test:\n        Y = dataset[['pe_present_on_image', 'rv_lv_ratio_gte_1', 'rv_lv_ratio_lt_1', 'leftsided_pe',\n                     'chronic_pe', 'rightsided_pe', 'acute_and_chronic_pe', 'central_pe', 'indeterminate'\n                    ]]\n        prefix = 'input/rsna-str-pulmonary-embolism-detection/train'\n        \n    else:\n        prefix = 'input/rsna-str-pulmonary-embolism-detection/test'\n    \n    X = []\n    batch = 0\n    for st, sr, so in fnames.values:\n        if debug:\n            print(f\"Current file: ../{prefix}/{st}/{sr}/{so}.dcm\")\n\n        dicom = get_img(f\"../{prefix}/{st}/{sr}/{so}.dcm\")\n        image = convert_to_rgb(dicom)\n        X.append(image)\n        \n        del st, sr, so\n        \n        if len(X) == batch_size:\n            if test:\n                yield np.array(X)\n                del X\n            else:\n                yield np.array(X), Y[batch*batch_size:(batch+1)*batch_size].values\n                del X\n                \n            gc.collect()\n            X = []\n            batch += 1\n        \n    if test:\n        yield np.array(X)\n    else:\n        yield np.array(X), Y[batch*batch_size:(batch+1)*batch_size].values\n        del Y\n    del X\n    gc.collect()\n    return","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Training the model with train data\n\nhistory = {}\nstart = time.time()\ndebug = 0\nbatch_size = 5000*strategy.num_replicas_in_sync\ntrain_size = int(batch_size*0.9)\n\nmax_train_time = 3600 * 6 #hours to seconds of training\n\ncheckpoint = MC(filepath='../working/pe_detection_model.h5', monitor='val_loss', save_best_only=True, verbose=1)\n#Train loop\nfor n, (x, y) in enumerate(custom_dcom_image_generator(batch_size, train.sample(frac=1), False, debug)):\n    \n    if len(x) < 10: #Tries to filter out empty or short data\n        break\n        \n    clear_output(wait=True)\n    print(\"Training batch: %i - %i\" %(batch_size*n, batch_size*(n+1)))\n    \n    model = load_model('../working/pe_detection_model.h5')\n    hist = model.fit(\n        x[:train_size], #Y values are in a dict as there's more than one target for training output\n        {'pe_present_on_image':y[:train_size, 0],\n         'rv_lv_ratio_gte_1':y[:train_size, 1],\n         'rv_lv_ratio_lt_1':y[:train_size, 2],\n         'leftsided_pe':y[:train_size, 3],\n         'chronic_pe':y[:train_size, 4],\n         'rightsided_pe':y[:train_size, 5],\n         'acute_and_chronic_pe':y[:train_size, 6],\n         'central_pe':y[:train_size, 7],\n         'indeterminate':y[:train_size, 8]},\n\n        callbacks = checkpoint,\n\n        validation_split=0.2,\n        epochs=5,\n        batch_size=8*strategy.num_replicas_in_sync,\n        verbose=debug\n    )\n    \n    print(\"Metrics for batch validation:\")\n    model.evaluate(x[train_size:],\n                   {'pe_present_on_image':y[train_size:, 0],\n                    'rv_lv_ratio_gte_1':y[train_size:, 1],\n                    'rv_lv_ratio_lt_1':y[train_size:, 2],\n                    'leftsided_pe':y[train_size:, 3],\n                    'chronic_pe':y[train_size:, 4],\n                    'rightsided_pe':y[train_size:, 5],\n                    'acute_and_chronic_pe':y[train_size:, 6],\n                    'central_pe':y[train_size:, 7],\n                    'indeterminate':y[train_size:, 8]\n                   }\n                  )\n    \n    try:\n        for key in hist.history.keys():\n            history[key] = np.concatenate([history[key], hist.history[key]], axis=0)\n    except:\n        for key in hist.history.keys():\n            history[key] = hist.history[key]\n            \n    #To make sure that our model don't train overtime\n    if time.time() - start >= max_train_time:\n        print(\"Time's up!\")\n        break\n        \n    model.save('pe_detection_model.h5')\n    del model, x, y, hist\n    K.clear_session()\n    gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for key in history.keys():\n    if key.startswith('val'):\n        continue\n    else:\n        epoch = range(len(history[key]))\n        plt.plot(epoch, history[key]) #X=epoch, Y=value\n        plt.plot(epoch, history['val_'+key])\n        plt.title(key)\n        if 'accuracy' in key:\n            plt.axis([0, len(history[key]), -0.1, 1.1]) #Xmin, Xmax, Ymin, Ymax\n        plt.legend(['train', 'validation'], loc='upper right')\n        plt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"References:\n\nhttps://www.kaggle.com/seraphwedd18/pe-detection-with-keras-model-creation/data\n\n"}],"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":4,"nbformat_minor":4}