{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"collapsed":true},"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 in \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 \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd \ndf = pd.read_csv('/kaggle/input/rsna-pneumonia-detection-challenge/stage_2_train_labels.csv')\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.drop_duplicates(inplace=True)\ndf['Target'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os \nprint(len(os.listdir('../input/rsna-pneumonia-detection-challenge/stage_2_train_images/')))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainfiles=[]\nfor file in os.listdir('../input/rsna-pneumonia-detection-challenge/stage_2_train_images/'):\n    trainfiles.append(file)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(trainfiles))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sick= df[df.Target==1]\nsick= sick[['patientId','Target']]\nsick.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sick.drop_duplicates(inplace = True)\nsick.shape","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"not_sick= df[df.Target ==0]\nnot_sick= not_sick[['patientId','Target']]\nnot_sick.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"not_sick.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install pydicom","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!mkdir train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cd train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!mkdir sick\n!mkdir notsick","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cd-","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!mkdir test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cd  test ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!mkdir sick\n!mkdir notsick","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pydicom, numpy as np\nimport matplotlib.pyplot as plt\nimport shutil\nimport cv2\nimport os\ntrain_notsick=\"/kaggle/working/train/notsick/\"\ntest_notsick= \"/kaggle/working/test/notsick/\"\ntrain_dir = '../input/rsna-pneumonia-detection-challenge/stage_2_train_images/'\ni=0\nfor idx, row in not_sick.iterrows():\n    patientId = row['patientId']\n    file='%s.dcm' % patientId\n    dcm_file = train_dir + file\n    ds =  pydicom.dcmread(dcm_file)\n    pixel_array_numpy = ds.pixel_array\n    dcmfile = '%s.png' % patientId\n    i=i+1\n    if i<5000 and file in trainfiles:\n        cv2.imwrite(os.path.join(train_notsick, dcmfile), pixel_array_numpy)\n    elif i >5000 and i<7000 and file in trainfiles:\n        cv2.imwrite(os.path.join(test_notsick, dcmfile), pixel_array_numpy)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cd train/notsick","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os \nprint(len(os.listdir(test_notsick)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_sick=\"/kaggle/working/train/sick/\"\ntest_sick= \"/kaggle/working/test/sick/\"\ni=0\nfor idx, row in sick.iterrows():\n    patientId = row['patientId']\n    file ='%s.dcm' % patientId\n    dcm_file = train_dir + file\n    ds =  pydicom.dcmread(dcm_file)\n    pixel_array_numpy = ds.pixel_array\n    dcmfile = '%s.png' % patientId\n    i=i+1\n    if i<4000 and file in trainfiles:\n        cv2.imwrite(os.path.join(train_sick, dcmfile), pixel_array_numpy)\n    elif i>4000 and file in trainfiles:\n        cv2.imwrite(os.path.join(test_sick, dcmfile), pixel_array_numpy)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(trainfiles[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(os.listdir(test_sick)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from os import listdir\nimport imageio\npath='/kaggle/working/train/sick/'\nfor file in listdir(path):\n    dcm_data = pydicom.read_file(path+file)\n    im = dcm_data.pixel_array\n    imageio.imwrite(path+file.replace('.dcm','.png'), im)\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, Activation, BatchNormalization\n\nmodel = Sequential()\nmodel.add(Conv2D(512, (3, 3), activation='relu',input_shape=(256, 256, 3)))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Conv2D(256, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Conv2D(128, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Conv2D(32, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='relu'))\nmodel.add(Dense(1, activation='sigmoid')) \nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ModelCheckpoint\ncheckpoint = ModelCheckpoint('rsna_model', monitor='loss', verbose=1, save_best_only=True)\ncallbacks_list = [checkpoint]\ntrain_datagen = ImageDataGenerator(rescale = 1./255, shear_range = 0.2,  horizontal_flip = True)\n\ntest_datagen = ImageDataGenerator(rescale = 1./255)\n\ntraining_set = train_datagen.flow_from_directory('/kaggle/working/train/',  target_size = (256, 256),\n                                                 batch_size = 32, class_mode = 'binary')\n\ntest_set = test_datagen.flow_from_directory('/kaggle/working/test/', target_size = (256, 256), \n                                            batch_size = 32,  class_mode = 'binary')\n\nmodel.fit_generator(training_set, steps_per_epoch = 282,epochs = 20,validation_data = test_set,validation_steps = 125\n                    ,callbacks=callbacks_list)","execution_count":null,"outputs":[]}],"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}