{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Prostate cANcer graDe Assessment (PANDA) Challenge: My First Submission"},{"metadata":{},"cell_type":"markdown","source":"# Introduction"},{"metadata":{},"cell_type":"markdown","source":"## Prostate Gland and Prostate Cancer"},{"metadata":{},"cell_type":"markdown","source":"The prostate is part of the male reproductive system. The function of the prostate gland is to secrete substances to the urethra. These secretions nurish and transport sperm. Prostate cancer is diagnosed from samples from a prostate biopsy (rmicrobe). The sample is first assigned as a gleason score. This score is converted to a ISUP grade of 0-5. The score of 0 is negative and the score of 5 is the most severe form of cancer (Prostate cANcer GraDe Assessment (PANDA) Challenge).\n\nThe purpose of this notebook is to create a submission notebook for the PANDAS competition."},{"metadata":{},"cell_type":"markdown","source":"## Predicting Test Data and Submitting submission.csv"},{"metadata":{},"cell_type":"markdown","source":"1. Commit current version and create submission.csv.\n2. Submit the current notebook to the competition to access the testing data.  The code will run in the background to evaluate the test dataset.  The test dataset will undergo the same image processing as the training dataset and is described in the next  following steps.\n2. Remove gray area surrounding the biopsy. The first step involves removing the gray area from around the biopsy (Zenify).\n3. Create 4X4 patched image. The second step is to take 16 samples that have the lowest portion of white. This ensures that the sample is most likely going to show the appropriate part of the sample (i.e. glands). (PAB97).\n4. Use test.pkl file to predict the test images.\n5. Arrange the test biopsies to the appropriate order. \n6. Create and save the predictions to a .csv for submission."},{"metadata":{},"cell_type":"markdown","source":"![image.png](attachment:image.png)","attachments":{"image.png":{"image/png":"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"}}},{"metadata":{},"cell_type":"markdown","source":"# Import fast.ai and Dependencies"},{"metadata":{},"cell_type":"markdown","source":"## Install fast.ai without Internet"},{"metadata":{},"cell_type":"markdown","source":"Internet is not allowed in this competition.  The files have to be loaded through the fastai2 dataset."},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"!pip install ../input/fastai2/fastprogress-0.2.3-py3-none-any.whl\n!pip install ../input/fastai2/fastcore-0.1.18-py3-none-any.whl\n!pip install ../input/fastai2/fastai2-0.0.17-py3-none-any.whl","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Import fast.ai"},{"metadata":{"trusted":true},"cell_type":"code","source":"import fastai2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from fastai2.basics import *\nfrom fastai2.callback.all import *\nfrom fastai2.vision.all import *","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fastai2.torch_core.defaults.device = 'cuda'","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Load Dependencies"},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport cv2\nimport PIL\nfrom PIL import Image as Img\nfrom PIL import ImageTk\nimport random\nimport openslide\nimport skimage.io\nimport skimage.color\nfrom skimage.color import rgb2hsv\nimport matplotlib\nimport numpy as np\nimport pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nfrom IPython.display import Image, display","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Set Random Seed"},{"metadata":{},"cell_type":"markdown","source":"Setting a random seed makes sure that all randomly picked sequences are in the same order.  It is important to keep the same number everytime to keep the same sequence everytime."},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"np.random.seed(2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Functions"},{"metadata":{},"cell_type":"markdown","source":"The enhance_image function removes the gray portion from around the prostate biopsy (Zenify)."},{"metadata":{"trusted":true},"cell_type":"code","source":"def enhance_image(slide_path, contrast=1, brightness=15):\n    image = skimage.io.MultiImage(slide_path)[-2]\n    image = np.array(image)\n    img_enhanced = cv2.addWeighted(image, contrast, image, 0, brightness)\n    return img_enhanced","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The function compute_statistics calculates the portion of white pixels in the region (PAB97)."},{"metadata":{"trusted":true},"cell_type":"code","source":"def compute_statistics(image):\n    width, height = image.shape[0], image.shape[1]\n    num_pixels = width * height\n    \n    num_white_pixels = 0\n    \n    summed_matrix = np.sum(image, axis=-1)\n    # Note: A 3-channel white pixel has RGB (255, 255, 255)\n    num_white_pixels = np.count_nonzero(summed_matrix > 620)\n    ratio_white_pixels = num_white_pixels / num_pixels\n    \n    green_concentration = np.mean(image[1])\n    blue_concentration = np.mean(image[2])\n    \n    return ratio_white_pixels, green_concentration, blue_concentration\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The functions select_k_best_regions and get_k_best_regions list and select the lowest porportion of white pixels in a particular region (PAB97)."},{"metadata":{"trusted":true},"cell_type":"code","source":"def select_k_best_regions(regions, k=20):\n    regions = [x for x in regions if x[3] > 180 and x[4] > 180]\n    k_best_regions = sorted(regions, key=lambda tup: tup[2])[:k]\n    return k_best_regions","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_k_best_regions(coordinates, image, window_size=512):\n    regions = {}\n    for i, tup in enumerate(coordinates):\n        x, y = tup[0], tup[1]\n        regions[i] = image[x : x+window_size, y : y+window_size, :]\n    \n    return regions","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The function generate_patches slides over the region to calculate the white pixels then calculates the statistics and then selects the region with the least amount of pixels (PAB97)."},{"metadata":{"trusted":true},"cell_type":"code","source":"def generate_patches(image, window_size=200, stride=128, k=20):\n        \n    max_width, max_height = image.shape[0], image.shape[1]\n    regions_container = []\n    i = 0\n    \n    while window_size + stride*i <= max_height:\n        j = 0\n        \n        while window_size + stride*j <= max_width:            \n            x_top_left_pixel = j * stride\n            y_top_left_pixel = i * stride\n            \n            patch = image[\n                x_top_left_pixel : x_top_left_pixel + window_size,\n                y_top_left_pixel : y_top_left_pixel + window_size,\n                :\n            ]\n            \n            ratio_white_pixels, green_concentration, blue_concentration = compute_statistics(patch)\n            \n            region_tuple = (x_top_left_pixel, y_top_left_pixel, ratio_white_pixels, green_concentration, blue_concentration)\n            regions_container.append(region_tuple)\n            \n            j += 1\n        \n        i += 1\n    \n    k_best_region_coordinates = select_k_best_regions(regions_container, k=k)\n    k_best_regions = get_k_best_regions(k_best_region_coordinates, image, window_size)\n    \n    return image, k_best_region_coordinates, k_best_regions","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The function glue_to_one_picture glues the 16 patches into one 4X4 image (PAB97)."},{"metadata":{"trusted":true},"cell_type":"code","source":"def glue_to_one_picture(image_patches, window_size=200, k=16):\n    side = int(np.sqrt(k))\n    image = np.zeros((side*window_size, side*window_size, 3), dtype=np.int16)\n        \n    for i, patch in image_patches.items():\n        x = i // side\n        y = i % side\n        image[\n            x * window_size : (x+1) * window_size,\n            y * window_size : (y+1) * window_size,\n            :\n        ] = patch\n    \n    return image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"WINDOW_SIZE = 128\nSTRIDE = 64\nK = 16","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Checkpoints Directory"},{"metadata":{},"cell_type":"markdown","source":"This creates a checkpoint directory for ResNet34 and copies the model to the directory."},{"metadata":{"trusted":true},"cell_type":"code","source":"Path('/root/.cache/torch/checkpoints/').mkdir(exist_ok=True, parents=True)\n!cp '../input/resnet34/resnet34.pth' '/root/.cache/torch/checkpoints/resnet34-333f7ec4.pth'","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Predict the ISUP Grade with ResNet34 and fast.ai using export.pkl"},{"metadata":{},"cell_type":"markdown","source":"The steps will be described using comments."},{"metadata":{"trusted":true},"cell_type":"code","source":"torch.cuda.is_available()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"torch.set_default_tensor_type('torch.cuda.FloatTensor')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_test_path = \"../input/prostate-cancer-grade-assessment/test_images/\"\nsample = '../input/prostate-cancer-grade-assessment/sample_submission.csv'\nsource = Path(\"../input/prostate-cancer-grade-assessment\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#This is the dataframe for sample_submission.csv.\nsub_df = pd.read_csv(sample)\n\n# This is the dataframe for test.csv.\ntest_df = pd.read_csv(source/f'test.csv')\n\n# If the submission_test_path exists, evaluate the test data and create the submission.csv file for the competition.\n#Else, create the submission.csv file to get access to the testing data.\nif os.path.exists(submission_test_path):\n    #get_i is a function that processes the images.\n    def get_i(df=test_df):\n            filename = f'{submission_test_path}/{df.image_id}.tiff'\n            enhanced_image = enhance_image (filename)\n            image, best_coordinates, best_regions = generate_patches(enhanced_image, window_size=WINDOW_SIZE, stride=STRIDE, k=K)\n            glued_image = glue_to_one_picture(best_regions, window_size=WINDOW_SIZE, k=K)\n            glued_image = np.uint8(glued_image)\n            return tensor(glued_image)\n        \n    #This part prepares the image without adding the label since this is test data.\n    blocks = (\n          ImageBlock,\n          CategoryBlock\n              )\n    getters = [\n           get_i\n              ]\n\n    trends = DataBlock(blocks=blocks,\n              getters=getters,\n              item_tfms=Resize(520)\n              )\n    \n    dls = trends.dataloaders(test_df)\n    \n    # This loads the export.pkl file.    \n    learn = load_learner ('../input/train-and-create-test-pkl-file/test.pkl')\n    \n    #This predicts the data from the train dataset and the validation dataset.\n    predictionIndex1= []\n    num = len (dls.train_ds)\n    \n    for i in range(num):\n        predictionIndex1.append (learn.predict(dls.train_ds[i][0]))\n    \n    singlepredictionIndex1 = []\n    num = len(predictionIndex1)\n\n    for i in range(num):\n        singlepredictionIndex1.append (predictionIndex1[i][0])\n    \n    prediction_df1 = dls.train_ds.items\n    \n    prediction_df1 = prediction_df1.assign(Prediction=singlepredictionIndex1)\n    \n        \n    predictionIndex2= []\n    num = len (dls.valid_ds)\n    \n    for i in range(num):\n        predictionIndex2.append (learn.predict(dls.valid_ds[i][0]))\n    \n    singlepredictionIndex2 = []\n    num = len(predictionIndex2)\n\n    for i in range(num):\n        singlepredictionIndex2.append (predictionIndex2[i][0])\n    \n    prediction_df2 = dls.valid_ds.items\n    \n    prediction_df2 = prediction_df2.assign(Prediction=singlepredictionIndex2)\n    \n    #Append and order the predictions to prepare the dataframe to be exported.\n    prediction_df = prediction_df1.append(prediction_df2, ignore_index=False)\n    \n    prediction_df = prediction_df.sort_index (ascending = True)\n    \n    prediction_df = prediction_df.reset_index()\n    \n    prediction_df = prediction_df[['image_id', 'Prediction']]\n    \n    prediction_df = prediction_df.rename({'Prediction':'isup_grade'}, axis=1)\n    \n    #Export to .csv.\n    prediction_df.to_csv ('submission.csv', index = False)\n    \n\n\nelse:\n    #File to commit so notebook can access the test data.\n    sub_df.to_csv(\"submission.csv\", index=False)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Works Cited"},{"metadata":{},"cell_type":"markdown","source":"Amrit Virdee. \"Fastai2 | Balanced | Stratified | Submission ✔\" Kaggle, June 30, 2020, https://www.kaggle.com/avirdee/fastai2-balanced-stratified-submission.\n\nPAB97. “Better image tiles - Removing white spaces.” Kaggle, 22 May 2020, www.kaggle.com/rftexas/better-image-tiles-removing-white-spaces.\n\n“Prostate CANcer GraDe Assessment (PANDA) Challenge.” Kaggle, www.kaggle.com/c/prostate-cancer-grade-assessment/overview/description.\n\nrmicrobe. “Microanatomy of the Prostate.” Kaggle, 11 June 2020, www.kaggle.com/rmicrobe/microanatomy-of-the-prostate.\n\nZenify. “Let's Enhance the Images!” Kaggle, 03 May 2020, www.kaggle.com/debanga/let-s-enhance-the-images."}],"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}