{"cells":[{"metadata":{},"cell_type":"markdown","source":"Dataset available here: https://www.kaggle.com/rohitsingh9990/image-mask-overlay-512x512"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport openslide\nimport matplotlib.pyplot as plt\nfrom PIL import Image\nimport cv2\nfrom tqdm.notebook import tqdm\nimport skimage.io\nimport PIL\nfrom skimage.transform import resize, rescale","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Load dataframe"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/prostate-cancer-grade-assessment/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_dir = '/kaggle/input/prostate-cancer-grade-assessment/train_images/'\nmask_dir = '/kaggle/input/prostate-cancer-grade-assessment/train_label_masks/'\nimages = os.listdir(mask_dir)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Start here"},{"metadata":{"trusted":true},"cell_type":"code","source":"def overlay_mask_on_slide(image_id, center='radboud', alpha=0.8, max_size=(800, 800)):\n    \"\"\"Show a mask overlayed on a slide.\"\"\"\n    \n    \n    slide = openslide.OpenSlide(os.path.join(data_dir, f'{image_id}.tiff'))\n    mask = openslide.OpenSlide(os.path.join(mask_dir, f'{image_id}_mask.tiff'))\n    slide_data = slide.read_region((0,0), slide.level_count - 1, slide.level_dimensions[-1])\n    mask_data = mask.read_region((0,0), mask.level_count - 1, mask.level_dimensions[-1])\n    mask_data = mask_data.split()[0]\n        \n        \n    # Create alpha mask\n    alpha_int = int(round(255*alpha))\n    if center == 'radboud':\n        alpha_content = np.less(mask_data.split()[0], 2).astype('uint8') * alpha_int + (255 - alpha_int)\n    elif center == 'karolinska':\n        alpha_content = np.less(mask_data.split()[0], 1).astype('uint8') * alpha_int + (255 - alpha_int)\n\n    alpha_content = PIL.Image.fromarray(alpha_content)\n    preview_palette = np.zeros(shape=768, dtype=int)\n\n    if center == 'radboud':\n        # Mapping: {0: background, 1: stroma, 2: benign epithelium, 3: Gleason 3, 4: Gleason 4, 5: Gleason 5}\n        preview_palette[0:18] = (np.array([0, 0, 0, 0.5, 0.5, 0.5, 0, 1, 0, 1, 1, 0.7, 1, 0.5, 0, 1, 0, 0]) * 255).astype(int)\n    elif center == 'karolinska':\n        # Mapping: {0: background, 1: benign, 2: cancer}\n        preview_palette[0:9] = (np.array([0, 0, 0, 0, 1, 0, 1, 0, 0]) * 255).astype(int)\n\n    mask_data.putpalette(data=preview_palette.tolist())\n    mask_rgb = mask_data.convert(mode='RGB')\n    overlayed_image = PIL.Image.composite(image1=slide_data, image2=mask_rgb, mask=alpha_content)\n    overlayed_image.thumbnail(size=max_size, resample=0)\n    \n    slide.close()\n    mask.close()   \n          \n    return overlayed_image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mkdir train_overlay_images","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"save_dir = \"train_overlay_images/\"\nos.makedirs(save_dir, exist_ok=True)\n\n\nfor img_id in tqdm(images[:5]):\n    img_id = img_id.replace('_mask.tiff', '')\n    save_path = save_dir + img_id + '.png'\n    provider = train[train.image_id == img_id]['data_provider'].values[0]\n    overlay = overlay_mask_on_slide(img_id, center = provider)\n    img = cv2.cvtColor(np.array(overlay), cv2.COLOR_RGB2BGR)\n    img = cv2.resize(img, (512, 512))\n    cv2.imwrite(save_path, img)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!tar -czf train_overlay_images.tar.gz train_overlay_images/*.png","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"If you like this kernel also visit following kernels:\n* https://www.kaggle.com/xhlulu/panda-resize-and-save-train-data\n* For EDA: https://www.kaggle.com/rohitsingh9990/panda-eda-better-visualization-simple-baseline\n* For ResNext Inference: https://www.kaggle.com/rohitsingh9990/panda-resnext-inference"},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}