Deep-Learning-Musculoskel / Git / [ffcb78] /Preprocessing Medical Data Pipeline/main.ipynb

Models:
JoelW/
Deep-Learning-Musculoskel
Downloads: 1
[ffcb78]: / Preprocessing Medical Data Pipeline / main.ipynb
History
Download this file
1695 lines (1694 with data), 413.2 kB

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Environment and Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Libraries\n",
    "import cv2\n",
    "import os\n",
    "import glob\n",
    "import warnings\n",
    "import numpy as np\n",
    "import SimpleITK as sitk\n",
    "import matplotlib.pyplot as plt\n",
    "# os.environ['PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION'] = 'python'\n",
    "from random import randint\n",
    "from tqdm import tqdm\n",
    "\n",
    "# import keras.api._v2.keras as keras\n",
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "# from tensorflow.keras import layers\n",
    "from keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D, Concatenate, BatchNormalization, Activation, Conv2DTranspose, concatenate, Dropout\n",
    "from keras.preprocessing.image import ImageDataGenerator\n",
    "from sklearn.model_selection import train_test_split\n",
    "from keras.models import Model, load_model\n",
    "from keras.optimizers import Adam\n",
    "from keras.callbacks import ModelCheckpoint\n",
    "from scipy.spatial.distance import directed_hausdorff\n",
    "\n",
    "if False:\n",
    "  # Google drive\n",
    "  from google.colab import drive\n",
    "  drive.mount('/content/drive')\n",
    "\n",
    "  # WD for Data\n",
    "  os.getcwd()\n",
    "  os.chdir('/content/drive/MyDrive/Colab Notebooks')\n",
    "\n",
    "  # GPU\n",
    "  device_name = tf.test.gpu_device_name()\n",
    "  if device_name != '/device:GPU:0':\n",
    "    raise SystemError('GPU device not found')\n",
    "  print('Found GPU at: {}'.format(device_name))\n",
    "\n",
    "  # TPU\n",
    "  # resolver = tf.distribute.cluster_resolver.TPUClusterResolver(tpu='')\n",
    "  # tf.config.experimental_connect_to_cluster(resolver)\n",
    "  # # This is the TPU initialization code that has to be at the beginning.\n",
    "  # tf.tpu.experimental.initialize_tpu_system(resolver)\n",
    "  # print(\"All devices: \", tf.config.list_logical_devices('TPU'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(581, 512, 512, 1)\n",
      "Not Augmented:  [0. 1. 3.]\n",
      "Augmented:  [0. 1. 2. 3.]\n"
     ]
    }
   ],
   "source": [
    "import nibabel as nib\n",
    "import numpy as np\n",
    "\n",
    "def find_unique_numbers(arr):\n",
    "    unique_numbers = np.unique(arr)\n",
    "    return unique_numbers\n",
    "\n",
    "\n",
    "nii_img_scan = nib.load(\"D:/MRI - Tairawhiti (User POV)/nnUNet Data/multiclass_masks/msk_004.nii.gz\")\n",
    "nii_img_scan_aug = nib.load(\"D:/MRI - Tairawhiti (User POV)/nnUNet Data/multiclass_masks/msk_004_aug0.nii.gz\")\n",
    "\n",
    "scan_data = nii_img_scan.get_fdata()\n",
    "scan_aug_data = nii_img_scan_aug.get_fdata()\n",
    "print(scan_aug_data.shape)\n",
    "\n",
    "# np.savetxt('scan.txt', scan_data[450,:,:,0], fmt=\"%d\", delimiter=\",\")\n",
    "# np.savetxt('scan_aug.txt', scan_aug_data[450,:,:,0], fmt=\"%d\", delimiter=\",\")\n",
    "\n",
    "scan_data = scan_data[450,:,:,0]\n",
    "unique_numbers = find_unique_numbers(scan_data)\n",
    "print('Not Augmented: ', unique_numbers)\n",
    "\n",
    "scan_aug_data = scan_aug_data[450,:,:,0]\n",
    "unique_numbers = find_unique_numbers(scan_aug_data)\n",
    "print('Augmented: ', unique_numbers)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['1_RR_fibula_15A.nii', '1_R_femur_15A.nii', '1_R_tibia_15A.nii']\n"
     ]
    }
   ],
   "source": [
    "# paitent_id = segmasks_fnames[0]\n",
    "import os \n",
    "scan_data_folders = ['1_AutoBind_WaterWATER_450_15A']\n",
    "paitent_id = (scan_data_folders[0].split('_'))[-1]\n",
    "scans_path = 'D:/MRI - Tairawhiti (User POV)'\n",
    "segmasks = []\n",
    "files = os.listdir(('{}/Raw NIFITI Segmentation Masks (3D Slicer Output)').format(scans_path))\n",
    "for file in files:\n",
    "    file_id = file.split('_')[-1]\n",
    "    file_id = file_id.split('.')[0]\n",
    "    if (file_id == paitent_id):\n",
    "        segmasks.append(file)\n",
    "print(segmasks)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Preprocessing Pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------------\n",
      "Loading and preprocessing training data...\n",
      "------------------------------\n",
      "Patient Scan Data Folders Included in Run:  ['6_AutoBindWATER_650_9B']\n",
      "\n",
      "\n",
      "Segmentation Mask:  6_RR_fibula_9B\n",
      "Patient Scan Data:  6_AutoBindWATER_650_9B\n",
      "AOI Slice Start:  745\n",
      "AOI Slice End:  958\n",
      "AOI Slice Range:  214\n",
      "\n",
      "\n",
      "Scans Normalized! [0-1]\n",
      "Masks Binarised! [0,1]\n",
      "\n",
      "\n",
      "Training Scans Input Shape:  (1015, 512, 512, 1)\n",
      "Training Masks Input Shape:  (1015, 512, 512, 1)\n",
      "Conversion to NIfTI complete with shape:  (1015, 512, 512, 1)\n",
      "\n",
      "\n",
      "Successfully Exported Preprocessed Data!\n",
      "Regions of Interest for Segmentation:  ['FEMUR', 'FIBULA', 'TIBIA']\n",
      "Number of Segmentation Classes:  3\n",
      "(467, 289, 317, 0)\n",
      "(958, 331, 363, 0)\n",
      "AOI Slice Start (Final with Thresholding):  447\n",
      "AOI Slice End (Final with Thresholding):  978\n",
      "Final Training Scans Input Shape:  (531, 512, 512, 1)\n",
      "Final Training Masks Input Shape:  (531, 512, 512, 1)\n",
      "\n",
      "\n",
      "MSK Multiclass Mask Made Using ['FEMUR', 'FIBULA', 'TIBIA'], Saved To D:/MRI - Tairawhiti/nnUNet Data/multiclass_masks/msk_006.nii.gz, and Region of Interest Slice Thresholding = True !\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\GGPC\\OneDrive\\Desktop\\Part 4 Project\\Part4Project\\preprocessing.py:78: RuntimeWarning: invalid value encountered in true_divide\n",
      "  image2 = image2 / np.max(image2)\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------------\n",
      "Completed Preprocessing Stage!\n",
      "------------------------------\n"
     ]
    }
   ],
   "source": [
    "from preprocessing import preprocessing, VisualValidationMSK\n",
    "from image_preprocessing import image_cropping, uniform_cropping, uniform_resizing\n",
    "from writeout_dataset import Export2CompressedNifiti\n",
    "from MSKMulticlass import CreateMasks4MulticlassMSK\n",
    "\n",
    "print('-'*30)\n",
    "print('Loading and preprocessing training data...')\n",
    "print('-'*30)\n",
    "\n",
    "# \\\\files.auckland.ac.nz\\research\\resmed202100086-tws ----> Address for raw data\n",
    "# \\\\files.auckland.ac.nz\\research\\resabi202200010-Friedlander\n",
    "total_slices_raw_data = 200\n",
    "DataOnlyAOI = False\n",
    "ExportDatasets = True\n",
    "Cropping = False\n",
    "# Only set multiclassSegmentation to True once all the AOI masks are preprocessed or its onto the final AOI\n",
    "multiclassSegmentation = True\n",
    "scans_path = 'D:/MRI - Tairawhiti'\n",
    "\n",
    "# segmasks_fnames = ['1_R_tibia_15A', '2_R_tibia_16A', '3_R_tibia_4A', '4_R_tibia_5A', '5_R_tibia_8A', '6_R_tibia_9B', '7_R_tibia_10B', '8_R_tibia_12A', '9_R_tibia_11A', '10_R_tibia_13A']\n",
    "# segmasks_fnames = ['1_R_femur_15A', '2_R_femur_16A', '3_R_femur_4A', '4_R_femur_5A', '5_R_femur_8A', '6_R_femur_9B']\n",
    "# segmasks_fnames = ['1_RR_fibula_15A', '2_RR_fibula_16A', '3_RR_fibula_4A', '4_RR_fibula_5A', '5_RR_fibula_8A', '6_RR_fibula_9B']\n",
    "# scan_data_folders = ['1_AutoBind_WaterWATER_450_15A', '2_AutoBindWATER_450_16A', '3_AutoBindWATER_650_4A', '4_AutoBindWATER_750_5A', '5_AutoBindWATER_1050_8A', '6_AutoBindWATER_650_9B', '7_AutoBindWATER_450_10B',\n",
    "#                     '8_AutoBindWATER_450_12A', '9_AutoBindWATER_550_11A', '10_AutoBindWATER_450_13A']\n",
    "\n",
    "segmasks_fnames = ['6_RR_fibula_9B']\n",
    "scan_data_folders = ['6_AutoBindWATER_650_9B']\n",
    "colab_fname = ['FIBULA_006']\n",
    "\n",
    "imgs_train, imgs_mask_train, median_aoi_index = preprocessing(scans_path, segmasks_fnames, scan_data_folders, total_slices_raw_data, DataOnlyAOI)\n",
    "\n",
    "if (Cropping == True):\n",
    "    imgs_train, imgs_mask_train = image_cropping(imgs_train, top = 56, bottom = 56, left = 56, right = 56), image_cropping(imgs_mask_train, top = 56, bottom = 56, left = 56, right = 56)\n",
    "    print(\"\\n\")\n",
    "    print('Preprocessed Final Training Image Input Shape (After Image Preprocessing): ', imgs_train.shape)\n",
    "    print('Preprocessed Final Training Mask Input Shape (After Image Preprocessing): ', imgs_mask_train.shape)\n",
    "\n",
    "if (ExportDatasets == True):\n",
    "    Export2CompressedNifiti(imgs_train, scans_path, colab_fname, imgs_mask_train)\n",
    "\n",
    "if (multiclassSegmentation == True):\n",
    "    # User Input\n",
    "    individual_mask_directory = 'D:/MRI - Tairawhiti/nnUNet Data/masks'\n",
    "    multiclass_mask_output_dir = 'D:/MRI - Tairawhiti/nnUNet Data/multiclass_masks'\n",
    "    scan_dir = 'D:/MRI - Tairawhiti/nnUNet Data/scans'\n",
    "    \n",
    "    TIBIA_encoding = 1\n",
    "    FEMUR_encoding = 2\n",
    "    FIBULA_encoding = 3\n",
    "    mask_index = int((colab_fname[0].split('_'))[1])\n",
    "    AOIThresholding = True\n",
    "\n",
    "    CreateMasks4MulticlassMSK(scan_dir, individual_mask_directory, mask_index, TIBIA_encoding, FEMUR_encoding, FIBULA_encoding, multiclass_mask_output_dir, AOIThresholding)\n",
    "\n",
    "\n",
    "# Validate Scans & Masks (2D Slice)\n",
    "if (multiclass_mask_output_dir != None):\n",
    "    VisualValidationMSK(colab_fname, 400, 400, multiclass_mask_output_dir, mask_index)\n",
    "else:\n",
    "    VisualValidationMSK(colab_fname, 400, 400, False, mask_index)\n",
    "\n",
    "print('-'*30)\n",
    "print('Completed Preprocessing Stage!')\n",
    "print('-'*30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Multi-Class Segmentation Task Data Preparation!\n",
      "Regions of Interest for Segmentation:  ['FEMUR', 'FIBULA', 'PELVIS', 'TIBIA']\n",
      "Number of Segmentation Classes:  4\n",
      "(21, 160, 44, 0)\n",
      "(854, 104, 177, 0)\n",
      "AOI Slice Start (Final with Thresholding):  21\n",
      "AOI Slice End (Final with Thresholding):  854\n",
      "Final Training Scans Input Shape:  (833, 277, 230, 1)\n",
      "Final Training Masks Input Shape:  (833, 277, 230, 1)\n",
      "\n",
      "\n",
      "MSK Multiclass Mask Made Using ['FEMUR', 'FIBULA', 'PELVIS', 'TIBIA'], Saved To D:/MRI - Friedlander/nnUNet Data/multiclass_masks/msk_001.nii.gz, and Region of Interest Slice Thresholding = True !\n",
      "Regions of Interest for Segmentation:  ['FEMUR', 'FIBULA', 'PELVIS', 'TIBIA']\n",
      "Number of Segmentation Classes:  4\n",
      "(30, 154, 51, 0)\n",
      "(796, 115, 174, 0)\n",
      "AOI Slice Start (Final with Thresholding):  30\n",
      "AOI Slice End (Final with Thresholding):  796\n",
      "Final Training Scans Input Shape:  (766, 260, 232, 1)\n",
      "Final Training Masks Input Shape:  (766, 260, 232, 1)\n",
      "\n",
      "\n",
      "MSK Multiclass Mask Made Using ['FEMUR', 'FIBULA', 'PELVIS', 'TIBIA'], Saved To D:/MRI - Friedlander/nnUNet Data/multiclass_masks/msk_002.nii.gz, and Region of Interest Slice Thresholding = True !\n",
      "Regions of Interest for Segmentation:  ['FEMUR', 'FIBULA', 'PELVIS', 'TIBIA']\n",
      "Number of Segmentation Classes:  4\n",
      "(11, 109, 22, 0)\n",
      "(915, 155, 81, 0)\n",
      "AOI Slice Start (Final with Thresholding):  11\n",
      "AOI Slice End (Final with Thresholding):  915\n",
      "Final Training Scans Input Shape:  (904, 216, 120, 1)\n",
      "Final Training Masks Input Shape:  (904, 216, 120, 1)\n",
      "\n",
      "\n",
      "MSK Multiclass Mask Made Using ['FEMUR', 'FIBULA', 'PELVIS', 'TIBIA'], Saved To D:/MRI - Friedlander/nnUNet Data/multiclass_masks/msk_003.nii.gz, and Region of Interest Slice Thresholding = True !\n",
      "Regions of Interest for Segmentation:  ['FEMUR', 'FIBULA', 'PELVIS', 'TIBIA']\n",
      "Number of Segmentation Classes:  4\n",
      "(42, 121, 67, 0)\n",
      "(689, 130, 78, 0)\n",
      "AOI Slice Start (Final with Thresholding):  42\n",
      "AOI Slice End (Final with Thresholding):  689\n",
      "Final Training Scans Input Shape:  (647, 217, 118, 1)\n",
      "Final Training Masks Input Shape:  (647, 217, 118, 1)\n",
      "\n",
      "\n",
      "MSK Multiclass Mask Made Using ['FEMUR', 'FIBULA', 'PELVIS', 'TIBIA'], Saved To D:/MRI - Friedlander/nnUNet Data/multiclass_masks/msk_004.nii.gz, and Region of Interest Slice Thresholding = True !\n",
      "Regions of Interest for Segmentation:  ['FEMUR', 'FIBULA', 'PELVIS', 'TIBIA']\n",
      "Number of Segmentation Classes:  4\n",
      "(124, 120, 40, 0)\n",
      "(922, 161, 88, 0)\n",
      "AOI Slice Start (Final with Thresholding):  124\n",
      "AOI Slice End (Final with Thresholding):  922\n",
      "Final Training Scans Input Shape:  (798, 218, 120, 1)\n",
      "Final Training Masks Input Shape:  (798, 218, 120, 1)\n",
      "\n",
      "\n",
      "MSK Multiclass Mask Made Using ['FEMUR', 'FIBULA', 'PELVIS', 'TIBIA'], Saved To D:/MRI - Friedlander/nnUNet Data/multiclass_masks/msk_005.nii.gz, and Region of Interest Slice Thresholding = True !\n"
     ]
    },
    {
     "ename": "",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31mThe Kernel crashed while executing code in the the current cell or a previous cell. Please review the code in the cell(s) to identify a possible cause of the failure. Click <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. View Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
     ]
    }
   ],
   "source": [
    "import nibabel as nib\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from skimage.transform import resize\n",
    "from MSKMulticlass import CreateMasks4MulticlassMSK\n",
    "\n",
    "def superimpose_images(image1, image2):\n",
    "    image1 = image1 / np.max(image1)\n",
    "    image2 = image2 / np.max(image2)\n",
    "    alpha = 0.5\n",
    "    superimposed_image = alpha * image1 + (1 - alpha) * image2\n",
    "    return superimposed_image\n",
    "\n",
    "def uniform_resizing(images, new_size):\n",
    "    \"\"\"\n",
    "    Applies uniform resizing to an array of images. ### bicubic_interpolation\n",
    "\n",
    "    Parameters:\n",
    "        images (numpy.ndarray): Input array of images with shape (x, 512, 512, 1).\n",
    "        new_size (tuple or int): The desired size of the resized images. If it's an int,\n",
    "                                 the new size will be (new_size, new_size).\n",
    "\n",
    "    Returns:\n",
    "        numpy.ndarray: Array of resized images with shape (x, new_height, new_width, 1).\n",
    "    \"\"\"\n",
    "    x, height, width, _ = images.shape\n",
    "\n",
    "    if isinstance(new_size, int):\n",
    "        new_height, new_width = new_size, new_size\n",
    "    elif isinstance(new_size, tuple) and len(new_size) == 2:\n",
    "        new_height, new_width = new_size\n",
    "    else:\n",
    "        raise ValueError(\"Invalid new_size argument. It should be an int or a tuple of two ints.\")\n",
    "\n",
    "    resized_images = np.zeros((x, new_height, new_width, 1))\n",
    "\n",
    "    for i in range(x):\n",
    "        resized_images[i, ..., 0] = resize(images[i, ..., 0], (new_height, new_width), mode='reflect', order=1)\n",
    "        # resized_images[i, ..., 0] = resize(images[i, ..., 0], (new_height, new_width), mode='constant', preserve_range=True)\n",
    "\n",
    "    return resized_images\n",
    "\n",
    "\n",
    "scans_path = 'D:/MRI - Friedlander'\n",
    "\n",
    "\n",
    "        \n",
    "\n",
    "# slice = 750\n",
    "# aoi = 'FEMUR'\n",
    "\n",
    "# tibia_PLB_02 = nib.load(('{}/{}/{}/{}_001.nii.gz').format(scans_path, 'nnUNet Data/masks', aoi, aoi))\n",
    "# tibia_PLB_02_data = tibia_PLB_02.get_fdata()\n",
    "# print(tibia_PLB_02_data.shape)\n",
    "\n",
    "# PLB_02 = nib.load(('{}/{}/msk_001.nii.gz').format(scans_path, 'nnUNet Data/scans'))\n",
    "# PLB_02_data = PLB_02.get_fdata()\n",
    "# # nii_img_mask = nib.Nifti1Image(PLB_02_data, affine=np.eye(4))\n",
    "# # output_file_path = ('D:/MRI - Tairawhiti/PLB-02.nii.gz')\n",
    "# # nib.save(nii_img_mask, output_file_path)   \n",
    "# print(PLB_02_data.shape)\n",
    "\n",
    "# image1 = PLB_02_data[:,slice,:]\n",
    "# image2 = tibia_PLB_02_data[:,slice,:]\n",
    "# superimposed_image = superimpose_images(image1, image2)\n",
    "\n",
    "\n",
    "# plt.imshow(PLB_02_data[:,slice,:], cmap='gray')\n",
    "# plt.axis('off')\n",
    "# plt.show()\n",
    "\n",
    "# plt.imshow(tibia_PLB_02_data[:,slice,:], cmap='gray')\n",
    "# plt.axis('off')\n",
    "# plt.show()\n",
    "\n",
    "# plt.imshow(superimposed_image, cmap='gray')\n",
    "# plt.axis('off')\n",
    "# plt.show()\n",
    "\n",
    "\n",
    "# PLB_02_data_512 = np.expand_dims(PLB_02_data, axis = -1)\n",
    "# PLB_02_data_512 = PLB_02_data_512.transpose(1, 0, 2, 3)\n",
    "# PLB_02_data_512 = uniform_resizing(PLB_02_data_512, 256)\n",
    "\n",
    "# tibia_PLB_02_data_512 = np.expand_dims(tibia_PLB_02_data, axis = -1)\n",
    "# tibia_PLB_02_data_512 = tibia_PLB_02_data_512.transpose(1, 0, 2, 3)\n",
    "# tibia_PLB_02_data_512 = uniform_resizing(tibia_PLB_02_data_512, 256)\n",
    "\n",
    "# plt.imshow(PLB_02_data_512[slice,:,:,0], cmap='gray')\n",
    "# plt.axis('off')\n",
    "# plt.show()\n",
    "\n",
    "# plt.imshow(tibia_PLB_02_data_512[slice,:,:,0], cmap='gray')\n",
    "# plt.axis('off')\n",
    "# plt.show()\n",
    "\n",
    "# superimposed_image = superimpose_images(PLB_02_data_512[slice,:,:,0], tibia_PLB_02_data_512[slice,:,:,0])\n",
    "\n",
    "# plt.imshow(superimposed_image, cmap='gray')\n",
    "# plt.axis('off')\n",
    "# plt.show()\n",
    "\n",
    "# nii_img_mask = nib.Nifti1Image(PLB_02_data_512, affine=np.eye(4))\n",
    "# output_file_path = ('D:/MRI - Tairawhiti/PLB_02_data_512.nii.gz')\n",
    "# nib.save(nii_img_mask, output_file_path)  \n",
    "\n",
    "# nii_img_mask = nib.Nifti1Image(tibia_PLB_02_data_512, affine=np.eye(4))\n",
    "# output_file_path = ('D:/MRI - Tairawhiti/tibia_PLB_02_data_512.nii.gz')\n",
    "# nib.save(nii_img_mask, output_file_path)   \n",
    "\n",
    "individual_mask_directory = ('{}/nnUNet Data/masks').format(scans_path)\n",
    "multiclass_mask_output_dir = ('{}/nnUNet Data/multiclass_masks').format(scans_path)\n",
    "scan_dir = ('{}/nnUNet Data/scans').format(scans_path)\n",
    "mask_index = [1,2,3,4,5]\n",
    "\n",
    "TIBIA_encoding = 1\n",
    "FEMUR_encoding = 2\n",
    "FIBULA_encoding = 3\n",
    "PELVIS_encoding = 4\n",
    "AOIThresholding = True\n",
    "FriedLanderDataset = True\n",
    "\n",
    "print('Multi-Class Segmentation Task Data Preparation!')\n",
    "\n",
    "for i in range (len(mask_index)):\n",
    "    CreateMasks4MulticlassMSK(scan_dir, individual_mask_directory, mask_index[i], TIBIA_encoding, FEMUR_encoding, FIBULA_encoding, PELVIS_encoding, multiclass_mask_output_dir, AOIThresholding, FriedLanderDataset)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "PLB_02 = nib.load(('{}/{}/msk_001.nii.gz').format(scans_path, 'nnUNet Data/scans'))\n",
    "PLB_02_data = PLB_02.get_fdata()\n",
    "\n",
    "len(PLB_02_data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(457, 512, 512, 1)\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import nibabel as nib\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "def superimpose_images(image1, image2):\n",
    "    image1 = image1 / np.max(image1)\n",
    "    image2 = image2 / np.max(image2)\n",
    "    alpha = 0.5\n",
    "    superimposed_image = alpha * image1 + (1 - alpha) * image2\n",
    "    return superimposed_image\n",
    "\n",
    "\n",
    "slice_idx = 500\n",
    "\n",
    "# nii_img_scan = nib.load('D:/MRI - Tairawhiti/nnUNet Data/scans/FEMUR_002.nii.gz')\n",
    "# nii_img_mask = nib.load('D:/MRI - Tairawhiti/nnUNet Data/masks/FEMUR/FEMUR_002.nii.gz')\n",
    "# mask_data = nii_img_mask.get_fdata()\n",
    "# scan_data = nii_img_scan.get_fdata()\n",
    "\n",
    "# image1 = scan_data[slice_idx, :, :, :]\n",
    "# image2 = mask_data[slice_idx, :, :, :]\n",
    "# superimposed_image = superimpose_images(image1, image2)\n",
    "# plt.imshow(superimposed_image, cmap='gray')\n",
    "# plt.axis('off')\n",
    "# plt.show()\n",
    "\n",
    "nii_img_mask = nib.load('D:/MRI - Tairawhiti (User POV)/nnUNet Data/scans/msk_001.nii.gz')\n",
    "mask_data = nii_img_mask.get_fdata()\n",
    "print(mask_data.shape)\n",
    "image3 = mask_data[400, :, :, 0]\n",
    "plt.imshow(image3, cmap='gray')\n",
    "plt.axis('off')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "FIBULA_020\n"
     ]
    }
   ],
   "source": [
    "def transform_string(input_string):\n",
    "    parts = input_string.split('_')\n",
    "    \n",
    "    if len(parts) < 2:\n",
    "        return None\n",
    "    \n",
    "    prefix = parts[-2].upper()\n",
    "    \n",
    "    try:\n",
    "        number_part = int(parts[0])\n",
    "    except ValueError:\n",
    "        return None\n",
    "    \n",
    "    new_string = f'{prefix}_{number_part:03d}'\n",
    "    return new_string\n",
    "\n",
    "input_string = '20_RR_fibula_100C'\n",
    "output_string = transform_string(input_string)\n",
    "print(output_string)  # Output: 'FIBULA_006'\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Aligning the Compressed Nifti Scans & Masks (Coordinate System, Direction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tibia_009\n"
     ]
    },
    {
     "ename": "OrientationError",
     "evalue": "Data array has fewer dimensions than orientation",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mOrientationError\u001b[0m                          Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[5], line 70\u001b[0m\n\u001b[0;32m     68\u001b[0m nii_file_path \u001b[39m=\u001b[39m (\u001b[39m'\u001b[39m\u001b[39mD:/MRI - Tairawhiti/nnUNet Data/scans/\u001b[39m\u001b[39m{}\u001b[39;00m\u001b[39m.nii.gz\u001b[39m\u001b[39m'\u001b[39m)\u001b[39m.\u001b[39mformat(fname)\n\u001b[0;32m     69\u001b[0m nii_img \u001b[39m=\u001b[39m nib\u001b[39m.\u001b[39mload(nii_file_path)\n\u001b[1;32m---> 70\u001b[0m reoriented_img \u001b[39m=\u001b[39m nib\u001b[39m.\u001b[39;49morientations\u001b[39m.\u001b[39;49mapply_orientation(nii_img, target_orientation)\n\u001b[0;32m     71\u001b[0m output_file_path \u001b[39m=\u001b[39m (\u001b[39m'\u001b[39m\u001b[39mD:/MRI - Tairawhiti/nnUNet Data/scans/\u001b[39m\u001b[39m{}\u001b[39;00m\u001b[39m.nii.gz\u001b[39m\u001b[39m'\u001b[39m)\u001b[39m.\u001b[39mformat(fname)\n\u001b[0;32m     72\u001b[0m nib\u001b[39m.\u001b[39msave(modified_nii_img, output_file_path)\n",
      "File \u001b[1;32mc:\\Users\\GGPC\\anaconda3\\envs\\Py39-CNN\\lib\\site-packages\\nibabel\\orientations.py:155\u001b[0m, in \u001b[0;36mapply_orientation\u001b[1;34m(arr, ornt)\u001b[0m\n\u001b[0;32m    153\u001b[0m n \u001b[39m=\u001b[39m ornt\u001b[39m.\u001b[39mshape[\u001b[39m0\u001b[39m]\n\u001b[0;32m    154\u001b[0m \u001b[39mif\u001b[39;00m t_arr\u001b[39m.\u001b[39mndim \u001b[39m<\u001b[39m n:\n\u001b[1;32m--> 155\u001b[0m     \u001b[39mraise\u001b[39;00m OrientationError(\u001b[39m'\u001b[39m\u001b[39mData array has fewer dimensions than orientation\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[0;32m    156\u001b[0m \u001b[39m# no coordinates can be dropped for applying the orientations\u001b[39;00m\n\u001b[0;32m    157\u001b[0m \u001b[39mif\u001b[39;00m np\u001b[39m.\u001b[39many(np\u001b[39m.\u001b[39misnan(ornt[:, \u001b[39m0\u001b[39m])):\n",
      "\u001b[1;31mOrientationError\u001b[0m: Data array has fewer dimensions than orientation"
     ]
    }
   ],
   "source": [
    "import nibabel as nib\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "fnames= ['Tibia_009', 'Tibia_010', 'Tibia_015']\n",
    "translate_y = False\n",
    "flip_direction = False\n",
    "\n",
    "for fname in fnames:\n",
    "    print(fname)\n",
    "    \n",
    "    nii_file_path = ('D:/MRI - Tairawhiti/nnUNet Data/masks/{}.nii.gz').format(fname)\n",
    "    nii_img = nib.load(nii_file_path)\n",
    "    affine_matrix = nii_img.affine\n",
    "    direction_mask = affine_matrix[:3, :3]\n",
    "    origin_coordinates_mask = affine_matrix[:3, 3]\n",
    "    # print(\"Mask Origin Coordinates:\", origin_coordinates_mask)\n",
    "    # print(\"Mask Direction Matrix:\", direction)\n",
    "    # print('\\n')\n",
    "    \n",
    "    nii_file_path = ('D:/MRI - Tairawhiti/nnUNet Data/scans/{}.nii.gz').format(fname)\n",
    "    nii_img = nib.load(nii_file_path)\n",
    "    affine_matrix = nii_img.affine\n",
    "    direction_scan = affine_matrix[:3, :3]\n",
    "    origin_coordinates_scan = affine_matrix[:3, 3]\n",
    "    # print(\"Scan Origin Coordinates:\", origin_coordinates)\n",
    "    # print(\"Scan Direction Matrix:\", direction)\n",
    "    # print('\\n')\n",
    "\n",
    "    if (translate_y == True):\n",
    "        nii_file_path = ('D:/MRI - Tairawhiti/nnUNet Data/scans/{}.nii.gz').format(fname)\n",
    "        nii_img = nib.load(nii_file_path)\n",
    "        affine_matrix = nii_img.affine\n",
    "\n",
    "        affine_matrix[:3, 3] = origin_coordinates_mask\n",
    "        modified_nii_img = nib.Nifti1Image(nii_img.get_fdata(), affine_matrix)\n",
    "\n",
    "        output_file_path = ('D:/MRI - Tairawhiti/nnUNet Data/scans/{}.nii.gz').format(fname)\n",
    "        nib.save(modified_nii_img, output_file_path)\n",
    "        # print(\"Scan Origin coordinates modified and file rewritten!\")\n",
    "\n",
    "        nii_img = nib.load(nii_file_path)\n",
    "        affine_matrix = nii_img.affine\n",
    "        origin_coordinates_scan = affine_matrix[:3, 3]\n",
    "        # print(\"Scan Origin Coordinates (Modified):\", origin_coordinates)\n",
    "        # print('\\n')\n",
    "\n",
    "    if (flip_direction == True):\n",
    "        nii_file_path = ('D:/MRI - Tairawhiti/nnUNet Data/scans/{}.nii.gz').format(fname)\n",
    "        nii_img = nib.load(nii_file_path)\n",
    "        direction = affine_matrix[:3, :3]\n",
    "\n",
    "        affine_matrix[:3, :3] = direction_mask\n",
    "        modified_nii_img = nib.Nifti1Image(nii_img.get_fdata(), affine_matrix)\n",
    "\n",
    "        output_file_path = ('D:/MRI - Tairawhiti/nnUNet Data/scans/{}.nii.gz').format(fname)\n",
    "        nib.save(modified_nii_img, output_file_path)\n",
    "        # print(\"Scan direction modified and file rewritten!\")\n",
    "\n",
    "        nii_img = nib.load(nii_file_path)\n",
    "        affine_matrix = nii_img.affine\n",
    "        direction_scan = affine_matrix[:3, :3]\n",
    "        # print(\"Scan Direction (Modified):\", direction_scan)\n",
    "        # print('\\n')\n",
    "\n",
    "\n",
    "    target_orientation = ('R', 'A', 'S')\n",
    "    nii_file_path = ('D:/MRI - Tairawhiti/nnUNet Data/scans/{}.nii.gz').format(fname)\n",
    "    nii_img = nib.load(nii_file_path)\n",
    "    reoriented_img = nib.orientations.apply_orientation(nii_img, target_orientation)\n",
    "    output_file_path = ('D:/MRI - Tairawhiti/nnUNet Data/scans/{}.nii.gz').format(fname)\n",
    "    nib.save(modified_nii_img, output_file_path)\n",
    "\n",
    "    target_orientation = ('R', 'A', 'S')\n",
    "    nii_file_path = ('D:/MRI - Tairawhiti/nnUNet Data/masks/{}.nii.gz').format(fname)\n",
    "    nii_img = nib.load(nii_file_path)\n",
    "    reoriented_img = nib.orientations.apply_orientation(nii_img, target_orientation)\n",
    "    output_file_path = ('D:/MRI - Tairawhiti/nnUNet Data/masks/{}.nii.gz').format(fname)\n",
    "    nib.save(modified_nii_img, output_file_path)    \n",
    "\n",
    "    if (np.array_equal(np.array(origin_coordinates_scan), np.array(origin_coordinates_mask)) == True):\n",
    "        print(('Mask and Scan Coordinate Systems Matching! ({})').format(fname))\n",
    "    else:\n",
    "        print('ERROR: Mask and Scan Coordinate Systems Mismatch!')\n",
    "    if (np.array_equal(np.array(direction_scan), np.array(direction_mask)) == True):\n",
    "        print(('Mask and Scan Directions Matching! ({})').format(fname)) \n",
    "    else:\n",
    "        print('ERROR: Mask and Scan Direction Mismatch!')\n",
    "    print('\\n')\n",
    "\n",
    "\n",
    "    slice_idx = 100\n",
    "\n",
    "    nii_img = nib.load(('D:/MRI - Tairawhiti/nnUNet Data/scans/{}.nii.gz').format(fname))\n",
    "    nii_data = nii_img.get_fdata()\n",
    "    plt.imshow(nii_data[:, :, slice_idx], cmap='gray')\n",
    "    plt.title('Scan Slice Visualization')\n",
    "    plt.colorbar()\n",
    "    plt.show()\n",
    "\n",
    "    nii_img = nib.load(('D:/MRI - Tairawhiti/nnUNet Data/masks/{}.nii.gz').format(fname))\n",
    "    nii_data = nii_img.get_fdata()\n",
    "    plt.imshow(nii_data[:, :, slice_idx], cmap='gray')\n",
    "    plt.title('Mask Slice Visualization')\n",
    "    plt.colorbar()\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Reversal within each NIfTI complete.\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import pydicom\n",
    "import nibabel as nib\n",
    "import numpy as np\n",
    "\n",
    "fnames = ['3_AutoBindWATER_650_4A', '4_AutoBindWATER_750_5A', '5_AutoBindWATER_1050_8A', '6_AutoBindWATER_650_9B', '7_AutoBindWATER_450_10B']\n",
    "dicom2nifiti = False\n",
    "reverseMasksNifiti = True\n",
    "\n",
    "\n",
    "if (dicom2nifiti == True):\n",
    "    for fname in fnames:\n",
    "        dicom_dir = ('D:/MRI - Tairawhiti/{}').format(fname)\n",
    "        \n",
    "        dicom_files = sorted([f for f in os.listdir(dicom_dir) if f.endswith('.dcm')])\n",
    "        dicom_data = [pydicom.dcmread(os.path.join(dicom_dir, f)) for f in dicom_files]\n",
    "        orientation = dicom_data[0].ImageOrientationPatient\n",
    "        pixel_data = [d.pixel_array for d in dicom_data]\n",
    "\n",
    "        volume = np.stack(pixel_data, axis=-1)\n",
    "\n",
    "        nii_img = nib.Nifti1Image(volume, np.eye(4))\n",
    "\n",
    "        orientation_matrix = np.array(orientation).reshape(2, 3)\n",
    "        affine_matrix = np.eye(4)\n",
    "        affine_matrix[:2, :3] = orientation_matrix\n",
    "\n",
    "        nii_img.set_qform(affine_matrix)\n",
    "\n",
    "        nii_output_path = ('D:/MRI - Tairawhiti/{}.nii.gz').format(fname)\n",
    "        nib.save(nii_img, nii_output_path)\n",
    "\n",
    "        print((\"Conversion complete for {}!\").format(fname))\n",
    "\n",
    "\n",
    "if (reverseMasksNifiti == True):\n",
    "    nii_dir = 'D:/MRI - Tairawhiti/nnUNet Data/masks'\n",
    "\n",
    "    nii_files = sorted([f for f in os.listdir(nii_dir) if f.endswith('.nii.gz')])\n",
    "\n",
    "    output_dir = 'D:/MRI - Tairawhiti/nnUNet Data/masks/idk'\n",
    "    os.makedirs(output_dir, exist_ok=True)\n",
    "\n",
    "    for nii_file in nii_files:\n",
    "        nii_path = os.path.join(nii_dir, nii_file)\n",
    "        nii_img = nib.load(nii_path)\n",
    "\n",
    "        # Get the data array and reverse the order of elements\n",
    "        nii_data = nii_img.get_fdata()\n",
    "        reversed_data = np.flip(nii_data, axis=-1)\n",
    "\n",
    "        # Create a new NIfTI image with the reversed data\n",
    "        reversed_nii_img = nib.Nifti1Image(reversed_data, nii_img.affine)\n",
    "\n",
    "        # Save the reversed NIfTI image\n",
    "        reversed_output_path = os.path.join(output_dir, f\"reversed_{nii_file}\")\n",
    "        nib.save(reversed_nii_img, reversed_output_path)\n",
    "\n",
    "    print(\"Reversal within each NIfTI complete.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Superimposed Mask Visualisation "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.0074625\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from preprocessing import preprocessing\n",
    "import numpy as np\n",
    "import SimpleITK as sitk\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "def superimpose_images(image1, image2):\n",
    "    image1 = image1 / np.max(image1)\n",
    "    image2 = image2 / np.max(image2)\n",
    "    alpha = 0.5\n",
    "    superimposed_image = alpha * image1 + (1 - alpha) * image2\n",
    "    return superimposed_image\n",
    "\n",
    "slice = 200\n",
    "image1 = imgs_train[slice]\n",
    "image2 = imgs_mask_train[slice]\n",
    "superimposed_image = superimpose_images(image1, image2)\n",
    "print(np.mean(image2))\n",
    "plt.imshow(superimposed_image, cmap='gray')\n",
    "plt.axis('off')\n",
    "plt.show()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Data Augmentation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------------\n",
      "Data Augmentation Starting...\n",
      "------------------------------\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 840/840 [00:12<00:00, 65.95it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of Augmentation per Input:  3\n",
      "\n",
      "\n",
      "Shape of Augmented Images:  (2520, 512, 512, 1)\n",
      "Shape of Augmented Masks:  (2520, 512, 512, 1)\n",
      "\n",
      "\n",
      "Shape of Training Image Data (Before):  (840, 512, 512, 1)\n",
      "Shape of Training Image Masks (Before):  (840, 512, 512, 1)\n",
      "\n",
      "\n",
      "Shape of Training Image Data (After):  (3360, 512, 512, 1)\n",
      "Shape of Training Image Masks (After):  (3360, 512, 512, 1)\n",
      "------------------------------\n",
      "Completed Data Augmentation Stage!\n",
      "------------------------------\n"
     ]
    }
   ],
   "source": [
    "from data_augmentation import DataAugmentation\n",
    "\n",
    "print('-'*30)\n",
    "print('Data Augmentation Starting...')\n",
    "print('-'*30)\n",
    "\n",
    "num_augmentations = 3\n",
    "augmented_images_train, augmented_masks_train = DataAugmentation(imgs_train, imgs_mask_train, num_augmentations)\n",
    "\n",
    "augmented_images_train = np.expand_dims(augmented_images_train, axis=-1)\n",
    "augmented_masks_train = np.expand_dims(augmented_masks_train, axis=-1)\n",
    "\n",
    "print('Number of Augmentation per Input: ', num_augmentations)\n",
    "print('\\n')\n",
    "print('Shape of Augmented Images: ', augmented_images_train.shape)\n",
    "print('Shape of Augmented Masks: ', augmented_masks_train.shape)\n",
    "print('\\n')\n",
    "print('Shape of Training Image Data (Before): ', imgs_train.shape)\n",
    "print('Shape of Training Image Masks (Before): ', imgs_mask_train.shape)\n",
    "print('\\n')\n",
    "\n",
    "if True:\n",
    "    imgs_train = np.concatenate((imgs_train, augmented_images_train), axis=0)\n",
    "    imgs_mask_train = np.concatenate((imgs_mask_train, augmented_masks_train), axis=0)\n",
    "\n",
    "print('Shape of Training Image Data (After): ', imgs_train.shape)\n",
    "print('Shape of Training Image Masks (After): ', imgs_mask_train.shape)\n",
    "\n",
    "print('-'*30)\n",
    "print('Completed Data Augmentation Stage!')\n",
    "print('-'*30)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exporting out Labelled Datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------------\n",
      "Exporting Scan & Mask Data...\n",
      "------------------------------\n",
      "------------------------------\n",
      "Completed Exporting Stage!\n",
      "------------------------------\n"
     ]
    }
   ],
   "source": [
    "# Exporting Training Scan and Mask Data\n",
    "from writeout_dataset import WriteOutTextFile, WriteOutImagePNGFiles, ReadInDatasets, ReadInDatasetNPY\n",
    "\n",
    "print('-'*30)\n",
    "print('Exporting Scan & Mask Data...')\n",
    "print('-'*30)\n",
    "\n",
    "# starting_slice = 70\n",
    "# save_directory_data_txt = 'D:/P4P Model Data/txt/Data_Tibia(Collab Sample)'\n",
    "# WriteOutTextFile(imgs_train[:, :, :, 0], save_directory_data_txt, starting_slice)  \n",
    "# save_directory_mask_txt = 'D:/P4P Model Data/txt/Mask_Tibia(Collab Sample)'\n",
    "# WriteOutTextFile(imgs_mask_train[:, :, :, 0], save_directory_mask_txt, starting_slice)   \n",
    "\n",
    "# np.save(\"D:/MRI - Tairawhiti/imgs_train_tibia.npy\", imgs_train)\n",
    "# np.save(\"D:/MRI - Tairawhiti/imgs_mask_train_tibia.npy\", imgs_train)\n",
    "\n",
    "imgs_train_scan_tibia = ReadInDatasetNPY('D:/MRI - Tairawhiti/Model Input Masks Tibia (Google Colab)')\n",
    "\n",
    "print('-'*30)\n",
    "print('Completed Exporting Stage!')\n",
    "print('-'*30)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2DUNet Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define U-Net model\n",
    "def unet_model(input_shape):\n",
    "    inputs = Input(input_shape)\n",
    "\n",
    "    # Encoder\n",
    "    conv1 = Conv2D(64, 3, activation='relu', padding='same')(inputs)\n",
    "    conv1 = Conv2D(64, 3, activation='relu', padding='same')(conv1)\n",
    "    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)\n",
    "\n",
    "    conv2 = Conv2D(128, 3, activation='relu', padding='same')(pool1)\n",
    "    conv2 = Conv2D(128, 3, activation='relu', padding='same')(conv2)\n",
    "    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)\n",
    "\n",
    "    conv3 = Conv2D(256, 3, activation='relu', padding='same')(pool2)\n",
    "    conv3 = Conv2D(256, 3, activation='relu', padding='same')(conv3)\n",
    "    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)\n",
    "\n",
    "    conv4 = Conv2D(512, 3, activation='relu', padding='same')(pool3)\n",
    "    conv4 = Conv2D(512, 3, activation='relu', padding='same')(conv4)\n",
    "    drop4 = Dropout(0.5)(conv4)\n",
    "    pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)\n",
    "\n",
    "    # Bottleneck\n",
    "    conv5 = Conv2D(1024, 3, activation='relu', padding='same')(pool4)\n",
    "    conv5 = Conv2D(1024, 3, activation='relu', padding='same')(conv5)\n",
    "    drop5 = Dropout(0.5)(conv5)\n",
    "\n",
    "    # Decoder\n",
    "    up6 = Conv2D(512, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(drop5))\n",
    "    merge6 = concatenate([drop4, up6], axis=3)\n",
    "    conv6 = Conv2D(512, 3, activation='relu', padding='same')(merge6)\n",
    "    conv6 = Conv2D(512, 3, activation='relu', padding='same')(conv6)\n",
    "\n",
    "    up7 = Conv2D(256, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(conv6))\n",
    "    merge7 = concatenate([conv3, up7], axis=3)\n",
    "    conv7 = Conv2D(256, 3, activation='relu', padding='same')(merge7)\n",
    "    conv7 = Conv2D(256, 3, activation='relu', padding='same')(conv7)\n",
    "\n",
    "    up8 = Conv2D(128, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(conv7))\n",
    "    merge8 = concatenate([conv2, up8], axis=3)\n",
    "    conv8 = Conv2D(128, 3, activation='relu', padding='same')(merge8)\n",
    "    conv8 = Conv2D(128, 3, activation='relu', padding='same')(conv8)\n",
    "\n",
    "    up9 = Conv2D(64, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(conv8))\n",
    "    merge9 = concatenate([conv1, up9], axis=3)\n",
    "    conv9 = Conv2D(64, 3, activation='relu', padding='same')(merge9)\n",
    "    conv9 = Conv2D(64, 3, activation='relu', padding='same')(conv9)\n",
    "\n",
    "    outputs = Conv2D(1, 1, activation='sigmoid')(conv9)\n",
    "\n",
    "    model = Model(inputs=inputs, outputs=outputs)\n",
    "\n",
    "    return model\n",
    "\n",
    "# Dice Coefficient Loss Function\n",
    "def dice_loss(y_true, y_pred):\n",
    "    smooth = 1e-5  # Adding a small constant to avoid division by zero\n",
    "    print(y_true.shape)\n",
    "    print(y_pred.shape)\n",
    "    intersection = tf.reduce_sum(y_true * y_pred, axis=[1, 2, 3])\n",
    "    print(intersection)\n",
    "    union = tf.reduce_sum(y_true, axis=[1, 2, 3]) + tf.reduce_sum(y_pred, axis=[1, 2, 3])\n",
    "    dice_coefficient = (2.0 * intersection + smooth) / (union + smooth)\n",
    "    loss = 1.0 - tf.reduce_mean(dice_coefficient)\n",
    "    return loss"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2D Dense UNet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.models import Model\n",
    "from keras.layers import Input, Concatenate, Conv2D, MaxPooling2D, UpSampling2D, Dropout\n",
    "\n",
    "def dense_block(x, filters, dropout_rate):\n",
    "    conv1 = Conv2D(filters, 3, activation='relu', padding='same')(x)\n",
    "    conv2 = Conv2D(filters, 3, activation='relu', padding='same')(conv1)\n",
    "    concat = Concatenate(axis=-1)([x, conv2])\n",
    "    if dropout_rate:\n",
    "        concat = Dropout(dropout_rate)(concat)\n",
    "    return concat\n",
    "\n",
    "def dense_unet(input_shape, num_classes, filters=16, num_layers=4, dropout_rate=0.2):\n",
    "    inputs = Input(input_shape)\n",
    "    skip_connections = []\n",
    "\n",
    "    # Downward path\n",
    "    x = inputs\n",
    "    for _ in range(num_layers):\n",
    "        x = dense_block(x, filters, dropout_rate)\n",
    "        skip_connections.append(x)\n",
    "        x = MaxPooling2D(pool_size=(2, 2))(x)\n",
    "        filters *= 2\n",
    "\n",
    "    # Bridge\n",
    "    x = dense_block(x, filters, dropout_rate)\n",
    "\n",
    "    # Upward path\n",
    "    for i in range(num_layers):\n",
    "        filters //= 2\n",
    "        x = UpSampling2D(size=(2, 2))(x)\n",
    "        x = Concatenate(axis=-1)([x, skip_connections.pop()])\n",
    "        x = dense_block(x, filters, dropout_rate)\n",
    "\n",
    "    # Output layer\n",
    "    outputs = Conv2D(num_classes, 1, activation='sigmoid')(x)\n",
    "\n",
    "    model = Model(inputs=inputs, outputs=outputs)\n",
    "    return model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "H-DenseUNet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "from keras.models import Model\n",
    "from keras.layers import Input, Conv2D, MaxPooling2D, Conv2DTranspose, concatenate\n",
    "\n",
    "def dense_block(x, filters, num_layers):\n",
    "    for _ in range(num_layers):\n",
    "        conv = Conv2D(filters=filters, kernel_size=(3, 3), activation='relu', padding='same')(x)\n",
    "        x = concatenate([x, conv], axis=-1)\n",
    "    return x\n",
    "\n",
    "def transition_down(x, filters):\n",
    "    x = Conv2D(filters=filters, kernel_size=(1, 1), activation='relu', padding='same')(x)\n",
    "    x = MaxPooling2D(pool_size=(2, 2))(x)\n",
    "    return x\n",
    "\n",
    "def transition_up(x, filters):\n",
    "    x = Conv2DTranspose(filters=filters, kernel_size=(3, 3), strides=(2, 2), padding='same')(x)\n",
    "    return x\n",
    "\n",
    "def h_dense_unet(input_shape, num_classes):\n",
    "    inputs = Input(input_shape)\n",
    "\n",
    "    # Initial Convolution Block\n",
    "    conv1 = Conv2D(filters=64, kernel_size=(3, 3), activation='relu', padding='same')(inputs)\n",
    "\n",
    "    # Downsample path\n",
    "    down1 = dense_block(conv1, filters=64, num_layers=4)\n",
    "    pool1 = transition_down(down1, filters=128)\n",
    "\n",
    "    down2 = dense_block(pool1, filters=128, num_layers=4)\n",
    "    pool2 = transition_down(down2, filters=256)\n",
    "\n",
    "    down3 = dense_block(pool2, filters=256, num_layers=4)\n",
    "    pool3 = transition_down(down3, filters=512)\n",
    "\n",
    "    down4 = dense_block(pool3, filters=512, num_layers=4)\n",
    "\n",
    "    # Upsample path\n",
    "    up4 = transition_up(down4, filters=256)\n",
    "    up4 = concatenate([up4, down3], axis=-1)\n",
    "    up4 = dense_block(up4, filters=256, num_layers=4)\n",
    "\n",
    "    up3 = transition_up(up4, filters=128)\n",
    "    up3 = concatenate([up3, down2], axis=-1)\n",
    "    up3 = dense_block(up3, filters=128, num_layers=4)\n",
    "\n",
    "    up2 = transition_up(up3, filters=64)\n",
    "    up2 = concatenate([up2, down1], axis=-1)\n",
    "    up2 = dense_block(up2, filters=64, num_layers=4)\n",
    "\n",
    "    # Output\n",
    "    outputs = Conv2D(filters=num_classes, kernel_size=(1, 1), activation='softmax')(up2)\n",
    "\n",
    "    model = Model(inputs=inputs, outputs=outputs)\n",
    "    return model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "nnUNet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Importing Preprocessed Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------------\n",
      "Importing Scan & Mask Data...\n",
      "------------------------------\n",
      "imgs_train size:  (214, 256, 256, 1)\n",
      "imgs_mask_train size:  (214, 256, 256, 1)\n",
      "------------------------------\n",
      "Importing Exporting Stage Completed!\n",
      "------------------------------\n"
     ]
    }
   ],
   "source": [
    "from writeout_dataset import ReadInDatasets, ReadInDatasetNPY\n",
    "\n",
    "print('-'*30)\n",
    "print('Importing Scan & Mask Data...')\n",
    "print('-'*30)\n",
    "\n",
    "# imgs_train = ReadInDatasetNPY('/content/drive/MyDrive/Colab Notebooks/Model Input Scans Tibia (Subset)')\n",
    "# imgs_mask_train = ReadInDatasetNPY('/content/drive/MyDrive/Colab Notebooks/Model Input Masks Tibia (Subset)')\n",
    "\n",
    "# imgs_train = ReadInDatasetNPY('/content/drive/MyDrive/Colab Notebooks/Model Input Scans Tibia (Subset)')\n",
    "# imgs_mask_train = ReadInDatasetNPY('/content/drive/MyDrive/Colab Notebooks/Model Input Masks Tibia (Subset)')\n",
    "\n",
    "imgs_train = ReadInDatasetNPY('D:/MRI - Tairawhiti/Model Input Scans Tibia (Subset)')\n",
    "imgs_mask_train = ReadInDatasetNPY('D:/MRI - Tairawhiti/Model Input Masks Tibia (Subset)')\n",
    "\n",
    "print('imgs_train size: ', imgs_train.shape)\n",
    "print('imgs_mask_train size: ', imgs_mask_train.shape)\n",
    "\n",
    "print('-'*30)\n",
    "print('Importing Exporting Stage Completed!')\n",
    "print('-'*30)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Training UNet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "------------------------------\n",
      "Training UNet Model...\n",
      "------------------------------\n",
      "Training Image Input Shape:  (168, 400, 400, 1)\n",
      "Training Mask Input Shape:  (168, 400, 400, 1)\n",
      "Validation Image Input Shape:  (42, 400, 400, 1)\n",
      "Validation Mask Input Shape:  (42, 400, 400, 1)\n",
      "------------------------------\n",
      "Creating and compiling model...\n",
      "------------------------------\n",
      "Epoch 1/10\n"
     ]
    }
   ],
   "source": [
    "print('-'*30)\n",
    "print('Training UNet Model...')\n",
    "print('-'*30)\n",
    "\n",
    "images_train, images_val, labels_train, labels_val = train_test_split(imgs_train, imgs_mask_train, test_size=0.2, random_state=0)\n",
    "print('Training Image Input Shape: ', images_train.shape)\n",
    "print('Training Mask Input Shape: ', labels_train.shape)\n",
    "print('Validation Image Input Shape: ', images_val.shape)\n",
    "print('Validation Mask Input Shape: ', labels_val.shape)\n",
    "\n",
    "\n",
    "print('-'*30)\n",
    "print('Creating and compiling model...')\n",
    "print('-'*30)\n",
    "\n",
    "# my_callbacks = [\n",
    "#     tf.keras.callbacks.EarlyStopping(patience=PATIENCE), # early stopping\n",
    "#     tf.keras.callbacks.ModelCheckpoint(filepath=MODEL_FNAME_PATTERN, save_best_only=True) # save the best based on validation\n",
    "# ]\n",
    "\n",
    "# input_shape = (256,256,1)\n",
    "# model = unet_model(input_shape)\n",
    "# model.compile(optimizer='adam', loss='binary_crossentropy')\n",
    "# # model.compile(optimizer='adam', loss=dice_loss)\n",
    "# checkpoint = ModelCheckpoint('model(loss=binary,batch_size=4,epochs=20,train_size=500,aoi=tibia).h5', monitor='val_loss', save_best_only=True, mode='min')\n",
    "# model.fit(x=images_train, y=labels_train, batch_size=4, epochs=20, validation_data=(images_val, labels_val), callbacks=[checkpoint])\n",
    "# model.summary()\n",
    "\n",
    "# Dense 2D UNet\n",
    "# input_shape = (512,512,1)\n",
    "# num_classes = 1\n",
    "# model = dense_unet(input_shape, num_classes)\n",
    "# model.compile(optimizer='adam', loss='binary_crossentropy')\n",
    "# checkpoint = ModelCheckpoint('model(Baseline + 2D Dense Layers 125 Epoch).h5', monitor='val_loss', save_best_only=True, mode='min')\n",
    "# model.fit(x=images_train, y=labels_train, batch_size=1, epochs=125, validation_data=(images_val, labels_val), callbacks=[checkpoint])\n",
    "# model.summary()\n",
    "\n",
    "\n",
    "# H-DenseUNet\n",
    "input_shape = (400,400,1)\n",
    "num_classes = 1\n",
    "batch_size = 2\n",
    "num_epochs = 10\n",
    "model = h_dense_unet(input_shape, num_classes)\n",
    "model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n",
    "model.fit(images_train, labels_train, validation_data=(images_val, labels_val), batch_size=batch_size, epochs=num_epochs)\n",
    "model.summary()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Prediction Mask"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "imgs_test size (Scans):  (214, 400, 400, 1)\n",
      "imgs_test_masks size (Masks):  (214, 400, 400, 1)\n",
      "------------------------------\n",
      "Prediction Made Using Weights From Model: D:/MRI - Tairawhiti/Trained Models/model(2D-UNet, 3 Patients, Tibia, 400x400x1, 60 epoches).h5\n",
      "------------------------------\n",
      "WARNING:tensorflow:6 out of the last 6 calls to <function Model.make_predict_function.<locals>.predict_function at 0x0000023044484EE0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.\n",
      "1/1 [==============================] - 3s 3s/step\n",
      "Testing Image Input Shape:  (400, 400, 1)\n",
      "\n",
      "\n",
      "Dice Similarity Coefficient (DSC) Metric Value for Specified Slice:  [0.15360412]\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# model = 'model(Baseline 125 Epoch).h5'\n",
    "# model = 'D:/MRI - Tairawhiti/Trained Models/model(2D UNet, 9 Patients, Tibia).h5'\n",
    "# model = 'D:/MRI - Tairawhiti/Trained Models/model(2D UNet, 9 Patients, Tibia).h5'\n",
    "# model = 'D:/MRI - Tairawhiti/Trained Models/H-DenseUNet.h5'\n",
    "model = 'D:/MRI - Tairawhiti/Trained Models/model(2D-UNet, 3 Patients, Tibia, 400x400x1, 60 epoches).h5'\n",
    "pred_img_idx = 50\n",
    "MaskStack2D = False\n",
    "\n",
    "from writeout_dataset import ReadInDatasets, ReadInDatasetNPY\n",
    "# imgs_test = ReadInDatasets('/content/drive/MyDrive/Colab Notebooks/Test_Data_Tibia(Collab Sample)', 0, 10)\n",
    "# imgs_test_masks = ReadInDatasets('/content/drive/MyDrive/Colab Notebooks/Test_Masks_Tibia(Collab Sample)', 0, 10)\n",
    "imgs_test = ReadInDatasetNPY('D:/MRI - Tairawhiti/Test_Data_Tibia(Collab Sample)')\n",
    "imgs_test_masks = ReadInDatasetNPY('D:/MRI - Tairawhiti/Test_Masks_Tibia(Collab Sample)')\n",
    "\n",
    "# imgs_test_masks = (imgs_test_masks > 0).astype(np.uint8)\n",
    "# testing_scans_processed = np.reshape(imgs_test, (len(imgs_test), 512, 512, 1))\n",
    "# testing_masks_processed = np.reshape(imgs_test_masks, (len(imgs_test), 512, 512, 1))\n",
    "print('imgs_test size (Scans): ', imgs_test.shape)\n",
    "print('imgs_test_masks size (Masks): ', imgs_test_masks.shape)\n",
    "\n",
    "def superimpose_images(image1, image2):\n",
    "    # Normalize the image intensities\n",
    "    image1 = image1 / np.max(image1)\n",
    "    image2 = image2 / np.max(image2)\n",
    "\n",
    "    alpha = 0.5  # Opacity of raw scan\n",
    "    superimposed_image = alpha * image1 + (1 - alpha) * image2\n",
    "    return superimposed_image\n",
    "\n",
    "def dice_coefficient(y_true, y_pred):\n",
    "    intersection = np.sum(y_true * y_pred, axis=(1, 2, 3))\n",
    "    union = np.sum(y_true, axis=(1, 2, 3)) + np.sum(y_pred, axis=(1, 2, 3))\n",
    "    dice = (2.0 * intersection) / (union + 1e-7)  # Adding a small epsilon to avoid division by zero\n",
    "    return dice\n",
    "\n",
    "print('-'*30)\n",
    "print(f'Prediction Made Using Weights From Model: {model}')\n",
    "print('-'*30)\n",
    "\n",
    "# Prediction\n",
    "best_model = load_model(model)\n",
    "prediction = best_model.predict(np.reshape(imgs_test[pred_img_idx], (1,imgs_test.shape[1],imgs_test.shape[2],1)))\n",
    "print('Testing Image Input Shape: ',imgs_test[pred_img_idx].shape)\n",
    "# print('Prediction Mask Shape: ', prediction.shape)\n",
    "print('\\n')\n",
    "\n",
    "# Evaluation\n",
    "rounded_array  = np.round(prediction, decimals=3)\n",
    "binary_pred = np.where(rounded_array != 0, 1, 0)\n",
    "DSC = dice_coefficient((np.reshape(imgs_test_masks[pred_img_idx], (1,imgs_test_masks.shape[1],imgs_test_masks.shape[2],1))), binary_pred)\n",
    "print('Dice Similarity Coefficient (DSC) Metric Value for Specified Slice: ', DSC)\n",
    "\n",
    "if (MaskStack2D == True):\n",
    "  DSC_stack = []\n",
    "  pred_stack = []\n",
    "  for i in tqdm(range(len(imgs_test_masks)), desc=\"Evaluating DSC on Paitent Scan Stack\"):\n",
    "    prediction_patient = best_model.predict(np.reshape(imgs_test[i], (1,imgs_test.shape[1],imgs_test.shape[2],1)))\n",
    "    rounded_array  = np.round(prediction_patient, decimals=3)\n",
    "    binary_pred_patient = np.where(rounded_array != 0, 1, 0)\n",
    "    pred_stack.append(binary_pred_patient)\n",
    "    DSC_patient = dice_coefficient((np.reshape(imgs_test_masks[i], (1,imgs_test_masks.shape[1],imgs_test_masks.shape[2],1))), binary_pred_patient)\n",
    "    DSC_stack.append(DSC_patient)\n",
    "  print('Average Dice Similarity Coefficient (DSC) Metric Value for Patient Scan Stack: ', np.mean(DSC_stack))\n",
    "  np.save('ManualSegStack.npy', DSC_stack)\n",
    "  print('\\n')\n",
    "\n",
    "# Visualisations\n",
    "cmap_binary = 'white'\n",
    "cmap_segmask = plt.cm.colors.ListedColormap(['black', cmap_binary])\n",
    "bounds = [0, 0.5, 1]\n",
    "norm = plt.cm.colors.BoundaryNorm(bounds, cmap_segmask.N)\n",
    "fig, ax = plt.subplots()\n",
    "ax.imshow(binary_pred[0, :, :, 0], cmap=cmap_segmask, norm=norm)\n",
    "ax.axis('on')\n",
    "plt.title('Model Outputted Segmentation Mask')\n",
    "plt.show()\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "ax.imshow(imgs_test_masks[pred_img_idx, :, :, 0], cmap='gray')\n",
    "ax.axis('on')\n",
    "plt.title('Groundtruth Mask')\n",
    "plt.show()\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "ax.imshow(imgs_test[pred_img_idx, :, :, 0], cmap='gray')\n",
    "ax.axis('on')\n",
    "plt.title('Raw Test Scan')\n",
    "plt.show()\n",
    "\n",
    "cmap_binary = 'YlOrBr'\n",
    "superimposed_image = superimpose_images(imgs_test_masks[pred_img_idx, :, :, 0], binary_pred[0, :, :, 0])\n",
    "# Define the cropping ranges\n",
    "x_start, x_end = 200, 400\n",
    "y_start, y_end = 200, 400\n",
    "cropped_image = superimposed_image[y_start:y_end, x_start:x_end]\n",
    "fig, ax = plt.subplots()\n",
    "cmap_superimposed = plt.cm.get_cmap(cmap_binary)\n",
    "ax.imshow(cropped_image, cmap=cmap_superimposed, vmin=0, vmax=1)\n",
    "ax.axis('on')\n",
    "plt.title('Superimposed Prediction Mask (Orange) & Groundtruth Mask (Black)')\n",
    "plt.show()\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "superimposed_image = superimpose_images(imgs_test[pred_img_idx, :, :, 0], imgs_test_masks[pred_img_idx, :, :, 0])\n",
    "ax.imshow(superimposed_image, cmap='gray')\n",
    "ax.axis('on')\n",
    "plt.title('Superimposed Raw Test Scan & Groundtruth Mask (Manually Segmented)')\n",
    "plt.show()\n",
    "\n",
    "fig, ax = plt.subplots()\n",
    "superimposed_image = superimpose_images(imgs_test[pred_img_idx, :, :, 0], binary_pred[0, :, :, 0])\n",
    "ax.imshow(superimposed_image, cmap='gray')\n",
    "ax.axis('on')\n",
    "plt.title('Superimposed Raw Test Scan & Prediction Mask (Automatically Segmented)')\n",
    "plt.show()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Evaluation Metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dice Similarity Coefficient (DSC) Metric Value:  [4.0989216e-06]\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def dice_coefficient(y_true, y_pred):\n",
    "    intersection = np.sum(y_true * y_pred, axis=(1, 2, 3))\n",
    "    union = np.sum(y_true, axis=(1, 2, 3)) + np.sum(y_pred, axis=(1, 2, 3))\n",
    "    dice = (2.0 * intersection) / (union + 1e-7)  # Adding a small epsilon to avoid division by zero\n",
    "    return dice\n",
    "\n",
    "def assd(y_true, y_pred, spacing):\n",
    "    surface_distances = surface_distance(y_true, y_pred, spacing)\n",
    "    avg_surface_distance = np.mean(surface_distances)\n",
    "    return avg_surface_distance\n",
    "\n",
    "def surface_distance(y_true, y_pred, spacing):\n",
    "    true_surface = find_surface_points(y_true, spacing)\n",
    "    pred_surface = find_surface_points(y_pred, spacing)\n",
    "\n",
    "    if true_surface.shape[0] == 0 or pred_surface.shape[0] == 0:\n",
    "        raise ValueError(\"One or both surface point arrays are empty.\")\n",
    "\n",
    "    try:\n",
    "        surface_distances_true_to_pred = directed_hausdorff(true_surface, pred_surface)[0]\n",
    "        surface_distances_pred_to_true = directed_hausdorff(pred_surface, true_surface)[0]\n",
    "        surface_distances = np.concatenate([surface_distances_true_to_pred, surface_distances_pred_to_true])\n",
    "    except ValueError as e:\n",
    "        print(\"Error occurred during Hausdorff distance calculation:\", e)\n",
    "        raise\n",
    "\n",
    "    return surface_distances\n",
    "\n",
    "def find_surface_points(mask, spacing):\n",
    "    mask_padded = np.pad(mask, 1, mode='constant')\n",
    "    mask_padded_diff = np.diff(mask_padded.astype(int), axis=0)\n",
    "\n",
    "    surface_points = []\n",
    "    for z in range(mask_padded_diff.shape[0]):\n",
    "        surface_indices = np.where(mask_padded_diff[z] != 0)\n",
    "        if len(surface_indices[0]) > 0:\n",
    "            surface_points.extend(list(zip(surface_indices[0], surface_indices[1])))\n",
    "\n",
    "    surface_points = np.array(surface_points)\n",
    "    surface_points_phys = surface_points * spacing\n",
    "\n",
    "    return surface_points_phys\n",
    "\n",
    "def volume_error(y_true, y_pred):\n",
    "    true_volume = np.sum(y_true)\n",
    "    pred_volume = np.sum(y_pred)\n",
    "    volume_error = np.abs(true_volume - pred_volume) / true_volume\n",
    "    return volume_error\n",
    "\n",
    "predictions_single_scan_binarized = np.reshape(predictions_single_scan_binarized,(1, 512, 512, 1))\n",
    "DSC = dice_coefficient(testing_masks_processed, predictions_single_scan_binarized)\n",
    "print('Dice Similarity Coefficient (DSC) Metric Value: ', DSC)\n",
    "print('\\n')\n",
    "\n",
    "# VError = volume_error(testing_masks_processed, prediction)\n",
    "# print('Volume Error (VError) Metric Value: ', VError)\n",
    "# print('\\n')\n",
    "\n",
    "# spacing = 1\n",
    "# ASSD = assd(testing_masks_processed, prediction, spacing)\n",
    "# print('Average Symmetric Surface Distance (ASSD) Metric Value: ', ASSD)\n",
    "# print('\\n')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.17"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}