{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# David Ouyang 10/2/2019\n",
    "\n",
    "# Notebook which iterates through a folder, including subfolders, \n",
    "# and convert DICOM files to AVI files of a defined size (natively 112 x 112)\n",
    "\n",
    "import re\n",
    "import os, os.path\n",
    "from os.path import splitext\n",
    "import pydicom as dicom\n",
    "import numpy as np\n",
    "from pydicom.uid import UID, generate_uid\n",
    "import shutil\n",
    "from multiprocessing import dummy as multiprocessing\n",
    "import time\n",
    "import subprocess\n",
    "import datetime\n",
    "from datetime import date\n",
    "import sys\n",
    "import cv2\n",
    "#from scipy.misc import imread\n",
    "import matplotlib.pyplot as plt\n",
    "import sys\n",
    "from shutil import copy\n",
    "import math\n",
    "\n",
    "destinationFolder = \"Output Folder Name\"\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: pillow in c:\\programdata\\anaconda3\\lib\\site-packages (6.2.0)\n",
      "Requirement already satisfied: scipy in c:\\programdata\\anaconda3\\lib\\site-packages (1.3.1)\n"
     ]
    }
   ],
   "source": [
    "# Dependencies you might need to run code\n",
    "# Commonly missing\n",
    "\n",
    "#!pip install pydicom\n",
    "#!pip install opencv-python\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def mask(output):\n",
    "    dimension = output.shape[0]\n",
    "    \n",
    "    # Mask pixels outside of scanning sector\n",
    "    m1, m2 = np.meshgrid(np.arange(dimension), np.arange(dimension))\n",
    "    \n",
    "\n",
    "    mask = ((m1+m2)>int(dimension/2) + int(dimension/10)) \n",
    "    mask *=  ((m1-m2)<int(dimension/2) + int(dimension/10))\n",
    "    mask = np.reshape(mask, (dimension, dimension)).astype(np.int8)\n",
    "    maskedImage = cv2.bitwise_and(output, output, mask = mask)\n",
    "    \n",
    "    #print(maskedImage.shape)\n",
    "    \n",
    "    return maskedImage\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def makeVideo(fileToProcess, destinationFolder):\n",
    "    try:\n",
    "        fileName = fileToProcess.split('\\\\')[-1] #\\\\ if windows, / if on mac or sherlock\n",
    "                                                 #hex(abs(hash(fileToProcess.split('/')[-1]))).upper()\n",
    "\n",
    "        if not os.path.isdir(os.path.join(destinationFolder,fileName)):\n",
    "\n",
    "            dataset = dicom.dcmread(fileToProcess, force=True)\n",
    "            testarray = dataset.pixel_array\n",
    "\n",
    "            frame0 = testarray[0]\n",
    "            mean = np.mean(frame0, axis=1)\n",
    "            mean = np.mean(mean, axis=1)\n",
    "            yCrop = np.where(mean<1)[0][0]\n",
    "            testarray = testarray[:, yCrop:, :, :]\n",
    "\n",
    "            bias = int(np.abs(testarray.shape[2] - testarray.shape[1])/2)\n",
    "            if bias>0:\n",
    "                if testarray.shape[1] < testarray.shape[2]:\n",
    "                    testarray = testarray[:, :, bias:-bias, :]\n",
    "                else:\n",
    "                    testarray = testarray[:, bias:-bias, :, :]\n",
    "\n",
    "\n",
    "            print(testarray.shape)\n",
    "            frames,height,width,channels = testarray.shape\n",
    "\n",
    "            fps = 30\n",
    "\n",
    "            try:\n",
    "                fps = dataset[(0x18, 0x40)].value\n",
    "            except:\n",
    "                print(\"couldn't find frame rate, default to 30\")\n",
    "\n",
    "            fourcc = cv2.VideoWriter_fourcc('M','J','P','G')\n",
    "            video_filename = os.path.join(destinationFolder, fileName + '.avi')\n",
    "            out = cv2.VideoWriter(video_filename, fourcc, fps, cropSize)\n",
    "\n",
    "\n",
    "            for i in range(frames):\n",
    "\n",
    "                outputA = testarray[i,:,:,0]\n",
    "                smallOutput = outputA[int(height/10):(height - int(height/10)), int(height/10):(height - int(height/10))]\n",
    "\n",
    "                # Resize image\n",
    "                output = cv2.resize(smallOutput, cropSize, interpolation = cv2.INTER_CUBIC)\n",
    "\n",
    "                finaloutput = mask(output)\n",
    "\n",
    "\n",
    "                finaloutput = cv2.merge([finaloutput,finaloutput,finaloutput])\n",
    "                out.write(finaloutput)\n",
    "\n",
    "            out.release()\n",
    "\n",
    "        else:\n",
    "            print(fileName,\"hasAlreadyBeenProcessed\")\n",
    "    except:\n",
    "        print(\"something filed, not sure what, have to debug\", fileName)\n",
    "    return 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "AllA4cNames = \"Input Folder Name\"\n",
    "\n",
    "count = 0\n",
    "    \n",
    "cropSize = (112,112)\n",
    "subfolders = os.listdir(AllA4cNames)\n",
    "\n",
    "\n",
    "for folder in subfolders:\n",
    "    print(folder)\n",
    "\n",
    "    for content in os.listdir(os.path.join(AllA4cNames, folder)):\n",
    "        for subcontent in os.listdir(os.path.join(AllA4cNames, folder, content)):\n",
    "            count += 1\n",
    "            \n",
    "\n",
    "            VideoPath = os.path.join(AllA4cNames, folder, content, subcontent)\n",
    "\n",
    "            print(count, folder, content, subcontent)\n",
    "\n",
    "            if not os.path.exists(os.path.join(destinationFolder,subcontent + \".avi\")):\n",
    "                makeVideo(VideoPath, destinationFolder)\n",
    "            else:\n",
    "                print(\"Already did this file\", VideoPath)\n",
    "\n",
    "\n",
    "print(len(AllA4cFilenames))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}