--- a
+++ b/1. Applying AI to 2D Medical Imaging Data/4. Prepare DICOM Images for ML Exercise/solution.ipynb
@@ -0,0 +1,427 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import pydicom\n",
+    "import glob"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## First, read all of my DICOM files into a list\n",
+    "mydicoms = glob.glob(\"*.dcm\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Let's look at the contents of the first DICOM:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dcm1 = pydicom.dcmread(mydicoms[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(0008, 0016) SOP Class UID                       UI: Secondary Capture Image Storage\n",
+       "(0008, 0018) SOP Instance UID                    UI: 1.3.6.1.4.1.11129.5.5.162426174634548301003630270411628292460952\n",
+       "(0008, 0060) Modality                            CS: 'DX'\n",
+       "(0008, 1030) Study Description                   LO: 'Effusion|Nodule|Pleural_Thickening|Mass'\n",
+       "(0010, 0020) Patient ID                          LO: '29579'\n",
+       "(0010, 0040) Patient's Sex                       CS: 'F'\n",
+       "(0010, 1010) Patient's Age                       AS: '24'\n",
+       "(0020, 000d) Study Instance UID                  UI: 1.3.6.1.4.1.11129.5.5.113025392650823751977671880960497589856674\n",
+       "(0020, 000e) Series Instance UID                 UI: 1.3.6.1.4.1.11129.5.5.168055162156043936178718006100964727334210\n",
+       "(0028, 0002) Samples per Pixel                   US: 1\n",
+       "(0028, 0004) Photometric Interpretation          CS: 'MONOCHROME2'\n",
+       "(0028, 0010) Rows                                US: 1024\n",
+       "(0028, 0011) Columns                             US: 1024\n",
+       "(0028, 0100) Bits Allocated                      US: 8\n",
+       "(0028, 0101) Bits Stored                         US: 8\n",
+       "(0028, 0102) High Bit                            US: 7\n",
+       "(0028, 0103) Pixel Representation                US: 0\n",
+       "(7fe0, 0010) Pixel Data                          OW: Array of 1048576 elements"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dcm1"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Looking at the attributes listed above, I can see that I'm looking to extract the following attributes: \n",
+    "* Modality\n",
+    "* Study Description\n",
+    "* Patient ID\n",
+    "* Patient's Sex\n",
+    "* Patient's Age\n",
+    "* Rows\n",
+    "* Columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'DX'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dcm1.Modality"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Effusion|Nodule|Pleural_Thickening|Mass'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dcm1.StudyDescription"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'29579'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dcm1.PatientID"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'F'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dcm1.PatientSex"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'24'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dcm1.PatientAge"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1024"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dcm1.Rows"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1024"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dcm1.Columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Now, let's create the dataframe that we want, and populate it in a loop with all of our DICOMS:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_data = []\n",
+    "\n",
+    "for i in mydicoms: \n",
+    "    dcm = pydicom.dcmread(i)\n",
+    "    fields = [dcm.PatientID, int(dcm.PatientAge), dcm.PatientSex, dcm.Modality, dcm.StudyDescription,\n",
+    "             dcm.Rows, dcm.Columns]\n",
+    "    all_data.append(fields)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mydata = pd.DataFrame(all_data, \n",
+    "                      columns = ['PatientID','PatientAge','PatientSex','Modality','Findings','Rows','Columns'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>PatientID</th>\n",
+       "      <th>PatientAge</th>\n",
+       "      <th>PatientSex</th>\n",
+       "      <th>Modality</th>\n",
+       "      <th>Findings</th>\n",
+       "      <th>Rows</th>\n",
+       "      <th>Columns</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>29579</td>\n",
+       "      <td>24</td>\n",
+       "      <td>F</td>\n",
+       "      <td>DX</td>\n",
+       "      <td>Effusion|Nodule|Pleural_Thickening|Mass</td>\n",
+       "      <td>1024</td>\n",
+       "      <td>1024</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1688</td>\n",
+       "      <td>59</td>\n",
+       "      <td>F</td>\n",
+       "      <td>DX</td>\n",
+       "      <td>Infiltration|Nodule</td>\n",
+       "      <td>1024</td>\n",
+       "      <td>1024</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>13659</td>\n",
+       "      <td>62</td>\n",
+       "      <td>F</td>\n",
+       "      <td>DX</td>\n",
+       "      <td>Consolidation|Mass|Pneumonia|Pneumothorax</td>\n",
+       "      <td>1024</td>\n",
+       "      <td>1024</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>13118</td>\n",
+       "      <td>69</td>\n",
+       "      <td>M</td>\n",
+       "      <td>DX</td>\n",
+       "      <td>Atelectasis</td>\n",
+       "      <td>1024</td>\n",
+       "      <td>1024</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>10172</td>\n",
+       "      <td>59</td>\n",
+       "      <td>F</td>\n",
+       "      <td>DX</td>\n",
+       "      <td>Atelectasis|Effusion</td>\n",
+       "      <td>1024</td>\n",
+       "      <td>1024</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>5066</td>\n",
+       "      <td>52</td>\n",
+       "      <td>M</td>\n",
+       "      <td>DX</td>\n",
+       "      <td>Cardiomegaly|Effusion|Infiltration</td>\n",
+       "      <td>1024</td>\n",
+       "      <td>1024</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>23075</td>\n",
+       "      <td>31</td>\n",
+       "      <td>M</td>\n",
+       "      <td>DX</td>\n",
+       "      <td>Mass</td>\n",
+       "      <td>1024</td>\n",
+       "      <td>1024</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  PatientID  PatientAge PatientSex Modality  \\\n",
+       "0     29579          24          F       DX   \n",
+       "1      1688          59          F       DX   \n",
+       "2     13659          62          F       DX   \n",
+       "3     13118          69          M       DX   \n",
+       "4     10172          59          F       DX   \n",
+       "5      5066          52          M       DX   \n",
+       "6     23075          31          M       DX   \n",
+       "\n",
+       "                                    Findings  Rows  Columns  \n",
+       "0    Effusion|Nodule|Pleural_Thickening|Mass  1024     1024  \n",
+       "1                        Infiltration|Nodule  1024     1024  \n",
+       "2  Consolidation|Mass|Pneumonia|Pneumothorax  1024     1024  \n",
+       "3                                Atelectasis  1024     1024  \n",
+       "4                       Atelectasis|Effusion  1024     1024  \n",
+       "5         Cardiomegaly|Effusion|Infiltration  1024     1024  \n",
+       "6                                       Mass  1024     1024  "
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mydata"
+   ]
+  }
+ ],
+ "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}