Merge pull request #17 from nriss/nr/add_em_dicom_extract

add em dicom extract
InstitutNationalduCancer · Oct 20, 2022 · e76142b · e76142b
2 parents 7291ebd + b6f5cae
commit e76142b
Show file tree

Hide file tree

Showing 4 changed files with 294 additions and 0 deletions.
diff --git a/notebooks/Dicom_API.ipynb b/notebooks/Dicom_API.ipynb
@@ -0,0 +1,290 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b9f92452-b2df-4fa2-b014-bd95e51ae571",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Extracting data from DICOM files\n",
+    "### This notebook extract data from Dicom files using the dicomTags."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2c857a38-eabe-497a-904e-39ad862dad9c",
+   "metadata": {},
+   "source": [
+    "#### Installing required packages:\n",
+    "\n",
+    "1. Create a new environment (https://docs.python.org/3/library/venv.html)\n",
+    "\n",
+    "```python\n",
+    "python3 -m venv /path/to/new/virtual/environment\n",
+    "```\n",
+    "2. Activate the new environment\n",
+    "\n",
+    "```python\n",
+    "source env/bin/activate\n",
+    "```\n",
+    "\n",
+    "3. Install required packages\n",
+    "\n",
+    "```python\n",
+    "pip install -r requirements.txt\n",
+    "```\n",
+    "\n",
+    "4. Run the notebook.  :)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "09335bfd-7719-4c49-ac02-ad28ad21f374",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from pydicom import dcmread\n",
+    "import re\n",
+    "import glob"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2409bef7-55d0-452b-a562-8903ec428e9b",
+   "metadata": {},
+   "source": [
+    "DICOM_file: The path containing the Dicom File.\n",
+    "tags_file_osiris: the file containing the dicomTags to be extracted.\n",
+    "For this example the original excel file of Christophe is used."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "085dd51a-7840-4329-a47a-2e5bdc7220f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DICOM_file = dcmread(\"dicom_file.dcm\")\n",
+    "DICOM_file = dcmread(\"files/1-01.dcm\")\n",
+    "tags_file_osiris = pd.read_excel(\n",
+    "    \"modele_osiris_radiomics.xlsx\", sheet_name=\"Feuil1\", header=0\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3b8b6f69-5c99-46a8-b933-44474b65427a",
+   "metadata": {},
+   "source": [
+    "#### Display tags_file_osiris and Dicom File"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74f1435d-e7e2-4a4c-965c-1028c77f1c26",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tags_file_osiris"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8ae59cfa-f60b-43e0-a62d-d8d1c0dab5a9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(DICOM_file)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "926bd5b8-176f-49d4-9d1e-b26e48af42f3",
+   "metadata": {},
+   "source": [
+    "### Extracting the data and building a data frame"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "395c5919-c8c8-430c-9bf0-b2128437e607",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list_tags = []\n",
+    "dicom_df = pd.DataFrame(columns=[\"tag\", \"name\", \"value\"])\n",
+    "\n",
+    "# extraction of dicomTags from the excel file\n",
+    "for j in range(len(tags_file_osiris)):\n",
+    "    try:\n",
+    "        tag_ext = re.search(r\"\\((.*?)\\)\", tags_file_osiris[\"Source\"][j]).group(1)\n",
+    "        tag_conv = \"0x\" + tag_ext[0:4] + tag_ext[5:]\n",
+    "        list_tags.append(tag_conv)\n",
+    "    except:\n",
+    "        pass\n",
+    "\n",
+    "# searching for the tags in the dicom file and building the dataframe\n",
+    "for i in list_tags:\n",
+    "    try:\n",
+    "        df_tag = str(DICOM_file[i].tag)\n",
+    "        df_name = DICOM_file[i].name\n",
+    "        df_value = DICOM_file[i].value\n",
+    "\n",
+    "        dicom_df = dicom_df.append(\n",
+    "            {\"tag\": df_tag, \"name\": df_name, \"value\": df_value}, ignore_index=True\n",
+    "        )\n",
+    "\n",
+    "    except:\n",
+    "        pass\n",
+    "\n",
+    "\n",
+    "dicom_df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b3a305ee-0a14-424e-8683-92c1ebc1c1ff",
+   "metadata": {},
+   "source": [
+    "#### Exporting to CSV"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "180c8dff-aae7-490a-83fb-209e670f5958",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dicom_df.to_csv('dicom_data-osiris.csv')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f5d14377-3613-4e57-b5c8-8627421bc5b8",
+   "metadata": {},
+   "source": [
+    "### Working with file lists and building a transposed dataframe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "89e65145-147b-40cc-a26d-6ed6d5d3bf40",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "dcm_files = (glob.glob(\"files/*.dcm\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d8752cb4-9ace-4798-ade6-a23034b2fa09",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list_tags = []\n",
+    "\n",
+    "\n",
+    "# extraction of dicomTags from the excel file\n",
+    "for j in range(len(tags_file_osiris)):\n",
+    "    try:\n",
+    "        tag_ext = re.search(r\"\\((.*?)\\)\", tags_file_osiris[\"Source\"][j]).group(1)\n",
+    "        tag_conv = \"0x\" + tag_ext[0:4] + tag_ext[5:]\n",
+    "        list_tags.append(tag_conv)\n",
+    "    except:\n",
+    "        pass\n",
+    "\n",
+    "dicom_df = pd.DataFrame(columns=[\"file\",\"tag\", \"value\"])\n",
+    "dicom_dict = {}\n",
+    "\n",
+    "# searching for the tags in the dicom file and building the dataframe\n",
+    "for i in dcm_files:\n",
+    "    DICOM_file = dcmread(i)\n",
+    "    dicom_dict[i] = {}\n",
+    "    for j in list_tags:\n",
+    "        try:\n",
+    "            tag = str(DICOM_file[j].tag)\n",
+    "            value = DICOM_file[j].value\n",
+    "            dicom_dict[i][tag] = value\n",
+    "        except:\n",
+    "            pass"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "71b5225c-dee9-46f5-920c-2d36ef0828d9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_dicom = pd.DataFrame.from_dict(dicom_dict, orient='index')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "03d3864d-8f63-49d1-96e0-b4b741111a25",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_dicom.head(10)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "307f6f7f-1b2e-4bd4-a7c4-b30ff5da7a7c",
+   "metadata": {},
+   "source": [
+    "#### Just for fun!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "225ea97e-e261-46f2-ae57-67018c62c828",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "plt.imshow(DICOM_file.pixel_array, cmap=plt.cm.gray)\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "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": "3.8.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/notebooks/dicom_file.dcm b/notebooks/dicom_file.dcm
diff --git a/notebooks/modele_osiris_radiomics.xlsx b/notebooks/modele_osiris_radiomics.xlsx
diff --git a/notebooks/requirements.txt b/notebooks/requirements.txt
@@ -0,0 +1,4 @@
+pandas==1.2.3
+numpy==1.20.2
+matplotlib==3.4.1
+pydicom==2.3.0.dev0