Working with medical images in Jupyter tutorial

medical_image_jupyter_tutorial.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Working with medical images in Jupyter\n",
    "## Jacob Reinhold\n",
    "\n",
    "If anaconda/[miniconda](https://docs.conda.io/en/latest/miniconda.html) isn't already installed, install it.\n",
    "\n",
    "Then run the [`create_env.sh` script](https://gist.github.com/jcreinhold/57ca03528916ce72914c89e5c5af4ddb) to create a working conda environment that supports all of the functionality in this notebook by running:\n",
    "\n",
    "```bash\n",
    "source create_env.sh\n",
    "```\n",
    "\n",
    "Now you should be able to run:\n",
    "\n",
    "```bash\n",
    "jupyter lab\n",
    "```\n",
    "\n",
    "in the terminal and run this notebook."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import random\n",
    "import sys\n",
    "import warnings\n",
    "\n",
    "with warnings.catch_warnings():\n",
    "    warnings.filterwarnings('ignore')\n",
    "    import matplotlib.pyplot as plt\n",
    "    import nibabel as nib\n",
    "    import nilearn.plotting as nip\n",
    "    import numpy as np\n",
    "\n",
    "    from niwidgets import NiftiWidget"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Report versions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "numpy version: 1.20.1\n",
      "matplotlib version: 3.3.4\n"
     ]
    }
   ],
   "source": [
    "print('numpy version: {}'.format(np.__version__))\n",
    "from matplotlib import __version__ as mplver\n",
    "print('matplotlib version: {}'.format(mplver))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "python version: 3.8.8\n"
     ]
    }
   ],
   "source": [
    "pv = sys.version_info\n",
    "print('python version: {}.{}.{}'.format(pv.major, pv.minor, pv.micro))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "seed = 1337\n",
    "random.seed(seed)\n",
    "np.random.seed(seed)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Download an example NIfTI image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = 'https://gitlab.com/jcreinhold/iacl-mni-atlas/-/raw/e4198d8f1a3baef255a30c1492b573ae9ca1bf1a/mni_icbm_152_2009c_t1_0p8mm_brain.nii.gz'\n",
    "test_nifti_file = 'test.nii.gz'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
      "                                 Dload  Upload   Total   Spent    Left  Speed\n",
      "100 9795k  100 9795k    0     0  11.4M      0 --:--:-- --:--:-- --:--:-- 11.4M\n"
     ]
    }
   ],
   "source": [
    "!curl {url} --output {test_nifti_file}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Visualize the downloaded image with `niwidgets`\n",
    "\n",
    "(Note that I created my own version of `niwidgets` ([see here](https://github.com/jcreinhold/niwidgets)) because the original `niwidgets` package on PyPI didn't install correctly.)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 432x288 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "393fca6657944dd0a60bc212691c7e95",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "interactive(children=(IntSlider(value=0, continuous_update=False, description='x', max=90, min=-90), IntSlider…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "widget = NiftiWidget(test_nifti_file)\n",
    "with warnings.catch_warnings():\n",
    "    warnings.filterwarnings('ignore', category=FutureWarning)\n",
    "    widget.nifti_plotter(nip.plot_anat, colormap='gray');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Open image with `nibabel` and manipulate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "image = nib.load(test_nifti_file)\n",
    "data = image.get_fdata()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "data **= 2.  # do a trivial gamma correction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_image = nib.Nifti1Image(data, image.affine, image.header, image.extra)\n",
    "new_nifti_file = 'new_test.nii.gz'\n",
    "new_image.to_filename(new_nifti_file)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Reopen the image and examine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 432x288 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "cb98428721834edd8161064fbe87842c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "interactive(children=(IntSlider(value=0, continuous_update=False, description='x', max=90, min=-90), IntSlider…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "widget = NiftiWidget(new_nifti_file)\n",
    "with warnings.catch_warnings():\n",
    "    warnings.filterwarnings('ignore', category=FutureWarning)\n",
    "    widget.nifti_plotter(nip.plot_anat, colormap='gray');"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:neuroimage] *",
   "language": "python",
   "name": "conda-env-neuroimage-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}

Code block #7: !curl {url} instead of !curl {test_nifti_file}

Good catch. Thanks!