Added example combining matplotlib and nilearn

f55e0b1e · Sean Fitzgibbon · Paul McCarthy · f1a842ea · f55e0b1e
Commit f55e0b1e authored 3 years ago by Sean Fitzgibbon Committed by Paul McCarthy 3 years ago
--- a/applications/nilearn/nilearn.ipynb
+++ b/applications/nilearn/nilearn.ipynb
@@ -40,6 +40,7 @@
    "from nilearn import plotting, datasets, surface\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
+    "import nibabel as nb\n",
    "%matplotlib inline\n",
    "\n",
    "# get path to FSL installation for the FSLDIR environment variable\n",
@@ -181,6 +182,49 @@
    "display.savefig('myplot.png')"
   ]
  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "`nilearn` plotting is built upon `matplotlib`, so we can use constructs from `matplotlib` to help us create more complex figures.  \n",
+    "\n",
+    "In this example we:\n",
+    "1. create a 1x2 grid of subplots using `subplots` from `matplotlib`\n",
+    "2. plot a single slice of the MNI152 T1w in the first subplot using `plot_anat` from `nilearn`\n",
+    "3. plot a histogram of the intensities of the MNI152 T12 in the second subplot using `hist` from `matplotlib`\n",
+    "4. style the histogram by setting the x/y labels\n",
+    "\n",
+    "> **NOTE:** Here we use `load` and `get_fdata` from the [`nibabel`](https://nipy.org/nibabel/) package to load the data from the MNI152 T1w nifti for the histogram."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create matplotlib figure with 1x2 subplots\n",
+    "fig, ax = plt.subplots(1, 2, figsize=(10, 5))\n",
+    "\n",
+    "# plot MNI T1w slice in first subplot\n",
+    "mni_t1 = f'{FSLDIR}/data/standard/MNI152_T1_1mm.nii.gz'\n",
+    "\n",
+    "display = plotting.plot_anat(\n",
+    "    mni_t1, \n",
+    "    dim=-0.5, \n",
+    "    axes=ax[0],\n",
+    "    display_mode='z', \n",
+    "    cut_coords=[15]\n",
+    ")\n",
+    "\n",
+    "# plot histogram of MNI T1w intensity in second subplot\n",
+    "mni_t1_data = nb.load(mni_t1).get_fdata().ravel()\n",
+    "\n",
+    "ax[1].hist(mni_t1_data, bins=25)\n",
+    "ax[1].set_ylabel('count')\n",
+    "ax[1].set_xlabel('intensity')"
+   ]
+  },
  {
   "cell_type": "markdown",
   "metadata": {},
@@ -434,7 +478,7 @@
    ">\n",
    "> **Exercise:**\n",
    "> \n",
-    "> Visualise thee **Harvard-Oxford** atlas on a surface in the weeb Browser"
+    "> Visualise thee **Harvard-Oxford** atlas on a surface in the web browser"
   ]
  },
  {
@@ -470,7 +514,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.7.9"
+   "version": "3.7.6"
  }
 },
 "nbformat": 4,

 %% Cell type:markdown id: tags:
 # `nilearn`
 `nilearn` is a python package that provides **statistical** and **machine learning** tools for working with neuroimaging data.
 According to https://nilearn.github.io/:
 >
 > Nilearn enables approachable and versatile analyses of brain volumes. It provides **statistical** and **machine-learning** tools, with instructive documentation & open community.
 >
 > It supports general linear model (GLM) based analysis and leverages the scikit-learn Python toolbox for multivariate statistics with applications such as predictive modelling, classification, decoding, or connectivity analysis.
 However, `nilearn` also provides a very convenient set of visualisation routines for neuroimaging data.  This notebook will focus on these visualisation tools.
 `nilearn` has very good documentation, and the examples below borrow heavily from the visualisation documentation: https://nilearn.github.io/plotting/index.html
 ## This notebook
 1. Plotting an anatomical image
 2. Plotting a statistical map
 3. 2D maximum intensity projection
 4. Surfaces
 Firstly we will import the necessary packages for this notebook:
 %% Cell type:code id: tags:
 ``` python
 import os
 from nilearn import plotting, datasets, surface
 import matplotlib as mpl
 import matplotlib.pyplot as plt
+import nibabel as nb
 %matplotlib inline
 # get path to FSL installation for the FSLDIR environment variable
 FSLDIR = os.environ['FSLDIR']
 ## figure styling
 mpl.rcParams['figure.dpi'] = 150
 ```
 %% Cell type:markdown id: tags:
 ## Plotting an anatomical image
 In this section we will use `nilearn` to plot an anatomical volume.  For these examples we will use the 1mm MNI152 T1w that is shipped with `FSL`.  In these examples you will see differnet plotting layouts, as well as different styling options.
 First we will use the `plot_anat` function (with default values) to plot the MNI152 T1w in an **ortho** view.
 > **NOTE:**
 > 1. Here we use [`plot_anat`](https://nilearn.github.io/modules/generated/nilearn.plotting.plot_anat.html) from the [`nilearn`](https://nilearn.github.io/index.html) package to plot the orthographic images
 > 2.  Here we use python [f-strings](https://www.python.org/dev/peps/pep-0498/), formally known as literal string interpolation, which allow for easy formatting
 %% Cell type:code id: tags:
 ``` python
 plotting.plot_anat(
    f'{FSLDIR}/data/standard/MNI152_T1_1mm.nii.gz'
 )
 ```
 %% Cell type:markdown id: tags:
 Here we adjust the brightness of the image using the `dim` argument, and add a title to the plot with the `title` argument.
 %% Cell type:code id: tags:
 ``` python
 plotting.plot_anat(
    f'{FSLDIR}/data/standard/MNI152_T1_1mm.nii.gz',
    dim=-0.5,
    title='MNI T1 1mm'
 )
 ```
 %% Cell type:markdown id: tags:
 Now we are going to use the `display_mode` argument to change to a **tiled** ortho view where the coronal and axial views are in a column, and the coronal and sagittal views are in a row.
 %% Cell type:code id: tags:
 ``` python
 plotting.plot_anat(
    f'{FSLDIR}/data/standard/MNI152_T1_1mm.nii.gz',
    dim=-0.5,
    title='MNI T1 1mm',
    display_mode='tiled'
 )
 ```
 %% Cell type:markdown id: tags:
 Now we are going to combine the `display_mode` and `cut_coords` arguments to create a row of 10 axial slices.
 Options for `display_mode` include:
 - `'x'` - sagittal
 - `'y'` - coronal
 - `'z'` - axial
 - `'ortho'` - three cuts are performed in orthogonal directions
 - `'tiled'` - three cuts are performed and arranged in a 2x2 grid
 In this instance, we give `cut_coords` a scalar integer that indicates the number of slices to show in the axial view.
 %% Cell type:code id: tags:
 ``` python
 plotting.plot_anat(
    f'{FSLDIR}/data/standard/MNI152_T1_1mm.nii.gz',
    dim=-0.5,
    title='MNI T1 1mm',
    display_mode='z',
    cut_coords=10
 )
 ```
 %% Cell type:markdown id: tags:
 In the example below, a `display` object is returned by `plot_anat`.  We can use this object to update/amend the plot.  Here we add an overlay of the *HarvardOxford* atlas that ships with `FSL` to the image.
 We also use the `display` object to save the plot as a `*.png` image.
 %% Cell type:code id: tags:
 ``` python
 # plot MNI152 T1w and return display object
 display = plotting.plot_anat(
    f'{FSLDIR}/data/standard/MNI152_T1_1mm.nii.gz',
    dim=-0.5,
    title='MNI T1 1mm'
 )
 # overlay the HarvardOxford atlas
 display.add_contours(
    f'{FSLDIR}/data/atlases/HarvardOxford/HarvardOxford-cort-maxprob-thr50-1mm.nii.gz',
    filled=True
 )
 # save plot to file
 display.savefig('myplot.png')
 ```
 %% Cell type:markdown id: tags:
+`nilearn` plotting is built upon `matplotlib`, so we can use constructs from `matplotlib` to help us create more complex figures.
+In this example we:
+1. create a 1x2 grid of subplots using `subplots` from `matplotlib`
+2. plot a single slice of the MNI152 T1w in the first subplot using `plot_anat` from `nilearn`
+3. plot a histogram of the intensities of the MNI152 T12 in the second subplot using `hist` from `matplotlib`
+4. style the histogram by setting the x/y labels
+> **NOTE:** Here we use `load` and `get_fdata` from the [`nibabel`](https://nipy.org/nibabel/) package to load the data from the MNI152 T1w nifti for the histogram.
+%% Cell type:code id: tags:
+``` python
+# create matplotlib figure with 1x2 subplots
+fig, ax = plt.subplots(1, 2, figsize=(10, 5))
+# plot MNI T1w slice in first subplot
+mni_t1 = f'{FSLDIR}/data/standard/MNI152_T1_1mm.nii.gz'
+display = plotting.plot_anat(
+    mni_t1,
+    dim=-0.5,
+    axes=ax[0],
+    display_mode='z',
+    cut_coords=[15]
+)
+# plot histogram of MNI T1w intensity in second subplot
+mni_t1_data = nb.load(mni_t1).get_fdata().ravel()
+ax[1].hist(mni_t1_data, bins=25)
+ax[1].set_ylabel('count')
+ax[1].set_xlabel('intensity')
+```
+%% Cell type:markdown id: tags:
 >
 > **Exercise:**
 >
 > Create a PNG figure that displays the same **Harvard-Oxford** parcellation, using a different colormap, and axial images in a 3x5 grid.
 >
 %% Cell type:code id: tags:
 ``` python
 # YOUR CODE HERE
 ```
 %% Cell type:markdown id: tags:
 ## Plotting a statistical map
 The examples in this section demonstrate how to plot a statistical map as an overlay on an anatomical image.  Both images must be in the same space.
 First we will download a motor task statistical map from NeuroVault.
 > **Note:** We use a method from [`nilearn`](https://nilearn.github.io/index.html) called [`fetch_neurovault_motor_task`](https://nilearn.github.io/modules/generated/nilearn.datasets.fetch_neurovault_motor_task.html) to download the statistical map.
 %% Cell type:code id: tags:
 ``` python
 motor_images = datasets.fetch_neurovault_motor_task()
 stat_img = motor_images.images[0]
 print(stat_img)
 ```
 %% Cell type:markdown id: tags:
 Now we can plot the statistical map as an overlay on the MNI152 T1w.  We theshold the statistical map using the `threshold` argument.
 > **NOTE:** Here we use [`plot_stat_map`](https://nilearn.github.io/modules/generated/nilearn.plotting.plot_stat_map.html) from the [`nilearn`](https://nilearn.github.io/index.html) package to plot the orthographic images
 %% Cell type:code id: tags:
 ``` python
 plotting.plot_stat_map(
    stat_img,
    threshold=3,
    bg_img=f'{FSLDIR}/data/standard/MNI152_T1_1mm.nii.gz'
 )
 ```
 %% Cell type:markdown id: tags:
 Like with the `plot_anat` examples earlier, we can style the plot and change the layout and views.
 %% Cell type:code id: tags:
 ``` python
 plotting.plot_stat_map(
    stat_img,
    threshold=3,
    bg_img=f'{FSLDIR}/data/standard/MNI152_T1_1mm.nii.gz',
    display_mode='z',
    cut_coords=10,
    title='motor-task',
    dim=-0.5,
    vmax=10
 )
 ```
 %% Cell type:markdown id: tags:
 In this next example we first find the coordinate of the centre of the largest connected component in the statistical map, then we plot an ortho view that is centred on this coordinate.
 %% Cell type:code id: tags:
 ``` python
 # find the coordinate of the centre of the largest connected component in the statistical map
 coord = plotting.find_xyz_cut_coords(stat_img)
 print(f'Center of the largest activation connected component = {coord}')
 # plot an ortho view that is centred on this coordinate
 plotting.plot_stat_map(
    stat_img,
    threshold=3,
    bg_img=f'{FSLDIR}/data/standard/MNI152_T1_1mm.nii.gz',
    display_mode='ortho',
    cut_coords=coord,
    title='motor-task',
    dim=-0.5,
    vmax=10
 )
 ```
 %% Cell type:markdown id: tags:
 `nilearn` has some support for **interactive** viewing of volumetic images with the `view_img` function.  Try clicking on the plot and moving the cursor around!
 %% Cell type:code id: tags:
 ``` python
 view = plotting.view_img(stat_img, threshold=3)
 view  # view interactive plot inline
 ```
 %% Cell type:code id: tags:
 ``` python
 view = plotting.view_img(stat_img, threshold=3)
 view.open_in_browser() # open interactive plot in new web browser
 ```
 %% Cell type:markdown id: tags:
 ## 2D maximum intensity projection
 > Maximum intensity projection (MIP) is a method for 3D data that projects in the visualization plane the voxels with maximum intensity that fall in the way of parallel rays traced from the viewpoint to the plane of projection. https://en.wikipedia.org/wiki/Maximum_intensity_projection
 `nilearn` can plot a maximum intensity projection overlayed on a brain schematic referred to as the "glass brain".  In this example, the MIP of the motor task statistical map used in the previous examples is plotted on the glass brain.
 > **NOTE:** Here we use [`plot_glass_brain`](https://nilearn.github.io/modules/generated/nilearn.plotting.plot_glass_brain.html) from the [`nilearn`](https://nilearn.github.io/index.html) package to plot the maximum intensity projection.
 %% Cell type:code id: tags:
 ``` python
 plotting.plot_glass_brain(
    stat_img,
    title='2D max-intensity projection',
    threshold=3,
 )
 ```
 %% Cell type:markdown id: tags:
 ## Surfaces
 `nilearn` has baked in functionality to project a volumetric image onto the surface and visualise it.
 Here we visualise the same volumetric motor task statistical map, from earlier examples, on the inflated surface.
 > **NOTE:** Here we use [`plot_img_on_surf`](https://nilearn.github.io/modules/generated/nilearn.plotting.plot_img_on_surf.html) from the [`nilearn`](https://nilearn.github.io/index.html) package to plot the volumetric statistical map on the surface.
 %% Cell type:code id: tags:
 ``` python
 plotting.plot_img_on_surf(
    stat_img,
    inflate=True,
    threshold=0.5,
    vmax=6
 );
 ```
 %% Cell type:markdown id: tags:
 `nilearn` also has some support for **interactive** viewing of volumetic images on the surface with the `view_img_on_surf` function. Try clicking on the plot and moving the cursor around!
 %% Cell type:code id: tags:
 ``` python
 view = plotting.view_img_on_surf(
    stat_img,
    threshold=0.5,
    surf_mesh='fsaverage',
    vmax=6
 )
 view # view interactive plot inline
 ```
 %% Cell type:code id: tags:
 ``` python
 view = plotting.view_img_on_surf(
    stat_img,
    threshold=0.5,
    surf_mesh='fsaverage',
    vmax=6
 )
 view.open_in_browser() # view interactive plot inline
 ```
 %% Cell type:markdown id: tags:
 >
 > **Exercise:**
 >
-> Visualise thee **Harvard-Oxford** atlas on a surface in the weeb Browser
+> Visualise thee **Harvard-Oxford** atlas on a surface in the web browser
 %% Cell type:code id: tags:
 ``` python
 # YOUR CODE HERE
 ```
 %% Cell type:markdown id: tags:
 That's all folks....