.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "auto_examples/03_connectivity/plot_extract_regions_dictlearning_maps.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code or to run this example in your browser via Binder .. rst-class:: sphx-glr-example-title .. _sphx_glr_auto_examples_03_connectivity_plot_extract_regions_dictlearning_maps.py: Regions extraction using dictionary learning and functional connectomes ======================================================================= This example shows how to use :class:`nilearn.regions.RegionExtractor` to extract spatially constrained brain regions from whole brain maps decomposed using :term:`Dictionary learning` and use them to build a :term:`functional connectome`. We used 20 movie-watching functional datasets from :func:`nilearn.datasets.fetch_development_fmri` and :class:`nilearn.decomposition.DictLearning` for set of brain atlas maps. This example can also be inspired to apply the same steps to even regions extraction using :term:`ICA` maps. In that case, idea would be to replace :term:`Dictionary learning` to canonical :term:`ICA` decomposition using :class:`nilearn.decomposition.CanICA` Please see the related documentation of :class:`nilearn.regions.RegionExtractor` for more details. .. GENERATED FROM PYTHON SOURCE LINES 27-31 Fetch brain development functional datasets ------------------------------------------- We use nilearn's datasets downloading utilities .. GENERATED FROM PYTHON SOURCE LINES 31-37 .. code-block:: Python from nilearn import datasets rest_dataset = datasets.fetch_development_fmri(n_subjects=20) func_filenames = rest_dataset.func confounds = rest_dataset.confounds .. GENERATED FROM PYTHON SOURCE LINES 38-45 Extract functional networks with :term:`Dictionary learning` ------------------------------------------------------------ Import :class:`~nilearn.decomposition.DictLearning` from the :mod:`~nilearn.decomposition` module, instantiate the object, and :meth:`~nilearn.decomposition.DictLearning.fit` the model to the functional datasets .. GENERATED FROM PYTHON SOURCE LINES 45-71 .. code-block:: Python from nilearn.decomposition import DictLearning # Initialize DictLearning object dict_learn = DictLearning( n_components=8, smoothing_fwhm=6.0, memory="nilearn_cache", memory_level=2, random_state=0, standardize="zscore_sample", ) # Fit to the data dict_learn.fit(func_filenames) # Resting state networks/maps in attribute `components_img_` components_img = dict_learn.components_img_ # Visualization of functional networks # Show networks using plotting utilities from nilearn import plotting plotting.plot_prob_atlas( components_img, view_type="filled_contours", title="Dictionary Learning maps", ) .. image-sg:: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_001.png :alt: plot extract regions dictlearning maps :srcset: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_001.png :class: sphx-glr-single-img .. rst-class:: sphx-glr-script-out .. code-block:: none /home/himanshu/Desktop/nilearn_work/nilearn/nilearn/plotting/displays/_axes.py:74: UserWarning: linewidths is ignored by contourf im = getattr(ax, type)( .. GENERATED FROM PYTHON SOURCE LINES 72-80 Extract regions from networks ----------------------------- Import :class:`~nilearn.regions.RegionExtractor` from the :mod:`~nilearn.regions` module. ``threshold=0.5`` indicates that we keep nominal of amount nonzero :term:`voxels` across all maps, less the threshold means that more intense non-voxels will be survived. .. GENERATED FROM PYTHON SOURCE LINES 80-110 .. code-block:: Python from nilearn.regions import RegionExtractor extractor = RegionExtractor( components_img, threshold=0.5, thresholding_strategy="ratio_n_voxels", extractor="local_regions", standardize="zscore_sample", standardize_confounds="zscore_sample", min_region_size=1350, ) # Just call fit() to process for regions extraction extractor.fit() # Extracted regions are stored in regions_img_ regions_extracted_img = extractor.regions_img_ # Each region index is stored in index_ regions_index = extractor.index_ # Total number of regions extracted n_regions_extracted = regions_extracted_img.shape[-1] # Visualization of region extraction results title = ( "%d regions are extracted from %d components." "\nEach separate color of region indicates extracted region" % (n_regions_extracted, 8) ) plotting.plot_prob_atlas( regions_extracted_img, view_type="filled_contours", title=title ) .. image-sg:: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_002.png :alt: plot extract regions dictlearning maps :srcset: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_002.png :class: sphx-glr-single-img .. rst-class:: sphx-glr-script-out .. code-block:: none /home/himanshu/.local/miniconda3/envs/nilearnpy/lib/python3.12/site-packages/numpy/ma/core.py:2820: UserWarning: Warning: converting a masked element to nan. _data = np.array(data, dtype=dtype, copy=copy, .. GENERATED FROM PYTHON SOURCE LINES 111-120 Compute correlation coefficients -------------------------------- First we need to do subjects timeseries signals extraction and then estimating correlation matrices on those signals. To extract timeseries signals, we call :meth:`~nilearn.regions.RegionExtractor.transform` onto each subject functional data stored in ``func_filenames``. To estimate correlation matrices we import connectome utilities from nilearn. .. GENERATED FROM PYTHON SOURCE LINES 120-143 .. code-block:: Python from nilearn.connectome import ConnectivityMeasure correlations = [] # Initializing ConnectivityMeasure object with kind='correlation' connectome_measure = ConnectivityMeasure( kind="correlation", standardize="zscore_sample", ) for filename, confound in zip(func_filenames, confounds): # call transform from RegionExtractor object to extract timeseries signals timeseries_each_subject = extractor.transform(filename, confounds=confound) # call fit_transform from ConnectivityMeasure object correlation = connectome_measure.fit_transform([timeseries_each_subject]) # saving each subject correlation to correlations correlations.append(correlation) # Mean of all correlations import numpy as np mean_correlations = np.mean(correlations, axis=0).reshape( n_regions_extracted, n_regions_extracted ) .. GENERATED FROM PYTHON SOURCE LINES 144-151 Plot resulting connectomes -------------------------- First we plot the mean of correlation matrices with :func:`~nilearn.plotting.plot_matrix`, and we use :func:`~nilearn.plotting.plot_connectome` to plot the connectome relations. .. GENERATED FROM PYTHON SOURCE LINES 151-167 .. code-block:: Python title = f"Correlation between {int(n_regions_extracted)} regions" # First plot the matrix display = plotting.plot_matrix( mean_correlations, vmax=1, vmin=-1, colorbar=True, title=title ) # Then find the center of the regions and plot a connectome regions_img = regions_extracted_img coords_connectome = plotting.find_probabilistic_atlas_cut_coords(regions_img) plotting.plot_connectome( mean_correlations, coords_connectome, edge_threshold="90%", title=title ) .. rst-class:: sphx-glr-horizontal * .. image-sg:: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_003.png :alt: Correlation between 14 regions :srcset: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_003.png :class: sphx-glr-multi-img * .. image-sg:: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_004.png :alt: plot extract regions dictlearning maps :srcset: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_004.png :class: sphx-glr-multi-img .. rst-class:: sphx-glr-script-out .. code-block:: none .. GENERATED FROM PYTHON SOURCE LINES 168-173 Plot regions extracted for only one specific network ---------------------------------------------------- First, we plot a network of ``index=4`` without region extraction (left plot). .. GENERATED FROM PYTHON SOURCE LINES 173-184 .. code-block:: Python from nilearn import image img = image.index_img(components_img, 4) coords = plotting.find_xyz_cut_coords(img) display = plotting.plot_stat_map( img, cut_coords=coords, colorbar=False, title="Showing one specific network", ) .. image-sg:: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_005.png :alt: plot extract regions dictlearning maps :srcset: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_005.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 185-191 Now, we plot (right side) same network after region extraction to show that connected regions are nicely separated. Each brain extracted region is identified as separate color. For this, we take the indices of the all regions extracted related to original network given as 4. .. GENERATED FROM PYTHON SOURCE LINES 191-207 .. code-block:: Python regions_indices_of_map3 = np.where(np.array(regions_index) == 4) display = plotting.plot_anat( cut_coords=coords, title="Regions from this network" ) # Add as an overlay all the regions of index 4 colors = "rgbcmyk" for each_index_of_map3, color in zip(regions_indices_of_map3[0], colors): display.add_overlay( image.index_img(regions_extracted_img, each_index_of_map3), cmap=plotting.cm.alpha_cmap(color), ) plotting.show() .. image-sg:: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_006.png :alt: plot extract regions dictlearning maps :srcset: /auto_examples/03_connectivity/images/sphx_glr_plot_extract_regions_dictlearning_maps_006.png :class: sphx-glr-single-img .. rst-class:: sphx-glr-timing **Total running time of the script:** (3 minutes 26.005 seconds) **Estimated memory usage:** 1382 MB .. _sphx_glr_download_auto_examples_03_connectivity_plot_extract_regions_dictlearning_maps.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: binder-badge .. image:: images/binder_badge_logo.svg :target: https://mybinder.org/v2/gh/nilearn/nilearn/0.10.4?urlpath=lab/tree/notebooks/auto_examples/03_connectivity/plot_extract_regions_dictlearning_maps.ipynb :alt: Launch binder :width: 150 px .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: plot_extract_regions_dictlearning_maps.ipynb ` .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: plot_extract_regions_dictlearning_maps.py ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_