Note
Go to the end to download the full example code. or to run this example in your browser via Binder
Group Sparse inverse covariance for multi-subject connectome¶
This example shows how to estimate a connectome on a group of subjects using the group sparse inverse covariance estimate.
This example is a toy example as running it on more subjects will require a longer run time.
dataset
This example uses the MSDL atlas to extract data from the development fMRI dataset.
import numpy as np
from nilearn.plotting import plot_matrix
def plot_matrices(cov, prec, title, labels):
"""Plot covariance and precision matrices, for a given processing."""
prec = prec.copy() # avoid side effects
# Put zeros on the diagonal, for graph clarity.
size = prec.shape[0]
prec[list(range(size)), list(range(size))] = 0
span = max(abs(prec.min()), abs(prec.max()))
# Display covariance matrix
plot_matrix(
cov,
vmin=-1,
vmax=1,
title=f"{title} / covariance",
labels=labels,
)
# Display precision matrix
plot_matrix(
prec,
vmin=-span,
vmax=span,
title=f"{title} / precision",
labels=labels,
)
Fetching datasets¶
from nilearn.datasets import fetch_development_fmri
n_subjects = 4 # subjects to consider for group-sparse covariance (max: 40)
rest_dataset = fetch_development_fmri(n_subjects=n_subjects)
# print basic information on the dataset
print(
f"First subject functional nifti image (4D) is at: {rest_dataset.func[0]}"
)
[fetch_development_fmri] Dataset directory found: /home/runner/work/nilearn/nilearn/nilearn_data/development_fmri
First subject functional nifti image (4D) is at: /home/runner/work/nilearn/nilearn/nilearn_data/development_fmri/sub-pixar123_task-pixar_space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz
Extracting region signals¶
from nilearn.datasets import fetch_atlas_msdl
from nilearn.maskers import MultiNiftiMapsMasker
atlas = fetch_atlas_msdl()
print(atlas.description.content)
atlas_img = atlas.maps
labels = atlas.labels
[fetch_atlas_msdl] Dataset directory found: /home/runner/work/nilearn/nilearn/nilearn_data/msdl_atlas
{'labels': {'type': list[str], 'desc': 'List of the names of the regions. There are 39 labels such that ``data.labels[i]`` corresponds to map ``i``.'}, 'maps': {'type': <class 'str'>, 'desc': 'Full path to nifti file containing the :term:`Probabilistic atlas` image (shape is equal to ``(40, 48, 35, 39)``).'}, 'networks': {'type': list[str], 'desc': 'List containing the names of the networks. There are 39 network names such that ``data.networks[i]`` is the network name of region ``i``.'}, 'region_coords': {'type': list[list[float]], 'desc': 'Length-3 :obj:`tuple` ``data.region_coords[i]`` contains the coordinates ``(x, y, z)`` of region ``i`` in :term:`MNI` space.'}, 'atlas_type': {'type': <class 'str'>, 'desc': '\n Type of atlas.\n See :term:`Probabilistic atlas` and :term:`Deterministic atlas`.'}, 'template': {'type': <class 'str'>, 'desc': 'The standardized space of analysis in which the data is provided.'}}
masker = MultiNiftiMapsMasker(
atlas_img,
resampling_target="maps",
detrend=True,
high_variance_confounds=True,
low_pass=None,
high_pass=0.01,
t_r=rest_dataset.t_r,
standardize="zscore_sample",
standardize_confounds=True,
memory="nilearn_cache",
memory_level=1,
verbose=1,
)
func_filenames = rest_dataset.func
confound_filenames = rest_dataset.confounds
subject_time_series = masker.fit_transform(
func_filenames, confounds=confound_filenames
)
[MultiNiftiMapsMasker.fit_transform] Loading data from [
sub-pixar123_task-...,
...
sub-pixar003_task-...,
]
[MultiNiftiMapsMasker.fit_transform] Loading regions from .../msdl_rois.nii
[MultiNiftiMapsMasker.fit_transform] Finished fit
________________________________________________________________________________
[Memory] Calling nilearn.image.image.high_variance_confounds...
high_variance_confounds('/home/runner/work/nilearn/nilearn/nilearn_data/development_fmri/sub-pixar123_task-pixar_space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz')
__________________________________________high_variance_confounds - 0.5s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.image.image.high_variance_confounds...
high_variance_confounds('/home/runner/work/nilearn/nilearn/nilearn_data/development_fmri/sub-pixar001_task-pixar_space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz')
__________________________________________high_variance_confounds - 0.4s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.image.image.high_variance_confounds...
high_variance_confounds('/home/runner/work/nilearn/nilearn/nilearn_data/development_fmri/sub-pixar002_task-pixar_space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz')
__________________________________________high_variance_confounds - 0.5s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.image.image.high_variance_confounds...
high_variance_confounds('/home/runner/work/nilearn/nilearn/nilearn_data/development_fmri/sub-pixar003_task-pixar_space-MNI152NLin2009cAsym_desc-preproc_bold.nii.gz')
__________________________________________high_variance_confounds - 0.4s, 0.0min
________________________________________________________________________________
[Memory] Calling nilearn.maskers.nifti_maps_masker.NiftiMapsMasker.transform_single_imgs...
transform_single_imgs(imgs=<nibabel.nifti1.Nifti1Image object at 0x72031a2d3110>, confounds=array([[-0.000233, ..., -0.048779],
...,
[-0.026896, ..., 0.155444]]), sample_mask=None)
/home/runner/work/nilearn/nilearn/examples/03_connectivity/plot_multi_subject_connectome.py:97: UserWarning:
Resampling images at transform time...
To avoid this warning, make sure to resample the images you want to transform to the shape of the maps or set resampling_target to 'data'.
________________________________________________________________________________
[Memory] Calling nilearn.maskers.base_masker.filter_and_extract...
filter_and_extract(<nibabel.nifti1.Nifti1Image object at 0x72031a2d3110>, <nilearn.maskers.nifti_maps_masker._ExtractionFunctor object at 0x72031a2d2810>, { 'allow_overlap': True,
'clean_args': None,
'clean_kwargs': {},
'cmap': 'CMRmap_r',
'detrend': True,
'dtype': None,
'high_pass': 0.01,
'high_variance_confounds': True,
'low_pass': None,
'maps_img': '/home/runner/work/nilearn/nilearn/nilearn_data/msdl_atlas/MSDL_rois/msdl_rois.nii',
'mask_img': None,
'reports': True,
'smoothing_fwhm': None,
'standardize': 'zscore_sample',
'standardize_confounds': True,
't_r': 2,
'target_affine': array([[ 4., 0., 0., -78.],
[ 0., 4., 0., -111.],
[ 0., 0., 4., -51.],
[ 0., 0., 0., 1.]]),
'target_shape': (40, 48, 35)}, confounds=array([[-0.000233, ..., -0.048779],
...,
[-0.026896, ..., 0.155444]]), sample_mask=None, memory=Memory(location=nilearn_cache/joblib), memory_level=1, verbose=1, sklearn_output_config=None)
[MultiNiftiMapsMasker.fit_transform] Loading data from <nibabel.nifti1.Nifti1Image object at 0x72031a2d3110>
[MultiNiftiMapsMasker.fit_transform] Resampling images
[MultiNiftiMapsMasker.fit_transform] Extracting region signals
[MultiNiftiMapsMasker.fit_transform] Cleaning extracted signals
_______________________________________________filter_and_extract - 4.2s, 0.1min
____________________________________________transform_single_imgs - 4.3s, 0.1min
________________________________________________________________________________
[Memory] Calling nilearn.maskers.nifti_maps_masker.NiftiMapsMasker.transform_single_imgs...
transform_single_imgs(imgs=<nibabel.nifti1.Nifti1Image object at 0x72031a2d37d0>, confounds=array([[ 0.013422, ..., -0.057023],
...,
[ 0.087146, ..., 0.102714]]), sample_mask=None)
/home/runner/work/nilearn/nilearn/examples/03_connectivity/plot_multi_subject_connectome.py:97: UserWarning:
Resampling images at transform time...
To avoid this warning, make sure to resample the images you want to transform to the shape of the maps or set resampling_target to 'data'.
________________________________________________________________________________
[Memory] Calling nilearn.maskers.base_masker.filter_and_extract...
filter_and_extract(<nibabel.nifti1.Nifti1Image object at 0x72031a2d37d0>, <nilearn.maskers.nifti_maps_masker._ExtractionFunctor object at 0x720320908b90>, { 'allow_overlap': True,
'clean_args': None,
'clean_kwargs': {},
'cmap': 'CMRmap_r',
'detrend': True,
'dtype': None,
'high_pass': 0.01,
'high_variance_confounds': True,
'low_pass': None,
'maps_img': '/home/runner/work/nilearn/nilearn/nilearn_data/msdl_atlas/MSDL_rois/msdl_rois.nii',
'mask_img': None,
'reports': True,
'smoothing_fwhm': None,
'standardize': 'zscore_sample',
'standardize_confounds': True,
't_r': 2,
'target_affine': array([[ 4., 0., 0., -78.],
[ 0., 4., 0., -111.],
[ 0., 0., 4., -51.],
[ 0., 0., 0., 1.]]),
'target_shape': (40, 48, 35)}, confounds=array([[ 0.013422, ..., -0.057023],
...,
[ 0.087146, ..., 0.102714]]), sample_mask=None, memory=Memory(location=nilearn_cache/joblib), memory_level=1, verbose=1, sklearn_output_config=None)
[MultiNiftiMapsMasker.fit_transform] Loading data from <nibabel.nifti1.Nifti1Image object at 0x72031a2d37d0>
[MultiNiftiMapsMasker.fit_transform] Resampling images
[MultiNiftiMapsMasker.fit_transform] Extracting region signals
[MultiNiftiMapsMasker.fit_transform] Cleaning extracted signals
_______________________________________________filter_and_extract - 4.2s, 0.1min
____________________________________________transform_single_imgs - 4.3s, 0.1min
________________________________________________________________________________
[Memory] Calling nilearn.maskers.nifti_maps_masker.NiftiMapsMasker.transform_single_imgs...
transform_single_imgs(imgs=<nibabel.nifti1.Nifti1Image object at 0x72031a2d3710>, confounds=array([[ 0. , ..., -0.087084],
...,
[ 0.00349 , ..., -0.02587 ]]), sample_mask=None)
/home/runner/work/nilearn/nilearn/examples/03_connectivity/plot_multi_subject_connectome.py:97: UserWarning:
Resampling images at transform time...
To avoid this warning, make sure to resample the images you want to transform to the shape of the maps or set resampling_target to 'data'.
________________________________________________________________________________
[Memory] Calling nilearn.maskers.base_masker.filter_and_extract...
filter_and_extract(<nibabel.nifti1.Nifti1Image object at 0x72031a2d3710>, <nilearn.maskers.nifti_maps_masker._ExtractionFunctor object at 0x7203581c5050>, { 'allow_overlap': True,
'clean_args': None,
'clean_kwargs': {},
'cmap': 'CMRmap_r',
'detrend': True,
'dtype': None,
'high_pass': 0.01,
'high_variance_confounds': True,
'low_pass': None,
'maps_img': '/home/runner/work/nilearn/nilearn/nilearn_data/msdl_atlas/MSDL_rois/msdl_rois.nii',
'mask_img': None,
'reports': True,
'smoothing_fwhm': None,
'standardize': 'zscore_sample',
'standardize_confounds': True,
't_r': 2,
'target_affine': array([[ 4., 0., 0., -78.],
[ 0., 4., 0., -111.],
[ 0., 0., 4., -51.],
[ 0., 0., 0., 1.]]),
'target_shape': (40, 48, 35)}, confounds=array([[ 0. , ..., -0.087084],
...,
[ 0.00349 , ..., -0.02587 ]]), sample_mask=None, memory=Memory(location=nilearn_cache/joblib), memory_level=1, verbose=1, sklearn_output_config=None)
[MultiNiftiMapsMasker.fit_transform] Loading data from <nibabel.nifti1.Nifti1Image object at 0x72031a2d3710>
[MultiNiftiMapsMasker.fit_transform] Resampling images
[MultiNiftiMapsMasker.fit_transform] Extracting region signals
[MultiNiftiMapsMasker.fit_transform] Cleaning extracted signals
_______________________________________________filter_and_extract - 4.3s, 0.1min
____________________________________________transform_single_imgs - 4.4s, 0.1min
________________________________________________________________________________
[Memory] Calling nilearn.maskers.nifti_maps_masker.NiftiMapsMasker.transform_single_imgs...
transform_single_imgs(imgs=<nibabel.nifti1.Nifti1Image object at 0x7203719e40d0>, confounds=array([[ 6.680960e-06, ..., -6.231628e-02],
...,
[ 2.379980e-02, ..., -2.286822e-02]]), sample_mask=None)
/home/runner/work/nilearn/nilearn/examples/03_connectivity/plot_multi_subject_connectome.py:97: UserWarning:
Resampling images at transform time...
To avoid this warning, make sure to resample the images you want to transform to the shape of the maps or set resampling_target to 'data'.
________________________________________________________________________________
[Memory] Calling nilearn.maskers.base_masker.filter_and_extract...
filter_and_extract(<nibabel.nifti1.Nifti1Image object at 0x7203719e40d0>, <nilearn.maskers.nifti_maps_masker._ExtractionFunctor object at 0x7203703f7490>, { 'allow_overlap': True,
'clean_args': None,
'clean_kwargs': {},
'cmap': 'CMRmap_r',
'detrend': True,
'dtype': None,
'high_pass': 0.01,
'high_variance_confounds': True,
'low_pass': None,
'maps_img': '/home/runner/work/nilearn/nilearn/nilearn_data/msdl_atlas/MSDL_rois/msdl_rois.nii',
'mask_img': None,
'reports': True,
'smoothing_fwhm': None,
'standardize': 'zscore_sample',
'standardize_confounds': True,
't_r': 2,
'target_affine': array([[ 4., 0., 0., -78.],
[ 0., 4., 0., -111.],
[ 0., 0., 4., -51.],
[ 0., 0., 0., 1.]]),
'target_shape': (40, 48, 35)}, confounds=array([[ 6.680960e-06, ..., -6.231628e-02],
...,
[ 2.379980e-02, ..., -2.286822e-02]]), sample_mask=None, memory=Memory(location=nilearn_cache/joblib), memory_level=1, verbose=1, sklearn_output_config=None)
[MultiNiftiMapsMasker.fit_transform] Loading data from <nibabel.nifti1.Nifti1Image object at 0x7203719e40d0>
[MultiNiftiMapsMasker.fit_transform] Resampling images
[MultiNiftiMapsMasker.fit_transform] Extracting region signals
[MultiNiftiMapsMasker.fit_transform] Cleaning extracted signals
_______________________________________________filter_and_extract - 4.2s, 0.1min
____________________________________________transform_single_imgs - 4.3s, 0.1min
Computing group-sparse precision matrices¶
from nilearn.connectome import GroupSparseCovarianceCV
gsc = GroupSparseCovarianceCV(verbose=1)
gsc.fit(subject_time_series)
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 7.2s finished
[GroupSparseCovarianceCV.fit] [GroupSparseCovarianceCV] Done refinement 0 out of 4
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 12.2s finished
[GroupSparseCovarianceCV.fit] [GroupSparseCovarianceCV] Done refinement 1 out of 4
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 14.2s finished
[GroupSparseCovarianceCV.fit] [GroupSparseCovarianceCV] Done refinement 2 out of 4
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 11.4s finished
[GroupSparseCovarianceCV.fit] [GroupSparseCovarianceCV] Done refinement 3 out of 4
[GroupSparseCovarianceCV.fit] Final optimization
from sklearn.covariance import GraphicalLassoCV
gl = GraphicalLassoCV(verbose=True)
gl.fit(np.concatenate(subject_time_series))
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 0.4s finished
[GraphicalLassoCV] Done refinement 1 out of 4: 0s
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 0.5s finished
[GraphicalLassoCV] Done refinement 2 out of 4: 0s
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 0.6s finished
[GraphicalLassoCV] Done refinement 3 out of 4: 1s
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 0.5s finished
[GraphicalLassoCV] Done refinement 4 out of 4: 2s
Displaying results¶
from nilearn.plotting import (
find_probabilistic_atlas_cut_coords,
plot_connectome,
show,
)
atlas_region_coords = find_probabilistic_atlas_cut_coords(atlas_img)
plot_connectome(
gl.covariance_,
atlas_region_coords,
edge_threshold="90%",
title="Covariance",
display_mode="lzr",
)
<nilearn.plotting.displays._projectors.LZRProjector object at 0x72036fae4950>
plot_connectome(
-gl.precision_,
atlas_region_coords,
edge_threshold="90%",
title="Sparse inverse covariance (GraphicalLasso)",
display_mode="lzr",
edge_vmax=0.5,
edge_vmin=-0.5,
)
plot_connectome(
-gsc.precisions_[..., 0],
atlas_region_coords,
edge_threshold="90%",
title="GroupSparseCovariance",
display_mode="lzr",
edge_vmax=0.5,
edge_vmin=-0.5,
)
show()
plot_matrices(gl.covariance_, gl.precision_, "GraphicalLasso", labels)
plot_matrices(
gsc.covariances_[..., 0],
gsc.precisions_[..., 0],
"GroupSparseCovariance",
labels,
)
show()
Total running time of the script: (1 minutes 16.881 seconds)
Estimated memory usage: 1434 MB
