MSDL atlas

Multi-Subject Dictionary learning atlas.

Access

See nilearn.datasets.fetch_atlas_msdl.

Notes

Result maps of sparse Dictionary learning based on resting-state data.

This can be understand as a variant of ICA based on the assumption of sparsity rather than independence.

Direct download link: https://team.inria.fr/parietal/files/2015/01/MSDL_rois.zip

It can be downloaded at Spatially Constrained Parcellation[1], and cited using Varoquaux et al.[2].

See also Varoquaux and Craddock[3] for more information.

For more information about this dataset’s structure: https://team.inria.fr/parietal/research/spatial_patterns/spatial-patterns-in-resting-state/

Content

  • atlas_type: str. Type of atlas. See Probabilistic atlas and Deterministic atlas.

  • labels: list of str. List of the names of the regions. There are 39 labels such that data.labels[i] corresponds to map i.

  • maps: str. Full path to nifti file containing the Probabilistic atlas image (shape is equal to (40, 48, 35, 39)).

  • networks: list of str. 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: list of list of float. Length-3 tuple data.region_coords[i] contains the coordinates (x, y, z) of region i in MNI space.

  • template: str. The standardized space of analysis in which the data is provided.

References

License

usage is unrestricted for non-commercial research purposes.