MSDL atlas

Access

See nilearn.datasets.fetch_atlas_msdl.

Notes

Multi-subject Dictionary learning atlas.

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.

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.

Content

‘maps’:

Nifti images with the (probabilistic) region definitions

‘labels’:

CSV file specifying the label information

References

[1]

Spatially constrained parcellation. https://team.inria.fr/parietal/files/2015/01/MSDL_rois.zip. Accessed: 2021-05-19.

[2]

Gael Varoquaux, Alexandre Gramfort, Fabian Pedregosa, Vincent Michel, and Bertrand Thirion. Multi-subject dictionary learning to segment an atlas of brain spontaneous activity. In Information Processing in Medical Imaging, 562–573. Berlin, Heidelberg, 2011. Springer Berlin Heidelberg.

[3]

Gaël Varoquaux and R. Cameron Craddock. Learning and comparing functional connectomes across subjects. NeuroImage, 80:405–415, 2013. Mapping the Connectome. URL: https://www.sciencedirect.com/science/article/pii/S1053811913003340, doi:https://doi.org/10.1016/j.neuroimage.2013.04.007.

For more information about this dataset’s structure: https://team.inria.fr/parietal/18-2/spatial_patterns/spatial-patterns-in-resting-state/

License

usage is unrestricted for non-commercial research purposes.