Brain functional networks and parcels can extracted from resting-state fMRI. For this purpose we use a multi-subject version of sparse dictionary learning and estimate a group-level atlas of brain networks. This can be understand as a variant of ICA based on the assumption of sparsity rather than independence.
Download MSDL Atlas
The functional regions defined by this approach can be downloaded in the following reference atlas [Varoquaux et al 2011].
Application in connectomics
These regions can be used to define the nodes of a functional connectome, as in [Varoquaux & Craddock 2013].
- Multi-subject dictionary learning to segment an atlas of brain spontaneous activity Gaël Varoquaux, Alexandre Gramfort, Fabian Pedregosa, Vincent Michel, Bertrand Thirion Information Processing in Medical Imaging, 2011, pp. 562-573, Lecture Notes in Computer Science
- Learning and comparing functional connectomes across subjects. Gaël Varoquaux, R.C. Craddock NeuroImage, 2013