Product Space Decompositions for Continuous Representations of Brain Connectivity.

We develop a method for the decomposition of structural brain connectivity estimates into locally coherent components, leveraging a non-parametric Bayesian hierarchical mixture model with tangent Gaussian components. This model provides a mechanism to share information across subjects while still including explicit mixture distributions of connections for each subject. It further uses mixture components defined directly on the surface of the brain, eschewing the usual graph-theoretic framework of structural connectivity in favor of a continuous model that avoids a priori assumptions of parcellation configuration. The results of two experiments on a test-retest dataset are presented, to validate the method. We also provide an example analysis of the components.