A0518
Title: Bayesian multi-modal data integration
Authors: Rajarshi Guhaniyogi - Texas A & M university (United States) [presenting]
Abstract: The focus is on a multi-modal imaging data application where structural/spatial information from grey matter (GM) and brain connectivity information in the form of a brain connectome network from functional magnetic resonance imaging (fMRI) are available for a number of subjects with different degrees of a neurodegenerative disorder (ND). The clinical/scientific goal becomes identifying brain regions of interest significantly related to the speech rate measure to gain insight into an ND pathway. Viewing the brain connectome network and GM images as objects, a flexible joint object response regression framework of network and GM images on the ND measure is developed. A novel joint prior formulation is proposed on the network and structural image coefficients to exploit network information of the brain connectome while leveraging the topological linkages among the connectome network and anatomical information from GM to draw inferences on brain regions significantly related to the ND. The principled Bayesian framework allows precise uncertainty characterisation in ascertaining a region being actively related to ND. Strategies to draw scalable Bayesian inference in these models will be discussed.
