|
Abstract:
|
Data on the brain's structural or functional connections are frequently represented in the form of networks, with a different network for each subject in the study. These networks all share the same set of nodes and can thus be analyzed jointly. Current work tends to either reduce them to global summaries such as modularity, or vectorize the edge values and ignore the network structure. I will give an overview of our recent work that aims to to take advantage of the underlying network structure in analysis of fMRI data without reducing it to global summaries. The methods cover both taking advantage of known anatomical or functional subnetworks of the brain, and learning new subnetworks that are correlated with a phenotype of interest. We consider applications to fMRI data on schizophrenia and on attention dysfunction in children.
Includes joint work with Yura Kim, Jesus Arroyo, Daniel Kessler, Chandra Sripada, and Stephan Taylor.
|
