Multigraph Visualization for Feature Classification of Brain Network Data

Abstract

A Multigraph is a set of graphs with a common set of nodes but different sets of edges. Multigraph visualization has not received much attention so far. In this paper, we introduce a multigraph application in brain network data analysis that has a strong need for multigraph visualization. In this application, multigraph is used to represent brain connectome networks of multiple human subjects. A volumetric data set is constructed from the matrix representation of the multigraph. A volume visualization tool is then developed to assist the user to interactively and iteratively detect network features that may contribute to certain neurological conditions. We apply this technique to a brain connectome dataset for feature detection in the classification of Alzheimer's Disease (AD) patients. Preliminary results show significant improvements when interactively selected features are used.