Dr. Brent Munsell’s Research Selected for Publication and Presentation with Medical Image Computing and Computer-Assisted Intervention (MICCAI)

Dr. Brent Munsell’s research on “Identifying Relationships in Functional and Structural Connectome Data Using a Hypergraph Learning Method” has been selected for publication in the medical journal, Medical Image Computing and Computer-Assisted Intervention (MICCAI).  Munsell will also attend the 19th International Conference, MICCAI 2016, to present the publication in October, in Athens, Greece.  

The 3-day MICCAI conference attracts world-leading biomedical scientists, engineers, and clinicians from a wide range of disciplines associated with medical imaging and computer assisted intervention.


The brain connectome provides an unprecedented degree of information about the organization of neuronal network architecture, both at a regional level, as well as regarding the entire brain network. Over the last several years, the neuroimaging community has made tremendous advancements in the analysis of structural connectomes derived from matter fiber tractography, or functional connectomes derived from time-series blood oxygen level signals. However, computational techniques that combine structural and functional connectome data to discover higher order relationships between fiber and signal synchronization, including the relationship with health and disease, has not been consistently performed. To overcome this shortcoming, a novel connectome feature selection technique is proposed that uses mathematical graphs to discover latent higher-order relationship in structural and functional connectome data when they are combined. Using publicly available connectome data from the UCMD database, experiments are provided that show SVM classifiers trained with structural and functional connectome features selected by our method are able to correctly identify Autism subjects with 88\% accuracy. Lastly, detailed information is provided that visually show the brain regions selected by our method whose fiber and signal synchronization characteristics are the most differentiating between Autism subjects and healthy controls.


For more information about the Department of Computer Science, visit compsci.cofc.edu.