Meeting Banner
Abstract #0307

Cerebral Cortex Parcellation by Fusion of Local and Global Functional Connectivity Feature

Alexander Schaefer1, Ru Kong1, Evan M. Gordon2, Timothy Laumann 3, Simon B. Eickhoff4,5, Xi-Nian Zuo6, Avram J. Holmes7, and B.T. Thomas Yeo1

1Department of Electrical and Computer Engineering, ASTAR-NUS Clinical Imaging Research Centre, Singapore Institute for Neurotechnology and Memory Networks Program, National University of Singapore, Singapore, Singapore, 2VISN 17 Center of Excellence for Research on Returning War Veterans, Waco, TX, United States, 3Department of Neurology, Washington University in St. Louis, St. Louis, MO, United States, 4Institut for Clinical Neuroscience, Heinrich Heine University, Düsseldorf, Germany, 5Institute for Neuroscience and Medicine, Research Center Jülich, Jülich, Germany, 6Lab for Functional Connectome and Development, Division of Cognitive and Developmental, Chinese Academy of Sciences, Beijing, China, People's Republic of, 7Department of Psychology, Yale University, New Haven, CT, United States

Current approaches to cerebral cortex parcellation with resting-state functional connectivity MRI (fcMRI) can be divided into local (e.g., fcMRI gradients) and global (e.g., clustering) approaches. Previous work suggests that local and global approaches capture complementary aspects of brain organization. Here we propose a novel hidden Markov Random Field model that fuses local connectivity gradients with global functional connectivity similarities. The resulting parcellation compares favorably with a state-of-the-art parcellation in terms of (1) parcel homogeneity in two different datasets and (2) agreement with cytoarchitectonic and visuotopic boundaries.

This abstract and the presentation materials are available to members only; a login is required.

Join Here