A Novel Sparse Group Gaussian Graphical Model for Functional Connectivity Estimation

• Published in: Information Processing in Medical Imaging Vol. 23; pp. 256 - 267
• Main Authors: Ng, Bernard, Varoquaux, Gaël, Poline, Jean Baptiste, Thirion, Bertrand
• Format: Book Chapter Journal Article
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2013
• Series: Lecture Notes in Computer Science
• Subjects: Algorithms; Brain - physiology; brain connectivity; Brain Mapping - methods; Computer Simulation; Connectome - methods; Data Interpretation, Statistical; fMRI; Gaussian graphical model; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Models, Neurological; Models, Statistical; Normal Distribution; Pattern Recognition, Automated - methods; regularized consensus optimization; Reproducibility of Results; Sensitivity and Specificity; sparse inverse covariance estimation
• ISBN: 3642388671; 9783642388675
• ISSN: 0302-9743; 1011-2499; 1611-3349
• DOI: 10.1007/978-3-642-38868-2_22

The estimation of intra-subject functional connectivity is greatly complicated by the small sample size and complex noise structure in functional magnetic resonance imaging (fMRI) data. Pooling samples across subjects improves the conditioning of the estimation, but loses subject-specific connectivity information. In this paper, we propose a new sparse group Gaussian graphical model (SGGGM) that facilitates joint estimation of intra-subject and group-level connectivity. This is achieved by casting functional connectivity estimation as a regularized consensus optimization problem, in which information across subjects is aggregated in learning group-level connectivity and group information is propagated back in estimating intra-subject connectivity. On synthetic data, we show that incorporating group information using SGGGM significantly enhances intra-subject connectivity estimation over existing techniques. More accurate group-level connectivity is also obtained. On real data from a cohort of 60 subjects, we show that integrating intra-subject connectivity estimated with SGGGM significantly improves brain activation detection over connectivity priors derived from other graphical modeling approaches.