Dynamic GSCANO (Generalized Structured Canonical Correlation Analysis) with applications to the analysis of effective connectivity in functional neuroimaging data

Effective connectivity in functional neuroimaging studies is defined as the time dependent causal influence that a certain brain region of interest (ROI) exerts on another. A new method of structural equation modeling (SEM) is proposed for analyzing common patterns among multiple subjects’ effective connectivity. The proposed method, called Dynamic GSCANO (Generalized Structured Canonical Correlation Analysis) incorporates contemporaneous and lagged effects between ROIs, direct and modulating effects of stimuli, as well as interaction effects among ROIs. An alternating least squares (ALS) algorithm is developed for estimating parameters. Synthetic and real data are analyzed to demonstrate the feasibility and usefulness of the proposed method.