Fusion of Multitask fMRI Data with Constrained Independent Vector Analysis

Abstract

Functional magnetic resonance imaging (fMRI) is a widely used neuroimaging tool for investigating brain function. In multitask fMRI analysis, data fusion methods enable the integration of information across tasks to provide a comprehensive understanding of brain activity. Independent vector analysis (IVA) provides an attractive framework for data fusion as it enables datasets to fully interact with each other by maximizing statistical dependence across the datasets. IVA with multivariate Laplacian distribution IVA-L provides a good model match for fMRI analysis as fMRI signals often exhibit multivariate heavy-tailed distributions. However, IVA can benefit from incorporating prior information when available. This paper proposes a novel way for multitask fMRI data fusion by integrating prior information into an optimized IVA-L framework using a constrained cost function. The proposed method is applied to a multitask fMRI dataset comprising 271 subjects, successfully identifying task-related group differences between healthy controls and schizophrenia patients. Identified important functional areas include the caudate and thalamus during the sensory-motor task (SM), as well as the inferior parietal lobule, superior medial frontal gyrus, and inferior frontal gyrus during the auditory oddball (AOD) task. Additionally, this work highlights the importance of selecting a higher model order and allowing some components to remain unconstrained for the constrained IVA-L framework. These choices enhance the estimation performance and allow the algorithm to capture important information not included in the prior information.