PARALLEL INDEPENDENT COMPONENT ANALYSIS FOR MULTIMODAL ANALYSIS: APPLICATION TO FMRI AND EEG DATA

This paper presents the technique of parallel independent component analysis (paraICA) with adaptive dynamic constraints applied to two datasets simultaneously. As a framework to investigate the integration of data from two imaging modalities, this method is dedicated to identify components of both modalities and connections between them through enhancing intrinsic interrelationships. The performance is assessed by simulations under different conditions of signal to noise ratio, connection strength and estimation of component order. An application to functional magnetic resonance images and electroencephalography data is conducted to illustrate the usage of paraICA. Results show that paraICA provides stable results and can identify the linked components with a relatively high accuracy. The application exhibits the ability to discover the connection between brain maps and event related potential time courses, and suggests a new way to investigate the coupling between hemodynamics and neural activity.