Group information guided ICA for fMRI data analysis

• Published in: NeuroImage (Orlando, Fla.) Vol. 69; pp. 157 - 197
• Main Authors: Du, Yuhui, Fan, Yong
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.04.2013; Elsevier; Elsevier Limited
• Subjects: Algorithms; Biological and medical sciences; Brain Mapping - methods; Brain research; Data analysis; Enhanced independence; Experiments; fMRI; Fundamental and applied biological sciences. Psychology; Group information; Humans; Image Interpretation, Computer-Assisted - methods; Independent component analysis; Magnetic Resonance Imaging - methods; Methods; Multi-objective optimization; NMR; Nuclear magnetic resonance; Optimization algorithms; Principal components analysis; Studies; Subject specific ICs reconstruction; Vertebrates: nervous system and sense organs; fMRI; Multi-objective optimization; Enhanced independence; Group information; Subject specific ICs reconstruction; Independent component analysis; Human; Nuclear magnetic resonance imaging; Functional imaging
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2012.11.008

Group independent component analysis (ICA) has been widely applied to studies of multi-subject fMRI data for computing subject specific independent components with correspondence across subjects. However, the independence of subject specific independent components (ICs) derived from group ICA has not been explicitly optimized in existing group ICA methods. In order to preserve independence of ICs at the subject level and simultaneously establish correspondence of ICs across subjects, we present a new framework for obtaining subject specific ICs, which we coined group-information guided ICA (GIG-ICA). In this framework, group information captured by standard ICA on the group level is exploited as guidance to compute individual subject specific ICs using a multi-objective optimization strategy. Specifically, we propose a framework with two stages: at first, group ICs (GICs) are obtained using standard group ICA tools, and then the GICs are used as references in a new one-unit ICA with spatial reference (ICA-R) using a multi-objective optimization solver. Comparison experiments with back-reconstruction (GICA1 and GICA3) and dual regression on simulated and real fMRI data have demonstrated that GIG-ICA is able to obtain subject specific ICs with stronger independence and better spatial correspondence across different subjects in addition to higher spatial and temporal accuracy. ► Group information is adopted to guide the computation of subject specific ICs. ► A multi-objective optimization framework is used to compute subject specific ICs. ► Subject specific ICs with enhanced independence and improved accuracy can be obtained.