Multi-subject fMRI analysis via combined independent component analysis and shift-invariant canonical polyadic decomposition

Li-Dan Kuang; Qiu-Hua Lin; Xiao-Feng Gong; Fengyu Cong; Jing Sui; Vince D Calhoun

doi:10.1016/j.jneumeth.2015.08.023

Multi-subject fMRI analysis via combined independent component analysis and shift-invariant canonical polyadic decomposition

J Neurosci Methods. 2015 Dec 30:256:127-40. doi: 10.1016/j.jneumeth.2015.08.023. Epub 2015 Sep 4.

Authors

Li-Dan Kuang¹, Qiu-Hua Lin², Xiao-Feng Gong¹, Fengyu Cong³, Jing Sui⁴, Vince D Calhoun⁵

Affiliations

¹ School of Information and Communication Engineering, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian 116024, China.
² School of Information and Communication Engineering, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian 116024, China. Electronic address: qhlin@dlut.edu.cn.
³ Department of Biomedical Engineering, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian 116024, China; Department of Mathematical Information Technology, University of Jyvaskyla, Finland.
⁴ Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
⁵ The Mind Research Network, Albuquerque, NM 87106, USA; Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, NM 87131, USA.

PMID: 26327319
DOI: 10.1016/j.jneumeth.2015.08.023

Abstract

Background: Canonical polyadic decomposition (CPD) may face a local optimal problem when analyzing multi-subject fMRI data with inter-subject variability. Beckmann and Smith proposed a tensor PICA approach that incorporated an independence constraint to the spatial modality by combining CPD with ICA, and alleviated the problem of inter-subject spatial map (SM) variability.

New method: This study extends tensor PICA to incorporate additional inter-subject time course (TC) variability and to connect CPD and ICA in a new way. Assuming multiple subjects share common TCs but with different time delays, we accommodate subject-dependent TC delays into the CP model based on the idea of shift-invariant CP (SCP). We use ICA as an initialization step to provide the aggregating mixing matrix for shift-invariant CPD to estimate shared TCs with subject-dependent delays and intensities. We then estimate shared SMs using a least-squares fit post shift-invariant CPD.

Results: Using simulated fMRI data as well as actual fMRI data we demonstrate that the proposed approach improves the estimates of the shared SMs and TCs, and the subject-dependent TC delays and intensities. The default mode component illustrates larger TC delays than the task-related component.

Comparison with existing method(s): The proposed approach shows improvements over tensor PICA in particular when TC delays are large, and also outperforms SCP with SM orthogonality constraint and SCP with ICA-based SM initialization.

Conclusions: TCs with subject-dependent delays conform to the true situation of multi-subject fMRI data. The proposed approach is suitable for decomposing multi-subject fMRI data with large inter-subject temporal and spatial variability.

Keywords: Canonical polyadic decomposition (CPD); Independent component analysis (ICA); Inter-subject variability; Multi-subject fMRI data; Shift-invariant CP (SCP); Tensor PICA.

Publication types

Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

Auditory Perception / physiology
Brain / physiology*
Brain Mapping / methods*
Computer Simulation
Fingers / physiology
Humans
Magnetic Resonance Imaging / methods*
Models, Neurological
Motor Activity / physiology
Neuropsychological Tests
Time

Abstract

Publication types

MeSH terms

Grants and funding