Research Article

A method for accurate group difference detection by constraining the mixing coefficients in an ICA framework

  1. Jing Sui1,
  2. Tülay Adali2,
  3. Godfrey D. Pearlson3,4,
  4. Vincent P. Clark1,5,
  5. Vince D. Calhoun1,3,4,6,*

Article first published online: 26 JAN 2009

DOI: 10.1002/hbm.20721

Issue

Human Brain Mapping

Human Brain Mapping

Volume 30, Issue 9, pages 2953–2970, 15 September 2009

Additional Information

How to Cite

Sui, J., Adali, T., Pearlson, G. D., Clark, V. P. and Calhoun, V. D. (2009), A method for accurate group difference detection by constraining the mixing coefficients in an ICA framework. Human Brain Mapping, 30: 2953–2970. doi: 10.1002/hbm.20721

Author Information

  1. 1

    The Mind Research Network, Albuquerque, New Mexico

  2. 2

    Department of CSEE, University of Maryland, Baltimore County, Baltimore, Maryland

  3. 3

    Olin Neuropsychiatry Research Center, Hartford, Connecticut

  4. 4

    Department of Psychiatry, Yale University, New Haven, Connecticut

  5. 5

    Department of Psychology, University of New Mexico, Albuquerque, New Mexico

  6. 6

    Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, New Mexico

*The Mind Research Network, 1101 Yale Blvd, NE, Albuquerque, NM 87106

Publication History

  1. Issue published online: 20 AUG 2009
  2. Article first published online: 26 JAN 2009
  3. Manuscript Accepted: 1 DEC 2008
  4. Manuscript Revised: 24 NOV 2008
  5. Manuscript Received: 14 JUL 2008

Funded by

  • National Institutes of Health. Grant Numbers: 1 R01 EB 006841, 1 R01 EB 005846, MH43775, MH074797, MH077945

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

View Full Article (HTML) Get PDF (618K)

Keywords:

  • fMRI;
  • independent component analysis;
  • group difference;
  • CC-ICA;
  • mixing coefficients;
  • Infomax;
  • biomarker

Abstract

Independent component analysis (ICA) is a promising method that is increasingly used to analyze brain imaging data such as functional magnetic resonance imaging (fMRI), structural MRI, and electroencephalography and has also proved useful for group comparison, e.g., differentiating healthy controls from patients. An advantage of ICA is its ability to identify components that are mixed in an unknown manner. However, ICA is not necessarily robust and optimal in identifying between-group effects, especially in highly noisy situations. Here, we propose a modified ICA framework for multigroup data analysis that incorporates prior information regarding group membership as a constraint into the mixing coefficients. Our approach, called coefficient-constrained ICA (CC-ICA), prioritizes identification of components that show a significant group difference. The performance of CC-ICA via synthetic and hybrid data simulations is evaluated under different hypothesis testing assumptions and signal to noise ratios (SNRs). Group analysis is also conducted on real multitask fMRI data. Results show that CC-ICA improves the estimation accuracy of the independent components greatly, especially those that have different patterns for different groups (e.g., patients vs. controls); In addition, it enhances the data extraction sensitivity to group differences by ranking components with P value or J-divergence more consistently with the ground truth. The proposed algorithm performs quite well for both group-difference detection and multitask fMRI data fusion, which may prove especially important for the identification of relevant disease biomarkers. Hum Brain Mapp 2009. © 2009 Wiley-Liss, Inc.

View Full Article (HTML) Get PDF (618K)