On the Independent Components of Functional Neuroimages

Kim Petersen, Lars Kai Hansen, Thomas Kolenda, Egill Rostrup

AbstractWe discuss the application of ICA procedures to fMRI
(functional Magnetic Resonance Imaging) sequences.
While principal component analysis can identify activation
patterns that are uncorrelated in both space and
time ICA can identify events that are independent in
either time or space. We show that the activation related
components found by either spatial or temporal
independency are consistent, hence robust to choice of
spatial or temporal separation and to choice of ICA approach.
We discuss these issues in the context of three
ICA algorithms applied to an fMRI visual activation
KeywordsIndependent componenet analysis, Molgedey-Schuster, Brain imageing
TypeConference paper [With referee]
ConferenceThird International Conference on Independent Component Analysis and Blind Source Separation
Year2000    pp. 615-620
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing