DocumentCode :
3411914
Title :
CCA for joint blind source separation of multiple datasets with application to group FMRI analysis
Author :
Li, Yi-Ou ; Wang, Wei ; Adal, Tülay ; Calhoun, Vince D.
Author_Institution :
Univ. of Maryland Baltimore County, Baltimore, MD
fYear :
2008
fDate :
March 31 2008-April 4 2008
Firstpage :
1837
Lastpage :
1840
Abstract :
In this work, we propose a scheme for joint blind source separation (BSS) of multiple datasets using canonical correlation analysis (CCA). The proposed scheme jointly extracts sources from each dataset in the order of between-set source correlations. We show that, when sources are uncorrelated within each dataset and correlated across different datasets only on corresponding indices, (i) CCA on two datasets achieves BSS when the sources from the two datasets have distinct between-set correlation coefficients, and (ii) CCA on multiple datasets (M-CCA) achieves BSS with a more relaxed condition on the between-set source correlation coefficients compared to CCA on two datasets. We present simulation results to demonstrate the properties of CCA and M-CCA on joint BSS. We apply M-CCA to group functional magnetic resonance imaging (fMRI) data acquired from several subjects performing a visuomotor task and obtain interesting brain activations as well as their correlation profiles across different subjects in the group.
Keywords :
biomedical MRI; blind source separation; brain; correlation methods; medical image processing; neurophysiology; vision; between-set source correlations; blind source separation; brain activations; canonical correlation analysis; correlation coefficients; correlation profiles; functional magnetic resonance imaging; group analysis; visuomotor task; Autocorrelation; Blind source separation; Eigenvalues and eigenfunctions; Image analysis; Independent component analysis; Magnetic analysis; Magnetic resonance imaging; Matrix decomposition; Multidimensional systems; Source separation; Canonical correlation analysis; blind source separation; group analysis; magnetic resonance imaging;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on
Conference_Location :
Las Vegas, NV
ISSN :
1520-6149
Print_ISBN :
978-1-4244-1483-3
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2008.4517990
Filename :
4517990
Link To Document :
بازگشت