This paper deals with the problem of blind source separation in fMRI data analysis. Our main contribution is to present a maximum likelihood based method to blindly separate the brain activations in an fMRI experiment. Choosing the time frequency domain as the signal representation space, our method relies on the second order statistics and exploits the inter-source diversity. It is efficiently implemented by the EM (expectation-maximization) algorithm where the time courses of the brain activations are considered as the hidden variables. The estimation variance of the STFT (short time Fourier transform) is reduced by averaging across time frequency sub-domains. The successful separation of the right and left visual cortex activations during a visual fMRI experiment, in a block design, and the extraction of only the relevant tasks corroborate the effectiveness of our proposed separating algorithm.
Bayesian blind source separation for brain imaging
IEEE International Conference on Image Processing 2005 ; 3 ; III-581
01.01.2005
159572 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Bayesian Blind Source Separation for Brain Imaging
British Library Conference Proceedings | 2005
|Convolutive Blind Source Separation for Noisy Mixtures
British Library Conference Proceedings | 2004
|Blind Source Separation and Beamforming: Algebraic Technique Analysis
Online Contents | 2004
|Evaluation of Blind Source Separation Methods in Acoustics
British Library Conference Proceedings | 2004
|