Table of Contents Author Guidelines Submit a Manuscript
International Journal of Biomedical Imaging
Volume 2011, Article ID 350838, 13 pages
http://dx.doi.org/10.1155/2011/350838
Research Article

Multiclass Sparse Bayesian Regression for fMRI-Based Prediction

1PARIETAL Team, INRIA Saclay-Île-de-France, 91191 Saclay, France
2Laboratoire de Mathématiques, Université Paris-Sud 11, 91400 Orsay, France
3CEA, DSV, I2BM, NeuroSpin, 91191 Gif-sur-Yvette, France
4CEA, DSV, I2BM, INSERM U562, 91191 Gif-sur-Yvette, France
5SELECT Team, INRIA Saclay-Île-de-France, 91400, France

Received 23 December 2010; Revised 3 March 2011; Accepted 7 April 2011

Academic Editor: Kenji Suzuki

Copyright © 2011 Vincent Michel et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Inverse inference has recently become a popular approach for analyzing neuroimaging data, by quantifying the amount of information contained in brain images on perceptual, cognitive, and behavioral parameters. As it outlines brain regions that convey information for an accurate prediction of the parameter of interest, it allows to understand how the corresponding information is encoded in the brain. However, it relies on a prediction function that is plagued by the curse of dimensionality, as there are far more features (voxels) than samples (images), and dimension reduction is thus a mandatory step. We introduce in this paper a new model, called Multiclass Sparse Bayesian Regression (MCBR), that, unlike classical alternatives, automatically adapts the amount of regularization to the available data. MCBR consists in grouping features into several classes and then regularizing each class differently in order to apply an adaptive and efficient regularization. We detail these framework and validate our algorithm on simulated and real neuroimaging data sets, showing that it performs better than reference methods while yielding interpretable clusters of features.