A Sparse Representation-Based Algorithm for Pattern Localization in Brain Imaging Data Analysis

Yuanqing Li,Lin He,Jinyi Long,Pei Sun,Zhenghui Gu,Haidong Lu,Essa Yacoub

doi:10.1371/journal.pone.0050332

Abstract

Considering the two-class classification problem in brain imaging data analysis, we propose a sparse representation-based multi-variate pattern analysis (MVPA) algorithm to localize brain activation patterns corresponding to different stimulus classes/brain states respectively. Feature selection can be modeled as a sparse representation (or sparse regression) problem. Such technique has been successfully applied to voxel selection in fMRI data analysis. However, single selection based on sparse representation or other methods is prone to obtain a subset of the most informative features rather than all. Herein, our proposed algorithm recursively eliminates informative features selected by a sparse regression method until the decoding accuracy based on the remaining features drops to a threshold close to chance level. In this way, the resultant feature set including all the identified features is expected to involve all the informative features for discrimination. According to the signs of the sparse regression weights, these selected features are separated into two sets corresponding to two stimulus classes/brain states. Next, in order to remove irrelevant/noisy features in the two selected feature sets, we perform a nonparametric permutation test at the individual subject level or the group level. In data analysis, we verified our algorithm with a toy data set and an intrinsic signal optical imaging data set. The results show that our algorithm has accurately localized two class-related patterns. As an application example, we used our algorithm on a functional magnetic resonance imaging (fMRI) data set. Two sets of informative voxels, corresponding to two semantic categories (i.e., “old people” and “young people”), respectively, are obtained in the human brain.

Highlights

One fundamental question in neuroscience focuses on determining how information is processed within local and global networks in the brain
For the purpose of identifying all the informative features, we proposed a sparse representation-based pattern localization algorithm combined with a nonparametric statistical test in this study
We summarized the process of the algorithm as three components: a K-fold cross-validation of recursive feature search where feature weights were determined by a sparse representation method, construction of two probability maps based on the selected features, and a permutation test at the individual or group level

Summary

Introduction

One fundamental question in neuroscience focuses on determining how information is processed within local and global networks in the brain. Multivariate pattern analysis (MVPA) approaches have been used successfully in revealing brain patterns activated by different stimulus conditions in brain imaging studies [1,2,3,4,5,6]. Three common strategies have been employed to determine where the brain contains discriminative information for different stimulus categories, and this is known as a pattern localization procedure. An alternative method is a local multivariate search approach (e.g. the searchlight algorithm), in which features are evaluated in local brain regions first and all of these local features are combined to form a whole-brain information mapping [11,12]. Whole-brain approach-based feature selection algorithms have been used to reveal fine-grained spatial discriminative patterns both in simulations and real functional magnetic resonance imaging (fMRI) data analysis [1,5,13,14]

Methods

Results

Conclusion