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

CORC > 上海神经科学研究所 > 中国科学院上海生命科学研究院神经科学研究所 > 神经所(总)

	A Sparse Representation-Based Algorithm for Pattern Localization in Brain Imaging Data Analysis
	Li, YQ ; Long, JY ; He, L ; Lu, HD ; Gu, ZH ; Sun, P
刊名	PLOS ONE
	2012
卷号	7 期号:12 页码:-e50332
关键词	SUPPORT VECTOR MACHINES MONKEY STRIATE CORTEX HUMAN EXTRASTRIATE CORTEX FUNCTIONAL ARCHITECTURE RECEPTIVE FIELDS VISUAL-CORTEX FMRI DATA FACES CLASSIFICATION ORIENTATION
ISSN号	1932-6203
通讯作者	Li, YQ (reprint author), S China Univ Technol, Ctr Brain Comp Interfaces & Brain Informat Proc, Guangzhou, Guangdong, Peoples R China.,auyqli@scut.edu.cn
英文摘要	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. Citation: Li Y, Long J, He L, Lu H, Gu Z, et al. (2012) A Sparse Representation-Based Algorithm for Pattern Localization in Brain Imaging Data Analysis. PLoS ONE 7(12): e50332. doi:10.1371/journal.pone.0050332
学科主题	Science & Technology - Other Topics
收录类别	SCI
资助信息	National High-Tech R&D Program of China (863 Program) [2012AA011601]; National Natural Science Foundation of China [91120305, 60825306, 61105121]; High Level Talent Project of Guangdong Province, People
语种	英语
公开日期	2013-06-04
内容类型	期刊论文
源URL	[http://ir.sibs.ac.cn/handle/331001/2474]
专题	上海神经科学研究所_神经所(总)
推荐引用方式 GB/T 7714	Li, YQ,Long, JY,He, L,et al. A Sparse Representation-Based Algorithm for Pattern Localization in Brain Imaging Data Analysis[J]. PLOS ONE,2012,7(12):-e50332.
APA	Li, YQ,Long, JY,He, L,Lu, HD,Gu, ZH,&Sun, P.(2012).A Sparse Representation-Based Algorithm for Pattern Localization in Brain Imaging Data Analysis.PLOS ONE,7(12),-e50332.
MLA	Li, YQ,et al."A Sparse Representation-Based Algorithm for Pattern Localization in Brain Imaging Data Analysis".PLOS ONE 7.12(2012):-e50332.