Institutional Repository, Institute of Psychology, Chinese Academy of Sciences
Ranking and averaging independent component analysis by reproducibility (RAICAR) | |
Yang, Zhi1,2,3; LaConte, Stephen1; Weng, Xuchu2; Hu, Xiaoping1; X. P. Hu | |
摘要 | Independent component analysis (ICA) is a data-driven approach that has exhibited great utility for functional magnetic resonance imaging (fMRI). Standard ICA implementations, however, do not provide the number and relative importance of the resulting components. In addition, ICA algorithms utilizing gradient-based optimization give decompositions that are dependent on initialization values, which can lead to dramatically different results. In this work, a new method, RAICAR (Ranking and Averaging Independent Component Analysis by Reproducibility), is introduced to address these issues for spatial ICA applied to fMRI. RAICAR utilizes repeated ICA realizations and relies on the reproducibility between them to rank and select components. Different realizations are aligned based on correlations, leading to aligned components. Each component is ranked and thresholded based on between-realization correlations. Furthermore, different realizations of each aligned component are selectively averaged to generate the final estimate of the given component. Reliability and accuracy of this method are demonstrated with both simulated and experimental fMRI data.; Independent component analysis (ICA) is a data-driven approach that has exhibited great utility for functional magnetic resonance imaging (fMRI). Standard ICA implementations, however, do not provide the number and relative importance of the resulting components. In addition, ICA algorithms utilizing gradient-based optimization give decompositions that are dependent on initialization values, which can lead to dramatically different results. In this work, a new method, RAICAR (Ranking and Averaging Independent Component Analysis by Reproducibility), is introduced to address these issues for spatial ICA applied to fMRI. RAICAR utilizes repeated ICA realizations and relies on the reproducibility between them to rank and select components. Different realizations are aligned based on correlations, leading to aligned components. Each component is ranked and thresholded based on between-realization correlations. Furthermore, different realizations of each aligned component are selectively averaged to generate the final estimate of the given component. Reliability and accuracy of this method are demonstrated with both simulated and experimental fMRI data. |
关键词 | fMRI independent component analysis data analysis |
学科领域 | 认知神经科学 |
2008-06-01 | |
语种 | 英语 |
发表期刊 | HUMAN BRAIN MAPPING |
ISSN | 1065-9471 |
卷号 | 29期号:6页码:711-725 |
期刊论文类型 | Article |
收录类别 | SCI |
WOS记录号 | WOS:000256609500008 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.psych.ac.cn/handle/311026/5653 |
专题 | 中国科学院心理研究所回溯数据库(1956-2010) |
通讯作者 | X. P. Hu |
作者单位 | 1.Emory Univ, Wallace H Coulter Dept Biomed Engn, Biomed Imaging Technol Ctr, Atlanta, GA 30322 USA 2.Chinese Acad Sci, Inst Psychol, Lab Higher Brain Funct, Beijing 100101, Peoples R China 3.Chinese Acad Sci, Grad Univ, Coll Humanities & Social Sci, Beijing 100101, Peoples R China |
第一作者单位 | 中国科学院心理研究所 |
推荐引用方式 GB/T 7714 | Yang, Zhi,LaConte, Stephen,Weng, Xuchu,et al. Ranking and averaging independent component analysis by reproducibility (RAICAR)[J]. HUMAN BRAIN MAPPING,2008,29(6):711-725. |
APA | Yang, Zhi,LaConte, Stephen,Weng, Xuchu,Hu, Xiaoping,&X. P. Hu.(2008).Ranking and averaging independent component analysis by reproducibility (RAICAR).HUMAN BRAIN MAPPING,29(6),711-725. |
MLA | Yang, Zhi,et al."Ranking and averaging independent component analysis by reproducibility (RAICAR)".HUMAN BRAIN MAPPING 29.6(2008):711-725. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Yang-2008-Ranking an(2201KB) | 开放获取 | -- | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论