Parallel group ICA plus ICA: Joint estimation of linked functional network variability and structural covariation with application to schizophrenia | |
Qi, Shile1,2; Sui, Jing3,4,5,6; Chen, Jiayu1,2; Liu, Jingyu1,2; Jiang, Rongtao3,4,5; Silva, Rogers1,2; Iraji, Armin1,2; Damaraju, Eswar1,2; Salman, Mustafa1,2; Lin, Dongdong1,2; Fu, Zening1,2; Zhi, Dongmei3,4,5; Turner, Jessica A.7; Bustillo, Juan8; Ford, Judith M.9; Mathalon, Daniel H.9; Voyvodic, James10; McEwen, Sarah11; Preda, Adrian12; Belger, Aysenil13; Potkin, Steven G.12; Mueller, Bryon A.14; Adali, Tulay15; Calhoun, Vince D.1,2,7,8,16 | |
发表期刊 | HUMAN BRAIN MAPPING |
ISSN | 1065-9471 |
2019-09-01 | |
卷号 | 40期号:13页码:3795-3809 |
摘要 | There is growing evidence that rather than using a single brain imaging modality to study its association with physiological or symptomatic features, the field is paying more attention to fusion of multimodal information. However, most current multimodal fusion approaches that incorporate functional magnetic resonance imaging (fMRI) are restricted to second-level 3D features, rather than the original 4D fMRI data. This trade-off is that the valuable temporal information is not utilized during the fusion step. Here we are motivated to propose a novel approach called "parallel group ICA+ICA" that incorporates temporal fMRI information from group independent component analysis (GICA) into a parallel independent component analysis (ICA) framework, aiming to enable direct fusion of first-level fMRI features with other modalities (e.g., structural MRI), which thus can detect linked functional network variability and structural covariations. Simulation results show that the proposed method yields accurate intermodality linkage detection regardless of whether it is strong or weak. When applied to real data, we identified one pair of significantly associated fMRI-sMRI components that show group difference between schizophrenia and controls in both modalities, and this linkage can be replicated in an independent cohort. Finally, multiple cognitive domain scores can be predicted by the features identified in the linked component pair by our proposed method. We also show these multimodal brain features can predict multiple cognitive scores in an independent cohort. Overall, results demonstrate the ability of parallel GICA+ICA to estimate joint information from 4D and 3D data without discarding much of the available information up front, and the potential for using this approach to identify imaging biomarkers to study brain disorders. |
关键词 | group independent component analysis multimodal fusion parallel independent component analysis schizophrenia subjects' variability temporal information |
DOI | 10.1002/hbm.24632 |
关键词[WOS] | INDEPENDENT COMPONENT ANALYSIS ; GRAY-MATTER ABNORMALITIES ; WORKING-MEMORY ; FMRI DATA ; MULTIMODAL FUSION ; CONNECTIVITY ; METAANALYSIS ; DISORDER ; INFERENCES ; PREDICTION |
收录类别 | SCI |
语种 | 英语 |
资助项目 | NIH[P30GM122734] ; NIH[R56MH117107] ; Beijing Municipal Science and Technology Commission[Z181100001518005] ; Natural Science Foundation of China[61773380] ; Natural Science Foundation of China[81471367] ; National Science Foundation (NSF)[1539067] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB03040100] ; NIH[1R01MH094524] ; NIH[R01EB005846] ; NIH[P20GM103472] ; NIH[P20GM103472] ; NIH[R01EB005846] ; NIH[1R01MH094524] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB03040100] ; National Science Foundation (NSF)[1539067] ; Natural Science Foundation of China[81471367] ; Natural Science Foundation of China[61773380] ; Beijing Municipal Science and Technology Commission[Z181100001518005] ; NIH[R56MH117107] ; NIH[P30GM122734] |
WOS研究方向 | Neurosciences & Neurology ; Radiology, Nuclear Medicine & Medical Imaging |
WOS类目 | Neurosciences ; Neuroimaging ; Radiology, Nuclear Medicine & Medical Imaging |
WOS记录号 | WOS:000478645900007 |
出版者 | WILEY |
七大方向——子方向分类 | 脑网络分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/27758 |
专题 | 脑网络组研究 |
通讯作者 | Sui, Jing; Calhoun, Vince D. |
作者单位 | 1.Mind Res Network, Albuquerque, NM USA 2.Emory, Georgia Tech, Georgia State, Triinst Ctr Translat Res Neuroimaging & Data Sci, Atlanta, GA 30303 USA 3.Brainnetome Ctr, Beijing 100190, Peoples R China 4.Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 5.Univ Chinese Acad Sci, Beijing, Peoples R China 6.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China 7.Georgia State Univ, Dept Psychol, Univ Plaza, Atlanta, GA 30303 USA 8.Univ New Mexico, Dept Psychiat, Albuquerque, NM 87131 USA 9.Univ Calif San Francisco, Dept Psychiat, San Francisco, CA USA 10.Duke Univ, Dept Radiol, Durham, NC 27710 USA 11.Univ Calif San Diego, Sch Med, Dept Psychiat, 9500 Gillman Dr, La Jolla, CA 92093 USA 12.Univ Calif Irvine, Dept Psychiat, Irvine, CA 92717 USA 13.Univ N Carolina, Sch Med, Dept Psychiat, Chapel Hill, NC 27515 USA 14.Univ Minnesota, Dept Psychiat, Minneapolis, MN 55455 USA 15.Univ Maryland Baltimore Country, Dept CSEE, Baltimore, MD USA 16.Univ New Mexico, Dept ECE, Albuquerque, NM 87131 USA |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Qi, Shile,Sui, Jing,Chen, Jiayu,et al. Parallel group ICA plus ICA: Joint estimation of linked functional network variability and structural covariation with application to schizophrenia[J]. HUMAN BRAIN MAPPING,2019,40(13):3795-3809. |
APA | Qi, Shile.,Sui, Jing.,Chen, Jiayu.,Liu, Jingyu.,Jiang, Rongtao.,...&Calhoun, Vince D..(2019).Parallel group ICA plus ICA: Joint estimation of linked functional network variability and structural covariation with application to schizophrenia.HUMAN BRAIN MAPPING,40(13),3795-3809. |
MLA | Qi, Shile,et al."Parallel group ICA plus ICA: Joint estimation of linked functional network variability and structural covariation with application to schizophrenia".HUMAN BRAIN MAPPING 40.13(2019):3795-3809. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
shile qi + Parallel (6363KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 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