Multi-subject fMRI data analysis: Shift-invariant tensor factorization vs. group independent component analysis

Li Dan Kuang; Qiu Hua Lin; Xiao Feng Gong; Jing Fan; Feng Yu Cong; Vince D. Calhoun

doi:10.1109/ChinaSIP.2013.6625342

Multi-subject fMRI data analysis: Shift-invariant tensor factorization vs. group independent component analysis

Li Dan Kuang, Qiu Hua Lin, Xiao Feng Gong, Jing Fan, Feng Yu Cong, Vince D. Calhoun

School of Medicine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

Abstract

Tensor decomposition of fMRI data has gradually drawn attention since it can explore the multi-way data's structure which exists inherently in brain imaging. For multi-subject fMRI data analysis, time shifts occur inevitably among different participants, therefore, shift-invariant tensor decomposition should be used. This method allows for arbitrary shifts along one modality, and can yield satisfactory results for analyzing multi-set fMRI data with time shifts of different datasets. In this study, we presented the first application of shift-invariant tensor decomposition to simulated multi-subject fMRI data with shifts of time courses and variations of spatial maps. By this method, time shifts, spatial maps, time courses, and subjects' amplitudes were better estimated in contrast to group independent component analysis. Therefore, shift-invariant tensor decomposition is promising for real multi-set fMRI data analysis.

Original language	English (US)
Title of host publication	2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings
Pages	269-272
Number of pages	4
DOIs	https://doi.org/10.1109/ChinaSIP.2013.6625342
State	Published - 2013
Event	2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Beijing, China Duration: Jul 6 2013 → Jul 10 2013

Publication series

Name	2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings

Other

Other	2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013
Country/Territory	China
City	Beijing
Period	7/6/13 → 7/10/13

Keywords

CP (CANDECOMP/PARAFAC)
fMRI
group ICA
shift-invariant CP (SCP)
tensor decomposition

ASJC Scopus subject areas

Information Systems
Signal Processing

Access to Document

10.1109/ChinaSIP.2013.6625342

Cite this

Kuang, L. D., Lin, Q. H., Gong, X. F., Fan, J., Cong, F. Y., & Calhoun, V. D. (2013). Multi-subject fMRI data analysis: Shift-invariant tensor factorization vs. group independent component analysis. In 2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings (pp. 269-272). Article 6625342 (2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings). https://doi.org/10.1109/ChinaSIP.2013.6625342

Multi-subject fMRI data analysis: Shift-invariant tensor factorization vs. group independent component analysis. / Kuang, Li Dan; Lin, Qiu Hua; Gong, Xiao Feng et al.
2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings. 2013. p. 269-272 6625342 (2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kuang, LD, Lin, QH, Gong, XF, Fan, J, Cong, FY & Calhoun, VD 2013, Multi-subject fMRI data analysis: Shift-invariant tensor factorization vs. group independent component analysis. in 2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings., 6625342, 2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings, pp. 269-272, 2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013, Beijing, China, 7/6/13. https://doi.org/10.1109/ChinaSIP.2013.6625342

Kuang LD, Lin QH, Gong XF, Fan J, Cong FY, Calhoun VD. Multi-subject fMRI data analysis: Shift-invariant tensor factorization vs. group independent component analysis. In 2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings. 2013. p. 269-272. 6625342. (2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings). doi: 10.1109/ChinaSIP.2013.6625342

Kuang, Li Dan ; Lin, Qiu Hua ; Gong, Xiao Feng et al. / Multi-subject fMRI data analysis : Shift-invariant tensor factorization vs. group independent component analysis. 2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings. 2013. pp. 269-272 (2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings).

@inproceedings{984ea9ee85f645298b913e6f69951294,

title = "Multi-subject fMRI data analysis: Shift-invariant tensor factorization vs. group independent component analysis",

abstract = "Tensor decomposition of fMRI data has gradually drawn attention since it can explore the multi-way data's structure which exists inherently in brain imaging. For multi-subject fMRI data analysis, time shifts occur inevitably among different participants, therefore, shift-invariant tensor decomposition should be used. This method allows for arbitrary shifts along one modality, and can yield satisfactory results for analyzing multi-set fMRI data with time shifts of different datasets. In this study, we presented the first application of shift-invariant tensor decomposition to simulated multi-subject fMRI data with shifts of time courses and variations of spatial maps. By this method, time shifts, spatial maps, time courses, and subjects' amplitudes were better estimated in contrast to group independent component analysis. Therefore, shift-invariant tensor decomposition is promising for real multi-set fMRI data analysis.",

keywords = "CP (CANDECOMP/PARAFAC), fMRI, group ICA, shift-invariant CP (SCP), tensor decomposition",

author = "Kuang, {Li Dan} and Lin, {Qiu Hua} and Gong, {Xiao Feng} and Jing Fan and Cong, {Feng Yu} and Calhoun, {Vince D.}",

note = "Copyright: Copyright 2013 Elsevier B.V., All rights reserved.; 2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 ; Conference date: 06-07-2013 Through 10-07-2013",

year = "2013",

doi = "10.1109/ChinaSIP.2013.6625342",

language = "English (US)",

isbn = "9781479910434",

series = "2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings",

pages = "269--272",

booktitle = "2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings",

}

TY - GEN

T1 - Multi-subject fMRI data analysis

T2 - 2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013

AU - Kuang, Li Dan

AU - Lin, Qiu Hua

AU - Gong, Xiao Feng

AU - Fan, Jing

AU - Cong, Feng Yu

AU - Calhoun, Vince D.

PY - 2013

Y1 - 2013

N2 - Tensor decomposition of fMRI data has gradually drawn attention since it can explore the multi-way data's structure which exists inherently in brain imaging. For multi-subject fMRI data analysis, time shifts occur inevitably among different participants, therefore, shift-invariant tensor decomposition should be used. This method allows for arbitrary shifts along one modality, and can yield satisfactory results for analyzing multi-set fMRI data with time shifts of different datasets. In this study, we presented the first application of shift-invariant tensor decomposition to simulated multi-subject fMRI data with shifts of time courses and variations of spatial maps. By this method, time shifts, spatial maps, time courses, and subjects' amplitudes were better estimated in contrast to group independent component analysis. Therefore, shift-invariant tensor decomposition is promising for real multi-set fMRI data analysis.

AB - Tensor decomposition of fMRI data has gradually drawn attention since it can explore the multi-way data's structure which exists inherently in brain imaging. For multi-subject fMRI data analysis, time shifts occur inevitably among different participants, therefore, shift-invariant tensor decomposition should be used. This method allows for arbitrary shifts along one modality, and can yield satisfactory results for analyzing multi-set fMRI data with time shifts of different datasets. In this study, we presented the first application of shift-invariant tensor decomposition to simulated multi-subject fMRI data with shifts of time courses and variations of spatial maps. By this method, time shifts, spatial maps, time courses, and subjects' amplitudes were better estimated in contrast to group independent component analysis. Therefore, shift-invariant tensor decomposition is promising for real multi-set fMRI data analysis.

KW - CP (CANDECOMP/PARAFAC)

KW - fMRI

KW - group ICA

KW - shift-invariant CP (SCP)

KW - tensor decomposition

UR - http://www.scopus.com/inward/record.url?scp=84889585982&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889585982&partnerID=8YFLogxK

U2 - 10.1109/ChinaSIP.2013.6625342

DO - 10.1109/ChinaSIP.2013.6625342

M3 - Conference contribution

AN - SCOPUS:84889585982

SN - 9781479910434

T3 - 2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings

SP - 269

EP - 272

BT - 2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings

Y2 - 6 July 2013 through 10 July 2013

ER -

Multi-subject fMRI data analysis: Shift-invariant tensor factorization vs. group independent component analysis

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this