IVA for multi-subject FMRI analysis: A comparative study using a new simulation toolbox

Josselin T. Dea; Matthew Anderson; Elena Allen; Vince D. Calhoun; Tülay Adali

doi:10.1109/MLSP.2011.6064618

IVA for multi-subject FMRI analysis: A comparative study using a new simulation toolbox

Josselin T. Dea, Matthew Anderson, Elena Allen, Vince D. Calhoun, Tülay Adali

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

21 Scopus citations

Abstract

Joint blind source separation (JBSS) techniques have proven to be a natural solution for achieving source separation of multiple data sets. JBSS algorithms, such as independent vector analysis (IVA), are a promising alternative to independent component analysis (ICA) based approaches for the analysis of multi-subject functional magnetic resonance imaging (fMRI) data. Unlike ICA, little is known about the effectiveness of JBSS methods for fMRI analysis. In this paper, a new fMRI simulation toolbox (SimTB) is used to simulate multi-subject realistic fMRI datasets that include inter-subject variability. We study the performance of two JBSS algorithms representing two different approaches to the problem: (1) a recently proposed IVA algorithm combining second-order and higher-order statistics denoted by IVA-GL; and (2) a JBSS solution found by jointly diagonalizing cross-cumulant matrices denoted IVA-GJD. We compare these two JBSS algorithms with similar ICA algorithms implemented in the widely used group ICA for fMRI toolbox (GIFT). The results show that in addition to offering an effective solution for making group inferences, IVA algorithms provide superior performance in terms of capturing spatial inter-subject variability.

Original language	English (US)
Title of host publication	2011 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2011
DOIs	https://doi.org/10.1109/MLSP.2011.6064618
State	Published - Dec 5 2011
Externally published	Yes
Event	21st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2011 - Beijing, China Duration: Sep 18 2011 → Sep 21 2011

Publication series

Name	IEEE International Workshop on Machine Learning for Signal Processing

Other

Other	21st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2011
Country/Territory	China
City	Beijing
Period	9/18/11 → 9/21/11

Keywords

IVA
fMRI
functional
group ICA
independent component analysis
independent vector analysis
simulation

ASJC Scopus subject areas

Human-Computer Interaction
Signal Processing

Access to Document

10.1109/MLSP.2011.6064618

Cite this

Dea, J. T., Anderson, M., Allen, E., Calhoun, V. D., & Adali, T. (2011). IVA for multi-subject FMRI analysis: A comparative study using a new simulation toolbox. In 2011 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2011 [6064618] (IEEE International Workshop on Machine Learning for Signal Processing). https://doi.org/10.1109/MLSP.2011.6064618

IVA for multi-subject FMRI analysis : A comparative study using a new simulation toolbox. / Dea, Josselin T.; Anderson, Matthew; Allen, Elena et al.

2011 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2011. 2011. 6064618 (IEEE International Workshop on Machine Learning for Signal Processing).

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

Dea, JT, Anderson, M, Allen, E, Calhoun, VD & Adali, T 2011, IVA for multi-subject FMRI analysis: A comparative study using a new simulation toolbox. in 2011 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2011., 6064618, IEEE International Workshop on Machine Learning for Signal Processing, 21st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2011, Beijing, China, 9/18/11. https://doi.org/10.1109/MLSP.2011.6064618

@inproceedings{1f05aaa324274e5f8ab214bc10769e24,

title = "IVA for multi-subject FMRI analysis: A comparative study using a new simulation toolbox",

abstract = "Joint blind source separation (JBSS) techniques have proven to be a natural solution for achieving source separation of multiple data sets. JBSS algorithms, such as independent vector analysis (IVA), are a promising alternative to independent component analysis (ICA) based approaches for the analysis of multi-subject functional magnetic resonance imaging (fMRI) data. Unlike ICA, little is known about the effectiveness of JBSS methods for fMRI analysis. In this paper, a new fMRI simulation toolbox (SimTB) is used to simulate multi-subject realistic fMRI datasets that include inter-subject variability. We study the performance of two JBSS algorithms representing two different approaches to the problem: (1) a recently proposed IVA algorithm combining second-order and higher-order statistics denoted by IVA-GL; and (2) a JBSS solution found by jointly diagonalizing cross-cumulant matrices denoted IVA-GJD. We compare these two JBSS algorithms with similar ICA algorithms implemented in the widely used group ICA for fMRI toolbox (GIFT). The results show that in addition to offering an effective solution for making group inferences, IVA algorithms provide superior performance in terms of capturing spatial inter-subject variability.",

keywords = "IVA, fMRI, functional, group ICA, independent component analysis, independent vector analysis, simulation",

author = "Dea, {Josselin T.} and Matthew Anderson and Elena Allen and Calhoun, {Vince D.} and T{\"u}lay Adali",

year = "2011",

month = dec,

day = "5",

doi = "10.1109/MLSP.2011.6064618",

language = "English (US)",

isbn = "9781457716232",

series = "IEEE International Workshop on Machine Learning for Signal Processing",

booktitle = "2011 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2011",

note = "21st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2011 ; Conference date: 18-09-2011 Through 21-09-2011",

}

TY - GEN

T1 - IVA for multi-subject FMRI analysis

T2 - 21st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2011

AU - Dea, Josselin T.

AU - Anderson, Matthew

AU - Allen, Elena

AU - Calhoun, Vince D.

AU - Adali, Tülay

PY - 2011/12/5

Y1 - 2011/12/5

N2 - Joint blind source separation (JBSS) techniques have proven to be a natural solution for achieving source separation of multiple data sets. JBSS algorithms, such as independent vector analysis (IVA), are a promising alternative to independent component analysis (ICA) based approaches for the analysis of multi-subject functional magnetic resonance imaging (fMRI) data. Unlike ICA, little is known about the effectiveness of JBSS methods for fMRI analysis. In this paper, a new fMRI simulation toolbox (SimTB) is used to simulate multi-subject realistic fMRI datasets that include inter-subject variability. We study the performance of two JBSS algorithms representing two different approaches to the problem: (1) a recently proposed IVA algorithm combining second-order and higher-order statistics denoted by IVA-GL; and (2) a JBSS solution found by jointly diagonalizing cross-cumulant matrices denoted IVA-GJD. We compare these two JBSS algorithms with similar ICA algorithms implemented in the widely used group ICA for fMRI toolbox (GIFT). The results show that in addition to offering an effective solution for making group inferences, IVA algorithms provide superior performance in terms of capturing spatial inter-subject variability.

AB - Joint blind source separation (JBSS) techniques have proven to be a natural solution for achieving source separation of multiple data sets. JBSS algorithms, such as independent vector analysis (IVA), are a promising alternative to independent component analysis (ICA) based approaches for the analysis of multi-subject functional magnetic resonance imaging (fMRI) data. Unlike ICA, little is known about the effectiveness of JBSS methods for fMRI analysis. In this paper, a new fMRI simulation toolbox (SimTB) is used to simulate multi-subject realistic fMRI datasets that include inter-subject variability. We study the performance of two JBSS algorithms representing two different approaches to the problem: (1) a recently proposed IVA algorithm combining second-order and higher-order statistics denoted by IVA-GL; and (2) a JBSS solution found by jointly diagonalizing cross-cumulant matrices denoted IVA-GJD. We compare these two JBSS algorithms with similar ICA algorithms implemented in the widely used group ICA for fMRI toolbox (GIFT). The results show that in addition to offering an effective solution for making group inferences, IVA algorithms provide superior performance in terms of capturing spatial inter-subject variability.

KW - IVA

KW - fMRI

KW - functional

KW - group ICA

KW - independent component analysis

KW - independent vector analysis

KW - simulation

UR - http://www.scopus.com/inward/record.url?scp=82455198925&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82455198925&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2011.6064618

DO - 10.1109/MLSP.2011.6064618

M3 - Conference contribution

AN - SCOPUS:82455198925

SN - 9781457716232

T3 - IEEE International Workshop on Machine Learning for Signal Processing

BT - 2011 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2011

Y2 - 18 September 2011 through 21 September 2011

ER -

IVA for multi-subject FMRI analysis: A comparative study using a new simulation toolbox

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this