Parallel group independent component analysis for massive fMRI data sets

Shaojie Chen, Lei Huang, Huitong Qiu, Mary Beth Nebel, Stewart H. Mostofsky, James J. Pekar, Martin A. Lindquist, Ani Eloyan, Brian S. Caffo

Research output: Contribution to journalArticle

Abstract

Independent component analysis (ICA) is widely used in the field of functional neuroimaging to decompose data into spatio-temporal patterns of co-activation. In particular, ICA has found wide usage in the analysis of resting state fMRI (rs-fMRI) data. Recently, a number of large-scale data sets have become publicly available that consist of rs-fMRI scans from thousands of subjects. As a result, efficient ICA algorithms that scale well to the increased number of subjects are required. To address this problem, we propose a two-stage likelihood-based algorithm for performing group ICA, which we denote Parallel Group Independent Component Analysis (PGICA). By utilizing the sequential nature of the algorithm and parallel computing techniques, we are able to efficiently analyze data sets from large numbers of subjects. We illustrate the efficacy of PGICA, which has been implemented in R and is freely available through the Comprehensive R Archive Network, through simulation studies and application to rs-fMRI data from two large multi-subject data sets, consisting of 301 and 779 subjects respectively.

Original languageEnglish (US)
Article numbere0173496
JournalPLoS ONE
Volume12
Issue number3
DOIs
StatePublished - Mar 1 2017

Fingerprint

Independent component analysis
Magnetic Resonance Imaging
Datasets
Airway Obstruction
Functional Neuroimaging
computer techniques
Belladonna Alkaloids
Cape Verde
Functional neuroimaging

ASJC Scopus subject areas

  • Medicine(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Parallel group independent component analysis for massive fMRI data sets. / Chen, Shaojie; Huang, Lei; Qiu, Huitong; Nebel, Mary Beth; Mostofsky, Stewart H.; Pekar, James J.; Lindquist, Martin A.; Eloyan, Ani; Caffo, Brian S.

In: PLoS ONE, Vol. 12, No. 3, e0173496, 01.03.2017.

Research output: Contribution to journalArticle

Chen S, Huang L, Qiu H, Nebel MB, Mostofsky SH, Pekar JJ et al. Parallel group independent component analysis for massive fMRI data sets. PLoS ONE. 2017 Mar 1;12(3). e0173496. Available from, DOI: 10.1371/journal.pone.0173496

Chen, Shaojie; Huang, Lei; Qiu, Huitong; Nebel, Mary Beth; Mostofsky, Stewart H.; Pekar, James J.; Lindquist, Martin A.; Eloyan, Ani; Caffo, Brian S. / Parallel group independent component analysis for massive fMRI data sets.

In: PLoS ONE, Vol. 12, No. 3, e0173496, 01.03.2017.

Research output: Contribution to journalArticle

@article{e3acfc0fd5b3423fa21337a590866109,
title = "Parallel group independent component analysis for massive fMRI data sets",
abstract = "Independent component analysis (ICA) is widely used in the field of functional neuroimaging to decompose data into spatio-temporal patterns of co-activation. In particular, ICA has found wide usage in the analysis of resting state fMRI (rs-fMRI) data. Recently, a number of large-scale data sets have become publicly available that consist of rs-fMRI scans from thousands of subjects. As a result, efficient ICA algorithms that scale well to the increased number of subjects are required. To address this problem, we propose a two-stage likelihood-based algorithm for performing group ICA, which we denote Parallel Group Independent Component Analysis (PGICA). By utilizing the sequential nature of the algorithm and parallel computing techniques, we are able to efficiently analyze data sets from large numbers of subjects. We illustrate the efficacy of PGICA, which has been implemented in R and is freely available through the Comprehensive R Archive Network, through simulation studies and application to rs-fMRI data from two large multi-subject data sets, consisting of 301 and 779 subjects respectively.",
author = "Shaojie Chen and Lei Huang and Huitong Qiu and Nebel, {Mary Beth} and Mostofsky, {Stewart H.} and Pekar, {James J.} and Lindquist, {Martin A.} and Ani Eloyan and Caffo, {Brian S.}",
year = "2017",
month = "3",
doi = "10.1371/journal.pone.0173496",
volume = "12",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "3",

}

TY - JOUR

T1 - Parallel group independent component analysis for massive fMRI data sets

AU - Chen,Shaojie

AU - Huang,Lei

AU - Qiu,Huitong

AU - Nebel,Mary Beth

AU - Mostofsky,Stewart H.

AU - Pekar,James J.

AU - Lindquist,Martin A.

AU - Eloyan,Ani

AU - Caffo,Brian S.

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Independent component analysis (ICA) is widely used in the field of functional neuroimaging to decompose data into spatio-temporal patterns of co-activation. In particular, ICA has found wide usage in the analysis of resting state fMRI (rs-fMRI) data. Recently, a number of large-scale data sets have become publicly available that consist of rs-fMRI scans from thousands of subjects. As a result, efficient ICA algorithms that scale well to the increased number of subjects are required. To address this problem, we propose a two-stage likelihood-based algorithm for performing group ICA, which we denote Parallel Group Independent Component Analysis (PGICA). By utilizing the sequential nature of the algorithm and parallel computing techniques, we are able to efficiently analyze data sets from large numbers of subjects. We illustrate the efficacy of PGICA, which has been implemented in R and is freely available through the Comprehensive R Archive Network, through simulation studies and application to rs-fMRI data from two large multi-subject data sets, consisting of 301 and 779 subjects respectively.

AB - Independent component analysis (ICA) is widely used in the field of functional neuroimaging to decompose data into spatio-temporal patterns of co-activation. In particular, ICA has found wide usage in the analysis of resting state fMRI (rs-fMRI) data. Recently, a number of large-scale data sets have become publicly available that consist of rs-fMRI scans from thousands of subjects. As a result, efficient ICA algorithms that scale well to the increased number of subjects are required. To address this problem, we propose a two-stage likelihood-based algorithm for performing group ICA, which we denote Parallel Group Independent Component Analysis (PGICA). By utilizing the sequential nature of the algorithm and parallel computing techniques, we are able to efficiently analyze data sets from large numbers of subjects. We illustrate the efficacy of PGICA, which has been implemented in R and is freely available through the Comprehensive R Archive Network, through simulation studies and application to rs-fMRI data from two large multi-subject data sets, consisting of 301 and 779 subjects respectively.

UR - http://www.scopus.com/inward/record.url?scp=85014930973&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014930973&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0173496

DO - 10.1371/journal.pone.0173496

M3 - Article

VL - 12

JO - PLoS One

T2 - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 3

M1 - e0173496

ER -