Decentralized temporal independent component analysis: Leveraging fMRI data in collaborative settings

Bradley T. Baker, Anees Abrol, Rogers F. Silva, Eswar Damaraju, Anand D. Sarwate, Vince Daniel Calhoun, Sergey M. Plis

Research output: Contribution to journalArticle

Abstract

The field of neuroimaging has recently witnessed a strong shift towards data sharing; however, current collaborative research projects may be unable to leverage institutional architectures that collect and store data in local, centralized data centers. Additionally, though research groups are willing to grant access for collaborations, they often wish to maintain control of their data locally. These concerns may stem from research culture as well as privacy and accountability concerns. In order to leverage the potential of these aggregated larger data sets, we require tools that perform joint analyses without transmitting the data. Ideally, these tools would have similar performance and ease of use as their current centralized counterparts. In this paper, we propose and evaluate a new Algorithm, decentralized joint independent component analysis (djICA), which meets these technical requirements. djICA shares only intermediate statistics about the data, plausibly retaining privacy of the raw information to local sites, thus making it amenable to further privacy protections, for example via differential privacy. We validate our method on real functional magnetic resonance imaging (fMRI) data and show that it enables collaborative large-scale temporal ICA of fMRI, a rich vein of analysis as of yet largely unexplored, and which can benefit from the larger-N studies enabled by a decentralized approach. We show that djICA is robust to different distributions of data over sites, and that the temporal components estimated with djICA show activations similar to the temporal functional modes analyzed in previous work, thus solidifying djICA as a new, decentralized method oriented toward the frontiers of temporal independent component analysis.

Original languageEnglish (US)
Pages (from-to)557-569
Number of pages13
JournalNeuroImage
Volume186
DOIs
StatePublished - Feb 1 2019
Externally publishedYes

Fingerprint

Joints
Privacy
Magnetic Resonance Imaging
Research
Activation Analysis
Information Dissemination
Social Responsibility
Neuroimaging
Veins

Keywords

  • Collaborative analysis
  • Decentralization
  • fMRI
  • Independent component analysis
  • Temporal independent component analysis

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Cite this

Decentralized temporal independent component analysis : Leveraging fMRI data in collaborative settings. / Baker, Bradley T.; Abrol, Anees; Silva, Rogers F.; Damaraju, Eswar; Sarwate, Anand D.; Calhoun, Vince Daniel; Plis, Sergey M.

In: NeuroImage, Vol. 186, 01.02.2019, p. 557-569.

Research output: Contribution to journalArticle

Baker, Bradley T. ; Abrol, Anees ; Silva, Rogers F. ; Damaraju, Eswar ; Sarwate, Anand D. ; Calhoun, Vince Daniel ; Plis, Sergey M. / Decentralized temporal independent component analysis : Leveraging fMRI data in collaborative settings. In: NeuroImage. 2019 ; Vol. 186. pp. 557-569.
@article{c240417f78fb483ba001914d4636f73e,
title = "Decentralized temporal independent component analysis: Leveraging fMRI data in collaborative settings",
abstract = "The field of neuroimaging has recently witnessed a strong shift towards data sharing; however, current collaborative research projects may be unable to leverage institutional architectures that collect and store data in local, centralized data centers. Additionally, though research groups are willing to grant access for collaborations, they often wish to maintain control of their data locally. These concerns may stem from research culture as well as privacy and accountability concerns. In order to leverage the potential of these aggregated larger data sets, we require tools that perform joint analyses without transmitting the data. Ideally, these tools would have similar performance and ease of use as their current centralized counterparts. In this paper, we propose and evaluate a new Algorithm, decentralized joint independent component analysis (djICA), which meets these technical requirements. djICA shares only intermediate statistics about the data, plausibly retaining privacy of the raw information to local sites, thus making it amenable to further privacy protections, for example via differential privacy. We validate our method on real functional magnetic resonance imaging (fMRI) data and show that it enables collaborative large-scale temporal ICA of fMRI, a rich vein of analysis as of yet largely unexplored, and which can benefit from the larger-N studies enabled by a decentralized approach. We show that djICA is robust to different distributions of data over sites, and that the temporal components estimated with djICA show activations similar to the temporal functional modes analyzed in previous work, thus solidifying djICA as a new, decentralized method oriented toward the frontiers of temporal independent component analysis.",
keywords = "Collaborative analysis, Decentralization, fMRI, Independent component analysis, Temporal independent component analysis",
author = "Baker, {Bradley T.} and Anees Abrol and Silva, {Rogers F.} and Eswar Damaraju and Sarwate, {Anand D.} and Calhoun, {Vince Daniel} and Plis, {Sergey M.}",
year = "2019",
month = "2",
day = "1",
doi = "10.1016/j.neuroimage.2018.10.072",
language = "English (US)",
volume = "186",
pages = "557--569",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Decentralized temporal independent component analysis

T2 - Leveraging fMRI data in collaborative settings

AU - Baker, Bradley T.

AU - Abrol, Anees

AU - Silva, Rogers F.

AU - Damaraju, Eswar

AU - Sarwate, Anand D.

AU - Calhoun, Vince Daniel

AU - Plis, Sergey M.

PY - 2019/2/1

Y1 - 2019/2/1

N2 - The field of neuroimaging has recently witnessed a strong shift towards data sharing; however, current collaborative research projects may be unable to leverage institutional architectures that collect and store data in local, centralized data centers. Additionally, though research groups are willing to grant access for collaborations, they often wish to maintain control of their data locally. These concerns may stem from research culture as well as privacy and accountability concerns. In order to leverage the potential of these aggregated larger data sets, we require tools that perform joint analyses without transmitting the data. Ideally, these tools would have similar performance and ease of use as their current centralized counterparts. In this paper, we propose and evaluate a new Algorithm, decentralized joint independent component analysis (djICA), which meets these technical requirements. djICA shares only intermediate statistics about the data, plausibly retaining privacy of the raw information to local sites, thus making it amenable to further privacy protections, for example via differential privacy. We validate our method on real functional magnetic resonance imaging (fMRI) data and show that it enables collaborative large-scale temporal ICA of fMRI, a rich vein of analysis as of yet largely unexplored, and which can benefit from the larger-N studies enabled by a decentralized approach. We show that djICA is robust to different distributions of data over sites, and that the temporal components estimated with djICA show activations similar to the temporal functional modes analyzed in previous work, thus solidifying djICA as a new, decentralized method oriented toward the frontiers of temporal independent component analysis.

AB - The field of neuroimaging has recently witnessed a strong shift towards data sharing; however, current collaborative research projects may be unable to leverage institutional architectures that collect and store data in local, centralized data centers. Additionally, though research groups are willing to grant access for collaborations, they often wish to maintain control of their data locally. These concerns may stem from research culture as well as privacy and accountability concerns. In order to leverage the potential of these aggregated larger data sets, we require tools that perform joint analyses without transmitting the data. Ideally, these tools would have similar performance and ease of use as their current centralized counterparts. In this paper, we propose and evaluate a new Algorithm, decentralized joint independent component analysis (djICA), which meets these technical requirements. djICA shares only intermediate statistics about the data, plausibly retaining privacy of the raw information to local sites, thus making it amenable to further privacy protections, for example via differential privacy. We validate our method on real functional magnetic resonance imaging (fMRI) data and show that it enables collaborative large-scale temporal ICA of fMRI, a rich vein of analysis as of yet largely unexplored, and which can benefit from the larger-N studies enabled by a decentralized approach. We show that djICA is robust to different distributions of data over sites, and that the temporal components estimated with djICA show activations similar to the temporal functional modes analyzed in previous work, thus solidifying djICA as a new, decentralized method oriented toward the frontiers of temporal independent component analysis.

KW - Collaborative analysis

KW - Decentralization

KW - fMRI

KW - Independent component analysis

KW - Temporal independent component analysis

UR - http://www.scopus.com/inward/record.url?scp=85057214883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057214883&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2018.10.072

DO - 10.1016/j.neuroimage.2018.10.072

M3 - Article

VL - 186

SP - 557

EP - 569

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -