Template Independent Component Analysis: Targeted and Reliable Estimation of Subject-level Brain Networks Using Big Data Population Priors

Amanda F. Mejia, Mary Beth Nebel, Yikai Wang, Brian S. Caffo, Ying Guo

Research output: Contribution to journalArticle

Abstract

Large brain imaging databases contain a wealth of information on brain organization in the populations they target, and on individual variability. While such databases have been used to study group-level features of populations directly, they are currently underutilized as a resource to inform single-subject analysis. Here, we propose leveraging the information contained in large functional magnetic resonance imaging (fMRI) databases by establishing population priors to employ in an empirical Bayesian framework. We focus on estimation of brain networks as source signals in independent component analysis (ICA). We formulate a hierarchical “template” ICA model where source signals—including known population brain networks and subject-specific signals—are represented as latent variables. For estimation, we derive an expectation–maximization (EM) algorithm having an explicit solution. However, as this solution is computationally intractable, we also consider an approximate subspace algorithm and a faster two-stage approach. Through extensive simulation studies, we assess performance of both methods and compare with dual regression, a popular but ad-hoc method. The two proposed algorithms have similar performance, and both dramatically outperform dual regression. We also conduct a reliability study utilizing the Human Connectome Project and find that template ICA achieves substantially better performance than dual regression, achieving 75–250% higher intra-subject reliability. Supplementary materials for this article, including a standardized description of the materials available for reproducing the work, are available as an online supplement.

Original languageEnglish (US)
JournalJournal of the American Statistical Association
DOIs
StateAccepted/In press - Jan 1 2019

Fingerprint

Independent Component Analysis
Template
Regression
Functional Magnetic Resonance Imaging
Expectation-maximization Algorithm
Latent Variables
Explicit Solution
Subspace
Imaging
Simulation Study
Resources
Target
Brain
Independent component analysis
Data base
Model

Keywords

  • Applications and case studies
  • Bayesian methods
  • Computationally intensive methods
  • Expectation–maximization
  • Neuroimaging

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{9da2ae47d1e64cc28c028bdbaf13d982,
title = "Template Independent Component Analysis: Targeted and Reliable Estimation of Subject-level Brain Networks Using Big Data Population Priors",
abstract = "Large brain imaging databases contain a wealth of information on brain organization in the populations they target, and on individual variability. While such databases have been used to study group-level features of populations directly, they are currently underutilized as a resource to inform single-subject analysis. Here, we propose leveraging the information contained in large functional magnetic resonance imaging (fMRI) databases by establishing population priors to employ in an empirical Bayesian framework. We focus on estimation of brain networks as source signals in independent component analysis (ICA). We formulate a hierarchical “template” ICA model where source signals—including known population brain networks and subject-specific signals—are represented as latent variables. For estimation, we derive an expectation–maximization (EM) algorithm having an explicit solution. However, as this solution is computationally intractable, we also consider an approximate subspace algorithm and a faster two-stage approach. Through extensive simulation studies, we assess performance of both methods and compare with dual regression, a popular but ad-hoc method. The two proposed algorithms have similar performance, and both dramatically outperform dual regression. We also conduct a reliability study utilizing the Human Connectome Project and find that template ICA achieves substantially better performance than dual regression, achieving 75–250{\%} higher intra-subject reliability. Supplementary materials for this article, including a standardized description of the materials available for reproducing the work, are available as an online supplement.",
keywords = "Applications and case studies, Bayesian methods, Computationally intensive methods, Expectation–maximization, Neuroimaging",
author = "Mejia, {Amanda F.} and Nebel, {Mary Beth} and Yikai Wang and Caffo, {Brian S.} and Ying Guo",
year = "2019",
month = "1",
day = "1",
doi = "10.1080/01621459.2019.1679638",
language = "English (US)",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",

}

TY - JOUR

T1 - Template Independent Component Analysis

T2 - Targeted and Reliable Estimation of Subject-level Brain Networks Using Big Data Population Priors

AU - Mejia, Amanda F.

AU - Nebel, Mary Beth

AU - Wang, Yikai

AU - Caffo, Brian S.

AU - Guo, Ying

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Large brain imaging databases contain a wealth of information on brain organization in the populations they target, and on individual variability. While such databases have been used to study group-level features of populations directly, they are currently underutilized as a resource to inform single-subject analysis. Here, we propose leveraging the information contained in large functional magnetic resonance imaging (fMRI) databases by establishing population priors to employ in an empirical Bayesian framework. We focus on estimation of brain networks as source signals in independent component analysis (ICA). We formulate a hierarchical “template” ICA model where source signals—including known population brain networks and subject-specific signals—are represented as latent variables. For estimation, we derive an expectation–maximization (EM) algorithm having an explicit solution. However, as this solution is computationally intractable, we also consider an approximate subspace algorithm and a faster two-stage approach. Through extensive simulation studies, we assess performance of both methods and compare with dual regression, a popular but ad-hoc method. The two proposed algorithms have similar performance, and both dramatically outperform dual regression. We also conduct a reliability study utilizing the Human Connectome Project and find that template ICA achieves substantially better performance than dual regression, achieving 75–250% higher intra-subject reliability. Supplementary materials for this article, including a standardized description of the materials available for reproducing the work, are available as an online supplement.

AB - Large brain imaging databases contain a wealth of information on brain organization in the populations they target, and on individual variability. While such databases have been used to study group-level features of populations directly, they are currently underutilized as a resource to inform single-subject analysis. Here, we propose leveraging the information contained in large functional magnetic resonance imaging (fMRI) databases by establishing population priors to employ in an empirical Bayesian framework. We focus on estimation of brain networks as source signals in independent component analysis (ICA). We formulate a hierarchical “template” ICA model where source signals—including known population brain networks and subject-specific signals—are represented as latent variables. For estimation, we derive an expectation–maximization (EM) algorithm having an explicit solution. However, as this solution is computationally intractable, we also consider an approximate subspace algorithm and a faster two-stage approach. Through extensive simulation studies, we assess performance of both methods and compare with dual regression, a popular but ad-hoc method. The two proposed algorithms have similar performance, and both dramatically outperform dual regression. We also conduct a reliability study utilizing the Human Connectome Project and find that template ICA achieves substantially better performance than dual regression, achieving 75–250% higher intra-subject reliability. Supplementary materials for this article, including a standardized description of the materials available for reproducing the work, are available as an online supplement.

KW - Applications and case studies

KW - Bayesian methods

KW - Computationally intensive methods

KW - Expectation–maximization

KW - Neuroimaging

UR - http://www.scopus.com/inward/record.url?scp=85075361398&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075361398&partnerID=8YFLogxK

U2 - 10.1080/01621459.2019.1679638

DO - 10.1080/01621459.2019.1679638

M3 - Article

AN - SCOPUS:85075361398

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

ER -