Distance canonical correlation analysis with application to an imaging-genetic study

Wenxing Hu, Aiying Zhang, Biao Cai, Vince Daniel Calhoun, Yu Ping Wang

Research output: Contribution to journalArticle

Abstract

Distance correlation is a measure that can detect both linear and nonlinear associations. However, applying distance correlation to imaging genetic studies often needs multiple testing correction due to the large number of multiple inferences. As a result, the sensitivity of its detection may be low. We propose a new model, distance canonical correlation analysis (DCCA), which overcomes this problem by searching a combination of features with the highest distance correlation. This is achieved by constructing a distance kernel function followed by solving a subsequent optimization problem. The ability to detect both linear and nonlinear associations makes DCCA suitable for analyzing complex multimodal and imaging-genetic associations. When applied to a brain imaging-genetic study from the Philadelphia Neurodevelopmental Cohort (PNC), DCCA detected several mental disorder-related gene pathways and brain networks. Experiments on brain connectivity found that the default mode network had strong nonlinear connections with other brain networks. When applied to the study of age effects, DCCA revealed that the connections of brain networks were relatively weak in younger groups but became stronger at older age stages. It indicates that adolescence is a vital stage for brain development. DCCA thus reveals a number of interesting findings and demonstrates a powerful new approach for analyzing multimodal brain imaging data.

Original languageEnglish (US)
Article number026501
JournalJournal of Medical Imaging
Volume6
Issue number2
DOIs
StatePublished - Apr 1 2019
Externally publishedYes

Fingerprint

Multimodal Imaging
Brain
Neuroimaging
Aptitude
Mental Disorders
Genes

Keywords

  • Brain networks
  • Distance correlation
  • Functional magnetic resonance imaging
  • Imaging genetics
  • Multimodal
  • Nonlinear

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Distance canonical correlation analysis with application to an imaging-genetic study. / Hu, Wenxing; Zhang, Aiying; Cai, Biao; Calhoun, Vince Daniel; Wang, Yu Ping.

In: Journal of Medical Imaging, Vol. 6, No. 2, 026501, 01.04.2019.

Research output: Contribution to journalArticle

@article{1bb7906638dd40098a85377854bbaa46,
title = "Distance canonical correlation analysis with application to an imaging-genetic study",
abstract = "Distance correlation is a measure that can detect both linear and nonlinear associations. However, applying distance correlation to imaging genetic studies often needs multiple testing correction due to the large number of multiple inferences. As a result, the sensitivity of its detection may be low. We propose a new model, distance canonical correlation analysis (DCCA), which overcomes this problem by searching a combination of features with the highest distance correlation. This is achieved by constructing a distance kernel function followed by solving a subsequent optimization problem. The ability to detect both linear and nonlinear associations makes DCCA suitable for analyzing complex multimodal and imaging-genetic associations. When applied to a brain imaging-genetic study from the Philadelphia Neurodevelopmental Cohort (PNC), DCCA detected several mental disorder-related gene pathways and brain networks. Experiments on brain connectivity found that the default mode network had strong nonlinear connections with other brain networks. When applied to the study of age effects, DCCA revealed that the connections of brain networks were relatively weak in younger groups but became stronger at older age stages. It indicates that adolescence is a vital stage for brain development. DCCA thus reveals a number of interesting findings and demonstrates a powerful new approach for analyzing multimodal brain imaging data.",
keywords = "Brain networks, Distance correlation, Functional magnetic resonance imaging, Imaging genetics, Multimodal, Nonlinear",
author = "Wenxing Hu and Aiying Zhang and Biao Cai and Calhoun, {Vince Daniel} and Wang, {Yu Ping}",
year = "2019",
month = "4",
day = "1",
doi = "10.1117/1.JMI.6.2.026501",
language = "English (US)",
volume = "6",
journal = "Journal of Medical Imaging",
issn = "0720-048X",
publisher = "Elsevier Ireland Ltd",
number = "2",

}

TY - JOUR

T1 - Distance canonical correlation analysis with application to an imaging-genetic study

AU - Hu, Wenxing

AU - Zhang, Aiying

AU - Cai, Biao

AU - Calhoun, Vince Daniel

AU - Wang, Yu Ping

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Distance correlation is a measure that can detect both linear and nonlinear associations. However, applying distance correlation to imaging genetic studies often needs multiple testing correction due to the large number of multiple inferences. As a result, the sensitivity of its detection may be low. We propose a new model, distance canonical correlation analysis (DCCA), which overcomes this problem by searching a combination of features with the highest distance correlation. This is achieved by constructing a distance kernel function followed by solving a subsequent optimization problem. The ability to detect both linear and nonlinear associations makes DCCA suitable for analyzing complex multimodal and imaging-genetic associations. When applied to a brain imaging-genetic study from the Philadelphia Neurodevelopmental Cohort (PNC), DCCA detected several mental disorder-related gene pathways and brain networks. Experiments on brain connectivity found that the default mode network had strong nonlinear connections with other brain networks. When applied to the study of age effects, DCCA revealed that the connections of brain networks were relatively weak in younger groups but became stronger at older age stages. It indicates that adolescence is a vital stage for brain development. DCCA thus reveals a number of interesting findings and demonstrates a powerful new approach for analyzing multimodal brain imaging data.

AB - Distance correlation is a measure that can detect both linear and nonlinear associations. However, applying distance correlation to imaging genetic studies often needs multiple testing correction due to the large number of multiple inferences. As a result, the sensitivity of its detection may be low. We propose a new model, distance canonical correlation analysis (DCCA), which overcomes this problem by searching a combination of features with the highest distance correlation. This is achieved by constructing a distance kernel function followed by solving a subsequent optimization problem. The ability to detect both linear and nonlinear associations makes DCCA suitable for analyzing complex multimodal and imaging-genetic associations. When applied to a brain imaging-genetic study from the Philadelphia Neurodevelopmental Cohort (PNC), DCCA detected several mental disorder-related gene pathways and brain networks. Experiments on brain connectivity found that the default mode network had strong nonlinear connections with other brain networks. When applied to the study of age effects, DCCA revealed that the connections of brain networks were relatively weak in younger groups but became stronger at older age stages. It indicates that adolescence is a vital stage for brain development. DCCA thus reveals a number of interesting findings and demonstrates a powerful new approach for analyzing multimodal brain imaging data.

KW - Brain networks

KW - Distance correlation

KW - Functional magnetic resonance imaging

KW - Imaging genetics

KW - Multimodal

KW - Nonlinear

UR - http://www.scopus.com/inward/record.url?scp=85065475280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065475280&partnerID=8YFLogxK

U2 - 10.1117/1.JMI.6.2.026501

DO - 10.1117/1.JMI.6.2.026501

M3 - Article

C2 - 31001569

AN - SCOPUS:85065475280

VL - 6

JO - Journal of Medical Imaging

JF - Journal of Medical Imaging

SN - 0720-048X

IS - 2

M1 - 026501

ER -