Bayesian scalar-on-image regression with application to association between intracranial DTI and cognitive outcomes

Lei Huang, Jeff Goldsmith, Philip T. Reiss, Daniel S. Reich, Ciprian M Crainiceanu

Research output: Contribution to journalArticle

Abstract

Diffusion tensor imaging (DTI) measures water diffusion within white matter, allowing for in vivo quantification of brain pathways. These pathways often subserve specific functions, and impairment of those functions is often associated with imaging abnormalities. As a method for predicting clinical disability from DTI images, we propose a hierarchical Bayesian "scalar-on-image" regression procedure. Our procedure introduces a latent binary map that estimates the locations of predictive voxels and penalizes the magnitude of effect sizes in these voxels, thereby resolving the ill-posed nature of the problem. By inducing a spatial prior structure, the procedure yields a sparse association map that also maintains spatial continuity of predictive regions. The method is demonstrated on a simulation study and on a study of association between fractional anisotropy and cognitive disability in a cross-sectional sample of 135 multiple sclerosis patients.

Original languageEnglish (US)
Pages (from-to)210-223
Number of pages14
JournalNeuroImage
Volume83
DOIs
StatePublished - Dec 2013

Fingerprint

Diffusion Tensor Imaging
Anisotropy
Multiple Sclerosis
Water
Brain

Keywords

  • Binary Markov random field
  • Diffusion tensor imaging
  • Ising prior
  • Multiple sclerosis

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Bayesian scalar-on-image regression with application to association between intracranial DTI and cognitive outcomes. / Huang, Lei; Goldsmith, Jeff; Reiss, Philip T.; Reich, Daniel S.; Crainiceanu, Ciprian M.

In: NeuroImage, Vol. 83, 12.2013, p. 210-223.

Research output: Contribution to journalArticle

Huang, Lei ; Goldsmith, Jeff ; Reiss, Philip T. ; Reich, Daniel S. ; Crainiceanu, Ciprian M. / Bayesian scalar-on-image regression with application to association between intracranial DTI and cognitive outcomes. In: NeuroImage. 2013 ; Vol. 83. pp. 210-223.
@article{dae1a31dbbe34bd1a1daba6062c67fd7,
title = "Bayesian scalar-on-image regression with application to association between intracranial DTI and cognitive outcomes",
abstract = "Diffusion tensor imaging (DTI) measures water diffusion within white matter, allowing for in vivo quantification of brain pathways. These pathways often subserve specific functions, and impairment of those functions is often associated with imaging abnormalities. As a method for predicting clinical disability from DTI images, we propose a hierarchical Bayesian {"}scalar-on-image{"} regression procedure. Our procedure introduces a latent binary map that estimates the locations of predictive voxels and penalizes the magnitude of effect sizes in these voxels, thereby resolving the ill-posed nature of the problem. By inducing a spatial prior structure, the procedure yields a sparse association map that also maintains spatial continuity of predictive regions. The method is demonstrated on a simulation study and on a study of association between fractional anisotropy and cognitive disability in a cross-sectional sample of 135 multiple sclerosis patients.",
keywords = "Binary Markov random field, Diffusion tensor imaging, Ising prior, Multiple sclerosis",
author = "Lei Huang and Jeff Goldsmith and Reiss, {Philip T.} and Reich, {Daniel S.} and Crainiceanu, {Ciprian M}",
year = "2013",
month = "12",
doi = "10.1016/j.neuroimage.2013.06.020",
language = "English (US)",
volume = "83",
pages = "210--223",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Bayesian scalar-on-image regression with application to association between intracranial DTI and cognitive outcomes

AU - Huang, Lei

AU - Goldsmith, Jeff

AU - Reiss, Philip T.

AU - Reich, Daniel S.

AU - Crainiceanu, Ciprian M

PY - 2013/12

Y1 - 2013/12

N2 - Diffusion tensor imaging (DTI) measures water diffusion within white matter, allowing for in vivo quantification of brain pathways. These pathways often subserve specific functions, and impairment of those functions is often associated with imaging abnormalities. As a method for predicting clinical disability from DTI images, we propose a hierarchical Bayesian "scalar-on-image" regression procedure. Our procedure introduces a latent binary map that estimates the locations of predictive voxels and penalizes the magnitude of effect sizes in these voxels, thereby resolving the ill-posed nature of the problem. By inducing a spatial prior structure, the procedure yields a sparse association map that also maintains spatial continuity of predictive regions. The method is demonstrated on a simulation study and on a study of association between fractional anisotropy and cognitive disability in a cross-sectional sample of 135 multiple sclerosis patients.

AB - Diffusion tensor imaging (DTI) measures water diffusion within white matter, allowing for in vivo quantification of brain pathways. These pathways often subserve specific functions, and impairment of those functions is often associated with imaging abnormalities. As a method for predicting clinical disability from DTI images, we propose a hierarchical Bayesian "scalar-on-image" regression procedure. Our procedure introduces a latent binary map that estimates the locations of predictive voxels and penalizes the magnitude of effect sizes in these voxels, thereby resolving the ill-posed nature of the problem. By inducing a spatial prior structure, the procedure yields a sparse association map that also maintains spatial continuity of predictive regions. The method is demonstrated on a simulation study and on a study of association between fractional anisotropy and cognitive disability in a cross-sectional sample of 135 multiple sclerosis patients.

KW - Binary Markov random field

KW - Diffusion tensor imaging

KW - Ising prior

KW - Multiple sclerosis

UR - http://www.scopus.com/inward/record.url?scp=84880946754&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880946754&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2013.06.020

DO - 10.1016/j.neuroimage.2013.06.020

M3 - Article

C2 - 23792220

AN - SCOPUS:84880946754

VL - 83

SP - 210

EP - 223

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -