Discovery and visualization of structural biomarkers from MRI using transport-based morphometry

Shinjini Kundu, Soheil Kolouri, Kirk I. Erickson, Arthur F. Kramer, Edward McAuley, Gustavo K. Rohde

Research output: Contribution to journalArticle

Abstract

Disease in the brain is often associated with subtle, spatially diffuse, or complex tissue changes that may lie beneath the level of gross visual inspection, even on magnetic resonance imaging (MRI). Unfortunately, current computer-assisted approaches that examine pre-specified features, whether anatomically-defined (i.e. thalamic volume, cortical thickness) or based on pixelwise comparison (i.e. deformation-based methods), are prone to missing a vast array of physical changes that are not well-encapsulated by these metrics. In this paper, we have developed a technique for automated pattern analysis that can fully determine the relationship between brain structure and observable phenotype without requiring any a priori features. Our technique, called transport-based morphometry (TBM), is an image transformation that maps brain images losslessly to a domain where they become much more separable. The new approach is validated on structural brain images of healthy older adult subjects where even linear models for discrimination, regression, and blind source separation enable TBM to independently discover the characteristic changes of aging and highlight potential mechanisms by which aerobic fitness may mediate brain health later in life. TBM is a generative approach that can provide visualization of physically meaningful shifts in tissue distribution through inverse transformation. The proposed framework is a powerful technique that can potentially elucidate genotype-structural-behavioral associations in myriad diseases.

Original languageEnglish (US)
Pages (from-to)256-275
Number of pages20
JournalNeuroImage
Volume167
DOIs
StatePublished - Feb 15 2018
Externally publishedYes

Fingerprint

Biomarkers
Magnetic Resonance Imaging
Brain
Brain Diseases
Tissue Distribution
Linear Models
Genotype
Phenotype
Health

Keywords

  • Aging
  • Computer-aided detection
  • Magnetic resonance imaging
  • Transport-based morphometry

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Cite this

Discovery and visualization of structural biomarkers from MRI using transport-based morphometry. / Kundu, Shinjini; Kolouri, Soheil; Erickson, Kirk I.; Kramer, Arthur F.; McAuley, Edward; Rohde, Gustavo K.

In: NeuroImage, Vol. 167, 15.02.2018, p. 256-275.

Research output: Contribution to journalArticle

Kundu, Shinjini ; Kolouri, Soheil ; Erickson, Kirk I. ; Kramer, Arthur F. ; McAuley, Edward ; Rohde, Gustavo K. / Discovery and visualization of structural biomarkers from MRI using transport-based morphometry. In: NeuroImage. 2018 ; Vol. 167. pp. 256-275.
@article{3992f7345a7643539de2a22473af8403,
title = "Discovery and visualization of structural biomarkers from MRI using transport-based morphometry",
abstract = "Disease in the brain is often associated with subtle, spatially diffuse, or complex tissue changes that may lie beneath the level of gross visual inspection, even on magnetic resonance imaging (MRI). Unfortunately, current computer-assisted approaches that examine pre-specified features, whether anatomically-defined (i.e. thalamic volume, cortical thickness) or based on pixelwise comparison (i.e. deformation-based methods), are prone to missing a vast array of physical changes that are not well-encapsulated by these metrics. In this paper, we have developed a technique for automated pattern analysis that can fully determine the relationship between brain structure and observable phenotype without requiring any a priori features. Our technique, called transport-based morphometry (TBM), is an image transformation that maps brain images losslessly to a domain where they become much more separable. The new approach is validated on structural brain images of healthy older adult subjects where even linear models for discrimination, regression, and blind source separation enable TBM to independently discover the characteristic changes of aging and highlight potential mechanisms by which aerobic fitness may mediate brain health later in life. TBM is a generative approach that can provide visualization of physically meaningful shifts in tissue distribution through inverse transformation. The proposed framework is a powerful technique that can potentially elucidate genotype-structural-behavioral associations in myriad diseases.",
keywords = "Aging, Computer-aided detection, Magnetic resonance imaging, Transport-based morphometry",
author = "Shinjini Kundu and Soheil Kolouri and Erickson, {Kirk I.} and Kramer, {Arthur F.} and Edward McAuley and Rohde, {Gustavo K.}",
year = "2018",
month = "2",
day = "15",
doi = "10.1016/j.neuroimage.2017.11.006",
language = "English (US)",
volume = "167",
pages = "256--275",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Discovery and visualization of structural biomarkers from MRI using transport-based morphometry

AU - Kundu, Shinjini

AU - Kolouri, Soheil

AU - Erickson, Kirk I.

AU - Kramer, Arthur F.

AU - McAuley, Edward

AU - Rohde, Gustavo K.

PY - 2018/2/15

Y1 - 2018/2/15

N2 - Disease in the brain is often associated with subtle, spatially diffuse, or complex tissue changes that may lie beneath the level of gross visual inspection, even on magnetic resonance imaging (MRI). Unfortunately, current computer-assisted approaches that examine pre-specified features, whether anatomically-defined (i.e. thalamic volume, cortical thickness) or based on pixelwise comparison (i.e. deformation-based methods), are prone to missing a vast array of physical changes that are not well-encapsulated by these metrics. In this paper, we have developed a technique for automated pattern analysis that can fully determine the relationship between brain structure and observable phenotype without requiring any a priori features. Our technique, called transport-based morphometry (TBM), is an image transformation that maps brain images losslessly to a domain where they become much more separable. The new approach is validated on structural brain images of healthy older adult subjects where even linear models for discrimination, regression, and blind source separation enable TBM to independently discover the characteristic changes of aging and highlight potential mechanisms by which aerobic fitness may mediate brain health later in life. TBM is a generative approach that can provide visualization of physically meaningful shifts in tissue distribution through inverse transformation. The proposed framework is a powerful technique that can potentially elucidate genotype-structural-behavioral associations in myriad diseases.

AB - Disease in the brain is often associated with subtle, spatially diffuse, or complex tissue changes that may lie beneath the level of gross visual inspection, even on magnetic resonance imaging (MRI). Unfortunately, current computer-assisted approaches that examine pre-specified features, whether anatomically-defined (i.e. thalamic volume, cortical thickness) or based on pixelwise comparison (i.e. deformation-based methods), are prone to missing a vast array of physical changes that are not well-encapsulated by these metrics. In this paper, we have developed a technique for automated pattern analysis that can fully determine the relationship between brain structure and observable phenotype without requiring any a priori features. Our technique, called transport-based morphometry (TBM), is an image transformation that maps brain images losslessly to a domain where they become much more separable. The new approach is validated on structural brain images of healthy older adult subjects where even linear models for discrimination, regression, and blind source separation enable TBM to independently discover the characteristic changes of aging and highlight potential mechanisms by which aerobic fitness may mediate brain health later in life. TBM is a generative approach that can provide visualization of physically meaningful shifts in tissue distribution through inverse transformation. The proposed framework is a powerful technique that can potentially elucidate genotype-structural-behavioral associations in myriad diseases.

KW - Aging

KW - Computer-aided detection

KW - Magnetic resonance imaging

KW - Transport-based morphometry

UR - http://www.scopus.com/inward/record.url?scp=85036596951&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85036596951&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2017.11.006

DO - 10.1016/j.neuroimage.2017.11.006

M3 - Article

C2 - 29117580

AN - SCOPUS:85036596951

VL - 167

SP - 256

EP - 275

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -