Biological brain age prediction using cortical thickness data: A large scale cohort study

Habtamu M. Aycheh, Jun Kyung Seong, Jeong Hyeon Shin, Duk L. Na, Byungkon Kang, Sang W. Seo, Kyung Ah Sohn

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Brain age estimation from anatomical features has been attracting more attention in recent years. This interest in brain age estimation is motivated by the importance of biological age prediction in health informatics, with an application to early prediction of neurocognitive disorders. It is well-known that normal brain aging follows a specific pattern, which enables researchers and practitioners to predict the age of a human's brain from its degeneration. In this paper, we model brain age predicted by cortical thickness data gathered from large cohort brain images. We collected 2,911 cognitively normal subjects (age 45-91 years) at a single medical center and acquired their brain magnetic resonance (MR) images. All images were acquired using the same scanner with the same protocol. We propose to first apply Sparse Group Lasso (SGL) for feature selection by utilizing the brain's anatomical grouping. Once the features are selected, a non-parametric non-linear regression using the Gaussian Process Regression (GPR) algorithm is applied to fit the final age prediction model. Experimental results demonstrate that the proposed method achieves the mean absolute error of 4.05 years, which is comparable with or superior to several recent methods. Our method can also be a critical tool for clinicians to differentiate patients with neurodegenerative brain disease by extracting a cortical thinning pattern associated with normal aging.

Original languageEnglish
Article number252
JournalFrontiers in Aging Neuroscience
Volume10
Issue numberAUG
DOIs
Publication statusPublished - 2018 Aug 22

Fingerprint

Cohort Studies
Brain
Informatics
Brain Diseases
Neurodegenerative Diseases
Magnetic Resonance Spectroscopy
Research Personnel
Health

Keywords

  • Aging
  • Cortical lobe
  • Cortical thickness
  • Gaussian process
  • Regression analysis
  • ROI
  • Sparse Group Lasso

ASJC Scopus subject areas

  • Ageing
  • Cognitive Neuroscience

Cite this

Biological brain age prediction using cortical thickness data : A large scale cohort study. / Aycheh, Habtamu M.; Seong, Jun Kyung; Shin, Jeong Hyeon; Na, Duk L.; Kang, Byungkon; Seo, Sang W.; Sohn, Kyung Ah.

In: Frontiers in Aging Neuroscience, Vol. 10, No. AUG, 252, 22.08.2018.

Research output: Contribution to journalArticle

Aycheh, Habtamu M. ; Seong, Jun Kyung ; Shin, Jeong Hyeon ; Na, Duk L. ; Kang, Byungkon ; Seo, Sang W. ; Sohn, Kyung Ah. / Biological brain age prediction using cortical thickness data : A large scale cohort study. In: Frontiers in Aging Neuroscience. 2018 ; Vol. 10, No. AUG.
@article{31949ce356494dc98cc8c764f3644184,
title = "Biological brain age prediction using cortical thickness data: A large scale cohort study",
abstract = "Brain age estimation from anatomical features has been attracting more attention in recent years. This interest in brain age estimation is motivated by the importance of biological age prediction in health informatics, with an application to early prediction of neurocognitive disorders. It is well-known that normal brain aging follows a specific pattern, which enables researchers and practitioners to predict the age of a human's brain from its degeneration. In this paper, we model brain age predicted by cortical thickness data gathered from large cohort brain images. We collected 2,911 cognitively normal subjects (age 45-91 years) at a single medical center and acquired their brain magnetic resonance (MR) images. All images were acquired using the same scanner with the same protocol. We propose to first apply Sparse Group Lasso (SGL) for feature selection by utilizing the brain's anatomical grouping. Once the features are selected, a non-parametric non-linear regression using the Gaussian Process Regression (GPR) algorithm is applied to fit the final age prediction model. Experimental results demonstrate that the proposed method achieves the mean absolute error of 4.05 years, which is comparable with or superior to several recent methods. Our method can also be a critical tool for clinicians to differentiate patients with neurodegenerative brain disease by extracting a cortical thinning pattern associated with normal aging.",
keywords = "Aging, Cortical lobe, Cortical thickness, Gaussian process, Regression analysis, ROI, Sparse Group Lasso",
author = "Aycheh, {Habtamu M.} and Seong, {Jun Kyung} and Shin, {Jeong Hyeon} and Na, {Duk L.} and Byungkon Kang and Seo, {Sang W.} and Sohn, {Kyung Ah}",
year = "2018",
month = "8",
day = "22",
doi = "10.3389/fnagi.2018.00252",
language = "English",
volume = "10",
journal = "Frontiers in Aging Neuroscience",
issn = "1663-4365",
publisher = "Frontiers Research Foundation",
number = "AUG",

}

TY - JOUR

T1 - Biological brain age prediction using cortical thickness data

T2 - A large scale cohort study

AU - Aycheh, Habtamu M.

AU - Seong, Jun Kyung

AU - Shin, Jeong Hyeon

AU - Na, Duk L.

AU - Kang, Byungkon

AU - Seo, Sang W.

AU - Sohn, Kyung Ah

PY - 2018/8/22

Y1 - 2018/8/22

N2 - Brain age estimation from anatomical features has been attracting more attention in recent years. This interest in brain age estimation is motivated by the importance of biological age prediction in health informatics, with an application to early prediction of neurocognitive disorders. It is well-known that normal brain aging follows a specific pattern, which enables researchers and practitioners to predict the age of a human's brain from its degeneration. In this paper, we model brain age predicted by cortical thickness data gathered from large cohort brain images. We collected 2,911 cognitively normal subjects (age 45-91 years) at a single medical center and acquired their brain magnetic resonance (MR) images. All images were acquired using the same scanner with the same protocol. We propose to first apply Sparse Group Lasso (SGL) for feature selection by utilizing the brain's anatomical grouping. Once the features are selected, a non-parametric non-linear regression using the Gaussian Process Regression (GPR) algorithm is applied to fit the final age prediction model. Experimental results demonstrate that the proposed method achieves the mean absolute error of 4.05 years, which is comparable with or superior to several recent methods. Our method can also be a critical tool for clinicians to differentiate patients with neurodegenerative brain disease by extracting a cortical thinning pattern associated with normal aging.

AB - Brain age estimation from anatomical features has been attracting more attention in recent years. This interest in brain age estimation is motivated by the importance of biological age prediction in health informatics, with an application to early prediction of neurocognitive disorders. It is well-known that normal brain aging follows a specific pattern, which enables researchers and practitioners to predict the age of a human's brain from its degeneration. In this paper, we model brain age predicted by cortical thickness data gathered from large cohort brain images. We collected 2,911 cognitively normal subjects (age 45-91 years) at a single medical center and acquired their brain magnetic resonance (MR) images. All images were acquired using the same scanner with the same protocol. We propose to first apply Sparse Group Lasso (SGL) for feature selection by utilizing the brain's anatomical grouping. Once the features are selected, a non-parametric non-linear regression using the Gaussian Process Regression (GPR) algorithm is applied to fit the final age prediction model. Experimental results demonstrate that the proposed method achieves the mean absolute error of 4.05 years, which is comparable with or superior to several recent methods. Our method can also be a critical tool for clinicians to differentiate patients with neurodegenerative brain disease by extracting a cortical thinning pattern associated with normal aging.

KW - Aging

KW - Cortical lobe

KW - Cortical thickness

KW - Gaussian process

KW - Regression analysis

KW - ROI

KW - Sparse Group Lasso

UR - http://www.scopus.com/inward/record.url?scp=85052296039&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052296039&partnerID=8YFLogxK

U2 - 10.3389/fnagi.2018.00252

DO - 10.3389/fnagi.2018.00252

M3 - Article

AN - SCOPUS:85052296039

VL - 10

JO - Frontiers in Aging Neuroscience

JF - Frontiers in Aging Neuroscience

SN - 1663-4365

IS - AUG

M1 - 252

ER -