Identifying the neuroanatomical basis of cognitive impairment in Alzheimer's disease by correlation-and nonlinearity-aware sparse bayesian learning

Jing Wan, Zhilin Zhang, Bhaskar D. Rao, Shiaofen Fang, Jingwen Yan, Andrew Saykin, Li Shen

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

Predicting cognitive performance of subjects from their magnetic resonance imaging (MRI) measures and identifying relevant imaging biomarkers are important research topics in the study of Alzheimer's disease. Traditionally, this task is performed by formulating a linear regression problem. Recently, it is found that using a linear sparse regression model can achieve better prediction accuracy. However, most existing studies only focus on the exploitation of sparsity of regression coefficients, ignoring useful structure information in regression coefficients. Also, these linear sparse models may not capture more complicated and possibly nonlinear relationships between cognitive performance and MRI measures. Motivated by these observations, in this work we build a sparse multivariate regression model for this task and propose an empirical sparse Bayesian learning algorithm. Different from existing sparse algorithms, the proposed algorithm models the response as a nonlinear function of the predictors by extending the predictor matrix with block structures. Further, it exploits not only inter-vector correlation among regression coefficient vectors, but also intra-block correlation in each regression coefficient vector. Experiments on the Alzheimer's Disease Neuroimaging Initiative database showed that the proposed algorithm not only achieved better prediction performance than state-of-the-art competitive methods, but also effectively identified biologically meaningful patterns.

Original languageEnglish
Article number6781587
Pages (from-to)1475-1487
Number of pages13
JournalIEEE Transactions on Medical Imaging
Volume33
Issue number7
DOIs
StatePublished - 2014

Fingerprint

Alzheimer Disease
Learning
Linear Models
Magnetic resonance
Imaging techniques
Magnetic Resonance Imaging
Neuroimaging
Biomarkers
Linear regression
Learning algorithms
Databases
Cognitive Dysfunction
Research
Experiments

Keywords

  • Alzheimer's disease (AD)
  • cognitive Impairment
  • neuroimaging
  • sparse Bayesian learning (SBL)

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software
  • Medicine(all)

Cite this

Identifying the neuroanatomical basis of cognitive impairment in Alzheimer's disease by correlation-and nonlinearity-aware sparse bayesian learning. / Wan, Jing; Zhang, Zhilin; Rao, Bhaskar D.; Fang, Shiaofen; Yan, Jingwen; Saykin, Andrew; Shen, Li.

In: IEEE Transactions on Medical Imaging, Vol. 33, No. 7, 6781587, 2014, p. 1475-1487.

Research output: Contribution to journalArticle

@article{bbd15410c67244c3b8f8b8aa17f7601a,
title = "Identifying the neuroanatomical basis of cognitive impairment in Alzheimer's disease by correlation-and nonlinearity-aware sparse bayesian learning",
abstract = "Predicting cognitive performance of subjects from their magnetic resonance imaging (MRI) measures and identifying relevant imaging biomarkers are important research topics in the study of Alzheimer's disease. Traditionally, this task is performed by formulating a linear regression problem. Recently, it is found that using a linear sparse regression model can achieve better prediction accuracy. However, most existing studies only focus on the exploitation of sparsity of regression coefficients, ignoring useful structure information in regression coefficients. Also, these linear sparse models may not capture more complicated and possibly nonlinear relationships between cognitive performance and MRI measures. Motivated by these observations, in this work we build a sparse multivariate regression model for this task and propose an empirical sparse Bayesian learning algorithm. Different from existing sparse algorithms, the proposed algorithm models the response as a nonlinear function of the predictors by extending the predictor matrix with block structures. Further, it exploits not only inter-vector correlation among regression coefficient vectors, but also intra-block correlation in each regression coefficient vector. Experiments on the Alzheimer's Disease Neuroimaging Initiative database showed that the proposed algorithm not only achieved better prediction performance than state-of-the-art competitive methods, but also effectively identified biologically meaningful patterns.",
keywords = "Alzheimer's disease (AD), cognitive Impairment, neuroimaging, sparse Bayesian learning (SBL)",
author = "Jing Wan and Zhilin Zhang and Rao, {Bhaskar D.} and Shiaofen Fang and Jingwen Yan and Andrew Saykin and Li Shen",
year = "2014",
doi = "10.1109/TMI.2014.2314712",
language = "English",
volume = "33",
pages = "1475--1487",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "7",

}

TY - JOUR

T1 - Identifying the neuroanatomical basis of cognitive impairment in Alzheimer's disease by correlation-and nonlinearity-aware sparse bayesian learning

AU - Wan, Jing

AU - Zhang, Zhilin

AU - Rao, Bhaskar D.

AU - Fang, Shiaofen

AU - Yan, Jingwen

AU - Saykin, Andrew

AU - Shen, Li

PY - 2014

Y1 - 2014

N2 - Predicting cognitive performance of subjects from their magnetic resonance imaging (MRI) measures and identifying relevant imaging biomarkers are important research topics in the study of Alzheimer's disease. Traditionally, this task is performed by formulating a linear regression problem. Recently, it is found that using a linear sparse regression model can achieve better prediction accuracy. However, most existing studies only focus on the exploitation of sparsity of regression coefficients, ignoring useful structure information in regression coefficients. Also, these linear sparse models may not capture more complicated and possibly nonlinear relationships between cognitive performance and MRI measures. Motivated by these observations, in this work we build a sparse multivariate regression model for this task and propose an empirical sparse Bayesian learning algorithm. Different from existing sparse algorithms, the proposed algorithm models the response as a nonlinear function of the predictors by extending the predictor matrix with block structures. Further, it exploits not only inter-vector correlation among regression coefficient vectors, but also intra-block correlation in each regression coefficient vector. Experiments on the Alzheimer's Disease Neuroimaging Initiative database showed that the proposed algorithm not only achieved better prediction performance than state-of-the-art competitive methods, but also effectively identified biologically meaningful patterns.

AB - Predicting cognitive performance of subjects from their magnetic resonance imaging (MRI) measures and identifying relevant imaging biomarkers are important research topics in the study of Alzheimer's disease. Traditionally, this task is performed by formulating a linear regression problem. Recently, it is found that using a linear sparse regression model can achieve better prediction accuracy. However, most existing studies only focus on the exploitation of sparsity of regression coefficients, ignoring useful structure information in regression coefficients. Also, these linear sparse models may not capture more complicated and possibly nonlinear relationships between cognitive performance and MRI measures. Motivated by these observations, in this work we build a sparse multivariate regression model for this task and propose an empirical sparse Bayesian learning algorithm. Different from existing sparse algorithms, the proposed algorithm models the response as a nonlinear function of the predictors by extending the predictor matrix with block structures. Further, it exploits not only inter-vector correlation among regression coefficient vectors, but also intra-block correlation in each regression coefficient vector. Experiments on the Alzheimer's Disease Neuroimaging Initiative database showed that the proposed algorithm not only achieved better prediction performance than state-of-the-art competitive methods, but also effectively identified biologically meaningful patterns.

KW - Alzheimer's disease (AD)

KW - cognitive Impairment

KW - neuroimaging

KW - sparse Bayesian learning (SBL)

UR - http://www.scopus.com/inward/record.url?scp=84903786312&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903786312&partnerID=8YFLogxK

U2 - 10.1109/TMI.2014.2314712

DO - 10.1109/TMI.2014.2314712

M3 - Article

C2 - 24710828

AN - SCOPUS:84903786312

VL - 33

SP - 1475

EP - 1487

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 7

M1 - 6781587

ER -