Multi-task exclusive relationship learning for alzheimer's disease progression prediction with longitudinal data

Mingliang Wang, Daoqiang Zhang, Dinggang Shen, Mingxia Liu

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by progressive impairment of memory and other cognitive functions. Currently, many multi-task learning approaches have been proposed to predict the disease progression at the early stage using longitudinal data, with each task corresponding to a particular time point. However, the underlying association among different time points in disease progression is still under-explored in previous studies. To this end, we propose a multi-task exclusive relationship learning model to automatically capture the intrinsic relationship among tasks at different time points for estimating clinical measures based on longitudinal imaging data. The proposed method can select the most discriminative features for different tasks and also model the intrinsic relatedness among different time points, by utilizing an exclusive lasso regularization and a relationship induced regularization. Specifically, the exclusive lasso regularization enables partial group structure feature selection among the longitudinal data, while the relationship induced regularization efficiently introduces the relationship information from data to guide knowledge transfer. We further develop an efficient optimization algorithm to solve the proposed objective function. Extensive experiments on both synthetic and real datasets demonstrate the effectiveness of our proposed method. In comparison with several state-of-the-art methods, our proposed method can achieve promising performance for cognitive status prediction and also can help discover disease-related biomarkers.

Original languageEnglish
Pages (from-to)111-122
Number of pages12
JournalMedical Image Analysis
Volume53
DOIs
Publication statusPublished - 2019 Apr 1
Externally publishedYes

Fingerprint

Disease Progression
Alzheimer Disease
Learning
Group Structure
Biomarkers
Neurodegenerative Diseases
Cognition
Feature extraction
Association reactions
Imaging techniques
Data storage equipment
Experiments
alachlor

Keywords

  • Alzheimer's disease
  • Clinical status
  • Exclusive lasso
  • Longitudinal analysis

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Multi-task exclusive relationship learning for alzheimer's disease progression prediction with longitudinal data. / Wang, Mingliang; Zhang, Daoqiang; Shen, Dinggang; Liu, Mingxia.

In: Medical Image Analysis, Vol. 53, 01.04.2019, p. 111-122.

Research output: Contribution to journalArticle

@article{2930ee29759b493dbf319684f3023357,
title = "Multi-task exclusive relationship learning for alzheimer's disease progression prediction with longitudinal data",
abstract = "Alzheimer's disease (AD) is a neurodegenerative disorder characterized by progressive impairment of memory and other cognitive functions. Currently, many multi-task learning approaches have been proposed to predict the disease progression at the early stage using longitudinal data, with each task corresponding to a particular time point. However, the underlying association among different time points in disease progression is still under-explored in previous studies. To this end, we propose a multi-task exclusive relationship learning model to automatically capture the intrinsic relationship among tasks at different time points for estimating clinical measures based on longitudinal imaging data. The proposed method can select the most discriminative features for different tasks and also model the intrinsic relatedness among different time points, by utilizing an exclusive lasso regularization and a relationship induced regularization. Specifically, the exclusive lasso regularization enables partial group structure feature selection among the longitudinal data, while the relationship induced regularization efficiently introduces the relationship information from data to guide knowledge transfer. We further develop an efficient optimization algorithm to solve the proposed objective function. Extensive experiments on both synthetic and real datasets demonstrate the effectiveness of our proposed method. In comparison with several state-of-the-art methods, our proposed method can achieve promising performance for cognitive status prediction and also can help discover disease-related biomarkers.",
keywords = "Alzheimer's disease, Clinical status, Exclusive lasso, Longitudinal analysis",
author = "Mingliang Wang and Daoqiang Zhang and Dinggang Shen and Mingxia Liu",
year = "2019",
month = "4",
day = "1",
doi = "10.1016/j.media.2019.01.007",
language = "English",
volume = "53",
pages = "111--122",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

TY - JOUR

T1 - Multi-task exclusive relationship learning for alzheimer's disease progression prediction with longitudinal data

AU - Wang, Mingliang

AU - Zhang, Daoqiang

AU - Shen, Dinggang

AU - Liu, Mingxia

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Alzheimer's disease (AD) is a neurodegenerative disorder characterized by progressive impairment of memory and other cognitive functions. Currently, many multi-task learning approaches have been proposed to predict the disease progression at the early stage using longitudinal data, with each task corresponding to a particular time point. However, the underlying association among different time points in disease progression is still under-explored in previous studies. To this end, we propose a multi-task exclusive relationship learning model to automatically capture the intrinsic relationship among tasks at different time points for estimating clinical measures based on longitudinal imaging data. The proposed method can select the most discriminative features for different tasks and also model the intrinsic relatedness among different time points, by utilizing an exclusive lasso regularization and a relationship induced regularization. Specifically, the exclusive lasso regularization enables partial group structure feature selection among the longitudinal data, while the relationship induced regularization efficiently introduces the relationship information from data to guide knowledge transfer. We further develop an efficient optimization algorithm to solve the proposed objective function. Extensive experiments on both synthetic and real datasets demonstrate the effectiveness of our proposed method. In comparison with several state-of-the-art methods, our proposed method can achieve promising performance for cognitive status prediction and also can help discover disease-related biomarkers.

AB - Alzheimer's disease (AD) is a neurodegenerative disorder characterized by progressive impairment of memory and other cognitive functions. Currently, many multi-task learning approaches have been proposed to predict the disease progression at the early stage using longitudinal data, with each task corresponding to a particular time point. However, the underlying association among different time points in disease progression is still under-explored in previous studies. To this end, we propose a multi-task exclusive relationship learning model to automatically capture the intrinsic relationship among tasks at different time points for estimating clinical measures based on longitudinal imaging data. The proposed method can select the most discriminative features for different tasks and also model the intrinsic relatedness among different time points, by utilizing an exclusive lasso regularization and a relationship induced regularization. Specifically, the exclusive lasso regularization enables partial group structure feature selection among the longitudinal data, while the relationship induced regularization efficiently introduces the relationship information from data to guide knowledge transfer. We further develop an efficient optimization algorithm to solve the proposed objective function. Extensive experiments on both synthetic and real datasets demonstrate the effectiveness of our proposed method. In comparison with several state-of-the-art methods, our proposed method can achieve promising performance for cognitive status prediction and also can help discover disease-related biomarkers.

KW - Alzheimer's disease

KW - Clinical status

KW - Exclusive lasso

KW - Longitudinal analysis

UR - http://www.scopus.com/inward/record.url?scp=85061314085&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061314085&partnerID=8YFLogxK

U2 - 10.1016/j.media.2019.01.007

DO - 10.1016/j.media.2019.01.007

M3 - Article

C2 - 30763830

AN - SCOPUS:85061314085

VL - 53

SP - 111

EP - 122

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -