Discriminative self-representation sparse regression for neuroimaging-based alzheimer’s disease diagnosis

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this paper, we propose a novel feature selection method by jointly considering (1) ‘task-specific’ relations between response variables (e.g., clinical labels in this work) and neuroimaging features and (2) ‘self-representation’ relations among neuroimaging features in a sparse regression framework. Specifically, the task-specific relation is devised to learn the relative importance of features for representation of response variables by a linear combination of the input features in a supervised manner, while the self-representation relation is used to take into account the inherent information among neuroimaging features such that any feature can be represented by a weighted sum of the other features, regardless of the label information, in an unsupervised manner. By integrating these two different relations along with a group sparsity constraint, we formulate a new sparse linear regression model for class-discriminative feature selection. The selected features are used to train a support vector machine for classification. To validate the effectiveness of the proposed method, we conducted experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset; experimental results showed superiority of the proposed method over the state-of-the-art methods considered in this work.

Original languageEnglish
Pages (from-to)1-14
Number of pages14
JournalBrain Imaging and Behavior
DOIs
Publication statusAccepted/In press - 2017 Jun 17

Fingerprint

Neuroimaging
Alzheimer Disease
Linear Models

Keywords

  • Alzheimer’s disease (AD)
  • Feature selection
  • Joint sparse learning
  • Mild cognitive impairment (MCI)
  • Self-representation

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Neurology
  • Clinical Neurology
  • Cognitive Neuroscience
  • Psychiatry and Mental health
  • Cellular and Molecular Neuroscience
  • Behavioral Neuroscience

Cite this

@article{96bdfc323e1c40e8b476ac79f06766fe,
title = "Discriminative self-representation sparse regression for neuroimaging-based alzheimer’s disease diagnosis",
abstract = "In this paper, we propose a novel feature selection method by jointly considering (1) ‘task-specific’ relations between response variables (e.g., clinical labels in this work) and neuroimaging features and (2) ‘self-representation’ relations among neuroimaging features in a sparse regression framework. Specifically, the task-specific relation is devised to learn the relative importance of features for representation of response variables by a linear combination of the input features in a supervised manner, while the self-representation relation is used to take into account the inherent information among neuroimaging features such that any feature can be represented by a weighted sum of the other features, regardless of the label information, in an unsupervised manner. By integrating these two different relations along with a group sparsity constraint, we formulate a new sparse linear regression model for class-discriminative feature selection. The selected features are used to train a support vector machine for classification. To validate the effectiveness of the proposed method, we conducted experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset; experimental results showed superiority of the proposed method over the state-of-the-art methods considered in this work.",
keywords = "Alzheimer’s disease (AD), Feature selection, Joint sparse learning, Mild cognitive impairment (MCI), Self-representation",
author = "Xiaofeng Zhu and Heung-Il Suk and Lee, {Seong Whan} and Dinggang Shen",
year = "2017",
month = "6",
day = "17",
doi = "10.1007/s11682-017-9731-x",
language = "English",
pages = "1--14",
journal = "Brain Imaging and Behavior",
issn = "1931-7557",
publisher = "Springer New York",

}

TY - JOUR

T1 - Discriminative self-representation sparse regression for neuroimaging-based alzheimer’s disease diagnosis

AU - Zhu, Xiaofeng

AU - Suk, Heung-Il

AU - Lee, Seong Whan

AU - Shen, Dinggang

PY - 2017/6/17

Y1 - 2017/6/17

N2 - In this paper, we propose a novel feature selection method by jointly considering (1) ‘task-specific’ relations between response variables (e.g., clinical labels in this work) and neuroimaging features and (2) ‘self-representation’ relations among neuroimaging features in a sparse regression framework. Specifically, the task-specific relation is devised to learn the relative importance of features for representation of response variables by a linear combination of the input features in a supervised manner, while the self-representation relation is used to take into account the inherent information among neuroimaging features such that any feature can be represented by a weighted sum of the other features, regardless of the label information, in an unsupervised manner. By integrating these two different relations along with a group sparsity constraint, we formulate a new sparse linear regression model for class-discriminative feature selection. The selected features are used to train a support vector machine for classification. To validate the effectiveness of the proposed method, we conducted experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset; experimental results showed superiority of the proposed method over the state-of-the-art methods considered in this work.

AB - In this paper, we propose a novel feature selection method by jointly considering (1) ‘task-specific’ relations between response variables (e.g., clinical labels in this work) and neuroimaging features and (2) ‘self-representation’ relations among neuroimaging features in a sparse regression framework. Specifically, the task-specific relation is devised to learn the relative importance of features for representation of response variables by a linear combination of the input features in a supervised manner, while the self-representation relation is used to take into account the inherent information among neuroimaging features such that any feature can be represented by a weighted sum of the other features, regardless of the label information, in an unsupervised manner. By integrating these two different relations along with a group sparsity constraint, we formulate a new sparse linear regression model for class-discriminative feature selection. The selected features are used to train a support vector machine for classification. To validate the effectiveness of the proposed method, we conducted experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset; experimental results showed superiority of the proposed method over the state-of-the-art methods considered in this work.

KW - Alzheimer’s disease (AD)

KW - Feature selection

KW - Joint sparse learning

KW - Mild cognitive impairment (MCI)

KW - Self-representation

UR - http://www.scopus.com/inward/record.url?scp=85020552403&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020552403&partnerID=8YFLogxK

U2 - 10.1007/s11682-017-9731-x

DO - 10.1007/s11682-017-9731-x

M3 - Article

C2 - 28624881

AN - SCOPUS:85020552403

SP - 1

EP - 14

JO - Brain Imaging and Behavior

JF - Brain Imaging and Behavior

SN - 1931-7557

ER -