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 language | English |
|---|---|
| Pages (from-to) | 1-14 |
| Number of pages | 14 |
| Journal | Brain Imaging and Behavior |
| DOIs | |
| Publication status | Accepted/In press - 2017 Jun 17 |
Fingerprint
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
Discriminative self-representation sparse regression for neuroimaging-based alzheimer’s disease diagnosis. / Zhu, Xiaofeng; Suk, Heung-Il; Lee, Seong Whan; Shen, Dinggang.
In: Brain Imaging and Behavior, 17.06.2017, p. 1-14.Research output: Contribution to journal › Article
}
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 -