Abstract
In this paper, we focus on joint regression and classification for Alzheimer's disease diagnosis and propose a new feature selection method by embedding the relational information inherent in the observations into a sparse multi-task learning framework. Specifically, the relational information includes three kinds of relationships (such as feature-feature relation, response-response relation, and sample-sample relation), for preserving three kinds of the similarity, such as for the features, the response variables, and the samples, respectively. To conduct feature selection, we first formulate the objective function by imposing these three relational characteristics along with an ℓ2,1-norm regularization term, and further propose a computationally efficient algorithm to optimize the proposed objective function. With the dimension-reduced data, we train two support vector regression models to predict the clinical scores of ADAS-Cog and MMSE, respectively, and also a support vector classification model to determine the clinical label. We conducted extensive experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset to validate the effectiveness of the proposed method. Our experimental results showed the efficacy of the proposed method in enhancing the performances of both clinical scores prediction and disease status identification, compared to the state-of-the-art methods.
| Original language | English |
|---|---|
| Journal | Medical Image Analysis |
| DOIs | |
| Publication status | Accepted/In press - 2014 Nov 9 |
Fingerprint
Keywords
- Alzheimer's disease
- Feature selection
- Manifold learning
- MCI conversion
- Sparse coding
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition
- Radiology Nuclear Medicine and imaging
- Health Informatics
- Radiological and Ultrasound Technology
Cite this
A novel relational regularization feature selection method for joint regression and classification in AD diagnosis. / Zhu, Xiaofeng; Suk, Heung-Il; Wang, Li; Lee, Seong Whan; Shen, Dinggang.
In: Medical Image Analysis, 09.11.2014.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A novel relational regularization feature selection method for joint regression and classification in AD diagnosis
AU - Zhu, Xiaofeng
AU - Suk, Heung-Il
AU - Wang, Li
AU - Lee, Seong Whan
AU - Shen, Dinggang
PY - 2014/11/9
Y1 - 2014/11/9
N2 - In this paper, we focus on joint regression and classification for Alzheimer's disease diagnosis and propose a new feature selection method by embedding the relational information inherent in the observations into a sparse multi-task learning framework. Specifically, the relational information includes three kinds of relationships (such as feature-feature relation, response-response relation, and sample-sample relation), for preserving three kinds of the similarity, such as for the features, the response variables, and the samples, respectively. To conduct feature selection, we first formulate the objective function by imposing these three relational characteristics along with an ℓ2,1-norm regularization term, and further propose a computationally efficient algorithm to optimize the proposed objective function. With the dimension-reduced data, we train two support vector regression models to predict the clinical scores of ADAS-Cog and MMSE, respectively, and also a support vector classification model to determine the clinical label. We conducted extensive experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset to validate the effectiveness of the proposed method. Our experimental results showed the efficacy of the proposed method in enhancing the performances of both clinical scores prediction and disease status identification, compared to the state-of-the-art methods.
AB - In this paper, we focus on joint regression and classification for Alzheimer's disease diagnosis and propose a new feature selection method by embedding the relational information inherent in the observations into a sparse multi-task learning framework. Specifically, the relational information includes three kinds of relationships (such as feature-feature relation, response-response relation, and sample-sample relation), for preserving three kinds of the similarity, such as for the features, the response variables, and the samples, respectively. To conduct feature selection, we first formulate the objective function by imposing these three relational characteristics along with an ℓ2,1-norm regularization term, and further propose a computationally efficient algorithm to optimize the proposed objective function. With the dimension-reduced data, we train two support vector regression models to predict the clinical scores of ADAS-Cog and MMSE, respectively, and also a support vector classification model to determine the clinical label. We conducted extensive experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset to validate the effectiveness of the proposed method. Our experimental results showed the efficacy of the proposed method in enhancing the performances of both clinical scores prediction and disease status identification, compared to the state-of-the-art methods.
KW - Alzheimer's disease
KW - Feature selection
KW - Manifold learning
KW - MCI conversion
KW - Sparse coding
UR - http://www.scopus.com/inward/record.url?scp=84949058046&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84949058046&partnerID=8YFLogxK
U2 - 10.1016/j.media.2015.10.008
DO - 10.1016/j.media.2015.10.008
M3 - Article
C2 - 26674971
AN - SCOPUS:84949058046
JO - Medical Image Analysis
JF - Medical Image Analysis
SN - 1361-8415
ER -