TY - JOUR
T1 - Discriminative multi-task feature selection for multi-modality classification of Alzheimer’s disease
AU - Ye, Tingting
AU - Zu, Chen
AU - Jie, Biao
AU - Shen, Dinggang
AU - Zhang, Daoqiang
AU - the Alzheimer’s Disease Neuroimaging Initiative, Alzheimer’s Disease Neuroimaging Initiative
N1 - Funding Information:
This work is supported in part by National Natural Science Foundation of China (Nos. 61422204, 61473149), the Jiangsu Natural Science Foundation for Distinguished Young Scholar (No. BK20130034), the Specialized Research Fund for the Doctoral Program of Higher Education (No. 20123218110009), the NUAA Fundamental Research Funds (No. NE2013105), and NIH grants (EB006733, EB008374, EB009634, and AG041721).
Publisher Copyright:
© 2015, Springer Science+Business Media New York.
PY - 2016/9/1
Y1 - 2016/9/1
N2 - Recently, multi-task based feature selection methods have been used in multi-modality based classification of Alzheimer’s disease (AD) and its prodromal stage, i.e., mild cognitive impairment (MCI). However, in traditional multi-task feature selection methods, some useful discriminative information among subjects is usually not well mined for further improving the subsequent classification performance. Accordingly, in this paper, we propose a discriminative multi-task feature selection method to select the most discriminative features for multi-modality based classification of AD/MCI. Specifically, for each modality, we train a linear regression model using the corresponding modality of data, and further enforce the group-sparsity regularization on weights of those regression models for joint selection of common features across multiple modalities. Furthermore, we propose a discriminative regularization term based on the intra-class and inter-class Laplacian matrices to better use the discriminative information among subjects. To evaluate our proposed method, we perform extensive experiments on 202 subjects, including 51 AD patients, 99 MCI patients, and 52 healthy controls (HC), from the baseline MRI and FDG-PET image data of the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The experimental results show that our proposed method not only improves the classification performance, but also has potential to discover the disease-related biomarkers useful for diagnosis of disease, along with the comparison to several state-of-the-art methods for multi-modality based AD/MCI classification.
AB - Recently, multi-task based feature selection methods have been used in multi-modality based classification of Alzheimer’s disease (AD) and its prodromal stage, i.e., mild cognitive impairment (MCI). However, in traditional multi-task feature selection methods, some useful discriminative information among subjects is usually not well mined for further improving the subsequent classification performance. Accordingly, in this paper, we propose a discriminative multi-task feature selection method to select the most discriminative features for multi-modality based classification of AD/MCI. Specifically, for each modality, we train a linear regression model using the corresponding modality of data, and further enforce the group-sparsity regularization on weights of those regression models for joint selection of common features across multiple modalities. Furthermore, we propose a discriminative regularization term based on the intra-class and inter-class Laplacian matrices to better use the discriminative information among subjects. To evaluate our proposed method, we perform extensive experiments on 202 subjects, including 51 AD patients, 99 MCI patients, and 52 healthy controls (HC), from the baseline MRI and FDG-PET image data of the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The experimental results show that our proposed method not only improves the classification performance, but also has potential to discover the disease-related biomarkers useful for diagnosis of disease, along with the comparison to several state-of-the-art methods for multi-modality based AD/MCI classification.
KW - Alzheimer’s disease
KW - Discriminative regularization
KW - Group-sparsity regularizer
KW - Multi-modality based classification
KW - Multi-task feature selection
UR - http://www.scopus.com/inward/record.url?scp=84940093077&partnerID=8YFLogxK
U2 - 10.1007/s11682-015-9437-x
DO - 10.1007/s11682-015-9437-x
M3 - Article
C2 - 26311394
AN - SCOPUS:84940093077
SN - 1931-7557
VL - 10
SP - 739
EP - 749
JO - Brain Imaging and Behavior
JF - Brain Imaging and Behavior
IS - 3
ER -