Sparse Feature Learning With Label Information for Alzheimer's Disease Classification Based on Magnetic Resonance Imaging

Abstract

Neuroimaging techniques have been used for automatic diagnosis and classification of Alzheimer's disease and mild cognitive impairment. How to select discriminant features from these data is the key that will affect the subsequent automatic diagnosis and classification performance. However, in the previous manifold regularized sparse regression models, the local neighborhood structure was constructed directly in the traditional Euclidean distance without fully utilizing the label information of the subjects, which leads to the selection of less discriminative features. In this paper, we propose a novel manifold regularized sparse regression model for learning discriminative features. Specifically, we first adopt ℓ2,1-norm regularization to jointly select a relevant feature subset among the samples. Then, to select more discriminative features, a novel manifold regularization term is constructed via the relative distance adjusted by the label information, which can simultaneously maintain the compactness of the intra-class samples and the separability of inter-class samples. The proposed feature learning method is further carried out for both the binary classification and the multi-class classification. The experimental results on Alzheimer's Disease Neuroimaging Initiative database demonstrate the effectiveness of the proposed method, which can be utilized for the diagnosis of Alzheimer's disease and mild cognitive impairment.