Discriminative multi-task feature selection for multi-modality classification of Alzheimer's disease

Abstract

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.

Keywords: Alzheimer’s disease; Discriminative regularization; Group-sparsity regularizer; Multi-modality based classification; Multi-task feature selection.

Fig. 1

Overview of proposed method

Fig. 2

The diagram of discriminative analysis

Fig. 3

ROC curves of the classification performance of different methods in AD/MCI and HC

Fig. 4

ROC curves of the classification performance of different methods in MCI-C and MCI-NC

Fig. 5

Top 15 brain regions in MCI vs. HC classification

Fig. 6

Classification accuracies under different values of λ

Fig. 7

Classification accuracy with the change of discriminative parameter σ