Inherent Structure-Based Multiview Learning With Multitemplate Feature Representation for Alzheimer's Disease Diagnosis

Abstract

Multitemplate-based brain morphometric pattern analysis using magnetic resonance imaging has been recently proposed for automatic diagnosis of Alzheimer's disease (AD) and its prodromal stage (i.e., mild cognitive impairment or MCI). In such methods, multiview morphological patterns generated from multiple templates are used as feature representation for brain images. However, existing multitemplate-based methods often simply assume that each class is represented by a specific type of data distribution (i.e., a single cluster), while in reality, the underlying data distribution is actually not preknown. In this paper, we propose an inherent structure-based multiview leaning method using multiple templates for AD/MCI classification. Specifically, we first extract multiview feature representations for subjects using multiple selected templates and then cluster subjects within a specific class into several subclasses (i.e., clusters) in each view space. Then, we encode those subclasses with unique codes by considering both their original class information and their own distribution information, followed by a multitask feature selection model. Finally, we learn an ensemble of view-specific support vector machine classifiers based on their, respectively, selected features in each view and fuse their results to draw the final decision. Experimental results on the Alzheimer's Disease Neuroimaging Initiative database demonstrate that our method achieves promising results for AD/MCI classification, compared to the state-of-the-art multitemplate-based methods.

Fig. 1

The flowchart of our proposed method, including three main steps: 1) multi-view feature extraction, 2) sub-class clustering based feature selection, and 3) SVM-based ensemble classification.

Fig. 2

Selected templates (i.e., exemplars) achieved by affinity propagation algorithm.

Fig. 3

An example illustration of our proposed sub-class clustering based encoding method in a specific view space, where subjects in Class 1 are partitioned into two sub-classes, while subjects in Class 2 are divided into three sub-classes.

Fig. 4

Averaged classification results achieved by different methods using different single-view features in (a) AD vs. NC, (b) pMCI vs. NC, and (c) pMCI vs. sMCI classification tasks.

Fig. 5

Classification results achieved by different methods using multi-view features and feature concatenation strategy in (a) AD vs. NC, (b) pMCI vs. NC, and (c) pMCI vs. sMCI classification tasks.

Fig. 6

Classification results achieved by different methods using multi-view features and ensemble classification strategy in (a) AD vs. NC, (b) pMCI vs. NC, and (c) pMCI vs. sMCI classification tasks.

Fig. 7

ROC curves achieved by different methods using the proposed ensemble classification strategy in (a) AD vs. NC, (b) pMCI vs. NC, and (c) pMCI vs. sMCI classification tasks.

Fig. 8

Classification accuracy vs. sub-class number, achieved by our ISML method using feature concatenation strategy in (a) AD vs. NC, (b) pMCI vs. NC, and (c) pMCI vs. sMCI classification tasks.

Fig. 9

Classification accuracy vs. sub-class number, achieved by our ISML method using ensemble classification strategy in (a) AD vs. NC, (b) pMCI vs. NC, and (c) pMCI vs. sMCI classification tasks.

Fig. 10

Diversities and mean classification errors achieved by seven ensemble-based methods in (a) AD vs. NC, (b) pMCI vs. NC, and (c) pMCI vs. sMCI classification tasks.