Classification of Depressive Disorder Based on RS-fMRI Using Multivariate Pattern Analysis with Multiple Features

Resting-state functional Magnetic Resonance Image (RS-fMRI) can be very useful to discriminate depressive disorder (DD) from healthy controls (HCs) in terms of diagnosis objectivity. Due to the lack of biomarkers, high dimension features of RS-fMRI and the unobservable alterations reflecting in RS-fMRI, it is still a major clinical challenge. Multivariate pattern analysis (MVPA) can be an effective method in feature selection and evaluation, especially at individual level, which can help us find more reliable biomarkers of DD. In this paper, we employ MVPA to discriminate depressive disorder (DD) from healthy controls (HCs). Four basic feature selection algorithms were used in MVPA to compare the discriminative ability of five major features extracted from RS-fMRI to find better feature for finding reliable biomarkers. For improving the accuracy of classification of DD, a weighted voting classifier was applied to fuse classification results based on single feature. The experimental results demonstrate Regional Homogeneity (ReHo) showed best discriminative and generalization ability than other features and a significant improvement of classification accuracy that 90.22% of the subjects were correctly classified by leave-one-out cross-validation (LOOCV) via voting classifier compared to 81.52% the best accuracy of classification using single feature.