Recently resting-state functional magnetic resonance imaging (R-fMRI) has been applied as a powerful tool to explore potential biomarkers of autism spectrum disorder (ASD). However, in clinical data, the number of ASD patients is significantly less than that of typical development (TD) subjects, which causes the production of imbalanced data. When the imbalanced data are used to predict ASD, the prediction results are not satisfactory. To improve the ASD prediction performance of imbalanced data, this paper adopts the clustering oversampling method to enhance the representation for minority class (ASD), expecting to obtain the balanced data distribution. For the imbalanced data after feature selection, the clustering algorithm is used to form a few clusters in the ASD group and in the TD group, respectively, and then new samples for each cluster are generated by synthetic minority oversampling technique (SMOTE) to make the imbalanced data convert into the balanced data. Finally, we construct the linear support vector machine (SVM) classification model for ASD prediction. The prediction accuracy of multi-center imbalanced R-fMRI data increased from 59.70% to 66.62% using hierarchical clustering oversampling. The results of experiment show that the clustering oversampling method can effectively improve the prediction performance of imbalanced R-fMRI data.

Date Published: 17 April 2019
PDF: 5 pages
Proc. SPIE 11071, Tenth International Conference on Signal Processing Systems, 110710W (17 April 2019); doi: 10.1117/12.2521016

Published in SPIE Proceedings Vol. 11071:
Tenth International Conference on Signal Processing Systems
Kezhi Mao; Xudong Jiang, Editor(s)