Domain Adaptation Using a Three-Way Decision Improves the Identification of Autism Patients from Multisite fMRI Data

Abstract

Machine learning methods are widely used in autism spectrum disorder (ASD) diagnosis. Due to the lack of labelled ASD data, multisite data are often pooled together to expand the sample size. However, the heterogeneity that exists among different sites leads to the degeneration of machine learning models. Herein, the three-way decision theory was introduced into unsupervised domain adaptation in the first time, and applied to optimize the pseudolabel of the target domain/site from functional magnetic resonance imaging (fMRI) features related to ASD patients. The experimental results using multisite fMRI data show that our method not only narrows the gap of the sample distribution among domains but is also superior to the state-of-the-art domain adaptation methods in ASD recognition. Specifically, the ASD recognition accuracy of the proposed method is improved on all the six tasks, by 70.80%, 75.41%, 69.91%, 72.13%, 71.01% and 68.85%, respectively, compared with the existing methods.

Keywords: autism spectrum disorder; domain adaptation; machine learning; three-way decision.

Figure 1

Classification accuracy versus the number of iterations on six domain pairs.

Figure 2

Classification accuracies with respect to different parameter values of $\alpha$ and $\beta$ on six domain pairs (a) NYU→UM; (b) NYU→USM; (c) USM→UM; (d) USM→NYU; (e) UM→NYU; (f) UM→USM.

Figure 2

Classification accuracies with respect to different parameter values of $\alpha$ and $\beta$ on six domain pairs (a) NYU→UM; (b) NYU→USM; (c) USM→UM; (d) USM→NYU; (e) UM→NYU; (f) UM→USM.

Figure 2

Classification accuracies with respect to different parameter values of $\alpha$ and $\beta$ on six domain pairs (a) NYU→UM; (b) NYU→USM; (c) USM→UM; (d) USM→NYU; (e) UM→NYU; (f) UM→USM.