Uncertainty Inspired Early Autism Spectrum Disorder Screening via Contrastive Image-Viewing Paradigm

Abstract

Eye-tracking technology is found effective in revealing the specific visual preference of Autism Spectrum Disorder (ASD) which can be characterized by high systemizing and low empathizing abilities. Early diagnosis is vital for ASD’s subsequent treatment. However, existing eye-tracking-based methods suffer from long diagnostic times and low diagnostic accuracy due to the lack of awareness of gaze preference derived from individual differences. Moreover, there is only one publicly available eye-tracking dataset that employs a simple image free-viewing paradigm to collect the gaze patterns of ASD and typically developed (TD) subjects with an average age of 8 years, thus can not effectively support the early diagnosis for preschool children. To tackle the difficulties, in this paper, we first propose an Uncertainty-inspired ASD Screening Network (UASN) that dynamically estimates the contribution of each stimulus viewed by different subjects, and secondly, we design a contrastive image-viewing paradigm and further collect eye movement data from preschool children to reveal the visual behaviors of ASD children accordingly. Specifically, in UASN, we estimate the uncertainty of each stimulus and use it for more efficient model training and a more simplified personalized diagnosis procedure. Besides, by synthesizing two images with the opposite semantic representations and recruiting ASD and TD subjects aged 2-6, we construct a new CI4ASD dataset, which offers a novel contrastive image-viewing paradigm for better diagnosis of ASD in children. Comprehensive experiments are conducted and results have evidenced the effectiveness of the proposed UASN and eye-tracking paradigm.

Keywords

• Autism spectrum disorder screening
• eye-tracking paradigm
• deep learning