3D Temporal Analysis for Autism Spectrum Disorder Screening During Attention Tasks

2026-06-03

AI Summary

This study addresses the limitations of current autism spectrum disorder (ASD) screening approaches, which predominantly rely on subjective assessments and two-dimensional behavioral analyses that fail to effectively capture the distinctive three-dimensional spatial movement patterns of children. To overcome this, the work proposes a novel multimodal framework for automated ASD screening in school-aged children by integrating DECA-based 3D head pose and facial expression temporal modeling, incorporating pose-invariant features. The framework employs PCA for dimensionality reduction and leverages LSTM or GRU architectures for temporal classification. Experimental results demonstrate that the GRU model achieves 83.9% accuracy using head pose alone and 81.4% with facial expressions alone; fusing both modalities further improves performance to 84.6%, significantly outperforming conventional 2D methods by 7.5%–10.7%.

Abstract

Accurate Autism Spectrum Disorder (ASD) screening for school-age children is crucial to identify cases that may have been missed earlier and to enable timely interventions supporting social, cognitive, and academic development. Current ASD screening relies on subjective assessments and 2D analysis methods that fail to capture spatial displacement patterns characteristic of ASD behaviors. In this study, a novel 3D temporal analysis framework is presented, built on top of DECA (Detailed Expression Capture and Animation), a 3D modeling framework, to extract comprehensive head pose parameters (including translational components $T_x, T_y, T_z$) and facial expressions independent of pose variations. LSTM and GRU-based temporal classifiers were trained on the extracted 3D features from video data collected from 39 participants (19 ASD, 20 TD) aged 7-12 years during Virtual Reality-Continuous Performance Test tasks. The GRU-based models demonstrated superior performance, with 3D head pose features achieving 83.9\% accuracy and 3D facial features reaching 81.4\% accuracy, outperforming 2D baseline approaches by 10.7\% and 7.5\%, respectively. Furthermore, multimodal fusion of 3D head pose and facial features with PCA-based dimensionality reduction achieved the highest accuracy of 84.6\%, outperforming unimodal approaches. This work establishes a foundation for objective, automated screening tools addressing current diagnostic limitations in ASD identification for school-age populations.

Problem

• Autism Spectrum Disorder
• 3D temporal analysis
• head pose
• facial expressions
• screening

Innovation

• 3D temporal analysis
• DECA
• head pose estimation
• multimodal fusion
• autism screening