Automated Detection of Autism in Children using Static Facial Features and Deep Learning Techniques

Abstract

Autism Spectrum Disorder (ASD) is a prevalent neurodevelopmental condition that significantly affects a child’s social and cognitive development. Despite growing awareness, early and accurate diagnosis remains a challenge due to the heavy reliance on time-intensive, observer-dependent behavioral assessments. In response, this paper introduces an automated, non-invasive screening framework that leverages static facial features and state-of-the-art deep learning techniques. The proposed system integrates a custom Convolutional Neural Network (CNN), ResNet-50, and VGG16 models within a modular architecture optimized using transfer learning. Experimental validation on the AFD-10K dataset—comprising 10,000 labeled facial images—demonstrates the framework’s high diagnostic performance, with ResNet-50 achieving an accuracy of 92.4%, F1-score of 91.7%, and AUC-ROC of 0.93. Grad-CAM visualizations confirm the model’s focus on clinically relevant facial asymmetries. The system’s design prioritizes reproducibility, scalability, and interpretability, incorporating audit-friendly logging, hyperparameter standardization, and cross-demographic validation. By significantly reducing diagnostic delays and minimizing subjective bias, this framework offers a practical foundation for AI-assisted ASD screening in real-world clinical settings.