AI-Driven Diagnosis of Autism Spectrum Disorder Using Retinal Fundus Imaging: A Comparison of Traditional and Deep Learning Feature Extraction Methods
DOI:
https://doi.org/10.47852/bonviewJCCE52026045Keywords:
ASD detection, deep learning approaches, retinal fundus images, traditional feature extraction, classification modelsAbstract
Autism spectrum disorder (ASD) is a complicated neurodevelopmental disorder. There is no definitive or easily interpretable medical test that aids in the early diagnosis of ASD, which leads to delays in its detection. In this study, we compared deep learning and traditional feature extraction methods used to detect ASD using retinal fundus images. The authors implemented convolutional neural networks (CNNs) such as ResNet50, EfficientNet, and vision transformers (ViTs), apart from the hybrid CNN + ViT model, for automated feature extraction. In addition, classic methods such as the gray level co-occurrence matrix for texture analysis, Frangi filters for measuring vessel density, and cup-to-disc ratio estimation were used to extract clinically relevant retinal features. To evaluate the discriminative power of the features obtained by each technique, classification models such as support vector machines, random forest, and XGBoost were implemented. Among the models used, hybrid CNN + ViT obtained the highest accuracy, which suggests that combining spatial and contextual retinal information enhances the detection of ASD. This study examined various feature extraction approaches in detail and elucidated the advantages of deep-learning-based approaches to enhance ASD diagnosis using retinal images. The results contribute to ongoing research on AI-supported ASD detection and provide crucial insights into the selection of optimal feature representation methods for future clinical applications.
Received: 29 April 2025 | Revised: 14 July 2025 | Accepted: 18 July 2025
Conflicts of Interest
The authors declare that they have no conflicts of interest to this work.
Data Availability Statement
Data are available on request from the corresponding author upon reasonable request.
Author Contribution Statement
Ayain John: Conceptualization, Methodology, Software, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Project administration. Santhanalakshmi S.: Validation, Formal analysis, Resources, Writing – review & editing, Supervision, Project administration.
Metrics
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Authors

This work is licensed under a Creative Commons Attribution 4.0 International License.