DeepASD: Facial Image Analysis for Autism Spectrum Diagnosis via Explainable Artificial Intelligence

Early and accurate diagnosis of Autism spectrum disorder (ASD) is crucial, but current diagnoses are subjective, time-consuming, and expensive. Recent studies used deep learning for facial images to diagnose ASD. However, the criteria are still unclear. To address these issues, we applied an explain...

Full description

Saved in:
Bibliographic Details
Published inInternational Conference on Ubiquitous and Future Networks (Online) pp. 625 - 630
Main Authors Kang, Hyebin, Yang, Minuk, Kim, Geun-Hyeon, Lee, Tae-Soo, Park, Seung
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.07.2023
Subjects
Artificial intelligence
Autism
Autism spectrum disorder
Convolutional neural network
Convolutional neural networks
Deep learning
Diagnosis
Explainable artificial intelligence
Gradient-weighted class activation mapping
Image analysis
Morphology
Neural networks
Online AccessGet full text
ISSN2165-8536
DOI10.1109/ICUFN57995.2023.10200203

Cover

More Information
Summary:Early and accurate diagnosis of Autism spectrum disorder (ASD) is crucial, but current diagnoses are subjective, time-consuming, and expensive. Recent studies used deep learning for facial images to diagnose ASD. However, the criteria are still unclear. To address these issues, we applied an explainable artificial intelligence technique to four convolutional neural networks (MobileNet, Xception, EfficientNet, and an ensemble model). We utilized gradient-weighted class activation mapping to suggest ASD diagnostic criteria based on facial morphology features. We achieved a high AUROC of 0.89 with the ensemble models. Our study provides objective and easy-to-understand diagnostic methods for early diagnosis of ASD.
ISSN:2165-8536
DOI:10.1109/ICUFN57995.2023.10200203