Hyebin Kang, Minuk Yang, Geun-Hyeon Kim, Tae-Soo Lee, Seung Park
{"title":"DeepASD: Facial Image Analysis for Autism Spectrum Diagnosis via Explainable Artificial Intelligence","authors":"Hyebin Kang, Minuk Yang, Geun-Hyeon Kim, Tae-Soo Lee, Seung Park","doi":"10.1109/ICUFN57995.2023.10200203","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":341881,"journal":{"name":"2023 Fourteenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 Fourteenth International Conference on Ubiquitous and Future Networks (ICUFN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICUFN57995.2023.10200203","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
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.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
