POWER OF ALIGNMENT: EXPLORING THE EFFECT OF FACE ALIGNMENT ON ASD DIAGNOSIS USING FACIAL IMAGES

IF 0.6 Q3 ENGINEERING, MULTIDISCIPLINARY IIUM Engineering Journal Pub Date : 2024-01-01 DOI:10.31436/iiumej.v25i1.2838
Muhammad Mahbubur Rashid, Mohammad Shafiul Alam
{"title":"POWER OF ALIGNMENT: EXPLORING THE EFFECT OF FACE ALIGNMENT ON ASD DIAGNOSIS USING FACIAL IMAGES","authors":"Muhammad Mahbubur Rashid, Mohammad Shafiul Alam","doi":"10.31436/iiumej.v25i1.2838","DOIUrl":null,"url":null,"abstract":"Autism Spectrum Disorder (ASD) is a developmental disorder that impacts social communication and conduct. ASD lacks standard treatment protocols or medication, thus early identification and proper intervention are the most effective procedures to treat this disorder. Artificial intelligence could be a very effective tool to be used in ASD diagnosis as this is free from human bias. This research examines the effect of face alignment for the early diagnosis of Autism Spectrum Disorder (ASD) using facial images with the possibility that face alignment can improve the prediction accuracy of deep learning algorithms. This work uses the SOTA deep learning-based face alignment algorithm MTCNN to preprocess the raw data. In addition, the impacts of facial alignment on ASD diagnosis using facial images are investigated using state-of-the-art CNN backbones such as ResNet50, Xception, and MobileNet. ResNet50V2 achieves the maximum prediction accuracy of 93.97% and AUC of 96.33% with the alignment of training samples, which is a substantial improvement over previous research. This research paves the way for a data-centric approach that can be applied to medical datasets in order to improve the efficacy of deep neural network algorithms used to develop smart medical devices for the benefit of mankind. ABSTRAK: Gangguan Spektrum Autisme (ASD) adalah gangguan perkembangan yang memberi kesan kepada komunikasi dan tingkah laku sosial. Kelemahan dalam rawatan ASD adalah ianya tidak mempunyai protokol rawatan standard atau ubat. Oleh itu pengenalan awal dan campur tangan betul merupakan prosedur paling berkesan bagi merawat gangguan ini. Kecerdasan buatan boleh menjadi alat berkesan bagi diagnosis ASD kerana bebas campur tangan manusia. Penyelidikan ini mengkaji kesan penjajaran muka bagi diagnosis awal ASD menggunakan imej muka dengan kebarangkalian penjajaran muka dapat meningkatkan ketepatan ramalan algoritma pembelajaran mendalam. Kajian ini menggunakan algoritma penjajaran muka MTCNN berasaskan pembelajaran mendalam SOTA bagi pra-proses data mentah. Selain itu, kesan penjajaran muka pada diagnosis ASD menggunakan imej muka disiasat menggunakan CNN terkini seperti ResNet50, Xception dan MobileNet. ResNet50V2 mencapai ketepatan ramalan maksimum sebanyak 93.97% dan AUC 96.33% dengan  sampel penjajaran latihan, yang merupakan peningkatan ketara berbanding penyelidikan terdahulu. Kajian ini membuka jalan bagi pendekatan data berpusat yang boleh digunakan pada set data perubatan bagi meningkatkan keberkesanan algoritma rangkaian saraf mendalam dan membangunkan peranti perubatan pintar bermanfaat untuk manusia.","PeriodicalId":13439,"journal":{"name":"IIUM Engineering Journal","volume":"38 19","pages":""},"PeriodicalIF":0.6000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IIUM Engineering Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.31436/iiumej.v25i1.2838","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Autism Spectrum Disorder (ASD) is a developmental disorder that impacts social communication and conduct. ASD lacks standard treatment protocols or medication, thus early identification and proper intervention are the most effective procedures to treat this disorder. Artificial intelligence could be a very effective tool to be used in ASD diagnosis as this is free from human bias. This research examines the effect of face alignment for the early diagnosis of Autism Spectrum Disorder (ASD) using facial images with the possibility that face alignment can improve the prediction accuracy of deep learning algorithms. This work uses the SOTA deep learning-based face alignment algorithm MTCNN to preprocess the raw data. In addition, the impacts of facial alignment on ASD diagnosis using facial images are investigated using state-of-the-art CNN backbones such as ResNet50, Xception, and MobileNet. ResNet50V2 achieves the maximum prediction accuracy of 93.97% and AUC of 96.33% with the alignment of training samples, which is a substantial improvement over previous research. This research paves the way for a data-centric approach that can be applied to medical datasets in order to improve the efficacy of deep neural network algorithms used to develop smart medical devices for the benefit of mankind. ABSTRAK: Gangguan Spektrum Autisme (ASD) adalah gangguan perkembangan yang memberi kesan kepada komunikasi dan tingkah laku sosial. Kelemahan dalam rawatan ASD adalah ianya tidak mempunyai protokol rawatan standard atau ubat. Oleh itu pengenalan awal dan campur tangan betul merupakan prosedur paling berkesan bagi merawat gangguan ini. Kecerdasan buatan boleh menjadi alat berkesan bagi diagnosis ASD kerana bebas campur tangan manusia. Penyelidikan ini mengkaji kesan penjajaran muka bagi diagnosis awal ASD menggunakan imej muka dengan kebarangkalian penjajaran muka dapat meningkatkan ketepatan ramalan algoritma pembelajaran mendalam. Kajian ini menggunakan algoritma penjajaran muka MTCNN berasaskan pembelajaran mendalam SOTA bagi pra-proses data mentah. Selain itu, kesan penjajaran muka pada diagnosis ASD menggunakan imej muka disiasat menggunakan CNN terkini seperti ResNet50, Xception dan MobileNet. ResNet50V2 mencapai ketepatan ramalan maksimum sebanyak 93.97% dan AUC 96.33% dengan  sampel penjajaran latihan, yang merupakan peningkatan ketara berbanding penyelidikan terdahulu. Kajian ini membuka jalan bagi pendekatan data berpusat yang boleh digunakan pada set data perubatan bagi meningkatkan keberkesanan algoritma rangkaian saraf mendalam dan membangunkan peranti perubatan pintar bermanfaat untuk manusia.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
对齐的力量:利用面部图像探索面部配准对ASD诊断的影响
自闭症谱系障碍(ASD)是一种影响社交沟通和行为的发育障碍。自闭症缺乏标准的治疗方案或药物,因此早期识别和适当干预是治疗这种疾病最有效的方法。人工智能可以成为诊断 ASD 的有效工具,因为它不存在人为偏见。本研究利用面部图像研究了人脸对齐对早期诊断自闭症谱系障碍(ASD)的影响,人脸对齐有可能提高深度学习算法的预测准确性。这项工作使用基于 SOTA 深度学习的人脸配准算法 MTCNN 对原始数据进行预处理。此外,还使用 ResNet50、Xception 和 MobileNet 等最先进的 CNN 骨干研究了面部配准对使用面部图像进行 ASD 诊断的影响。在训练样本对齐的情况下,ResNet50V2 实现了 93.97% 的最高预测准确率和 96.33% 的 AUC,与之前的研究相比有了大幅提高。这项研究为以数据为中心的方法铺平了道路,这种方法可应用于医疗数据集,从而提高深度神经网络算法的功效,用于开发造福人类的智能医疗设备。摘要自闭症谱系障碍(ASD)是一种影响沟通和社交行为的发育障碍。治疗自闭症的缺点是没有标准化的治疗方案或药物。因此,早期识别和正确干预是治疗这种疾病最有效的方法。人工智能无需人工干预,可以成为诊断 ASD 的有效工具。本研究利用人脸图像研究了人脸对齐对早期诊断 ASD 的影响,认为人脸对齐可以提高深度学习算法的预测准确性。本研究使用 SOTA 基于深度学习的 MTCNN 人脸配准算法对原始数据进行预处理。此外,还使用 ResNet50、Xception 和 MobileNet 等最先进的 CNN 研究了人脸配准对使用人脸图像诊断 ASD 的影响。ResNet50V2 在训练对齐样本的情况下,预测准确率最高达到 93.97%,AUC 最高达到 96.33%,与之前的研究相比有了显著提高。这项研究为以数据为中心的方法铺平了道路,这些方法可用于医疗数据集,以提高深度神经网络算法的功效,并为人类开发有用的智能医疗设备。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
IIUM Engineering Journal
IIUM Engineering Journal ENGINEERING, MULTIDISCIPLINARY-
CiteScore
2.10
自引率
20.00%
发文量
57
审稿时长
40 weeks
期刊介绍: The IIUM Engineering Journal, published biannually (June and December), is a peer-reviewed open-access journal of the Faculty of Engineering, International Islamic University Malaysia (IIUM). The IIUM Engineering Journal publishes original research findings as regular papers, review papers (by invitation). The Journal provides a platform for Engineers, Researchers, Academicians, and Practitioners who are highly motivated in contributing to the Engineering disciplines, and Applied Sciences. It also welcomes contributions that address solutions to the specific challenges of the developing world, and address science and technology issues from an Islamic and multidisciplinary perspective. Subject areas suitable for publication are as follows: -Chemical and Biotechnology Engineering -Civil and Environmental Engineering -Computer Science and Information Technology -Electrical, Computer, and Communications Engineering -Engineering Mathematics and Applied Science -Materials and Manufacturing Engineering -Mechanical and Aerospace Engineering -Mechatronics and Automation Engineering
期刊最新文献
PHOTOVOLTAIC MODULE TEMPERATURE ESTIMATION MODEL FOR THE ONE-TIME-POINT DAILY ESTIMATION METHOD BIPHASIC CRUDE PALM OIL DECHLORINATION: EFFECT OF VOLUME RATIO AND CONCENTRATION OF SODIUM SILICATE TO HYDROXIDE ION DISTRIBUTION MIXING SEQUENCE EFFECT OF CEMENT COMPOSITES WITH CARBON FIBRES EFFECTS OF SOIL ERODIBILITY ON RIVERBANK EROSION AND FAILURES KEY SUCCESS FACTORS IN ROAD MAINTENANCE MANAGEMENT PROJECTS (A CASE STUDY OF MAYSAN PROVINCE, IRAQ)
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1