Al-Nefaie Abdullah H, Aldhyani Theyazn H H, Ahmad Sultan, Alzahrani Eidah M
King Salman Center for Disability Research, Riyadh, Saudi Arabia.
Department of Quantitative Methods, School of Business, King Faisal University, Hofuf, Saudi Arabia.
Front Med (Lausanne). 2025 May 21;12:1569464. doi: 10.3389/fmed.2025.1569464. eCollection 2025.
Symptoms of autism spectrum disorder (ASD) range from mild to severe and are evident in early childhood. Children with ASD have difficulties with social interaction, language development, and behavioral regulation. ASD is a mental condition characterized by challenges in communication, restricted behaviors, difficulties with speech, non-verbal interaction, and distinctive facial features in children. The early diagnosis of ASD depends on identifying anomalies in facial function, which may be minimal or missing in the first stages of the disorder. Due to the unique behavioral patterns shown by children with ASD, facial expression analysis has become an effective method for the early identification of ASD.
Hence, utilizing deep learning (DL) methodologies presents an excellent opportunity for improving diagnostic precision and efficacy. This study examines the effectiveness of DL algorithms in differentiating persons with ASD from those without, using a comprehensive dataset that includes images of children and ASD-related diagnostic categories. In this research, ResNet50, Inception-V3, and VGG-19 models were used to identify autism based on the facial traits of children. The assessment of these models used a dataset obtained from Kaggle, consisting of 2,940 face images.
The suggested Inception-V3 model surpassed current transfer learning algorithms, achieving a 98% accuracy rate.
Regarding performance assessment, the suggested technique demonstrated advantages over the latest models. Our methodology enables healthcare physicians to verify the first screening for ASDs in children.
自闭症谱系障碍（ASD）的症状从轻度到重度不等，在幼儿期就很明显。患有ASD的儿童在社交互动、语言发展和行为调节方面存在困难。ASD是一种精神疾病，其特征是儿童在沟通、行为受限、言语、非言语互动以及独特面部特征方面存在挑战。ASD的早期诊断取决于识别面部功能异常，而在该疾病的最初阶段，这些异常可能很轻微或不存在。由于患有ASD的儿童表现出独特的行为模式，面部表情分析已成为早期识别ASD的有效方法。
因此，利用深度学习（DL）方法为提高诊断精度和效率提供了绝佳机会。本研究使用一个包含儿童图像和与ASD相关诊断类别的综合数据集，检验DL算法在区分患有ASD的人和未患ASD的人方面的有效性。在本研究中，使用ResNet50、Inception-V3和VGG-19模型根据儿童的面部特征识别自闭症。这些模型的评估使用了从Kaggle获得的一个数据集，该数据集由2940张面部图像组成。
所建议的Inception-V3模型超越了当前的迁移学习算法，准确率达到了98%。
关于性能评估，所建议的技术比最新模型具有优势。我们的方法使医疗保健医生能够验证对儿童ASD的初次筛查。
