Related Experiment Video
Updated: Aug 20, 2025
Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
Published on: December 8, 2023
RETRACTED: Empirical Study of Autism Spectrum Disorder Diagnosis Using Facial Images by Improved Transfer Learning
Md Shafiul Alam1, Muhammad Mahbubur Rashid1, Rupal Roy1
1Department of Mechatronics Engineering, International Islamic University Malaysia, Kula Lumpur 43200, Malaysia.
Insights
This study introduces a novel method using deep convolutional neural networks (CNNs) to detect autism spectrum disorder (ASD) in children via facial images. A modified Xception model achieved 95% accuracy, offering a promising tool for early ASD screening.
Area of Science:
- Neurology
- Computer Science
- Biomedical Engineering
Background:
- Autism spectrum disorder (ASD) presents significant challenges in diagnosis due to the absence of specific medical tests.
- Early intervention is crucial for improving brain functionality in children with ASD.
- Facial features can serve as potential biomarkers reflecting neurological development, aiding in early detection.
Purpose of the Study:
- To investigate the efficacy of deep convolutional neural network (CNN)-based transfer learning approaches for detecting ASD in children using facial images.
- To optimize CNN models by selecting the best hyperparameters and optimizers for enhanced diagnostic accuracy.
- To develop a computational tool to assist clinicians in the early screening and validation of ASD diagnoses.
Main Methods:
- Utilized several deep convolutional neural network (CNN) architectures, including Xception, VGG19, ResNet50V2, MobileNetV2, and EfficientNetB0, for facial image analysis.
- Employed transfer learning techniques to adapt pre-trained models for the specific task of ASD detection.
- Conducted an empirical study to fine-tune optimizers and hyperparameters for optimal model performance.
Main Results:
- The modified Xception model achieved the highest accuracy of 95% in detecting ASD from facial images.
- Other evaluated models showed strong performance: ResNet50V2 (94%), MobileNetV2 (92%), VGG19 (86.5%), and EfficientNetB0 (85.8%).
- The developed transfer learning approaches demonstrated superior performance compared to existing methods.
Conclusions:
- Deep learning models, particularly the modified Xception network, show significant potential for accurate and early detection of ASD using facial biomarkers.
- This AI-driven approach can serve as a valuable supplementary tool for healthcare professionals in validating initial ASD screenings.
- Facial image analysis via CNNs offers a non-invasive and accessible method for improving early diagnosis and intervention for autism spectrum disorder.
Abstract:
Autism spectrum disorder (ASD) is a neurological illness characterized by deficits in cognition, physical activities, and social skills. There is no specific medication to treat this illness; only early intervention can improve brain functionality. Since there is no medical test to identify ASD, a diagnosis might be challenging. In order to determine a diagnosis, doctors consider the child's behavior and developmental history. The human face can be used as a biomarker as it is one of the potential reflections of the brain and thus can be used as a simple and handy tool for early diagnosis. This study uses several deep convolutional neural network (CNN)-based transfer learning approaches to detect autistic children using the facial image. An empirical study is conducted to select the best optimizer and set of hyperparameters to achieve better prediction accuracy using the CNN model. After training and validating with the optimized setting, the modified Xception model demonstrates the best performance by achieving an accuracy of 95% on the test set, whereas the VGG19, ResNet50V2, MobileNetV2, and EfficientNetB0 achieved 86.5%, 94%, 92%, and 85.8%, accuracy, respectively. Our preliminary computational results demonstrate that our transfer learning approaches outperformed existing methods. Our modified model can be employed to assist doctors and practitioners in validating their initial screening to detect children with ASD disease.
