Authors : Anurag Agarwal; Vikas Arora; Deepak Kumar; Mohd Farman Sajid

Volume/Issue : Volume 10 - 2025, Issue 11 - November

Google Scholar : https://tinyurl.com/yy5vbx47

Scribd : https://tinyurl.com/bdhsrkec

DOI : https://doi.org/10.38124/ijisrt/25nov726

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Autism Spectrum Disorder (ASD) is a neurodevelopment disorder that is complicated and associated with social, behavioral, and communication issues. It should also be diagnosed early enough so that the appropriate treatment is administered in time and better results are realized. The recent tendencies in the field of deep learning (DL) allowed to implement neuroimaging, in the present case, the magnetic resonance imaging (MRI) to ASD diagnosis, which can be automated, to the given field. The publicly available ABIDE MRI data were used in this research and assisted in comparing some of the latest DL models, such as a blank Convolutional Neural Network (CNN), ResNet50, EfficientNet, and Vision Transformer (ViT). Data normalization, skull stripping, and data augmentation were used as preprocessing. The models were trained using Adam optimizer and categorical cross-entropy loss and assessed according to accuracy, precision, recall, F1-score and AUC-ROC. The best and highest performance one was the Vision Transformer (ViT) that achieved the highest accuracy of 97.1% and 0.99 AUC- ROC, which shows the superiority in the ASD detection in the ABIDE MRI data. These results favor the fact that the transformer-based models are powerful diagnostic tools of ASD detection.

Keywords : Autism Spectrum Disorder (ASD), Deep Learning, Autism Brain Imaging Data Exchange (ABIDE), Convolutional Neural Networks (CNN), Vision Transformer (ViT), Neuroimaging.

References :

1. N. H. Deshmukh and H. Gadade, “autism spectrum disorder: A Global Review of Analysis, Intervention and Support Approaches,” in Proc. Int. Conf. on Machine Learning and Autonomous Systems (ICMLAS), Pune, India, 2025, pp. 806–810. doi: 10.1109/ICMLAS64557.2025.10968790.
2. Singh, A., et al. "Applying Machine Learning for Autism Risk Evaluation Using a Decision Tree Classification Technique." Proceedings of the International Conference on Artificial Intelligence, 2024.
3. Gupta, R., et al. "Applying Machine Learning and the Gradient Boosting Classification Method for Evaluating the Probability of Autism." Journal of Machine Learning Research, vol. 25, no. 3, 2024, pp. 123-134.
4. Mittal, K., Gill, K., Aggarwal, P., and Rawat, R. S. "Leveraging Machine Learning with AdaBoost Classification to Assess Autism Spectrum Disorder (ASD) Probability." Proceedings of the Asia Pacific Conference on Innovation in Technology, IEEE, 2024.
5. Arunprasath, T., Niranjana, M., and Pandian, B. "Prediction of Autism Spectrum Disorder Using Machine Learning." Proceedings of the Third International Conference on Intelligent Techniques in Control, Optimization, and Signal Processing, IEEE, 2024.
6. Alam, M. B., et al. "An Autism Detection Architecture with Fusion of Feature Extraction and Classification." 2023 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD), IEEE, 2023.
7. Mishra, M., and Pati, U. C. "A Classification Framework for Autism Spectrum Disorder Detection Using sMRI: Optimizer-Based Ensemble of Deep Convolution Neural Networks." Biomedical Signal Processing and Control, vol. 84, 2023, pp. 104686.
8. Khan, L., et al. "Autism and Pregnancy, Is It Preventable?" Journal of Clinical Trials Case Studies, 2019, pp. 145-153.
9. [9] Washington, P., and Wall, D. P. "A Review of and Roadmap for Data Science and Machine Learning for the Neuropsychiatric Phenotype of Autism." Annual Review of Biomedical Data Science, vol. 6, 2023, pp. 15-32.
10. Druitt, F., et al. "Do Autism Spectrum Disorders (ASD) Increase the Risk of Terrorism Engagement?" Journal of Policing, Intelligence, and Counterterrorism, vol. 18, no. 3, 2023, pp. 307–332.
11. Anderson, A. H., et al. "A Systematic Literature Review of the Experiences and Supports of Students with Autism Spectrum Disorder in Post-secondary Education." Journal of Educational Studies, 2017.
12. Sauer, A. K., et al. "autism spectrum disorder in High-Risk Populations." Journal of Brain Nervous, vol. 45, no. 6, 2023, pp. 123-135.
13. Baron-Cohen, S., et al. "Early Behavioral Indicators of Autism." Journal of Child Psychology and Psychiatry, vol. 62, no. 2, 2021, pp. 205-215.
14. Hampton, S., et al. "Autistic People’s Perinatal Experiences: A Survey of Pregnancy Experiences." Journal of Autism and Developmental Disorders, vol. 53, no. 7, 2022, pp. 243-255.
15. Zhang, Y., et al. "A Feature-Based Machine Learning Model for Autism Detection in Preschoolers." Neural Networks and Applications, vol. 58, 2022, pp. 45-58.
16. Sharma, B., and Koundal, D. "A Survey on Machine Learning Applications in ASD Detection." Journal of Healthcare Informatics, vol. 12, no. 4, 2019, pp. 98-110.
17. Wu, L., et al. "Classification of Coherence Indices Extracted from EEG Signals of Mild and Severe Autism." International Journal of Advanced Computer Science and Applications, vol. 14, no. 9, 2023, pp. 24-38.
18. Li, Z., et al. "Investigating the Impact of Demographic Features on Autism Screening Outcomes." Journal of Public Health Informatics, vol. 35, no. 1, 2023, pp. 110-125.
19. Alam, S., et al. "Role of Machine Learning in Early Detection of ASD Using Behavioral Data." IEEE Transactions on Neural Networks, vol. 34, no. 2, 2023, pp. 212-228.
20. Gill, K. S., et al. "Improving Autism Detection via Advanced Neural Architectures." Proceedings of the Asian Conference on Machine Learning, IEEE, 2023.
21. Mishra, S., and Sharma, P. "Feature Selection Techniques for ASD Prediction: A Comparative Study." Journal of Machine Learning in Healthcare, vol. 23, no. 4, 2023, pp. 98-112.
22. Li, J., et al. "Deep Learning for Autism Spectrum Disorder Diagnosis: Challenges and Opportunities." Annual Review of AI Applications in Healthcare, vol. 15, 2022, pp. 65-88.
23. Zhu, X., et al. "Improving Autism Risk Assessment with Multi-Modal Data Fusion." Journal of Computational Intelligence, vol. 45, no. 5, 2022, pp. 77-95.
24. Alam, F., et al. "A Comparative Analysis of Machine Learning Techniques for Autism Risk Prediction." International Journal of Medical Informatics, vol. 12, no. 3, 2023, pp. 140-153.
25. Gill, P., et al. "EEG-Based Detection of Autism Using Logistic Regression Models." Proceedings of the IEEE Conference on Neural Engineering, 2023.