Cross-Domain Transfer Learning for Domain Adaptation in Autism Spectrum Disorder Diagnosis

Kush Gupta, Amir Aly, Emmanuel Ifecahor

2025

Abstract

A cross-domain transfer learning approach is introduced to address the challenges of diagnosing individuals with Autism Spectrum Disorder (ASD) using small-scale fMRI datasets. Vision Transformer (ViT) and TinyViT models pre-trained on the ImageNet, were employed to transfer knowledge from the natural image domain to the brain imaging domain. The models were fine-tuned on ABIDE and CMI-HBN, using a teacher-student framework with knowledge distillation loss. Experimental results demonstrated that our method out-performed previous studies, ViT models, and CNN-based models. Our approach achieved competitive performance (F-1 score 78.72%) with a much smaller parameter size. This study highlights the effectiveness of cross-domain transfer learning in medical applications, particularly for scenarios with small datasets. It suggests that pre-trained models can be leveraged to improve diagnostic accuracy for neuro-developmental disorders such as ASD. The findings indicate that the features learned from natural images can be adapted to fMRI data using the proposed method, potentially providing a reliable and efficient approach to diagnosing autism.

Paper Citation

in Harvard Style

Gupta K., Aly A. and Ifecahor E. (2025). Cross-Domain Transfer Learning for Domain Adaptation in Autism Spectrum Disorder Diagnosis. In Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF; ISBN 978-989-758-731-3, SciTePress, pages 53-64. DOI: 10.5220/0013113000003911

in Bibtex Style

@conference{healthinf25,
author={Kush Gupta and Amir Aly and Emmanuel Ifecahor},
title={Cross-Domain Transfer Learning for Domain Adaptation in Autism Spectrum Disorder Diagnosis},
booktitle={Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF},
year={2025},
pages={53-64},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013113000003911},
isbn={978-989-758-731-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF
TI - Cross-Domain Transfer Learning for Domain Adaptation in Autism Spectrum Disorder Diagnosis
SN - 978-989-758-731-3
AU - Gupta K.
AU - Aly A.
AU - Ifecahor E.
PY - 2025
SP - 53
EP - 64
DO - 10.5220/0013113000003911
PB - SciTePress