Vision-based Approach for Autism Diagnosis using Transfer Learning and Eye-tracking

Mahmoud Elbattah, Mahmoud Elbattah, Jean-Luc Guérin, Romuald Carette, Federica Cilia, Gilles Dequen

2022

Abstract

The potentials of Transfer Learning (TL) have been well-researched in areas such as Computer Vision and Natural Language Processing. This study aims to explore a novel application of TL to detect Autism Spectrum Disorder. We seek to develop an approach that combines TL and eye-tracking, which is commonly used for analyzing autistic features. The key idea is to transform eye-tracking scanpaths into a visual representation, which could facilitate using pretrained vision models. Our experiments implemented a set of widely used models including VGG-16, ResNet, and DenseNet. Our results showed that the TL approach could realize a promising accuracy of classification (ROC-AUC up to 0.78). The proposed approach is not claimed to provide superior performance compared to earlier work. However, the study is primarily thought to convey an interesting aspect regarding the use of (synthetic) visual representations of eye-tracking output as a means to transfer representations from models pretrained on large-scale datasets such as ImageNet.

Paper Citation

in Harvard Style

Elbattah M., Guérin J., Carette R., Cilia F. and Dequen G. (2022). Vision-based Approach for Autism Diagnosis using Transfer Learning and Eye-tracking. In Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 5: HEALTHINF; ISBN 978-989-758-552-4, SciTePress, pages 256-263. DOI: 10.5220/0010975500003123

in Bibtex Style

@conference{healthinf22,
author={Mahmoud Elbattah and Jean-Luc Guérin and Romuald Carette and Federica Cilia and Gilles Dequen},
title={Vision-based Approach for Autism Diagnosis using Transfer Learning and Eye-tracking},
booktitle={Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 5: HEALTHINF},
year={2022},
pages={256-263},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010975500003123},
isbn={978-989-758-552-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 5: HEALTHINF
TI - Vision-based Approach for Autism Diagnosis using Transfer Learning and Eye-tracking
SN - 978-989-758-552-4
AU - Elbattah M.
AU - Guérin J.
AU - Carette R.
AU - Cilia F.
AU - Dequen G.
PY - 2022
SP - 256
EP - 263
DO - 10.5220/0010975500003123
PB - SciTePress