Medi-CAT: Contrastive Adversarial Training for Medical Image Classification

Pervaiz Khan, Pervaiz Khan, Andreas Dengel, Andreas Dengel, Sheraz Ahmed

2024

Abstract

There are not many large medical image datasets available. Too small deep learning models can’t learn useful features, so they don’t work well due to underfitting, and too big models tend to overfit the limited data. As a result, there is a compromise between the two issues. This paper proposes a training strategy to overcome the aforementioned issues in medical imaging domain. Specifically, it employs a large pre-trained vision transformers to overcome underfitting and adversarial and contrastive learning techniques to prevent overfitting. The presented method has been trained and evaluated on four medical image classification datasets from the MedMNIST collection. Experimental results indicate the effectiveness of the method by improving the accuracy up-to 2% on three benchmark datasets compared to well-known approaches and up-to 4.1% over the baseline methods. Code can be accessed at: https://github.com/pervaizniazi/medicat.

Paper Citation

in Harvard Style

Khan P., Dengel A. and Ahmed S. (2024). Medi-CAT: Contrastive Adversarial Training for Medical Image Classification. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 832-839. DOI: 10.5220/0012396500003636

in Bibtex Style

@conference{icaart24,
author={Pervaiz Khan and Andreas Dengel and Sheraz Ahmed},
title={Medi-CAT: Contrastive Adversarial Training for Medical Image Classification},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={832-839},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012396500003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Medi-CAT: Contrastive Adversarial Training for Medical Image Classification
SN - 978-989-758-680-4
AU - Khan P.
AU - Dengel A.
AU - Ahmed S.
PY - 2024
SP - 832
EP - 839
DO - 10.5220/0012396500003636
PB - SciTePress