Minimalist CNN for Medical Imaging Classification with Small Dataset: Does Size Really Matter and How?

Marie Économidès, Marie Économidès, Pascal Desbarats

2024

Abstract

Deep learning has become a key method in computer vision, and has seen an increase in the size of both the networks used and the databases. However, its application in medical imaging faces limitations due to the size of datasets, especially for larger networks. This article aims to answer two questions: How can we design a simple model without compromising classification performance, making training more efficient? And, how much data is needed for our network to learn effectively? The results show that we can find a minimalist CNN adapted to a dataset that gives results comparable to larger architectures. The minimalist CNN does not have a fixed architecture. Its architecture varies according to the dataset and various criteria such as overall performance, training stability, and visual interpretation of network predictions. We hope this work can serve as inspiration for others concerned with these challenges.

Paper Citation

in Harvard Style

Économidès M. and Desbarats P. (2024). Minimalist CNN for Medical Imaging Classification with Small Dataset: Does Size Really Matter and How?. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 755-762. DOI: 10.5220/0012452700003660

in Bibtex Style

@conference{visapp24,
author={Marie Économidès and Pascal Desbarats},
title={Minimalist CNN for Medical Imaging Classification with Small Dataset: Does Size Really Matter and How?},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={755-762},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012452700003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Minimalist CNN for Medical Imaging Classification with Small Dataset: Does Size Really Matter and How?
SN - 978-989-758-679-8
AU - Économidès M.
AU - Desbarats P.
PY - 2024
SP - 755
EP - 762
DO - 10.5220/0012452700003660
PB - SciTePress