Magnification Invariant Medical Image Analysis: A Comparison of Convolutional Networks, Vision Transformers, and Token Mixers

Pranav Jeevan, Nikhil Kurian, Amit Sethi

2024

Abstract

Convolution neural networks (CNNs) are widely used in medical image analysis, but their performance degrades when the magnification of testing images differs from that of training images. The inability of CNNs to generalize across magnification scales can result in sub-optimal performance on external datasets. This study aims to evaluate the robustness of various deep learning architectures for breast cancer histopathological image classification when the magnification scales are varied between training and testing stages. We compare the performance of multiple deep learning architectures, including CNN-based ResNet and MobileNet, self-attention-based Vision Transformers and Swin Transformers, and token-mixing models, such as FNet, ConvMixer, MLP-Mixer, and WaveMix. The experiments are conducted using the BreakHis dataset, which contains breast cancer histopathological images at varying magnification levels. We show that the performance of WaveMix is invariant to the magnification of training and testing data and can provide stable and good classification accuracy. These evaluations are critical in identifying deep learning architectures that can robustly handle domain changes, such as magnification scale.

Paper Citation

in Harvard Style

Jeevan P., Kurian N. and Sethi A. (2024). Magnification Invariant Medical Image Analysis: A Comparison of Convolutional Networks, Vision Transformers, and Token Mixers. In Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING; ISBN 978-989-758-688-0, SciTePress, pages 216-222. DOI: 10.5220/0012362900003657

in Bibtex Style

@conference{bioimaging24,
author={Pranav Jeevan and Nikhil Kurian and Amit Sethi},
title={Magnification Invariant Medical Image Analysis: A Comparison of Convolutional Networks, Vision Transformers, and Token Mixers},
booktitle={Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING},
year={2024},
pages={216-222},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012362900003657},
isbn={978-989-758-688-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING
TI - Magnification Invariant Medical Image Analysis: A Comparison of Convolutional Networks, Vision Transformers, and Token Mixers
SN - 978-989-758-688-0
AU - Jeevan P.
AU - Kurian N.
AU - Sethi A.
PY - 2024
SP - 216
EP - 222
DO - 10.5220/0012362900003657
PB - SciTePress