A Comparative Study of Deep Neural Network Architectures in Magnification Invariant Breast Cancer Histopathology Image Analysis
Published in Biomedical Engineering Systems and Technologies, 17th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2024) Selected Papers, Springer, 2025
Convolution Neural Networks (CNNs) are widely used in medical image analysis, but their performance degrades when the magnification of testing images differs from the training images. The inability of CNNs to generalize across magnification scales can result in sub-optimal performance on external datasets. This study evaluates the robustness of various deep learning architectures in the analysis of breast cancer histopathological images with varying magnification scales at training and testing stages. We explore and 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. This extended chapter provides a deeper comparison of these architectures, critical for identifying deep learning models that robustly handle changes in magnification scale.
Recommended citation: Jeevan, P., Kurian, N., Sethi, A. (2025). A Comparative Study of Deep Neural Network Architectures in Magnification Invariant Breast Cancer Histopathology Image Analysis. In: Biomedical Engineering Systems and Technologies — BIOSTEC 2024 Selected Papers. Springer, Cham. https://doi.org/10.1007/978-3-031-96899-0_8