Vision Mamba for Classification of Breast Ultrasound Images

TL;DR

This paper evaluates Mamba-based vision models for breast ultrasound image classification, showing they often outperform CNNs and ViTs with statistically significant improvements, especially in limited data scenarios.

Contribution

It introduces a comprehensive comparison of Mamba-based models with traditional CNNs and ViTs on breast ultrasound datasets, highlighting their superior performance and suitability for limited data.

Findings

Mamba models outperform CNNs and ViTs in accuracy and AUC.

Statistically significant performance improvements are observed.

Mamba models effectively capture long-range dependencies.

Abstract

Mamba-based models, VMamba and Vim, are a recent family of vision encoders that offer promising performance improvements in many computer vision tasks. This paper compares Mamba-based models with traditional Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) using the breast ultrasound BUSI dataset and Breast Ultrasound B dataset. Our evaluation, which includes multiple runs of experiments and statistical significance analysis, demonstrates that some of the Mamba-based architectures often outperform CNN and ViT models with statistically significant results. For example, in the B dataset, the best Mamba-based models have a 1.98\% average AUC and a 5.0\% average Accuracy improvement compared to the best non-Mamba-based model in this study. These Mamba-based models effectively capture long-range dependencies while maintaining some inductive biases, making them suitable for applications with limited data. The code is available at \url{https://github.com/anasiri/BU-Mamba}