CVJul 4, 2024

Vision Mamba for Classification of Breast Ultrasound Images

arXiv:2407.03552v212 citationsh-index: 3Has Code
Originality Synthesis-oriented
AI Analysis

This work addresses breast cancer diagnosis from ultrasound images, offering incremental performance gains for medical imaging applications.

The paper compares Mamba-based vision models with CNNs and ViTs for breast ultrasound image classification, finding that Mamba models outperform others with improvements like 1.98% AUC and 5.0% accuracy on a dataset.

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}

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes