An Uncertainty-Aware Generalization Framework for Cardiovascular Image Segmentation

TL;DR

This paper presents UU-Mamba, a novel uncertainty-aware framework that improves cardiovascular image segmentation by enhancing generalization and robustness using Sharpness-Aware Minimization and a comprehensive uncertainty-aware loss.

Contribution

The paper introduces UU-Mamba, extending U-Mamba with SAM and a new uncertainty-aware loss for better generalization and accuracy in complex cardiovascular segmentation tasks.

Findings

UU-Mamba outperforms existing models like TransUNet and nnUNet.

The model demonstrates strong robustness on complex datasets.

Incorporating SAM and uncertainty-aware loss improves segmentation quality.

Abstract

Deep learning models have achieved significant success in segmenting cardiovascular structures, but there is a growing need to improve their generalization and robustness. Current methods often face challenges such as overfitting and limited accuracy, largely due to their reliance on large annotated datasets and limited optimization techniques. This paper introduces the UU-Mamba model, an extension of the U-Mamba architecture, designed to address these challenges in both cardiac and vascular segmentation. By incorporating Sharpness-Aware Minimization (SAM), the model enhances generalization by seeking flatter minima in the loss landscape. Additionally, we propose an uncertainty-aware loss function that integrates region-based, distribution-based, and pixel-based components, improving segmentation accuracy by capturing both local and global features. We expand our evaluations on the ImageCAS (coronary artery) and Aorta (aortic branches and zones) datasets, which present more complex segmentation challenges than the ACDC dataset (left and right ventricles) used in prior work, showcasing the model's adaptability and resilience. Our results confirm UU-Mamba's superior performance compared to leading models such as TransUNet, Swin-Unet, nnUNet, and nnFormer. We also provide a more in-depth assessment of the model's robustness and segmentation accuracy through extensive experiments.