arXiv 2511.021932025-11-10cs.CVcs.AI

MM-UNet：用于视网膜血管分割的Morph Mamba U型卷积网络

MM-UNet: Morph Mamba U-shaped Convolutional Networks for Retinal Vessel Segmentation

South China University of Technology（华南理工大学）；Jiangxi University of Finance and Economics（江西财经大学）；New York University（纽约大学）；Sichuan University（四川大学）

Jiawen Liu, Yuanbo Zeng, Jiaming Liang, Yizhen Yang, Yiheng Zhang, Enhui Cai, Xiaoqi Sheng, Hongmin Cai

备注：: This paper was accepted by IEEE BIBM 2025 conference

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出MM-UNet，通过Morph Mamba Convolution层和Reverse Selective State Guidance模块增强视网膜血管分支拓扑感知与几何边界意识，在DRIVE和STARE数据集上分别取得1.64%和1.25%的F1分数提升。

摘要：

视网膜血管的准确检测在眼科疾病临床诊断中对于反映广泛的健康状态指标起着关键作用。近年来，深度学习的进展推动了视网膜血管分割方法的激增，这些方法显著促进了血管形态的定量分析。然而，视网膜血管系统与常规分割目标存在显著差异，因为它由极其纤细且分支复杂的结构组成，其全局形态在不同图像之间差异很大。这些特性持续对分割精度和鲁棒性构成挑战。为了解决这些问题，我们提出了MM-UNet，这是一种专为高效视网膜血管分割而设计的新型架构。该模型融合了Morph Mamba Convolution层，通过形态化、状态感知的特征采样取代逐点卷积，以增强分支拓扑感知能力。此外，Reverse Selective State Guidance模块将反向引导理论与状态空间建模相结合，以提高几何边界感知能力和解码效率。在两个公开的视网膜血管分割数据集上进行的大量实验证明了所提方法在分割精度上的优越性能。与现有方法相比，MM-UNet在DRIVE上实现了1.64%的F1分数提升，在STARE上实现了1.25%的F1分数提升，证明了其有效性和先进性。项目代码已通过https://github.com/liujiawen-jpg/MM-UNet公开。

英文摘要：

Accurate detection of retinal vessels plays a critical role in reflecting a wide range of health status indicators in the clinical diagnosis of ocular diseases. Recently, advances in deep learning have led to a surge in retinal vessel segmentation methods, which have significantly contributed to the quantitative analysis of vascular morphology. However, retinal vasculature differs significantly from conventional segmentation targets in that it consists of extremely thin and branching structures, whose global morphology varies greatly across images. These characteristics continue to pose challenges to segmentation precision and robustness. To address these issues, we propose MM-UNet, a novel architecture tailored for efficient retinal vessel segmentation. The model incorporates Morph Mamba Convolution layers, which replace pointwise convolutions to enhance branching topological perception through morph, state-aware feature sampling. Additionally, Reverse Selective State Guidance modules integrate reverse guidance theory with state-space modeling to improve geometric boundary awareness and decoding efficiency. Extensive experiments conducted on two public retinal vessel segmentation datasets demonstrate the superior performance of the proposed method in segmentation accuracy. Compared to the existing approaches, MM-UNet achieves F1-score gains of 1.64 % on DRIVE and 1.25 % on STARE, demonstrating its effectiveness and advancement. The project code is public via https://github.com/liujiawen-jpg/MM-UNet.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。