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

TL;DR

MM-UNet introduces a novel architecture with Morph Mamba Convolution and Reverse Selective State Guidance modules, significantly improving retinal vessel segmentation accuracy by addressing the unique challenges of vascular morphology.

Contribution

The paper presents MM-UNet, a new deep learning model specifically designed for retinal vessel segmentation, incorporating innovative convolution and guidance modules for enhanced performance.

Findings

Achieves higher F1-scores on DRIVE and STARE datasets.

Outperforms existing methods in segmentation accuracy.

Demonstrates robustness in detecting thin and branching vessels.

Abstract

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.