Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

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

TL;DR

Retinal vessel segmentation is challenged by extremely thin, branching vasculature. The authors introduce MM-UNet, a U-shaped network that replaces standard pointwise convolutions with Morph Mamba Convolution layers and integrates Reverse Selective State Guidance to improve topological perception and boundary delineation. On DRIVE and STARE, MM-UNet achieves state-of-the-art F1-scores and boundary accuracy, with ablations confirming the essential roles of MMC and RSSG. The approach offers a practical, scalable solution with public code and potential clinical impact in automated vascular analysis.

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.

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

TL;DR

Retinal vessel segmentation is challenged by extremely thin, branching vasculature. The authors introduce MM-UNet, a U-shaped network that replaces standard pointwise convolutions with Morph Mamba Convolution layers and integrates Reverse Selective State Guidance to improve topological perception and boundary delineation. On DRIVE and STARE, MM-UNet achieves state-of-the-art F1-scores and boundary accuracy, with ablations confirming the essential roles of MMC and RSSG. The approach offers a practical, scalable solution with public code and potential clinical impact in automated vascular analysis.

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.

Paper Structure

This paper contains 16 sections, 3 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Relate Works
  3. Methodology
  4. U-shaped Framework Overview
  5. Morph Mamba Convolution Layers
  6. Reverse Selective State Guidance
  7. Experiments
  8. Datasets
  9. Implementation Details
  10. Performance
  11. Ablation Study
  12. Visual Comparisons
  13. Performance
  14. Error Map
  15. Conclusion
  16. ...and 1 more sections

Figures (4)

  • Figure 1: (a) Limitations: regular convolutional layers fail to accurately capture intricate vessel topology; (b) Improvements: MMC layers integrate a dynamic morph convolution mechanism with morph state-space modeling to effectively construct accurate topological representations.
  • Figure 2: Overview of MM-UNet.
  • Figure 3: Visual comparisons of proposed MM-UNet and other SOTA methods.
  • Figure 4: Error map of proposed MM-UNet and other SOTA methods.