Serp-Mamba: Advancing High-Resolution Retinal Vessel Segmentation with Selective State-Space Model
You can access the paper here.
Requirements: Ubuntu 20.04, CUDA 12.2
1. Create a virtual environment: conda create -n Serp-mamba python=3.10 -y and conda activate Serp-mamba, cd SerpMamba
2. Pytorch : pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cu121
3. Install mamba_ssm and causal-conv1d: download causal_conv1d-1.1.3.post1+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
and mamba_ssm-1.1.1+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl. Then insert pip install causal_conv1d-1.1.3.post1+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86 _64.whl and pip install mamba_ssm-1.1.1+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
4. pip install -r requirements.txt
python train.py
python test.py
Multi-center UWF-SLO Vessel Segmentation (MU-VS) dataset
For PRIME-FP20: please refer to this IEEE article and dataset link.
For Center A and Center B: please contact Hongqiu (hongqiuwang16@gmail.com) for the dataset. One step is needed to download the dataset: **1) Use your google email to apply for the download permission (OneDrive, BaiduPan-A, BaiduPan-B). We just handle the real-name email and your email suffix must match your affiliation. The email should contain the following information:
Name/Homepage/Google Scholar: (Tell us who you are.)
Primary Affiliation: (The name of your institution or university, etc.)
Job Title: (E.g., Professor, Associate Professor, Ph.D., etc.)
Affiliation Email: (the password will be sent to this email, we just reply to the email which is the end of "edu".)
How to use: (Only for academic research, not for commercial use or second-development.)
The data provided cannot be forwarded to others, and only individuals with approved applications are authorized to use them.
Thanks for understanding and cooperation!
If you find our work useful or relevant to your research, please consider citing:
@article{wang2025serp,
title={Serp-mamba: Advancing high-resolution retinal vessel segmentation with selective state-space model},
author={Wang, Hongqiu and Chen, Yixian and Chen, Wu and Xu, Huihui and Zhao, Haoyu and Sheng, Bin and Fu, Huazhu and Yang, Guang and Zhu, Lei},
journal={IEEE Transactions on Medical Imaging},
year={2025},
publisher={IEEE}
}
We thank the authors of nnU-Net, Mamba, U-mamba, and DSCNet for open-sourcing their valuable code.