OCTAMamba: A State-Space Model Approach for Precision OCTA Vasculature Segmentation

Shun Zou ^*, Zhuo Zhang ^*, Guangwei Gao ^†

^*Equal Contribution, ^†Corresponding authors

arXiv

PDF

Code

Abstract

Optical Coherence Tomography Angiography (OCTA) is a crucial imaging technique for visualizing retinal vasculature and diagnosing eye diseases such as diabetic retinopathy and glaucoma. However, precise segmentation of OCTA vasculature remains challenging due to the multi-scale vessel structures and noise from poor image quality and eye lesions. In this study, we proposed OCTAMamba, a novel U-shaped network based on the Mamba architecture, designed to segment vasculature in OCTA accurately. OCTAMamba integrates a Quad Stream Efficient Mining Embedding Module for local feature extraction, a Multi-Scale Dilated Asymmetric Convolution Module to capture multi-scale vasculature, and a Focused Feature Recalibration Module to filter noise and highlight target areas. Our method achieves efficient global modeling and local feature extraction while maintaining linear complexity, making it suitable for low-computation medical applications. Extensive experiments on the OCTA 3M, OCTA 6M, and ROSSA datasets demonstrated that OCTAMamba outperforms state-of-the-art methods, providing a new reference for efficient OCTA segmentation. Code is available at https://github.com/zs1314/OCTAMamba.

Pipeline of OCTAMamba

Quantitative results

Performance comparison of different methods on three public datasets. The best results are highlighted in bold fonts. “ ↑ ”and “ ↓ ” indicate that larger or smaller is better.

Qualitative visualization

Qualitative visualization of different methods. Best viewed by zooming in the figures on high-resolution displays.

Ablation Study

To explore the impact of each component on model performance, we conducted ablation experiments on ROSSA 3M. From Table II, it is evident that QSEME, MSDAM, and FFRM all enhanced the model’s segmentation of the target area to varying degrees. The performance of OCATMamba was optimal when all three modules were used simultaneously.

Bibtex

      
@article{zou2024octamamba,
  title={OCTAMamba: A State-Space Model Approach for Precision OCTA Vasculature Segmentation},
  author={Zou, Shun and Zhang, Zhuo and Gao, Guangwei},
  journal={arXiv preprint arXiv:2409.08000},
  year={2024}
}