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

2024-09-12

arXiv.org

AI Summary

OCTA image segmentation suffers from low accuracy due to large inter-vessel scale variations, intense noise, and severe pathological interference. To address this, we propose Mamba-U-Net—the first U-shaped network incorporating the Mamba state-space model. Our method introduces three novel components: a quad-stream embedding module, a multi-scale dilated asymmetric convolution module, and a focus-aware feature recalibration module. These modules jointly capture long-range dependencies and fine-grained local structures while preserving linear computational complexity with respect to sequence length. Extensive experiments on three large-scale public OCTA benchmarks—OCTA-3M, OCTA-6M, and ROSSA—demonstrate consistent and significant improvements over state-of-the-art methods in both segmentation accuracy and robustness. The source code is publicly available.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Mixture of Experts (MoE)
• Intelligent Robots: State Estimation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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

Problem

• OCTA Image Analysis
• Vascular Structure Recognition
• Disease Diagnosis Assistance

Innovation

• OCTAMamba
• Multi-scale Vessel Capturing
• Interference Filtering and Vessel Highlighting