VFGS-Net: Frequency-Guided State-Space Learning for Topology-Preserving Retinal Vessel Segmentation

2026-02-11

AI Summary

Existing retinal vessel segmentation methods struggle to preserve fine capillaries while maintaining global topological continuity, particularly when confronted with challenges such as elongated structures, multi-scale variations, and low contrast. To address this limitation, this work proposes VFGS-Net, an end-to-end segmentation framework that jointly optimizes local details and global structure through a dual-path convolutional module, a vessel-aware frequency-domain channel attention mechanism, and a bidirectional asymmetric state space model based on Mamba2. The proposed architecture effectively captures multi-scale semantics and long-range spatial dependencies, achieving state-of-the-art performance across four public datasets. Notably, it significantly improves segmentation accuracy and connectivity in fine vessels, complex bifurcations, and low-contrast regions.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate retinal vessel segmentation is a critical prerequisite for quantitative analysis of retinal images and computer-aided diagnosis of vascular diseases such as diabetic retinopathy. However, the elongated morphology, wide scale variation, and low contrast of retinal vessels pose significant challenges for existing methods, making it difficult to simultaneously preserve fine capillaries and maintain global topological continuity. To address these challenges, we propose the Vessel-aware Frequency-domain and Global Spatial modeling Network (VFGS-Net), an end-to-end segmentation framework that seamlessly integrates frequency-aware feature enhancement, dual-path convolutional representation learning, and bidirectional asymmetric spatial state-space modeling within a unified architecture. Specifically, VFGS-Net employs a dual-path feature convolution module to jointly capture fine-grained local textures and multi-scale contextual semantics. A novel vessel-aware frequency-domain channel attention mechanism is introduced to adaptively reweight spectral components, thereby enhancing vessel-relevant responses in high-level features. Furthermore, at the network bottleneck, we propose a bidirectional asymmetric Mamba2-based spatial modeling block to efficiently capture long-range spatial dependencies and strengthen the global continuity of vascular structures. Extensive experiments on four publicly available retinal vessel datasets demonstrate that VFGS-Net achieves competitive or superior performance compared to state-of-the-art methods. Notably, our model consistently improves segmentation accuracy for fine vessels, complex branching patterns, and low-contrast regions, highlighting its robustness and clinical potential.

Problem

• retinal vessel segmentation
• topology preservation
• low contrast
• scale variation
• fine capillaries

Innovation

• frequency-domain attention
• state-space modeling
• retinal vessel segmentation
• dual-path convolution
• topology preservation