SFD-Mamba2Net: Strcture-Guided Frequency-Enhanced Dual-Stream Mamba2 Network for Coronary Artery Segmentation

2025-09-10

AI Summary

Segmenting coronary arteries and detecting stenoses in invasive coronary angiography (ICA) images remains challenging due to low vessel contrast, high noise levels, and fine-grained vascular structures. To address these issues, we propose a dual-stream encoder-decoder network integrating structural prior guidance, long-range dependency modeling via the state-space model Mamba2, multi-level wavelet-domain enhancement, curvature-aware feature learning, and progressive high-frequency recovery. This design enables synergistic modeling of global vessel morphology and local structural details. Evaluated on public ICA datasets, our method achieves state-of-the-art performance across all eight segmentation metrics. For stenosis detection, it attains the highest true positive rate (TPR) and positive predictive value (PPV), demonstrating superior accuracy and robustness for clinical decision support.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

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

Abstract

Background: Coronary Artery Disease (CAD) is one of the leading causes of death worldwide. Invasive Coronary Angiography (ICA), regarded as the gold standard for CAD diagnosis, necessitates precise vessel segmentation and stenosis detection. However, ICA images are typically characterized by low contrast, high noise levels, and complex, fine-grained vascular structures, which pose significant challenges to the clinical adoption of existing segmentation and detection methods. Objective: This study aims to improve the accuracy of coronary artery segmentation and stenosis detection in ICA images by integrating multi-scale structural priors, state-space-based long-range dependency modeling, and frequency-domain detail enhancement strategies. Methods: We propose SFD-Mamba2Net, an end-to-end framework tailored for ICA-based vascular segmentation and stenosis detection. In the encoder, a Curvature-Aware Structural Enhancement (CASE) module is embedded to leverage multi-scale responses for highlighting slender tubular vascular structures, suppressing background interference, and directing attention toward vascular regions. In the decoder, we introduce a Progressive High-Frequency Perception (PHFP) module that employs multi-level wavelet decomposition to progressively refine high-frequency details while integrating low-frequency global structures. Results and Conclusions: SFD-Mamba2Net consistently outperformed state-of-the-art methods across eight segmentation metrics, and achieved the highest true positive rate and positive predictive value in stenosis detection.

Problem

• Segmenting coronary arteries in low-contrast, noisy angiography images
• Detecting stenosis in complex fine-grained vascular structures
• Enhancing segmentation accuracy despite background interference challenges

Innovation

• Curvature-Aware Structural Enhancement module
• Progressive High-Frequency Perception module
• State-space-based long-range dependency modeling