FAD-Net: Frequency-Domain Attention-Guided Diffusion Network for Coronary Artery Segmentation using Invasive Coronary Angiography

2025-06-13

AI Summary

To address the challenges of low segmentation and stenosis detection accuracy in invasive coronary angiography (ICA) caused by thin, low-contrast, and noisy vessels, this paper proposes a frequency-domain attention-guided diffusion network. The method innovatively integrates wavelet-based multi-scale frequency decomposition, a frequency-domain multi-level self-attention (MLSA) mechanism, and a low-frequency diffusion module (LFDM), while introducing a high-frequency detail inverse fusion reconstruction strategy. This constitutes the first approach to model query-key similarity in the frequency domain and achieve continuous anatomical structure enhancement. Evaluated on a public ICA dataset, the proposed method achieves a Dice score of 0.8717 for coronary artery segmentation and attains a true positive rate of 0.6140 and a positive predictive value of 0.6398 for stenosis detection—both significantly surpassing current state-of-the-art methods.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Web Mining and Content Analysis: Content-based information diffusion
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Background: Coronary artery disease (CAD) remains one of the leading causes of mortality worldwide. Precise segmentation of coronary arteries from invasive coronary angiography (ICA) is critical for effective clinical decision-making. Objective: This study aims to propose a novel deep learning model based on frequency-domain analysis to enhance the accuracy of coronary artery segmentation and stenosis detection in ICA, thereby offering robust support for the stenosis detection and treatment of CAD. Methods: We propose the Frequency-Domain Attention-Guided Diffusion Network (FAD-Net), which integrates a frequency-domain-based attention mechanism and a cascading diffusion strategy to fully exploit frequency-domain information for improved segmentation accuracy. Specifically, FAD-Net employs a Multi-Level Self-Attention (MLSA) mechanism in the frequency domain, computing the similarity between queries and keys across high- and low-frequency components in ICAs. Furthermore, a Low-Frequency Diffusion Module (LFDM) is incorporated to decompose ICAs into low- and high-frequency components via multi-level wavelet transformation. Subsequently, it refines fine-grained arterial branches and edges by reintegrating high-frequency details via inverse fusion, enabling continuous enhancement of anatomical precision. Results and Conclusions: Extensive experiments demonstrate that FAD-Net achieves a mean Dice coefficient of 0.8717 in coronary artery segmentation, outperforming existing state-of-the-art methods. In addition, it attains a true positive rate of 0.6140 and a positive predictive value of 0.6398 in stenosis detection, underscoring its clinical applicability. These findings suggest that FAD-Net holds significant potential to assist in the accurate diagnosis and treatment planning of CAD.

Problem

• Enhance coronary artery segmentation accuracy in ICA
• Improve stenosis detection for CAD diagnosis
• Integrate frequency-domain analysis for precise segmentation

Innovation

• Frequency-domain attention mechanism enhances segmentation
• Cascading diffusion strategy improves anatomical precision
• Multi-level wavelet transformation refines arterial details