HTC-SGA Former: A Hybrid Transformer-CNN Network with Self-Guided Attention and a New Boundary-Weighted Adaptive Loss for Coronary DSA Vessel Segmentation
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a new computer method called HTC-SGA Former to help identify tiny blood vessels in heart X-ray images more accurately. Their approach combines two types of machine learning models to better understand both small vessel details and overall image context. They also developed special techniques to focus on hard-to-see vessel edges and improve learning. Tests showed this method works better than many other existing techniques while being efficient and lightweight. Overall, their work aims to support accurate heart vessel analysis for medical use.
Digital Subtraction AngiographyCoronary artery diseaseVessel segmentationTransformerConvolutional Neural NetworkAttention mechanismBoundary detectionLoss functionComputer-aided diagnosisMedical image analysis
Authors
Rayan Merghani Ahmed, Marwa Omer Mohammed Omer, Mohamed Elmanna, Shijie Li, Bin Li, Shoujun Zhoua
Abstract
Accurate coronary Digital Subtraction Angiography (DSA) vessel segmentation is essential for computer-aided diagnosis and treatment planning of coronary artery disease (CAD). However, thin low-contrast vessels, background interference, and severe vessel-background class imbalance make reliable segmentation of weak distal branches and vessel boundaries challenging. Existing methods struggle to balance global contextual reasoning with preservation of weak vessels, vessel continuity, and fine boundaries. To address these limitations, we propose HTC-SGA Former, a lightweight hybrid Transformer-CNN framework for coronary DSA vessel segmentation. It employs a CNN encoder for local vessel morphology extraction and a Transformer decoder for contextual feature modeling. A Multi-Scale Global-Local Window Attention (MS-GLWA) block performs efficient global-local contextual modeling, while a Self-Guided Feature Attention (SGFA) module enhances weak-vessel responses. In addition, a Boundary-Weighted Adaptive Compound Loss (BWACL) emphasizes thin-vessel boundaries and adaptively balances vessel recovery and boundary refinement. Experiments on private right and left coronary artery DSA subsets show that HTC-SGA Former outperforms 14 state-of-the-art segmentation methods while maintaining a compact architecture with only 0.81M parameters. BWACL also improves performance over binary cross-entropy and Dice losses across four encoder-decoder architectures, demonstrating strong cross-backbone applicability. HTC-SGA Former improves thin-vessel recovery, vessel continuity, and boundary localization through complementary global-local contextual modeling, vessel-focused refinement, and adaptive optimization, supporting reliable and computationally efficient coronary vessel analysis for future computer-assisted cardiovascular interventions.