DOSTA-Net: Domain-Shuffle Temporal Attention Network for Vessel Extraction in X-Ray Coronary Angiography Using...

Artery extraction from X-ray coronary angiography (XCA) images is essential for the accurate diagnosis and treatment of coronary artery diseases. However, vessel visibility is significantly obscured by superimposed fluoroscopic densities from bones and soft tissues. Traditional digital subtraction angiography techniques are ineffective due to severe image degradation caused by cardiac motion. The development of deep learning-based methods has been hindered by the lack of large-scale datasets with high-quality annotations. To address this challenge, recent studies have explored training-free vessel extraction models, but their non-data-driven nature limits robustness in handling complex real-world data. In this work, we propose a novel framework that leverages synthetic temporal XCA data to a train deep learning model without the need for human annotation. First, we develop a comprehensive pipeline to synthesize large-scale, realistic temporal XCA data with anatomical variability and realistic artifacts simulation. Second, we introduce a DOmain-Shuffle Temporal Attention Network (DOSTA-Net), which enhances temporal feature learning by shuffling synthetic and real data along the temporal channel, effectively utilizing temporal information while mitigating domain discrepancies. Third, we generate the pseudo-label for real data and employ an annealing loss function to further reduce the domain gap between real and synthetic data to better utilize the unlabeled real data. The proposed method is evaluated based on the vessel segmentation performance on two datasets using the extracted arteries. Additionally, we conduct a reader study on an in-house real XCA dataset through subjective image quality assessment. Experimental results demonstrate that our approach outperforms state-of-the-art methods. Code and trained model weights are available at https://github.com/Advanced-AI-in-Medicine-and-Physics-Lab/DOSTA-Net.