A novel multi-attention, multi-scale 3D deep network for coronary artery segmentation.

Area of Science:

• Medical imaging analysis
• Artificial intelligence in healthcare
• Cardiovascular disease research

Background:

• Accurate coronary artery segmentation (CAS) is crucial for diagnosing coronary artery disease (CAD).
• Existing CAS methods face challenges due to vessel variations, complex anatomy, and low contrast.
• Limited high-quality annotated data hinders the development of robust CAS models.

Purpose of the Study:

• To develop a novel 3D deep network, CAS-Net, for improved automatic coronary artery segmentation.
• To address the challenges of vessel variability, complex morphology, and low contrast in CAS.
• To enhance feature representation and fusion for more accurate vessel map generation.

Main Methods:

• Proposed CAS-Net, a multi-attention, multi-scale 3D deep network.
• Introduced attention-guided feature fusion (AGFF) and scale-aware feature enhancement (SAFE) modules.
• Developed a new dataset of 119 coronary computed tomographic angiography (CCTA) volumes for training and validation.

Main Results:

• CAS-Net demonstrated superior segmentation performance and generalization ability across multiple datasets.
• The proposed method significantly outperformed state-of-the-art algorithms, improving Dice similarity coefficient (DSC) by at least 4% compared to U-Net3D.
• The synergistic effect of AGFF, SAFE, and multi-scale feature aggregation (MSFA) modules contributed to enhanced segmentation accuracy.

Conclusions:

• CAS-Net offers a robust solution for automatic coronary artery segmentation, aiding in CAD diagnosis.
• The novel network architecture effectively handles variations and complexities in coronary artery imaging.
• The developed dataset and open-source implementation facilitate further research in cardiovascular image analysis.