LWT-ARTERY-LABEL: A Lightweight Framework for Automated Coronary Artery Identification.

Area of Science:

• Cardiovascular Imaging
• Medical Image Analysis
• Computational Anatomy

Background:

• Coronary artery disease (CAD) is a leading global cause of mortality.
• Computed Tomography Coronary Angiography (CTCA) is crucial for treatment decisions.
• Automated analysis of CTCA data is hindered by coronary tree anatomical variability and labor-intensive feature identification.

Purpose of the Study:

• To develop an efficient automated method for coronary artery labelling.
• To overcome limitations of traditional knowledge-based and resource-intensive deep-learning approaches.
• To facilitate detailed computational analysis of coronary arteries from CTCA images.

Main Methods:

• A novel lightweight method integrating anatomical knowledge with rule-based topology constraints.
• Development of an automated system for coronary artery labelling.
• Validation on benchmark datasets for coronary artery analysis.

Main Results:

• Achieved state-of-the-art performance in coronary artery labelling.
• Demonstrated effectiveness in overcoming anatomical variability challenges.
• Provided a promising alternative for automated coronary artery analysis.

Conclusions:

• The proposed method offers an efficient solution for automated coronary artery labelling.
• This approach facilitates the identification of artery-specific features for computational modeling.
• Enables more efficient and accurate analysis in cardiovascular research and clinical practice.