Automated Coronary Artery Identification in CT Angiography: A Deep Learning Approach Using Bounding Boxes

Introduction: Ischemic heart disease represents one of the main causes of mortality and morbidity, requiring accurate, noninvasive imaging. Coronary Computed Tomography Angiography (CCTA) offers a detailed coronary assessment but can be labor-intensive and operator-dependent. Methods: We developed a bounding box-based object detection method using deep learning to identify the right coronary artery (RCA), left anterior descending artery (LCA-LAD), and left circumflex artery (LCA-CX) in the CCTA cross-sections. A total of 19,047 images, which were recorded from 52 patients, underwent a five-fold cross-validation. The evaluation metrics included Average Precision (AP), Intersection over Union (IoU), Dice Similarity Coefficient (DSC), and Mean Absolute Error (MAE) to achieve both detection accuracy and spatial localization precision. Results: The mean AP scores for RCA, LCA-LAD, and LCA-CX were 0.71, 0.70, and 0.61, respectively. IoU and DSC indicated a better overlap for LCA-LAD, whereas LCA-CX was more challenging to detect. The MAE analysis showed the largest centroid deviation in RCA, highlighting variable performance across the artery classes. Discussion: These findings demonstrate the feasibility of automated coronary artery detection, potentially reducing observer variability and expediting CCTA analysis. They also highlight the need to refine the approach for complex anatomical variants or calcified plaques. Conclusion: A bounding box-based approach can thereby streamline clinical workflows by localizing major coronary arteries. Future research with diverse datasets and advanced visualization techniques may further enhance diagnostic accuracy and efficiency.