Automatic labeling of coronary arteries in computed tomography angiography images

The objectives of this study were to develop an automatic algorithm for labeling coronary arteries in coronary computed tomography angiography (CCTA) images and to examine the reliabilities of this method. In total, 157 patients who underwent CCTA scanning were retrospectively included. An automatic coronary artery labeling algorithm based on the distance transformation algorithm is proposed to identify the anatomical segments of the centerlines extracted from CCTA images. Sixteen segments were identified and labeled. The results obtained via the algorithm were recorded and reviewed by three experts. The performance of segment detection and labeling of each segment was evaluated, and the proportion of agreement between the two experts on the manually labeled segments was also calculated. Compared with the labels of the experts, 117 labels (5.37%) (2180 segments) from the algorithm needed to be changed or removed. The overall accuracy of label presence was 96.21%. The average overlap between the expert reference and algorithm labels was 94.03%. The average agreement between the two experts was 94.98%. An automatic labeling algorithm was proposed, and a preliminary evaluation showed a high accuracy of the algorithm labels with respect to the labels from the clinical experts. This method is promising for labeling coronary arteries automatically and alleviating the workload of radiologists in the near future. Clinical Relevance— The automatic labeling algorithm established with the distance to the LA and LV can help improve the segment detection and labeling accuracy for CT imaging. The proposed algorithm can accelerate the report generation process and provide bases for diagnosis.