Coronary artery centerline extraction using a robust lightweight CNN approach

In cardiac CT angiography imaging, extracting coronary centerlines can be a tedious and time-consuming task for radiologists. In this paper, we propose a deep-learning method that can automatically track vessels from seed points to their ends without manual intervention. Our network consists of two lightweight 3D convolutional neural networks, one trained to predict forward and backward directions, and the other to generate a vessel distance map. The distance map generator is important for vessel tracking, as it not only aids in extracting seed points but also provides a robust stopping mechanism before the tracking extends beyond the vessel of interest. The proposed networks were trained using data from 55 patients, with 2 for validation and 5 for inference. Our experimental studies show that the overall performance of the proposed method for the right coronary artery and the left coronary artery has a misclassification rate of about 14%, with mean sensitivity and overlap of about 95%. These results demonstrate that our method can reliably track coronary arteries.