科研之友
微信
新浪微博
Facebook
分享链接
摘要
It has been a challenging but significant research topic to extract the centerlines of the coronary arteries of the cardiac computed tomography angiography volume in clinical applications. A new method is proposed to full-automatically extract and recognize the centerlines of the major branches instead of manual interaction in this paper, which employs a new path tracking algorithm that combines direction features from atlases and inertia features from previous extracted centerline points, referred to as model-mapped and inertia-guided minimum path. This method first registers a pre-constructed coronary model that contains the right coronary artery, the left anterior descending artery, the left circumflex artery coronary artery to the target cardiac computed tomography, to provide initial reference positions and direction information of the coronary artery. After getting the reference regions based on the registration, the two ostia positions are detected automatically by the learning-based method, which is based on the probability boosting tree and 3D Haar features, in the region of interest of the cardiac computed tomography volume. The starting points are then as the ostia in the evolution of minimum path. Meanwhile, to boost the robustness of the evolution, the tracked path of the last step is used to generate the inertia-driven force. Finally, based on a new automatic endpoint detection algorithm, the longest centerline of a particular coronary branch can be extracted with the proposed method. We tested the robustness of our method in the Rotterdam Coronary Artery Algorithm Evaluation framework. The proposed method is fully automatic and obtains the optimal effect among the fully automatic methods in Rotterdam framework.
