新型基于分层多假设跟踪的冠脉骨架提取算法

为解决大多数脉管骨架提取算法中存在的运算复杂、准确率低以及无法同步获取脉管半径问题，提出了一种新型基于分层多假设跟踪的冠脉骨架提取算法. 首先，提出改进局部形状分析方法用于冠脉预分割，通过引入单连通约束和体积约束和降低非血管型结构及细小类血管型结构误分割率；其次，定义新的中心检测能量函数，增强骨架定位能力，并提出分层多假设策略，避免跟踪过程产生局部最优解和实现脉管半径同步获取；此外，通过生成水平集图，使算法可根据脉管树分支情况自动初始化多条跟踪路径，具有较好的拓扑适应性. 实验表明，与其他骨架提取算法相比，该算法可以同步获取冠脉骨架及半径等信息，且结果精度较高.

A New Coronary Artery Skeleton Extraction Method Based on Layered Multiple Hypothesis Tracking

To address the most common problems such as high computational complexity, low extraction accuracy and having difficulty capturing skeleton points and radius simultaneously, a new coronary skeleton extraction method based on layered multiple hypothesis tracking is proposed. First, the improved local shape analysis (ILSA) method is proposed for coronary artery pre-segmentation. Through introducing simply connected and volume constraints, segmentation error rate caused by non-vascular structures and tiny vascular-like structures can be reduced. Secondly, a new medialness measuring energy function (MMEF) is defined to enhance the skeleton point positioning performance. A layered multiple hypothesis tracking (LMHT) strategy is proposed to avoid locally optimal results and obtain vessel radius simultaneously. Additionally, by the level-set graph, multiple tracking paths can be adaptively initialized with better topological flexibility. Experimental analysis shows that compared with other methods, the proposed algorithm can obtain better skeleton extraction performance.