一种新颖的CT血管造影图像的血管中心线提取方法

A novel vascular centerline extraction method of CT angiography

目的提取CT血管造影图像的血管中心线。方法 本算法由两个步骤组成:首先,一种新的多尺度滤波算法被用于增强血管结构;其次,在滤波后的图像上进行基于最小路径和贝叶斯跟踪的血管中心线提取算法。结果 实验结果表明所提出的方法能有效提取血管中心线而且能获得中心线分支信息。结论 与同类算法相比,本算法能很好地增强细小血管结构,对噪声和伪影的抑制作用更强。

Objective To extract the vascular centerline of CT angiography.Methods In order to obtain centerline branch information,a method based on minimum path and Bayesian tracking was proposed in this article.The algorithm in this article was divided into two steps:firstly,a new multiscale filtering algorithm was used to enhance vascular structure;secondly,vascular centerline extraction algorithm based on minimum path and Bayesian tracking was performed.Result The proposed method not only could effectively extract vascular centerline,obtain centerline branch information.Conclusion Compared with similar algorithms,this algorithm can enhance the vascular structure well and inhibit the noise and artifacts effectively.