计算机工程与应用 ›› 2015, Vol. 51 ›› Issue (2): 156-160.

• 图形图像处理 • 上一篇    下一篇

基于最小代价路径的血管中心线提取

盛惠娟1,2,邓振生1,2,欧阳丽蓉3   

  1. 1.中南大学 有色金属成矿预测教育部重点实验室,长沙 410083
    2.中南大学 地球科学与信息物理学院,长沙 410083
    3.中南大学湘雅医院 放射科,长沙 410008
  • 出版日期:2015-01-15 发布日期:2015-01-12

Vessel centerline extraction based on minimum cost path algorithm

SHENG Huijuan1,2, DENG Zhensheng1,2, OUYANG Lirong3   

  1. 1.Key Laboratory of Metallogenic Predication of Nonferrous Metals, Ministry of Educating, Central South University, Changsha 410083, China
    2.School of Geosciences and Info-Physics, Central South University, Changsha 410083, China
    3.Department of Radiology, Xiangya Hospital of Central South University, Changsha 410008, China
  • Online:2015-01-15 Published:2015-01-12

摘要: 为解决传统最小代价路径算法提取血管中心线时存在偏向血管侧壁的问题,提出一种基于点的中心线校正方法。应用最小代价路径算法初步提取中心线,然后根据血管剖面灰阶值呈高斯分布的特点对每个中心点进行校正,再利用三次B样条将离散的中心点拟合为一条连续的中心线。实验结果表明,该算法提取的中心线更靠近血管的中心处,且对噪声具有鲁棒性。此外,将该算法用于起点、终点位置的校正,则提取的中心线对用户定义点的位置不敏感。

关键词: 血管, 中心线提取, 最小代价路径算法, 高斯剖面, 中心校正

Abstract: Applying the traditional minimum cost path algorithm to find the centerline through bend vessel yields a biased path which closes to the one side of vessel wall. To solve this problem, a centering method based on points is proposed. The centerline is extracted preliminary by minimum cost path algorithm, then the center point is corrected by gray Gaussian curve fitting, and a smoothed centerline is obtained finally by using cubic B-spline fitting to the discrete corrected points. The experimental results show that this method is robust to the noise and the extracted centerline is closer to the center of vessel at the areas of high curvature. Besides, this centerline is not sensitive to the user-defined points by applying the centering method to correct the position of start-point and end-point.

Key words: vessel, centerline extraction, minimum cost path algorithm, Gaussian profile, centering