Journal of Northeastern University ›› 2011, Vol. 32 ›› Issue (1): 27-31.DOI: -

• OriginalPaper • Previous Articles     Next Articles

Automatic centerline extraction based on tubular feature for coronary arteries

Wang, Sheng-Jun (1); Fu, Ling (2); Kang, Yan (2); Liu, Ji-Ren (1)   

  1. (1) School of Information Science and Engineering, Northeastern University, Shenyang 110819, China; (2) School of Sino-Dutch Biomedical and Information Engineering, Northeastern University, Shenyang 110819, China
  • Received:2013-06-19 Revised:2013-06-19 Published:2013-04-04
  • Contact: Wang, S.-J.
  • About author:-
  • Supported by:
    -

Abstract: To solve the problem of improper centerline extraction due to the improper segmentation of coronary arteries and obviously changed vessel curvature, an algorithm based on tubular structure was proposed for the automatic centerline extraction of coronary arteries. The coronary artery centerline was extracted roughly on the basis of the configuration of the skeleton nodes, and then the criteria were proposed for the three kinds of blood vessel structures according to the tubular structure of coronary so as to detect the actualities of the improper segmentation of coronary arteries. As a result, the disconnected centerline was regulated and joined on the basis of local vascular structure, thus obtaining the complete and connective centerline of coronary arteries. The experimental results of coronary CTA volume data indicated that the proposed algorithm is able to solve well the problem of improper centerline extraction due to improper segmentation of coronary arteries and obviously changed vessel curvature, with high robustness provided.

CLC Number: