Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (6): 36-38.

• 博士论坛 • Previous Articles     Next Articles

Medical image registration based on mutual information and mutual edge distance

HU Shun-bo1,2,LIU Chang-chun1   

  1. 1.School of Control Science and Engineering,Shandong University,Ji’nan 250061,China
    2.Department of Physics,Linyi Normal University,Linyi,Shandong 276005,China
  • Received:2007-11-02 Revised:2008-01-07 Online:2008-02-21 Published:2008-02-21
  • Contact: HU Shun-bo

基于互信息与边缘互距离的医学图像配准

胡顺波1,2,刘常春1   

  1. 1.山东大学 控制科学与工程学院,济南 250061
    2.临沂师范学院 物理系,山东 临沂 276005
  • 通讯作者: 胡顺波

Abstract: A new medical image registration measure based on mutual information and mutual edge distance is proposed in this paper.It takes advantage of the information contributed by the overall intensity values of registering images as well as the mutual mean distance and mutual distance variance derived from edge distance images.It has been proven by tests that this measure inherits most merits of mutual information and additionally bears several improved attributes:the measure curves are smoother and steeper.The areas of total curves’ convergence are wider.The new measure has less extreme point and better robustness to image size.It can identify different images even if their mutual information are same.

摘要: 提出了一种基于互信息与边缘互距离信息的医学图像配准新测度。该种测度既利用了待配准图像间的灰度互信息,又利用了图像边缘间的互距离均值和互距离方差空间信息,从而改进了互信息测度。实验证明这种测度得到的配准参数曲线光滑且峰值尖锐,收敛范围宽,对图像大小有更强的鲁棒性,在图像互信息值一样的情况下,仍有辨识能力。