首页 | 本学科首页   官方微博 | 高级检索  
检索        

基于刚-弹性变换的医学图像塔式配准新算法
引用本文:刘新刚,陈武凡,陈光杰.基于刚-弹性变换的医学图像塔式配准新算法[J].南方医科大学学报,2006,26(5):587-590,593.
作者姓名:刘新刚  陈武凡  陈光杰
作者单位:南方医科大学生物医学工程学院医学信息研究所,广东,广州,510515;南方医科大学生物医学工程学院医学信息研究所,广东,广州,510515;南方医科大学生物医学工程学院医学信息研究所,广东,广州,510515
基金项目:国家重点基础研究发展计划(973计划);国家自然科学基金
摘    要:提出了利用B样条实现医学图像从刚性到弹性配准的统一的塔式算法。选取图像的四个顶点作为构成变形函数的B样条的节点,合理选择B样条的次数,可以实现图像的仿射变换。沿X和Y方向均匀增加节点数量,逐步增加变形函数的复杂性,通过选择B样条的不同的次数n,可以实现图像的分块仿射变换或n-1阶导数连续的弹性变换。整个匹配算法体现了从整体到细节的匹配思想。实验证明,这种配准方法比单纯的弹性配准方法鲁棒性有很大提高。

关 键 词:B样条  配准  刚性变换  弹性变换
文章编号:1673-4254(2006)05-0587-04

A new mixing rigid-elastic multiresolution algorithm for medical image registration
LIU Xin-gang,CHEN Wu-fan,CHEN Guang-jie.A new mixing rigid-elastic multiresolution algorithm for medical image registration[J].Journal of Southern Medical University,2006,26(5):587-590,593.
Authors:LIU Xin-gang  CHEN Wu-fan  CHEN Guang-jie
Institution:School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China. xjlxg@163.com
Abstract:We present a new mixing rigid-elastic multiresolution algorithm for medical image registration from global registration to local registration in sequence.The global registration is achieved by the method of affine transformation composed of B spline,which knots are the four vertexes of the medical image.When increasing the number of the knots of the B spline along the X and Y axis,the transformation function will be more complex and "elastic",which can complete the elastic aligning for the detail of the medical image.The results of experiment demonstrated that the presented algorithm was more robust than the previous elastic algorithm of registration.
Keywords:B spline  registration  rigid registration  elastic registration
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号