首页 | 本学科首页   官方微博 | 高级检索  
     

基于投影近似不变性的3D-2D医学图像配准
引用本文:秦中元,牟轩沁. 基于投影近似不变性的3D-2D医学图像配准[J]. 计算机工程, 2006, 32(17): 22-24
作者姓名:秦中元  牟轩沁
作者单位:1. 东南大学无线电工程系,南京,210096;西安交通大学电子与信息工程学院,西安,710049
2. 西安交通大学电子与信息工程学院,西安,710049
基金项目:国家自然科学基金;教育部高校骨干教师资助计划
摘    要:研究了同一病人的MRA和DSA图像之间的3D-2D配准问题,提出了一种基于投影近似不变性的配准算法,即在同一视角下,同一病人的三维MRA血管骨架的投影与二维DSA的骨架保持一致。通过定义二者之间的代价函数,并利用牛顿迭代法可得到视角参数的最优解。针对临床采集的MRA和DSA数据进行了实验,取得了较为满意的结果。

关 键 词:医学图像配准  投影相似性  3D-2D配准
文章编号:1000-3428(2006)17-0022-03
收稿时间:2005-09-15
修稿时间:2005-09-15

3D-2D Medical Image Registration Based on Near Projective Invariance
QIN Zhongyuan,MOU Xuanqin. 3D-2D Medical Image Registration Based on Near Projective Invariance[J]. Computer Engineering, 2006, 32(17): 22-24
Authors:QIN Zhongyuan  MOU Xuanqin
Affiliation:(1. Department of Radio Engineering, Southeast University, Nanjing 210096; 2. School of Electronics and Information Engineering, Xi’an Jiaotong University, Xi’an 710049)
Abstract:The registration between MRA and DSA of a same patient is studied in this paper. The registration algorithm based on near projection invariance is presented, i.e. the projection of 3D MRA skeleton should accord with the 2D DSA skeleton under the same perspective view. After the cost function between the projections is defined, the view angle can then be obtained through maximizing the cost function using Newton iteration method. Satisfactory results are obtained in the clinical MRA and DSA data of the same patient.
Keywords:Medical image registration   Near projection invariance   3D-2D registration
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机工程》浏览原始摘要信息
点击此处可从《计算机工程》下载全文
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