首页 | 本学科首页   官方微博 | 高级检索  
     

基于吸引区域的多模态脑磁共振图像仿射配准
引用本文:孙创日,甄帅,夏顺仁.基于吸引区域的多模态脑磁共振图像仿射配准[J].浙江大学学报(自然科学版 ),2012(9):1722-1728.
作者姓名:孙创日  甄帅  夏顺仁
作者单位:浙江大学生物医学工程教育部重点实验室;金策工业综合大学电子系
基金项目:国家自然科学基金资助项目(81101903,60772092)
摘    要:针对单个对象的多模态脑磁共振图像之间的几何形变较小的情形,为达到全局优化的目的,提出一种基于吸引区域的多模态脑磁共振图像仿射配准方法.把配准优化搜索过程分成两个步骤:寻找包含全局最小值的吸引区域和在吸引区域中进行最小值搜索.该配准优化使用吸引区域里目标函数的近似对称性予以实现.对于正常人群和脑胶质瘤患者群,进行了磁共振T1加权和扩散加权图像之间多模态配准实验,并使用两种相似测度对3种不同的配准方法进行评价,实验结果表明:该方法与传统的局部优化方法相比,配准后的相似性测度均有显著性改善.

关 键 词:磁共振成像  扩散加权成像  全局最优  仿射配准  吸引区域

Attractor range based affine registration of multi-modal brain magnetic resonance images
SON Chang-il,ZHEN Shuai,XIA Shun-ren.Attractor range based affine registration of multi-modal brain magnetic resonance images[J].Journal of Zhejiang University(Engineering Science),2012(9):1722-1728.
Authors:SON Chang-il  ZHEN Shuai  XIA Shun-ren
Affiliation:1(1.Key Laboratory of Biomedical Engineering of Ministry of Education,Zhejiang University,Hangzhou 310027,China; 2.Department of Electronics,Kim Chaek University of Technology,Pyongyang 104919,DPR of Korea)
Abstract:In view of the fact that the geometrical deformation between multi-modal brain magnetic resonance images(MRI) of the single subject is small,a attractor range based method for affine registration between multi-modal brain MRI was proposed to achieve the global optimization.The process of registration optimization search was divided into two steps: the search for "attractor range" which contained the global minimum,and the search for global minimum within the attractor range.The registration optimization was realized by using the approximate symmetry of the objective function in the attractor range.The multi-modal registration experiments between MRI T1-weighted and diffusion weighted brain images were performed for a healthy control group and a patient group with glioma,and two similarity measures were used to evaluate three different registration algorithms.Compared with the traditional schemes using local optimization,the registration quality using the proposed algorithm was significantly improved.
Keywords:MRI  diffusion weighted imaging  global optimization  affine registration  attractor range
本文献已被 CNKI 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