首页 | 本学科首页   官方微博 | 高级检索  
     

利用高维互信息的多模态医学图像配准
引用本文:胡永祥,汤井田,蒋 鸿. 利用高维互信息的多模态医学图像配准[J]. 计算机工程与应用, 2007, 43(24): 242-245
作者姓名:胡永祥  汤井田  蒋 鸿
作者单位:中南大学,信息物理工程学院,生物医学工程研究所,长沙,410083;湖南工业大学,计算机与通信学院,湖南,株洲,412008;中南大学,信息物理工程学院,生物医学工程研究所,长沙,410083;湖南工业大学,计算机与通信学院,湖南,株洲,412008
摘    要:互信息相似性测度在多模态医学图像配准中获得了广泛的应用,然而其不足之处在于没用充分利用图像固有的空间信息。针对这一不足,提出了利用图像邻域信息的高维互信息配准方法。首先用图像像素及其邻域构成高维向量的集合,然后利用基于最近邻的熵估计法来估计集合的高维熵,并采用近似最近邻搜索算法来加快高维熵的计算。实验结果验证了新的相似性测度的有效性。

关 键 词:高维互信息  多模态医学图像  图像配准
文章编号:1002-8331(2007)24-0242-04
修稿时间:2007-01-01

Multi-modality medical image registration using high dimension mutual information
HU Yong-xiang,TANG Jing-tian,JIANG Hong. Multi-modality medical image registration using high dimension mutual information[J]. Computer Engineering and Applications, 2007, 43(24): 242-245
Authors:HU Yong-xiang  TANG Jing-tian  JIANG Hong
Affiliation:1.Institute of Biomedical Engineering,Central South University,Changsha 410083,China 2.Institute of Computer & Communication,Hunan University of Technology,Zhuzhou,Hunan 412008,China
Abstract:Mutual Information(MI) based similarity measure has been widely used in multi-modal medical image registration.One drawback of MI,however,is that it fails to take into account the spatial information of image.In this paper,we propose a novel extension to MI called High-dimension Mutual Information(HMI).This extension takes advantage of neighbor pixels to construct a set of high dimension vector,and then evaluates high dimension entropy using an algorithm based on Nearest Neighbor Search(NNS).In order to compute HMI effectively,we adopt an algorithm called approximate nearest neighbor search.Experiments demonstrate the validation of the extended methods.
Keywords:High-dimension Mutual Information(HMI)  multi-modality medical image  image 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《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载免费的PDF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