UM  > 科技學院
Automatic Medical Image Registration Based on an Integrated Method Combining Feature and Area Information
Xie, Jiucheng1; Pun, Chi-Man2; Pan, Zhaoqing3; Gao, Hao1; Wang, Baoyun1
2018-03-06
Source PublicationNeural Process Lett
Volume49Issue:1Pages:263-284
Abstract

Multi-modal image registration plays an increasing role in diagnosis, surveillance, and treatment of disease. This paper proposes a new registration measure, called contour and neighbor volume similarity method, which incorporates the merits of both area-based and feature-based methods. The implementation of this integrated method can be illustrated with a coarse-to-fine registration framework. In the coarse registration stage, the closed contours of the objects are first extracted as a stable feature set. Based on a distance measure, the feature set is used to rapidly estimate an initial transformation in the global scope. Subsequently, in response to the possible false alignment when registering symmetrical objects with feature-based methods, we employ an alignment correction procedure to ensure the reliability of the original transformation. Finally, the modified feature neighborhood and mutual information, an area-based method characterized by multiscale filtering mechanism, is adopted in the fine registration stage to obtain a precise final transformation. In addition, we introduce a differential evolution algorithm with an equilibrium strategy for estimating transformation parameters in the coarse registration stage. Our proposed method has been extensively evaluated by comparing with several state-of-the-art registration approaches on multi-modal brain images. The results indicate that it can automatically align images in various environments (different shapes of targets or different noise levels) with high accuracy and robustness.

DOIhttps://doi.org/10.1007/s11063-018-9808-6
URLView the original
Language英语
全文获取链接
引用统计
Document TypeJournal article
专题Faculty of Science and Technology
DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Affiliation1.Nanjing University of Posts and Telecommunications
2.University of Macau
3.Nanjing University of Information Science & Technology
推荐引用方式
GB/T 7714
Xie, Jiucheng,Pun, Chi-Man,Pan, Zhaoqing,et al. Automatic Medical Image Registration Based on an Integrated Method Combining Feature and Area Information[J]. Neural Process Lett,2018,49(1):263-284.
APA Xie, Jiucheng,Pun, Chi-Man,Pan, Zhaoqing,Gao, Hao,&Wang, Baoyun.(2018).Automatic Medical Image Registration Based on an Integrated Method Combining Feature and Area Information.Neural Process Lett,49(1),263-284.
MLA Xie, Jiucheng,et al."Automatic Medical Image Registration Based on an Integrated Method Combining Feature and Area Information".Neural Process Lett 49.1(2018):263-284.
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
Google Scholar
中相似的文章 Google Scholar
[Xie, Jiucheng]的文章
[Pun, Chi-Man]的文章
[Pan, Zhaoqing]的文章
Baidu academic
中相似的文章 Baidu academic
[Xie, Jiucheng]的文章
[Pun, Chi-Man]的文章
[Pan, Zhaoqing]的文章
Bing Scholar
中相似的文章 Bing Scholar
[Xie, Jiucheng]的文章
[Pun, Chi-Man]的文章
[Pan, Zhaoqing]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。