Active contour model coupling with backward diffusion for medical image segmentation

Guodong Wang, Zhenkuan Pan, Weizhong Zhang, Qian Dong
{"title":"Active contour model coupling with backward diffusion for medical image segmentation","authors":"Guodong Wang, Zhenkuan Pan, Weizhong Zhang, Qian Dong","doi":"10.1109/BMEI.2013.6746915","DOIUrl":null,"url":null,"abstract":"Active contour models are very useful for image segmentation, but it is not true for images with intensity inhomogeneities which often occur in medical images. The reason is that the weak edge informations are disturbed by the intensity inhomogeneities, and the segmentation will be success if we enhance the edges. In order to overcome the difficulties caused by intensity inhomogeneities, we propose a region-based active contour model that coupling with backward diffusion which has the ability of edge enhancement for segmentation. In our model we replace the data term of piecewise constant approximation in CCV (Convex Chan-Vese) model with backward diffusion model to realize the alternating minimization of parameters of active contour evolution. Finally, the fast Split Bregman algorithm of the proposed coupling model is designed for the segmentation implementation. The performance of our method is demonstrated through numerical experiments of some medical image segmentations.","PeriodicalId":163211,"journal":{"name":"2013 6th International Conference on Biomedical Engineering and Informatics","volume":"62 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 6th International Conference on Biomedical Engineering and Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BMEI.2013.6746915","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Active contour models are very useful for image segmentation, but it is not true for images with intensity inhomogeneities which often occur in medical images. The reason is that the weak edge informations are disturbed by the intensity inhomogeneities, and the segmentation will be success if we enhance the edges. In order to overcome the difficulties caused by intensity inhomogeneities, we propose a region-based active contour model that coupling with backward diffusion which has the ability of edge enhancement for segmentation. In our model we replace the data term of piecewise constant approximation in CCV (Convex Chan-Vese) model with backward diffusion model to realize the alternating minimization of parameters of active contour evolution. Finally, the fast Split Bregman algorithm of the proposed coupling model is designed for the segmentation implementation. The performance of our method is demonstrated through numerical experiments of some medical image segmentations.
用于医学图像分割的主动轮廓模型与后向扩散耦合
主动轮廓模型对于图像分割非常有用,但对于医学影像中经常出现的强度不均匀的图像却并非如此。原因在于,弱边缘信息会受到强度不均匀性的干扰,如果我们增强边缘信息,分割就会成功。为了克服强度不均匀性带来的困难,我们提出了一种基于区域的主动轮廓模型,该模型与后向扩散耦合,具有增强边缘的分割能力。在我们的模型中,我们用后向扩散模型取代了 CCV(Convex Chan-Vese)模型中的片常数近似数据项,实现了主动轮廓演化参数的交替最小化。最后,我们设计了耦合模型的快速 Split Bregman 算法来实现分割。我们通过一些医学图像分割的数值实验证明了我们方法的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信