基于二维pca的椎体水平集分割框架的形状先验

A. Shalaby, M. Aslan, H. Abdelmunim, A. Farag
{"title":"基于二维pca的椎体水平集分割框架的形状先验","authors":"A. Shalaby, M. Aslan, H. Abdelmunim, A. Farag","doi":"10.1109/CIBEC.2012.6473317","DOIUrl":null,"url":null,"abstract":"In this paper, a novel statistical shape modeling method is developed for the vertebral body (VB) segmentation framework. Two-dimensional principle component analysis (2D-PCA) technique is exploited to extract the shape prior. The obtained shape prior is then embedded into the image domain to develop a new shape-based segmentation approach. Our framework consists of four main steps: i) shape model construction using 2D-PCA, ii) Detection of the VB region using the Matched filter, iii) Initial segmentation using the graph cuts which integrates the intensity and spatial interaction models, and iv) Registration of the shape prior and initially segmented region to obtain the final segmentation. The proposed method is validated on a Phantom as well as clinical CT images with various Gaussian noise levels. The experimental results show that the noise immunity and the segmentation accuracy of 2D-PCA based approach are much higher than conventional PCA approach.","PeriodicalId":416740,"journal":{"name":"2012 Cairo International Biomedical Engineering Conference (CIBEC)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"2D PCA-based shape prior for level sets segmentation framework of the vertebral body\",\"authors\":\"A. Shalaby, M. Aslan, H. Abdelmunim, A. Farag\",\"doi\":\"10.1109/CIBEC.2012.6473317\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, a novel statistical shape modeling method is developed for the vertebral body (VB) segmentation framework. Two-dimensional principle component analysis (2D-PCA) technique is exploited to extract the shape prior. The obtained shape prior is then embedded into the image domain to develop a new shape-based segmentation approach. Our framework consists of four main steps: i) shape model construction using 2D-PCA, ii) Detection of the VB region using the Matched filter, iii) Initial segmentation using the graph cuts which integrates the intensity and spatial interaction models, and iv) Registration of the shape prior and initially segmented region to obtain the final segmentation. The proposed method is validated on a Phantom as well as clinical CT images with various Gaussian noise levels. The experimental results show that the noise immunity and the segmentation accuracy of 2D-PCA based approach are much higher than conventional PCA approach.\",\"PeriodicalId\":416740,\"journal\":{\"name\":\"2012 Cairo International Biomedical Engineering Conference (CIBEC)\",\"volume\":\"90 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2012 Cairo International Biomedical Engineering Conference (CIBEC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CIBEC.2012.6473317\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 Cairo International Biomedical Engineering Conference (CIBEC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIBEC.2012.6473317","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8

摘要

针对VB分割框架,提出了一种新的统计形状建模方法。利用二维主成分分析(2D-PCA)技术提取形状先验。然后将获得的形状先验嵌入到图像域中,从而开发出一种新的基于形状的分割方法。我们的框架包括四个主要步骤:i)使用2D-PCA构建形状模型,ii)使用匹配滤波器检测VB区域,iii)使用集成强度和空间相互作用模型的图切割进行初始分割,iv)将形状先验和初始分割区域进行配准以获得最终分割。该方法在具有不同高斯噪声水平的幻影和临床CT图像上进行了验证。实验结果表明,基于二维主成分分析方法的抗噪性和分割精度都明显高于传统的主成分分析方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
2D PCA-based shape prior for level sets segmentation framework of the vertebral body
In this paper, a novel statistical shape modeling method is developed for the vertebral body (VB) segmentation framework. Two-dimensional principle component analysis (2D-PCA) technique is exploited to extract the shape prior. The obtained shape prior is then embedded into the image domain to develop a new shape-based segmentation approach. Our framework consists of four main steps: i) shape model construction using 2D-PCA, ii) Detection of the VB region using the Matched filter, iii) Initial segmentation using the graph cuts which integrates the intensity and spatial interaction models, and iv) Registration of the shape prior and initially segmented region to obtain the final segmentation. The proposed method is validated on a Phantom as well as clinical CT images with various Gaussian noise levels. The experimental results show that the noise immunity and the segmentation accuracy of 2D-PCA based approach are much higher than conventional PCA approach.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
3D automated colon segmentation for efficient polyp detection Pectoral muscle identification in mammograms for Computer Aided Diagnosis of breast cancer High performance multi-dimensional (2D/3D) FFT-Shift implementation on Graphics Processing Units (GPUs) A system dynamics based model for medical equipment maintenance procedure planning in developing countries Accurate analysis of cardiac tagged MRI using combined HARP and optical flow tracking
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1