{"title":"利用马尔科夫随机场边缘先验对标记磁共振图像进行二维左心室位移和轮廓联合重建","authors":"L. Yan, T. Denney","doi":"10.1109/BIA.1998.692408","DOIUrl":null,"url":null,"abstract":"Magnetic Resonance (MR) tagging has been shown to be a useful method for non-invasively measuring the deformation of the left ventricle (LV), during the cardiac cycle. By reconstructing a displacement field based on the movement of the tag lines, one can compute myocardial contraction measures such as strain. Existing methods depend on user-defined LV contours, which require human intervention and are therefore the biggest bottleneck in the reconstruction process. Here, the authors present a method for reconstructing 2-D LV deformation without user-defined contours. They use a compound Gauss-Markov random field to model the 2-D vector displacement field, which is parameterized by two closed and smooth contours. By iteratively optimizing the contours, the displacement field, and the parameters, the authors obtain an estimate of the displacement field and the contours. Experimental results on in vivo human data are presented that demonstrate the accuracy of the authors' algorithm.","PeriodicalId":261632,"journal":{"name":"Proceedings. Workshop on Biomedical Image Analysis (Cat. No.98EX162)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1998-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Joint reconstruction of 2-D left ventricular displacement and contours from tagged magnetic resonance images using Markov random field edge prior\",\"authors\":\"L. Yan, T. Denney\",\"doi\":\"10.1109/BIA.1998.692408\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Magnetic Resonance (MR) tagging has been shown to be a useful method for non-invasively measuring the deformation of the left ventricle (LV), during the cardiac cycle. By reconstructing a displacement field based on the movement of the tag lines, one can compute myocardial contraction measures such as strain. Existing methods depend on user-defined LV contours, which require human intervention and are therefore the biggest bottleneck in the reconstruction process. Here, the authors present a method for reconstructing 2-D LV deformation without user-defined contours. They use a compound Gauss-Markov random field to model the 2-D vector displacement field, which is parameterized by two closed and smooth contours. By iteratively optimizing the contours, the displacement field, and the parameters, the authors obtain an estimate of the displacement field and the contours. Experimental results on in vivo human data are presented that demonstrate the accuracy of the authors' algorithm.\",\"PeriodicalId\":261632,\"journal\":{\"name\":\"Proceedings. Workshop on Biomedical Image Analysis (Cat. No.98EX162)\",\"volume\":\"10 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1998-06-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings. Workshop on Biomedical Image Analysis (Cat. No.98EX162)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/BIA.1998.692408\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. Workshop on Biomedical Image Analysis (Cat. No.98EX162)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BIA.1998.692408","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Joint reconstruction of 2-D left ventricular displacement and contours from tagged magnetic resonance images using Markov random field edge prior
Magnetic Resonance (MR) tagging has been shown to be a useful method for non-invasively measuring the deformation of the left ventricle (LV), during the cardiac cycle. By reconstructing a displacement field based on the movement of the tag lines, one can compute myocardial contraction measures such as strain. Existing methods depend on user-defined LV contours, which require human intervention and are therefore the biggest bottleneck in the reconstruction process. Here, the authors present a method for reconstructing 2-D LV deformation without user-defined contours. They use a compound Gauss-Markov random field to model the 2-D vector displacement field, which is parameterized by two closed and smooth contours. By iteratively optimizing the contours, the displacement field, and the parameters, the authors obtain an estimate of the displacement field and the contours. Experimental results on in vivo human data are presented that demonstrate the accuracy of the authors' algorithm.