...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Discrete and Continuous Dynamical Systems,Series S >SIGNED-DISTANCE FUNCTION BASED NON-RIGID REGISTRATION OF IMAGE SERIES WITH VARYING IMAGE INTENSITY
【24h】

SIGNED-DISTANCE FUNCTION BASED NON-RIGID REGISTRATION OF IMAGE SERIES WITH VARYING IMAGE INTENSITY

机译：基于符号距离的图像系列非刚性注册，不同图像强度

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper we propose a method for locally adjusted opticalow-based registration of multimodal images, which uses the segmentation ofobject of interest and its representation by the signed-distance function (OF~（dist）method). We deal with non-rigid registration of the image series acquired bythe Modied Look-Locker Inversion Recovery (MOLLI) magnetic resonanceimaging sequence, which is used for a pixel-wise estimation of T1 relaxationtime. The spatial registration of the images within the series is necessary tocompensate the patient's imperfect breath-holding. The evolution of intensi-ties and a large variation of image contrast within the MOLLI image series,together with the myocardium of left ventricle (the object of interest) typicallynot being the most distinct object in the scene, makes the registration chal-lenging. The paper describes all components of the proposed OF~（dist） methodand their implementation. The method is then compared to the performance ofa standard mutual information maximization-based registration method, ap-plied either to the original image (MIM) or to the signed-distance function(MIM~(dist)). Several experiments with synthetic and real MOLLI images arecarried out. On synthetic image with a single object, MIM performed the best,while OF~(dist) and MIM~(dist) provided better results on synthetic images withmore than one object and on real images. When applied to signed-distancefunction of two objects of interest, MIM~（dist） provided a larger registration er-ror, but more homogeneously distributed, compared to OF~（dist）. For the realMOLLI image series with left ventricle pre-segmented using a level-set method,the proposed OF~(dist) registration performed the best, as is demonstrated vi-sually and by measuring the increase of mutual information in the object ofinterest and its neighborhood.
机译：在本文中，我们提出了一种用于局部调整光学的方法基于OW的多模式图像登记，使用分割感兴趣的对象及其符号距离功能的表示（〜（dist）方法）。我们处理由此获得的图像系列的非刚性注册修改的外观储物柜反转恢复（Molli）磁共振成像序列，用于PIXEL-WISE估计T1松弛时间。该系列内的图像的空间登记是必要的补偿患者不完美的呼吸持有。连环的演变 - 在Molli Image系列中的图像对比的关系和大量变化，通常与左心室的心肌（兴趣的对象）一起不是现场中最独特的物体，使注册挑战 - 愣。本文描述了〜（DIST）方法所提出的所有组件及其实施。然后将该方法与性能进行比较基于标准的相互信息最大化的注册方法，AP-将原始图像（MIM）或符号距离函数覆盖（mim〜（dist））。具有合成和真实的Molli图像的几个实验执行。在具有单个对象的合成图像上，MIM表现最佳，〜（dist）和mim〜（dist）在合成图像上提供更好的结果不止一个对象和真实的图像。当应用于符号距离时两个兴趣对象的功能，MIM〜（DIST）提供了更大的登记ER-与〜（dist）相比，ror，但更加正常分布。对于真实的Molli Image系列与左心室使用级别的方法预先分割，〜（dist）注册的提议表现了最好的，如vi-SILLALL和测量对象中的相互信息的增加兴趣及其社区。

著录项

  • 来源
  • 作者

    KATERINA SKARDOVA; TOMAS OBERHUBER; JAROSLAV TINTERA; RADOM CHABINIOK;

  • 作者单位

    Department of Mathematics FNSPE Czech Technical University in PragueTrojanova 13 120 00 Prague Czech Republic;

    Department of Mathematics FNSPE Czech Technical University in PragueTrojanova 13 120 00 Prague Czech Republic;

    Department of Radiology Institute for clinical and experimental medicineVdenska 1958/9 Praha 4 140 21 Czech Republic;

    Department of Mathematics FNSPE Czech Technical University in PragueTrojanova 13 120 00 Prague Czech Republic Inria France LMS Ecole Polytechnique CNRSInstitut Polytechnique de Paris France School of Biomedical Engineering & Imaging SciencesSt Thomas' Hospital King's College London UK;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Distance function; locally adjusted image registration; image segmen-tation; optical ow;

    机译：距离功能;本地调整的图像配准;图像Segmen-tation;光学的ow;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号