首页> 外文期刊>International journal of biomedical imaging >Diffeomorphic Registration of Images with Variable Contrast Enhancement
【24h】

Diffeomorphic Registration of Images with Variable Contrast Enhancement

机译:具有可变对比度增强的图像的微形配准

获取原文
       

摘要

Nonrigid image registration is widely used to estimatetissue deformations in highly deformable anatomies. Amongthe existing methods, nonparametric registration algorithmssuch as optical flow, or Demons, usually have the advantage ofbeing fast and easy to use. Recently, a diffeomorphic versionof the Demons algorithm was proposed. This provides theadvantage of producing invertible displacement fields, whichis a necessary condition for these to be physical. However,such methods are based on the matching of intensities andare not suitable for registering images with different contrastenhancement. In such cases, a registration method based on thelocal phase like the Morphons has to be used. In this paper, adiffeomorphic version of the Morphons registration method isproposed and compared to conventional Morphons, Demons,and diffeomorphic Demons. The method is validated in thecontext of radiotherapy for lung cancer patients on several4D respiratory-correlated CT scans of the thorax with and withoutvariable contrast enhancement.
机译:非刚性图像配准被广泛用于估计高度可变形解剖结构中的组织变形。在现有方法中,非参数配准算法(例如光流或恶魔)通常具有快速且易于使用的优势。最近,提出了魔鬼算法的微分形式。这提供了产生可逆位移场的优势,这是使它们成为物理条件的必要条件。然而,这种方法基于强度的匹配,并且不适合配准具有不同对比度的图像。在这种情况下,必须使用基于本地阶段的注册方法,例如Morphons。本文提出了Morphons配准方法的非同构形式,并将其与常规Morphons,Demons和非同构恶魔进行了比较。该方法在放疗的背景下在对肺癌患者进行了多次4D呼吸相关的胸部CT扫描时进行了验证,无论有无造影剂增强。

著录项

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