首页> 外文会议>Visualization, Imaging, and Image Processing >REGISTRATION OF PORTAL IMAGES USING SELF-ORGANIZING MAPS
【24h】

REGISTRATION OF PORTAL IMAGES USING SELF-ORGANIZING MAPS

机译:使用自组织映射对门户图像进行注册

获取原文

摘要

Portal imaging refers to a procedure for monitoring the setup geometry in radiation therapy using X-ray images acquired in very high energy (approximately 10 MeV). Portal imaging has become significant in recent years, since it provides a means for the detection of setup errors, including the exclusion of part of the target volume from the beam or unwanted inclusion of normal tissue. In this paper, a new method, for the registration of portal images is presented. The method employs Self Organizing Maps (SOMs), which operate on the original raw data, in order to estimate the displacement and the angle of rotation of a treatment image with respect to a reference one. The proposed registration method was tested on phantom and real data and an average error below 1mm was achieved The obtained results strongly indicate that the proposed system is suitable for detecting and quantifying patient setup errors.
机译:门静脉成像是指使用放射能量很高(约10 MeV)的X射线图像监视放射治疗中的设置几何形状的过程。近年来,门静脉成像已变得越来越重要,因为它提供了一种检测设置错误的方法,包括从光束中排除部分目标体积或正常组织的不必要包容。本文提出了一种新的门户图像配准方法。该方法采用对原始原始数据进行操作的自组织图(SOM),以便估计治疗图像相对于参考图像的位移和旋转角度。对拟议的配准方法进行了幻像和真实数据测试,平均误差低于1mm。获得的结果强烈表明,拟议的系统适用于检测和量化患者设置误差。

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