首页> 外文期刊>電子情報通信学会技術研究報告. パターン認識·メディア理解. Pattern Recognition and Media Understanding >Automated extraction of aorta regions from 3D abdominal X-ray CT images using anatomical knowledge
【24h】

Automated extraction of aorta regions from 3D abdominal X-ray CT images using anatomical knowledge

机译:使用解剖学知识从3D腹部X射线CT图像中自动提取主动脉区域

获取原文
获取原文并翻译 | 示例
       

摘要

This paper describes a method for automated extraction of aorta regions from 3D abdominal X-ray CT images using anatomical knowledge. We have developed the method for automated extraction of aorta regions, based on the shape recovery technique by the distance and the reverse distance transformations. However, in the case that the intensity contrast between abdominal organs and the aorta is low, mis-segmentation of other organs occurs in the shape modification process. The proposed method uses the Hough transformation in addition to the distance transformation to extract a medial line of the aorta. Also it uses the variance of CT values of recovered aorta region to prevent mis-segmentations. The proposed method is applied to twenty two cases of 3D abdominal X-ray CT images. The extraction results showed that aorta regions could be extracted satisfactorily and stably.
机译:本文介绍了一种使用解剖学知识从3D腹部X射线CT图像自动提取主动脉区域的方法。我们已经开发了一种自动提取主动脉区域的方法,该方法基于通过距离和反向距离转换的形状恢复技术。然而,在腹部器官和主动脉之间的强度对比度较低的情况下,在形状改变过程中会发生其他器官的错误分割。所提出的方法除了使用距离变换之外还使用霍夫变换来提取主动脉的中线。此外,它使用恢复的主动脉区域的CT值的方差来防止错误分割。该方法适用于22例3D腹部X射线CT图像。提取结果表明,主动脉区域可被满意,稳定地提取。

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