• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computers in Biology and Medicine >A new nonparametric statistical approach to detect lumen and Media-Adventitia borders in intravascular ultrasound frames
【24h】

A new nonparametric statistical approach to detect lumen and Media-Adventitia borders in intravascular ultrasound frames

机译：一种新的非参数统计方法，用于检测血管内超声框架中的腔和媒体外膜边界

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

Intravascular ultrasound (IVUS) imaging is widely known as a powerful interventional imaging modality for diagnosing atherosclerosis, and for treatment planning. In this regard, the detection of lumen and media adventitia (MA) borders is considered to be a vital process. However, the manual detection of these two borders by the physician is cumbersome due to the large number of frames in a sequence. In addition, no approved universal automatic method has been presented so far due to the great diversity in the appearance of the coronary artery in the images acquired by different IVUS systems. To this end, the present study aimed to provide a new border search theory on the radial profile, based upon the nonparametric statistical approach, and to develop a generic and fully automatic three-step process for extracting the lumen and MA borders in IVUS frames based on the proposed theory. Thereafter, the proposed theory and three-step process were evaluated on synthetic images, as well as on a test set of standard publicly available images, respectively. The results showed that our three-step process could segment the borders with = 0.82 and with = 0.75 Jaccard measure (JM) to manual borders in IVUS frames acquired by the 20 MHz and 40 MHz probes, respectively. Based on the results, the lumen and MA borders can be extracted automatically, and the border extraction process can be implemented in parallel for a polar image due to the capability of the present proposed method to estimate the borders for each angle independently.
机译：血管内超声（IVUS）成像被广泛称为强大的介入性成像模型，用于诊断动脉粥样硬化，以及治疗计划。在这方面，检测腔和媒体外膜（MA）边界被认为是一个重要的过程。然而，由于序列中的大量帧，医生对这两个边界的手动检测是麻烦的。此外，到目前为止没有批准的通用自动方法是由于不同IVUS系统获取的图像中的冠状动脉外观的巨大变化。为此，本研究旨在基于非参数统计方法在径向轮廓上提供新的边界搜索理论，并开发一种通用和全自动三步过程，用于基于IVUS帧中提取内腔和MA边框论提出的理论。此后，在合成图像中评估所提出的理论和三步过程，以及分别在标准公共可用图像的测试集。结果表明，我们的三步过程可以将边界分段为＆ = 0.82且与＆ = 0.75 jaccard措施（JM）分别在由20MHz和40MHz探针获得的IVUS帧中进行手动边框。基于该结果，可以自动提取腔和MA边框，并且由于本所提出的方法独立地为每个角度估计边界的能力，边界提取过程可以与极性图像并联地实现。

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