文献速递外周血管神经技术与安全US

颈动脉超声图像中内膜-中膜的智能分割与斑块识别

Intelligent Segmentation of Intima-Media and Plaque Recognition in Carotid Artery Ultrasound Images.
PubMed 文献 · Ultrasound Med Biol · 2021-12-04

本文提出一种可自动分割颈动脉超声图像中内膜-中膜的二维V-Net模型,并描述了一种自动识别斑块受累区域的斑块识别算法。性能测试显示内膜-中膜分割的平均交并比(管腔-内膜边界/中膜-外膜边界)为0.752/0.813,斑块识别的平均交并比为0.785;作者认为该结果满足临床应用阈值,所提模型可辅助医生做出更高效、更准确的诊断。

要点

  • 内膜-中膜分割平均交并比:管腔-内膜边界0.752、中膜-外膜边界0.813。
  • 内膜-中膜分割平均像素准确率:管腔-内膜边界0.813、中膜-外膜边界0.885。
  • 斑块识别平均交并比0.785,平均像素准确率0.825。

核心结论

  • 所提二维V-Net模型与斑块识别算法的性能测试结果满足临床应用阈值,提示该模型可辅助医生进行更高效、更准确的诊断。

研究设计与样本

  • 研究提出一种可自动分割颈动脉超声图像中内膜-中膜的二维V-Net模型,并描述一种自动识别斑块受累区域的斑块识别算法;性能测试以管腔-内膜边界和中膜-外膜边界为对象评估分割与识别效果。

关键影像表现/征象

  • 内膜-中膜分割平均交并比:管腔-内膜边界0.752、中膜-外膜边界0.813。
  • 内膜-中膜分割平均像素准确率:管腔-内膜边界0.813、中膜-外膜边界0.885。
  • 内膜-中膜分割平均Dice损失:管腔-内膜边界0.858、中膜-外膜边界0.897。
  • 斑块识别平均交并比0.785、平均像素准确率0.825、平均Dice损失0.866。

诊断标准与关键数值

  • 内膜-中膜分割交并比:管腔-内膜边界0.752、中膜-外膜边界0.813。
  • 内膜-中膜分割像素准确率:管腔-内膜边界0.813、中膜-外膜边界0.885。
  • 内膜-中膜分割Dice损失:管腔-内膜边界0.858、中膜-外膜边界0.897。
  • 斑块识别交并比0.785、像素准确率0.825、Dice损失0.866。

临床应用与阅片要点

  • 模型可自动分割颈动脉超声图像中的内膜-中膜并识别斑块受累区域,结果满足临床应用阈值,可辅助医生进行更高效、更准确的诊断。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Ultrasound imaging has been established as an effective method for measuring the thickness of the intima-media, the thickening of which, along with carotid plaque, is an indicator of cerebrovascular diseases. Here, a 2-D V-Net model that can automatically segment the intima-media in carotid artery ultrasound images is proposed. Moreover, a plaque recognition algorithm that automatically identifies plaque-affected areas is described. Performance tests to determine the average accuracy of the intima-media segmentation yielded the following results (expressed as lumen-intima boundary/media-adventitia boundary): intersection over union (IOU) of 0.752/0.813, pixel accuracy of 0.813/0.885 and Dice loss of 0.858/0.897. Finally, average IOU of 0.785, pixel accuracy of 0.825 and Dice loss of 0.866 were obtained for plaque recognition. These results satisfy the threshold for clinical application and indicate that the proposed model can assist doctors in making more efficient and accurate diagnoses.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Lin, Huang, Chen, et al. Intelligent Segmentation of Intima-Media and Plaque Recognition in Carotid Artery Ultrasound Images. Ultrasound Med Biol. 2021. PMID: 34872788. doi:10.1016/j.ultrasmedbio.2021.11.001

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。