文献速递乳腺US

定量超声与机器学习在BI-RADS 4-5类实性乳腺病灶评估中的附加价值

Added Value of Quantitative Ultrasound and Machine Learning in BI-RADS 4-5 Assessment of Solid Breast Lesions.
PubMed 文献 · Ultrasound Med Biol · 2019-11-27

研究纳入103例BI-RADS 4-5类可疑实性乳腺病灶患者,在活检前采集剪切波弹性成像及超声电影序列,提取剪切波弹性、统计与频谱背散射特征共13项并结合BI-RADS分类,用随机森林构建ROC曲线。加入BI-RADS分类可提升其他特征的分类性能,最佳组合的ROC曲线下面积为0.97,在98%敏感度下特异度为75.9%。

要点

  • BI-RADS 4-5类实性乳腺病灶中,加入BI-RADS分类可提升剪切波弹性、统计与频谱背散射特征的分类性能。
  • 随机森林最佳组合的AUC为0.97,在98%敏感度下特异度为75.9%。
  • 特征提取涵盖病灶内、病灶上方及病灶下方三个区域的同态K分布参数图。

核心结论

  • 加入BI-RADS分类可改善其他特征的分类性能,随机森林最佳组合的AUC为0.97,在98%敏感度下特异度为75.9%。

研究设计与样本

  • 本研究纳入103例女性患者的103个可疑实性乳腺病灶(BI-RADS 4-5类),活检前额外采集剪切波弹性图像及超声电影序列。
  • 勾画病灶轮廓后在病灶内、病灶上方及病灶下方三个区域计算同态K分布参数图,并提取最大弹性及总衰减系数。
  • 采用随机森林对基于剪切波弹性、组织统计与频谱背散射特性及BI-RADS分类的13项特征的不同组合生成ROC曲线。

诊断标准与关键数值

  • 随机森林最佳组合的ROC曲线下面积为0.97,在98%敏感度下特异度为75.9%。

临床应用与阅片要点

  • 对BI-RADS 4-5类实性乳腺病灶,除常规BI-RADS分类外可结合剪切波弹性、统计与频谱背散射定量特征进行随机森林分类评估。
  • 特征提取需覆盖病灶内、病灶上方及病灶下方三个区域,并纳入最大弹性与总衰减系数。

局限性

  • 原文未报告局限性。

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

The purpose of this study was to evaluate various combinations of 13 features based on shear wave elasticity (SWE), statistical and spectral backscatter properties of tissues, along with the Breast Imaging Reporting and Data System (BI-RADS), for classification of solid breast lesions at ultrasonography by means of random forests. One hundred and three women with 103 suspicious solid breast lesions (BI-RADS categories 4-5) were enrolled. Before biopsy, additional SWE images and a cine sequence of ultrasound images were obtained. The contours of lesions were delineated, and parametric maps of the homodyned-K distribution were computed on three regions: intra-tumoral, supra-tumoral and infra-tumoral zones. Maximum elasticity and total attenuation coefficient were also extracted. Random forests yielded receiver operating characteristic (ROC) curves for various combinations of features. Adding BI-RADS category improved the classification performance of other features. The best result was an area under the ROC curve of 0.97, with 75.9% specificity at 98% sensitivity.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Destrempes F, Trop I, Allard L, et al. Added Value of Quantitative Ultrasound and Machine Learning in BI-RADS 4-5 Assessment of Solid Breast Lesions. Ultrasound Med Biol. 2019. PMID: 31785840. doi:10.1016/j.ultrasmedbio.2019.10.024

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。