文献速递腹部US

应用卷积神经网络与定量超声诊断脂肪肝

Use of a convolutional neural network and quantitative ultrasound for diagnosis of fatty liver.
PubMed 文献 · Ultrasound Med Biol · 2020-12-25

研究用定量超声(QUS)和1维卷积神经网络(CNN)对高脂饮食和/或定期注射CCl4诱导肝病的兔进行脂肪肝分类,以Folch法脂质百分比和羟脯氨酸浓度作为参照。QUS参数可区分肝脂质水平高于或低于5%,但对纤维化不敏感;CNN直接分析原始射频信号,在测试数据上区分低/高脂质水平的准确率74%高于QUS参数联合支持向量机的59%。

要点

  • CNN直接分析原始射频超声信号,无需外部参考扫描即可分类肝脂质水平高于或低于5%。
  • 在测试数据上,CNN区分低与高脂质肝的准确率为74%,高于QUS参数联合支持向量机的59%。
  • QUS参数可区分肝脂质水平高于或低于5%,但对纤维化不敏感。

核心结论

  • CNN对脂肪肝状态的预测准确率远高于QUS参数联合支持向量机,且不需要外部参考扫描。
  • CNN未提供组织特性(如介质衰减或散射体特性)的物理解释。

研究设计与样本

  • 研究类型为动物实验,使用高脂饮食和/或定期注射CCl4诱导肝病的兔模型。
  • 以Folch法估计的肝脏脂质百分比和羟脯氨酸浓度量化纤维化作为肝脏状态参照标准。
  • 使用SonixOne扫描仪和L9-4/38线阵探头进行活体超声扫描。

诊断标准与关键数值

  • 以肝脏脂质百分比5%为阈值,将肝分类为高于或低于5%脂肪水平。
  • 在测试数据上,CNN区分低与高脂质肝水平的准确率为74%,QUS参数联合支持向量机为59%。

局限性

  • CNN未提供组织特性(如介质衰减或散射体特性)的物理解释。

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

Quantitative ultrasound (QUS) was used to classify rabbits that were induced to have liver disease by placing them on a fatty diet for a defined duration and/or periodically injecting them with CCl4. The ground truth of the liver state was based on lipid liver percents estimated via the Folch assay and hydroxyproline concentration to quantify fibrosis. Rabbits were scanned ultrasonically in vivo using a SonixOne scanner and an L9-4/38 linear array. Liver fat percentage was classified based on the ultrasonic backscattered radiofrequency (RF) signals from the livers using either QUS or a 1-D convolutional neural network (CNN). Use of QUS parameters with linear regression and canonical correlation analysis demonstrated that the QUS parameters could differentiate between livers with lipid levels above or below 5%. However, the QUS parameters were not sensitive to fibrosis. The CNN was implemented by analyzing raw RF ultrasound signals without using separate reference data. The CNN outputs the classification of liver as either above or below a threshold of 5% fat level in the liver. The CNN outperformed the classification utilizing the QUS parameters combined with a support vector machine in differentiating between low and high lipid liver levels (i.e., accuracies of 74% versus 59% on the testing data). Therefore, although the CNN did not provide a physical interpretation of the tissue properties (e.g., attenuation of the medium or scatterer properties) the CNN had much higher accuracy in predicting fatty liver state and did not require an external reference scan.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Nguyen TN, Podkowa AS, Park TH, et al. Use of a convolutional neural network and quantitative ultrasound for diagnosis of fatty liver. Ultrasound Med Biol. 2020. PMID: 33358553. doi:10.1016/j.ultrasmedbio.2020.10.025

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。