文献速递腹部技术与安全US

放射科医生与深度学习在超声分级肝脂肪变性中的比较

Comparison of Radiologists and Deep Learning for US Grading of Hepatic Steatosis.
PubMed 文献 · Radiology · 2023-01-01

这项回顾性研究纳入199例经活检证实的NAFLD患者及无肝脂肪变性的对照患者,比较6名放射科医生与深度学习模型在超声图像上对肝脂肪变性的分级一致性及诊断效能。在52例测试集上,医生间一致性为一般(κ 0.30–0.37),深度学习模型在S0 vs ≥S1的AUC为0.85(95%CI 0.83, 0.87),医生AUC为0.49–0.84;结论认为深度学习模型在检测和分级肝脂肪变性方面与人类读者表现相当。

要点

  • 深度学习模型在B型超声上检测肝脂肪变性(S0 vs ≥S1)的AUC为0.85,医生AUC范围0.49–0.84。
  • 放射科医生对肝脂肪变性分级的阅片者间一致性为一般(κ 0.30–0.37)。
  • 深度学习模型在S0/S1 vs S2/S3和≤S2 vs S3的AUC分别为0.73和0.67,与医生表现相当。

核心结论

  • 应用于B型超声图像的深度学习方法在检测和分级肝脂肪变性方面与人类读者表现相当。

研究设计与样本

  • 回顾性研究,纳入199例NAFLD患者及无肝脂肪变性的对照患者(平均年龄53岁±13[SD],101名男性),均于2010年9月至2019年10月期间接受腹部超声和同期肝活检;6名读者间隔2周对超声图像进行两次视觉分级;采用三种深度学习技术应用于B型超声图像对二分类脂肪变性等级进行分类;在独立测试集(n=52)上评估AUC。

诊断标准与关键数值

  • S0 vs S1或更高:放射科医生阅片者间一致性κ为0.34(95%CI 0.31, 0.37),AUC介于0.49和0.84之间;深度学习模型AUC为0.85(95%CI 0.83, 0.87)。
  • S0或S1 vs S2或S3:放射科医生阅片者间一致性κ为0.30(95%CI 0.27, 0.33),AUC介于0.57和0.76之间;深度学习模型AUC为0.73(95%CI 0.71, 0.75)。
  • S2或更低 vs S3:放射科医生阅片者间一致性κ为0.37(95%CI 0.33, 0.40),AUC介于0.52和0.81之间;深度学习模型AUC为0.67(95%CI 0.64, 0.69)。

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

Background Screening for nonalcoholic fatty liver disease (NAFLD) is suboptimal due to the subjective interpretation of US images. Purpose To evaluate the agreement and diagnostic performance of radiologists and a deep learning model in grading hepatic steatosis in NAFLD at US, with biopsy as the reference standard. Materials and Methods This retrospective study included patients with NAFLD and control patients without hepatic steatosis who underwent abdominal US and contemporaneous liver biopsy from September 2010 to October 2019. Six readers visually graded steatosis on US images twice, 2 weeks apart. Reader agreement was assessed with use of κ statistics. Three deep learning techniques applied to B-mode US images were used to classify dichotomized steatosis grades. Classification performance of human radiologists and the deep learning model for dichotomized steatosis grades (S0, S1, S2, and S3) was assessed with area under the receiver operating characteristic curve (AUC) on a separate test set. Results The study included 199 patients (mean age, 53 years ± 13 [SD]; 101 men). On the test set (n = 52), radiologists had fair interreader agreement (0.34 [95% CI: 0.31, 0.37]) for classifying steatosis grades S0 versus S1 or higher, while AUCs were between 0.49 and 0.84 for radiologists and 0.85 (95% CI: 0.83, 0.87) for the deep learning model. For S0 or S1 versus S2 or S3, radiologists had fair interreader agreement (0.30 [95% CI: 0.27, 0.33]), while AUCs were between 0.57 and 0.76 for radiologists and 0.73 (95% CI: 0.71, 0.75) for the deep learning model. For S2 or lower versus S3, radiologists had fair interreader agreement (0.37 [95% CI: 0.33, 0.40]), while AUCs were between 0.52 and 0.81 for radiologists and 0.67 (95% CI: 0.64, 0.69) for the deep learning model. Conclusion Deep learning approaches applied to B-mode US images provided comparable performance with human readers for detection and grading of hepatic steatosis. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Tuthill in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Vianna P, Calce SI, Boustros P, et al. Comparison of Radiologists and Deep Learning for US Grading of Hepatic Steatosis. Radiology. 2023. PMID: 37787678. doi:10.1148/radiol.230659

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。