文献速递腹部技术与安全CT

基于肝脏对比剂增强CT图像的深度学习系统用于肝纤维化分期:开发与验证

Development and Validation of a Deep Learning System for Staging Liver Fibrosis by Using Contrast Agent-enhanced CT Images in the Liver.
PubMed 文献 · Radiology · 2018-09-04

本研究开发并验证了基于门静脉期CT图像的深度学习系统用于肝纤维化分期,开发集纳入7461例病理确诊肝纤维化患者,独立测试集891例。测试集中分期准确率79.4%,诊断显著纤维化(F2-4)、进展期纤维化(F3-4)和肝硬变(F4)的AUROC分别为0.96、0.97和0.95;该系统(Obuchowski指数0.94)优于放射科医师判读、APRI和FIB-4(Obuchowski指数范围0.71-0.81,P < .001)。

要点

  • 基于门静脉期CT的深度学习系统对肝纤维化分期准确率达79.4%,F2-4、F3-4、F4的AUROC分别为0.96、0.97、0.95。
  • 该系统分期性能(Obuchowski指数0.94)优于放射科医师判读、APRI和FIB-4(0.71-0.81,P < .001)。
  • 病理纤维化分期是影响分期准确率的唯一显著因素(F1和F2分别与F4相比,P = .016和.013),病因和CT技术不影响。

核心结论

  • 深度学习系统可利用CT图像对肝纤维化进行准确分期。

研究设计与样本

  • 开发并验证深度学习系统用于CT肝纤维化分期的研究,开发数据集纳入7461例病理确诊肝纤维化患者的门静脉期CT图像。
  • 在891例患者的独立测试数据集中评估诊断性能,并在421例患者子集中与放射科医师判读、APRI和FIB-4比较。
  • 采用逻辑回归分析评估患者特征和CT技术对分期准确率的影响,采用AUROC和Obuchowski指数评估诊断性能。

诊断标准与关键数值

  • 测试数据集中深度学习系统分期准确率为79.4%(707/891)。
  • 诊断显著纤维化(F2-4)的AUROC为0.96,诊断进展期纤维化(F3-4)的AUROC为0.97,诊断肝硬变(F4)的AUROC为0.95。
  • 深度学习系统的Obuchowski指数为0.94,放射科医师判读、APRI和FIB-4的Obuchowski指数范围为0.71-0.81(P < .001)。
  • 多变量分析中,病理纤维化分期是影响分期准确率的唯一显著因素(F1和F2分别与F4相比,P = .016和.013),肝病病因和CT技术无显著影响。

临床应用与阅片要点

  • 深度学习系统可基于门静脉期CT图像对肝纤维化进行分期,其性能优于放射科医师判读、APRI和FIB-4。
  • 病理纤维化分期可能影响深度学习系统分期准确率,F1和F2与F4相比差异有统计学意义(P = .016和.013),阅片时需结合病理分期理解系统输出。

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

Purpose To develop and validate a deep learning system (DLS) for staging liver fibrosis by using CT images in the liver. Materials and Methods DLS for CT-based staging of liver fibrosis was created by using a development data set that included portal venous phase CT images in 7461 patients with pathologically confirmed liver fibrosis. The diagnostic performance of the DLS was evaluated in separate test data sets for 891 patients. The influence of patient characteristics and CT techniques on the staging accuracy of the DLS was evaluated by logistic regression analysis. In a subset of 421 patients, the diagnostic performance of the DLS was compared with that of the radiologist's assessment, aminotransferase-to-platelet ratio index (APRI), and fibrosis-4 index by using the area under the receiver operating characteristic curve (AUROC) and Obuchowski index. Results In the test data sets, the DLS had a staging accuracy of 79.4% (707 of 891) and an AUROC of 0.96, 0.97, and 0.95 for diagnosing significant fibrosis (F2-4), advanced fibrosis (F3-4), and cirrhosis (F4), respectively. At multivariable analysis, only pathologic fibrosis stage significantly affected the staging accuracy of the DLS (P = .016 and .013 for F1 and F2, respectively, compared with F4), whereas etiology of liver disease and CT technique did not. The DLS (Obuchowski index, 0.94) outperformed the radiologist's interpretation, APRI, and fibrosis-4 index (Obuchowski index range, 0.71-0.81; P ˂ .001) for staging liver fibrosis. Conclusion The deep learning system allows for accurate staging of liver fibrosis by using CT images. © RSNA, 2018 Online supplemental material is available for this article.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Choi KJ, Jang JK, Lee SS, et al. Development and Validation of a Deep Learning System for Staging Liver Fibrosis by Using Contrast Agent-enhanced CT Images in the Liver. Radiology. 2018. PMID: 30179104. doi:10.1148/radiol.2018180763

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。