文献速递腹部MR

自动化卷积神经网络分析与手动分析在非酒精性脂肪性肝病MR弹性成像中的方法间一致性与纤维化分期判别性能比较

Automated CNN-Based Analysis Versus Manual Analysis for MR Elastography in Nonalcoholic Fatty Liver Disease: Intermethod Agreement and Fibrosis Stage Discriminative Performance.
PubMed 文献 · AJR Am J Roentgenol · 2022-02-02

本研究开发了基于卷积神经网络(CNN)的肝脏MR弹性成像自动分析方法,在675例多中心临床试验参与者中与手动ROI分析比较一致性(ICC 0.98,95%CI 0.97-0.98),并在81例单中心临床患者中外部验证(ICC 0.99,95%CI 0.98-0.99);两种方法对二分组织学纤维化分期的AUC范围为CNN 0.89-0.93 vs 手动0.87-0.93(p=.23-.75),CNN方法可行且可能减少对专家图像分析师的依赖。

要点

  • 自动CNN与手动ROI肝脏MRE硬度测量一致性极高,临床试验组ICC 0.98(95%CI 0.97-0.98),临床患者组ICC 0.99(95%CI 0.98-0.99)。
  • 对二分组织学纤维化分期,CNN分析AUC 0.89-0.93,手动ROI分析AUC 0.87-0.93,两者差异无统计学意义(p=.23-.75)。
  • CNN方法在不同MRI系统和场强下与手动分析一致,外部测试判别性能优良,可能减少对专家图像分析师的依赖。

核心结论

  • 自动CNN方法的肝脏MRE硬度测量在不同MRI系统和场强下与手动ROI分析高度一致,外部测试中对组织学确定的二分纤维化分期具有优良判别性能。

研究设计与样本

  • 回顾性横断面研究,675例来自五项非酒精性脂肪性肝炎多中心国际临床试验的参与者(28个成像中心,使用不同MRI系统和场强)用于算法开发及自动CNN与手动ROI分析一致性的内部测试;81例(52女,29男,平均年龄54岁)在单中心因临床目的行3-T MRE和肝活检的患者用于两种方法一致性的外部测试及纤维化分期判别性能评估,以组织学为参考标准。

诊断标准与关键数值

  • 一致性用组内相关系数(ICC)评估,自举法计算95%CI;临床试验参与者中CNN与手动ROI硬度均值范围分别为3.21-3.34 kPa,ICC 0.98(95%CI 0.97-0.98);临床患者中分别为3.21-3.30 kPa,ICC 0.99(95%CI 0.98-0.99);二分组织学纤维化分期分类AUC:CNN 0.89-0.93,手动ROI 0.87-0.93(p=.23-.75)。

临床应用与阅片要点

  • 原文未据此给出推荐。

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. Histologic fibrosis stage is the most important prognostic factor in chronic liver disease. MR elastography (MRE) is the most accurate noninvasive method for detecting and staging liver fibrosis. Although accurate, manual ROI-based MRE analysis is complex, time-consuming, requires specialized readers, and is prone to methodologic variability and suboptimal interreader agreement. OBJECTIVE. The purpose of this study was to develop an automated convolutional neural network (CNN)-based method for liver MRE analysis, evaluate its agreement with manual ROI-based analysis, and assess its performance for classifying dichotomized fibrosis stages using histology as the reference standard. METHODS. In this retrospective cross-sectional study, 675 participants who underwent MRE using different MRI systems and field strengths at 28 imaging sites from five multicenter international clinical trials of nonalcoholic steatohepatitis were included for algorithm development and internal testing of agreement between automated CNN-based and manual ROI-based analyses. Eighty-one patients (52 women, 29 men; mean age, 54 years) who underwent MRE using a single 3-T system and liver biopsy for clinical purposes at a single institution were included for external testing of agreement between the two analysis methods and assessment of fibrosis stage discriminative performance. Agreement was evaluated using intraclass correlation coefficients (ICCs). Bootstrapping was used to compute 95% CIs. Discriminative performance of each method for dichotomized histologic fibrosis stage was evaluated by AUC and compared using bootstrapping. RESULTS. Mean CNN- and manual ROI-based stiffness measurements ranged from 3.21 to 3.34 kPa in trial participants and from 3.21 to 3.30 kPa in clinical patients. ICC for CNN- and manual ROI-based measurements was 0.98 (95% CI, 0.97-0.98) in trial participants and 0.99 (95% CI, 0.98-0.99) in clinical patients. AUCs for classification of dichotomized fibrosis stage ranged from 0.89 to 0.93 for CNN-based analysis and 0.87 to 0.93 for manual ROI-based analysis (p = .23-.75). CONCLUSION. Stiffness measurements using the automated CNN-based method agreed strongly with manual ROI-based analysis across MRI systems and field strengths, with excellent discriminative performance for histology-determined dichotomized fibrosis stages in external testing. CLINICAL IMPACT. Given the high incidence of chronic liver disease worldwide, it is important that noninvasive tools to assess fibrosis are applied reliably across different settings. CNN-based analysis is feasible and may reduce reliance on expert image analysts.

来源:AJR Am J Roentgenol,查看原文。版权归原作者所有。

引用

  1. Cunha, Delgado, Middleton, et al. Automated CNN-Based Analysis Versus Manual Analysis for MR Elastography in Nonalcoholic Fatty Liver Disease: Intermethod Agreement and Fibrosis Stage Discriminative Performance. AJR Am J Roentgenol. 2022. PMID: 35107306. doi:10.2214/AJR.21.27135

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。