文献速递青光眼

卷积神经网络在房角照相中专家级检测房角关闭:中美眼病研究

Glaucoma Expert-Level Detection of Angle Closure in Goniophotographs With Convolutional Neural Networks: The Chinese American Eye Study.
PubMed 文献 · Am J Ophthalmol · 2021-02-09

本研究基于中美眼病研究,利用ResNet-50架构的卷积神经网络(CNN)分类器,在EyeCam房角照相中检测房角关闭(定义为无法视见色素性小梁网)。CNN在独立测试集上基于单一专家标签的AUC为0.969,基于共识标签的AUC为0.952,与共识标签的一致性(κ=0.746)超过所有非参考人类评分者(κ=0.578-0.702)。结论认为CNN可有效检测房角关闭,性能与经验丰富的青光眼专家相当。

要点

  • CNN分类器基于29,706张开放和2,929张关闭房角图像训练,独立测试集含600张开放和400张关闭图像。
  • CNN基于单一专家标签的AUC=0.969,基于共识标签的AUC=0.952,表现优异。
  • CNN与共识标签的一致性(κ=0.746)超过所有非参考人类评分者(κ=0.578-0.702)。

核心结论

  • CNN分类器能有效检测房角照相中的房角关闭,性能与经验丰富的青光眼专家相当。
  • 该方法为远程检测原发性房角关闭青光眼高危患者提供了自动化手段。

研究设计与样本

  • 回顾性横断面研究,受试者来自中美眼病研究,接受EyeCam四象限房角照相。
  • 基于ResNet-50架构的CNN分类器以单一经验丰富青光眼专家的参考标签训练,用于检测房角关闭(无法视见色素性小梁网)。
  • CNN性能在独立测试集上评估,参考标签为单一专家或3名青光眼专家共识,并与9名不同临床经验的人类评分者比较。

主要发现

  • CNN训练使用29,706张开放和2,929张关闭房角图像,独立测试集含600张开放和400张关闭图像。
  • CNN基于单一评分者标签的AUC=0.969,基于共识标签的AUC=0.952。
  • CNN与共识标签的一致性κ=0.746,超过所有非参考人类评分者(κ=0.578-0.702)。
  • 人类评分者与共识标签的一致性随临床经验提高(P=0.03)。

关键数值与推荐

  • 房角关闭定义为无法视见色素性小梁网。
  • CNN基于单一专家标签的AUC=0.969,基于共识标签的AUC=0.952。
  • CNN与共识标签的κ=0.746,非参考人类评分者κ=0.578-0.702。

临床怎么用

  • CNN可辅助远程筛查房角关闭,支持原发性房角关闭青光眼高危患者的自动化检测。
  • 在临床应用中,CNN检测性能与经验丰富的青光眼专家相当,可作为辅助诊断工具。

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)。

原文

PURPOSE: To compare the performance of a novel convolutional neural network (CNN) classifier and human graders in detecting angle closure in EyeCam (Clarity Medical Systems, Pleasanton, California, USA) goniophotographs. DESIGN: Retrospective cross-sectional study. METHODS: Subjects from the Chinese American Eye Study underwent EyeCam goniophotography in 4 angle quadrants. A CNN classifier based on the ResNet-50 architecture was trained to detect angle closure, defined as inability to visualize the pigmented trabecular meshwork, using reference labels by a single experienced glaucoma specialist. The performance of the CNN classifier was assessed using an independent test dataset and reference labels by the single glaucoma specialist or a panel of 3 glaucoma specialists. This performance was compared to that of 9 human graders with a range of clinical experience. Outcome measures included area under the receiver operating characteristic curve (AUC) metrics and Cohen kappa coefficients in the binary classification of open or closed angle. RESULTS: The CNN classifier was developed using 29,706 open and 2,929 closed angle images. The independent test dataset was composed of 600 open and 400 closed angle images. The CNN classifier achieved excellent performance based on single-grader (AUC = 0.969) and consensus (AUC = 0.952) labels. The agreement between the CNN classifier and consensus labels (κ = 0.746) surpassed that of all non-reference human graders (κ = 0.578-0.702). Human grader agreement with consensus labels improved with clinical experience (P = 0.03). CONCLUSION: A CNN classifier can effectively detect angle closure in goniophotographs with performance comparable to that of an experienced glaucoma specialist. This provides an automated method to support remote detection of patients at risk for primary angle closure glaucoma.

来源:Am J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Chiang M, Guth D, Pardeshi AA, et al. Glaucoma Expert-Level Detection of Angle Closure in Goniophotographs With Convolutional Neural Networks: The Chinese American Eye Study. Am J Ophthalmol. 2021. PMID: 33577791. doi:10.1016/j.ajo.2021.02.004

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。