文献速递青光眼

基于OCT的深度学习分类器在社区与医院环境中检测房角镜检查房角关闭的泛化性与性能

Generalisability and performance of an OCT-based deep learning classifier for community-based and hospital-based detection of gonioscopic angle closure.
PubMed 文献 · Br J Ophthalmol · 2021-10-20

该研究评估了基于前段OCT(AS-OCT)图像的卷积神经网络分类器在三个独立人群中检测房角镜检查房角关闭的泛化性与性能。分类器在CHES、新加坡和USC队列中AUC分别为0.917、0.894和0.922,与人类检查者间一致性相近,表明其在不同人群中性能一致。

要点

  • 分类器在三个独立队列中AUC均高于0.89,性能稳定。
  • 分类器与人类检查者的一致性(κ=0.700和0.704)接近人类检查者间一致性(κ=0.693)。
  • 该自动化方法可辅助眼科医生评估不同人群的房角状态。

核心结论

  • 基于OCT的深度学习分类器在三个独立患者人群中检测房角镜检查房角关闭表现出 consistent 性能。
  • 该自动化方法可辅助眼科医生评估不同人群的房角状态。

研究设计与样本

  • 使用中美眼科研究(CHES)数据开发的卷积神经网络(CNN)模型,在AS-OCT图像中检测房角镜检查房角关闭,参考标准为培训有素眼科医生的房角镜分级。
  • 独立测试数据来自基于人群的CHES、新加坡社区诊所和南加州大学(USC)医院诊所。
  • 使用受试者工作特征曲线和曲线下面积(AUC)评估分类器性能,使用Cohen kappa系数计算USC队列中分类器与两名人类检查者的一致性。

主要发现

  • 分类器在CHES(AUC=0.917)、新加坡(AUC=0.894)和USC(AUC=0.922)队列中性能相似。
  • 标准化各队列房角镜分级分布后产生相似AUC指标(范围0.890-0.932)。
  • CNN分类器与两名人类检查者的一致性(κ=0.700和0.704)接近USC队列中人类检查者间一致性(κ=0.693)。

关键数值与推荐

  • 分类器在CHES队列AUC=0.917,新加坡队列AUC=0.894,USC队列AUC=0.922。
  • 标准化房角镜分级分布后AUC范围为0.890-0.932。
  • CNN与两名人类检查者一致性κ=0.700和0.704,人类检查者间一致性κ=0.693。

临床怎么用

  • 该自动化方法可辅助眼科医生在不同患者人群中评估房角状态。
  • 基于AS-OCT图像的深度学习分类器可用于检测房角镜检查房角关闭。

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 assess the generalisability and performance of a deep learning classifier for automated detection of gonioscopic angle closure in anterior segment optical coherence tomography (AS-OCT) images. METHODS: A convolutional neural network (CNN) model developed using data from the Chinese American Eye Study (CHES) was used to detect gonioscopic angle closure in AS-OCT images with reference gonioscopy grades provided by trained ophthalmologists. Independent test data were derived from the population-based CHES, a community-based clinic in Singapore, and a hospital-based clinic at the University of Southern California (USC). Classifier performance was evaluated with receiver operating characteristic curve and area under the receiver operating characteristic curve (AUC) metrics. Interexaminer agreement between the classifier and two human examiners at USC was calculated using Cohen's kappa coefficients. RESULTS: The classifier was tested using 640 images (311 open and 329 closed) from 127 Chinese Americans, 10 165 images (9595 open and 570 closed) from 1318 predominantly Chinese Singaporeans and 300 images (234 open and 66 closed) from 40 multiethnic USC patients. The classifier achieved similar performance in the CHES (AUC=0.917), Singapore (AUC=0.894) and USC (AUC=0.922) cohorts. Standardising the distribution of gonioscopy grades across cohorts produced similar AUC metrics (range 0.890-0.932). The agreement between the CNN classifier and two human examiners (Ҡ=0.700 and 0.704) approximated interexaminer agreement (Ҡ=0.693) in the USC cohort. CONCLUSION: An OCT-based deep learning classifier demonstrated consistent performance detecting gonioscopic angle closure across three independent patient populations. This automated method could aid ophthalmologists in the assessment of angle status in diverse patient populations.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Randhawa J, Chiang M, Porporato N, et al. Generalisability and performance of an OCT-based deep learning classifier for community-based and hospital-based detection of gonioscopic angle closure. Br J Ophthalmol. 2021. PMID: 34670749. doi:10.1136/bjophthalmol-2021-319470

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。