基于眼前节 OCT 图像的自动检测房角关闭的深度学习分类器。
Deep Learning Classifiers for Automated Detection of Gonioscopic Angle Closure Based on Anterior Segment OCT Images.
机构信息
Roski Eye Institute, Department of Ophthalmology, Keck School of Medicine at the University of Southern California, Los Angeles, California, USA.
Sol Price School of Public Policy, University of Southern California, Los Angeles, California, USA.
出版信息
Am J Ophthalmol. 2019 Dec;208:273-280. doi: 10.1016/j.ajo.2019.08.004. Epub 2019 Aug 22.
PURPOSE
To develop and test deep learning classifiers that detect gonioscopic angle closure and primary angle closure disease (PACD) based on fully automated analysis of anterior segment OCT (AS-OCT) images.
METHODS
Subjects were recruited as part of the Chinese-American Eye Study (CHES), a population-based study of Chinese Americans in Los Angeles, California, USA. Each subject underwent a complete ocular examination including gonioscopy and AS-OCT imaging in each quadrant of the anterior chamber angle (ACA). Deep learning methods were used to develop 3 competing multi-class convolutional neural network (CNN) classifiers for modified Shaffer grades 0, 1, 2, 3, and 4. Binary probabilities for closed (grades 0 and 1) and open (grades 2, 3, and 4) angles were calculated by summing over the corresponding grades. Classifier performance was evaluated by 5-fold cross-validation and on an independent test dataset. Outcome measures included area under the receiver operating characteristic curve (AUC) for detecting gonioscopic angle closure and PACD, defined as either 2 or 3 quadrants of gonioscopic angle closure per eye.
RESULTS
A total of 4036 AS-OCT images with corresponding gonioscopy grades (1943 open, 2093 closed) were obtained from 791 CHES subjects. Three competing CNN classifiers were developed with a cross-validation dataset of 3396 images (1632 open, 1764 closed) from 664 subjects. The remaining 640 images (311 open, 329 closed) from 127 subjects were segregated into a test dataset. The best-performing classifier was developed by applying transfer learning to the ResNet-18 architecture. For detecting gonioscopic angle closure, this classifier achieved an AUC of 0.933 (95% confidence interval, 0.925-0.941) on the cross-validation dataset and 0.928 on the test dataset. For detecting PACD based on 2- and 3-quadrant definitions, the ResNet-18 classifier achieved AUCs of 0.964 and 0.952, respectively, on the test dataset.
CONCLUSION
Deep learning classifiers effectively detect gonioscopic angle closure and PACD based on automated analysis of AS-OCT images. These methods could be used to automate clinical evaluations of the ACA and improve access to eye care in high-risk populations.
目的
开发并测试基于前节 OCT（AS-OCT）图像全自动分析的青光眼和原发性闭角型青光眼（PACD）的深度学习分类器。
方法
研究对象为美国加利福尼亚州洛杉矶的中美眼病研究（CHES）的一部分，这是一项针对美籍华人的基于人群的研究。每位受试者均接受了全面的眼部检查，包括房角镜检查和前房角（ACA）每个象限的 AS-OCT 成像。使用深度学习方法开发了 3 种竞争的多类卷积神经网络（CNN）分类器，用于修改的 Shaffer 等级 0、1、2、3 和 4。通过对相应等级进行求和，计算出闭角（等级 0 和 1）和开角（等级 2、3 和 4）的二进制概率。通过 5 折交叉验证和独立测试数据集评估分类器性能。评估指标包括检测房角镜下闭角和 PACD 的受试者工作特征曲线（ROC）下面积（AUC），定义为每只眼 2 或 3 象限的房角镜下闭角。
结果
从 791 名 CHES 受试者中获得了 4036 张 AS-OCT 图像和相应的房角镜分级（1943 张开放，2093 张闭合）。使用来自 664 名受试者的 3396 张图像（1632 张开放，1764 张闭合）的交叉验证数据集开发了 3 种竞争的 CNN 分类器。来自 127 名受试者的 640 张图像（311 张开放，329 张闭合）被分离到测试数据集。应用于 ResNet-18 架构的迁移学习开发了性能最佳的分类器。在交叉验证数据集上，该分类器检测房角镜下闭角的 AUC 为 0.933（95%置信区间，0.925-0.941），在测试数据集上为 0.928。基于 2 象限和 3 象限定义，ResNet-18 分类器在测试数据集上的 AUC 分别为 0.964 和 0.952。
结论
基于 AS-OCT 图像的自动分析，深度学习分类器可有效检测房角镜下闭角和 PACD。这些方法可用于自动评估 ACA，并改善高危人群的眼保健服务。
Zotero 插件