Purpose

To assess the performance of a deep learning algorithm for detecting referable glaucomatous optic neuropathy (GON) based on color fundus photographs.

Design

A deep learning system for the classification of GON was developed for automated classification of GON on color fundus photographs.

Participants

We retrospectively included 48 116 fundus photographs for the development and validation of a deep learning algorithm.

Methods

This study recruited 21 trained ophthalmologists to classify the photographs. Referable GON was defined as vertical cup-to-disc ratio of 0.7 or more and other typical changes of GON. The reference standard was made until 3 graders achieved agreement. A separate validation dataset of 8000 fully gradable fundus photographs was used to assess the performance of this algorithm.

Main Outcome Measures

The area under receiver operator characteristic curve (AUC) with sensitivity and specificity was applied to evaluate the efficacy of the deep learning algorithm detecting referable GON.

Results

In the validation dataset, this deep learning system achieved an AUC of 0.986 with sensitivity of 95.6% and specificity of 92.0%. The most common reasons for false-negative grading (n = 87) were GON with coexisting eye conditions (n = 44 [50.6%]), including pathologic or high myopia (n = 37 [42.6%]), diabetic retinopathy (n = 4 [4.6%]), and age-related macular degeneration (n = 3 [3.4%]). The leading reason for false-positive results (n = 480) was having other eye conditions (n = 458 [95.4%]), mainly including physiologic cupping (n = 267 [55.6%]). Misclassification as false-positive results amidst a normal-appearing fundus occurred in only 22 eyes (4.6%).

Conclusions

A deep learning system can detect referable GON with high sensitivity and specificity. Coexistence of high or pathologic myopia is the most common cause resulting in false-negative results. Physiologic cupping and pathologic myopia were the most common reasons for false-positive results.

中文翻译：

---

基于彩色眼底照片的深度学习系统检测青光眼视神经病变的功效

目的

评估用于基于彩色眼底照片检测可参考的青光眼性视神经病变（GON）的深度学习算法的性能。

设计

开发了用于GON分类的深度学习系统，用于在彩色眼底照片上对GON进行自动分类。

参加者

我们回顾性地纳入了48116张眼底照片，用于开发和验证深度学习算法。

方法

这项研究招募了21位训练有素的眼科医生对照片进行分类。合格的GON定义为垂直杯杯比为0.7或更高，以及GON的其他典型变化。制定参考标准，直到3年级学生达成协议。单独的8000个完全可分级眼底照片验证数据集用于评估该算法的性能。

主要观察指标

接收器操作员特征曲线（AUC）下具有灵敏度和特异性的区域用于评估深度学习算法检测可参考GON的功效。

结果

在验证数据集中，该深度学习系统的AUC为0.986，灵敏度为95.6％，特异性为92.0％。假阴性分级（n = 87）的最常见原因是GON与并存的眼部疾病（n = 44 [50.6％]），包括病理性或高度近视（n = 37 [42.6％]），糖尿病性视网膜病变（n = 4 [4.6％]）和与年龄有关的黄斑变性（n = 3 [3.4％]）。假阳性结果（n = 480）的主要原因是患有其他眼部疾病（n = 458 [95.4％]），主要包括生理性拔罐（n = 267 [55.6％]）。在眼底正常出现的情况下，错误分类为假阳性结果的仅22只眼（4.6％）。

结论

深度学习系统可以高灵敏度和高特异性地检测可参考的GON。高度近视眼或病理性近视眼共存是导致假阴性结果的最常见原因。生理性拔罐和病理性近视是导致假阳性结果的最常见原因。