Purpose: Optic disc (OD) and cup (OC) segmentation are fundamental for fundus image analysis. Manual annotation is time consuming, expensive, and highly subjective, while an automated system is invaluable to the medical community. The aim of this study is to develop a deep learning system to segment OD and OC in fundus photos, and evaluate how the algorithm compares against manual annotations. Methods: A total of 1200 fundus photos with 120 glaucoma cases were collected. The OD and OC annotations were labeled by seven licensed ophthalmologists, and glaucoma diagnoses were based on comprehensive evaluations of the subject medical records. A deep learning system for OD and OC segmentation was developed. The performances of segmentation and glaucoma discriminating based on the cup-to-disc ratio (CDR) of automated model were compared against the manual annotations. Results: The algorithm achieved an OD dice of 0.938 (95% confidence interval (CI), 0.934-0.941), OC dice of 0.801 (95% CI, 0.793-0.809), and CDR mean absolute error (MAE) of 0.077 (95% CI, 0.073-0.082). For glaucoma discriminating based on CDR calculations, the algorithm obtained an area under receiver operator characteristic curve (AUC) of 0.948 (95% CI, 0.920-0.973), with a sensitivity of 0.850 (95% CI, 0.794-0.923) and specificity of 0.853 (95% CI, 0.798-0.918). Conclusions: We demonstrated the potential of the deep learning system to assist ophthalmologists in analyzing OD and OC segmentation and discriminating glaucoma from non-glaucoma subjects based on CDR calculations. Translational Relevance: We investigate the segmentation of OD and OC by deep learning system compared against the manual annotations.

中文翻译：

---

眼底照片中视盘和视杯分割的深度学习与手动注释的回顾性比较

目的：视盘（OD）和杯（OC）分割是眼底图像分析的基础。手动注释非常耗时，昂贵且主观性很高，而自动化系统对医学界来说却是无价之宝。这项研究的目的是开发一种深度学习系统，以对眼底照片中的OD和OC进行分割，并评估该算法如何与手动注释进行比较。方法：收集120例青光眼患者的1200张眼底照片。OD和OC注释由七名执业的眼科医生标记，青光眼的诊断是基于对病历的综合评估。开发了用于OD和OC细分的深度学习系统。将基于自动模型的杯碟比（CDR）进行的分割和青光眼识别性能与手动注解进行了比较。结果：该算法的OD骰子为0.938（95％置信区间（CI），0.934-0.941），OC骰子为0.801（95％CI，0.793-0.809），CDR平均绝对误差（MAE）为0.077（95） ％CI，0.073-0.082）。对于基于CDR计算的青光眼鉴别，该算法获得的接收者操作员特征曲线下面积（AUC）为0.948（95％CI，0.920-0.973），灵敏度为0.850（95％CI，0.794-0.923），特异性为0.853（95％CI，0.798-0.918）。结论：我们证明了深度学习系统有助于眼科医生分析OD和OC分割并根据CDR计算将青光眼与非青光眼患者区分开的潜力。