Eye Research Center, The Five Senses Institute, Rassoul Akram Hospital, Iran University of Medical Sciences, Tehran, Iran.
Eye Research Center, Farabi Eye Hospital, Tehran University of Medical Sciences, Tehran, Iran.
Sci Rep. 2021 Jan 13;11(1):1031. doi: 10.1038/s41598-020-80058-x.
The purpose of this study was to introduce a new deep learning (DL) model for segmentation of the fovea avascular zone (FAZ) in en face optical coherence tomography angiography (OCTA) and compare the results with those of the device's built-in software and manual measurements in healthy subjects and diabetic patients. In this retrospective study, FAZ borders were delineated in the inner retinal slab of 3 × 3 enface OCTA images of 131 eyes of 88 diabetic patients and 32 eyes of 18 healthy subjects. To train a deep convolutional neural network (CNN) model, 126 enface OCTA images (104 eyes with diabetic retinopathy and 22 normal eyes) were used as training/validation dataset. Then, the accuracy of the model was evaluated using a dataset consisting of OCTA images of 10 normal eyes and 27 eyes with diabetic retinopathy. The CNN model was based on Detectron2, an open-source modular object detection library. In addition, automated FAZ measurements were conducted using the device's built-in commercial software, and manual FAZ delineation was performed using ImageJ software. Bland-Altman analysis was used to show 95% limit of agreement (95% LoA) between different methods. The mean dice similarity coefficient of the DL model was 0.94 ± 0.04 in the testing dataset. There was excellent agreement between automated, DL model and manual measurements of FAZ in healthy subjects (95% LoA of - 0.005 to 0.026 mm between automated and manual measurement and 0.000 to 0.009 mm between DL and manual FAZ area). In diabetic eyes, the agreement between DL and manual measurements was excellent (95% LoA of - 0.063 to 0.095), however, there was a poor agreement between the automated and manual method (95% LoA of - 0.186 to 0.331). The presence of diabetic macular edema and intraretinal cysts at the fovea were associated with erroneous FAZ measurements by the device's built-in software. In conclusion, the DL model showed an excellent accuracy in detection of FAZ border in enfaces OCTA images of both diabetic patients and healthy subjects. The DL and manual measurements outperformed the automated measurements of the built-in software.
本研究旨在介绍一种新的深度学习（DL）模型，用于分割眼前节光学相干断层扫描血管造影（OCTA）中的中心凹无血管区（FAZ），并将结果与该设备内置软件和健康受试者及糖尿病患者的手动测量结果进行比较。在这项回顾性研究中，在 88 例糖尿病患者的 131 只眼和 18 例健康受试者的 32 只眼中，在 3×3 眼前节 OCTA 图像的内视网膜层面描绘 FAZ 边界。为了训练深度卷积神经网络（CNN）模型，使用 126 张眼前节 OCTA 图像（104 只眼患有糖尿病视网膜病变和 22 只正常眼）作为训练/验证数据集。然后，使用由 10 只正常眼和 27 只糖尿病视网膜病变眼的 OCTA 图像组成的数据集评估模型的准确性。CNN 模型基于 Detectron2，这是一个开源的模块化目标检测库。此外，还使用设备内置的商业软件进行自动 FAZ 测量，并使用 ImageJ 软件进行手动 FAZ 描绘。Bland-Altman 分析用于显示不同方法之间 95%的一致性界限（95%LoA）。在测试数据集上，DL 模型的平均骰子相似系数为 0.94±0.04。在健康受试者中，自动、DL 模型和手动 FAZ 测量之间存在极好的一致性（自动与手动测量之间的 95%LoA 为-0.005 至 0.026mm，DL 与手动 FAZ 面积之间的 95%LoA 为 0.000 至 0.009mm）。在糖尿病眼中，DL 与手动测量之间的一致性极好（95%LoA 为-0.063 至 0.095），然而，自动与手动方法之间的一致性较差（95%LoA 为-0.186 至 0.331）。黄斑水肿和视网膜内囊泡的存在与设备内置软件的错误 FAZ 测量有关。总之，该 DL 模型在糖尿病患者和健康受试者的眼前节 OCTA 图像中 FAZ 边界的检测中表现出优异的准确性。DL 和手动测量优于内置软件的自动测量。
