Zhu Huishan, Ji Jie, Lin Jian-Wei, Wang Ji, Zheng Yi, Xie Peiwen, Liu Cui, Ng Tsz Kin, Huang Jinqu, Xiong Yongqun, Wu Hanfu, Lin Leixian, Zhang Mingzhi, Zhang Guihua
Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, China.
Shantou University Medical College, Shantou, China.
BMJ Open. 2025 May 31;15(5):e099167. doi: 10.1136/bmjopen-2025-099167.
To develop and validate an automated diabetic macular oedema (DME) classification system based on the images from different three-dimensional optical coherence tomography (3-D OCT) devices.
A multicentre, platform-based development study using retrospective and cross-sectional data. Data were subjected to a two-level grading system by trained graders and a retina specialist, and categorised into three types: no DME, non-centre-involved DME and centre-involved DME (CI-DME). The 3-D convolutional neural networks algorithm was used for DME classification system development. The deep learning (DL) performance was compared with the diabetic retinopathy experts.
Data were collected from Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Chaozhou People's Hospital and The Second Affiliated Hospital of Shantou University Medical College from January 2010 to December 2023.
7790 volumes of 7146 eyes from 4254 patients were annotated, of which 6281 images were used as the development set and 1509 images were used as the external validation set, split based on the centres.
Accuracy, F1-score, sensitivity, specificity, area under receiver operating characteristic curve (AUROC) and Cohen's kappa were calculated to evaluate the performance of the DL algorithm.
In classifying DME with non-DME, our model achieved an AUROCs of 0.990 (95% CI 0.983 to 0.996) and 0.916 (95% CI 0.902 to 0.930) for hold-out testing dataset and external validation dataset, respectively. To distinguish CI-DME from non-centre-involved-DME, our model achieved AUROCs of 0.859 (95% CI 0.812 to 0.906) and 0.881 (95% CI 0.859 to 0.902), respectively. In addition, our system showed comparable performance (Cohen's κ: 0.85 and 0.75) to the retina experts (Cohen's κ: 0.58-0.92 and 0.70-0.71).
Our DL system achieved high accuracy in multiclassification tasks on DME classification with 3-D OCT images, which can be applied to population-based DME screening.
基于来自不同三维光学相干断层扫描（3-D OCT）设备的图像，开发并验证一种自动化糖尿病性黄斑水肿（DME）分类系统。
一项基于平台的多中心开发研究，使用回顾性和横断面数据。数据由经过培训的分级人员和一名视网膜专家进行两级分级系统评估，并分为三种类型：无DME、非中心累及DME和中心累及DME（CI-DME）。使用三维卷积神经网络算法开发DME分类系统。将深度学习（DL）性能与糖尿病视网膜病变专家的性能进行比较。
数据收集于2010年1月至2023年12月期间的汕头大学·香港中文大学联合汕头国际眼科中心、潮州市人民医院和汕头大学医学院第二附属医院。
对4254例患者的7146只眼睛的7790份图像进行了标注，其中6281幅图像用作开发集，1509幅图像用作外部验证集，根据中心进行划分。
计算准确率、F1分数、灵敏度、特异性、受试者操作特征曲线下面积（AUROC）和科恩kappa系数，以评估DL算法的性能。
在区分DME与非DME时，我们的模型在留出测试数据集和外部验证数据集上的AUROC分别为0.990（95%CI 0.983至0.996）和0.916（95%CI 0.902至0.930）。为了区分CI-DME与非中心累及DME，我们的模型的AUROC分别为0.859（95%CI 0.812至0.906）和0.881（95%CI 0.859至0.902）。此外，我们的系统与视网膜专家的表现相当（科恩kappa系数：0.85和0.75）（科恩kappa系数：0.58 - 0.92和0.70 - 0.71）。
我们的DL系统在使用3-D OCT图像进行DME分类的多分类任务中实现了高精度，可应用于基于人群的DME筛查。
