Wu Hongkang, Jin Kai, Jing Yiyang, Shen Wenyue, Tham Yih Chung, Pan Xiangji, Koh Victor, Grzybowski Andrzej, Ye Juan
Zhejiang Provincial Key Laboratory of Ophthalmology, Zhejiang Provincial Clinical Research Center for Eye Diseases, Zhejiang Provincial Engineering Institute on Eye Diseases, Eye Center of Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China.
College of Control Science and Engineering, Zhejiang University, Hangzhou, China.
Ophthalmol Sci. 2025 Mar 11;5(5):100755. doi: 10.1016/j.xops.2025.100755. eCollection 2025 Sep-Oct.
To develop and validate an artificial intelligence (AI)-based system, Diabetic Retinopathy Analysis Model Assistant (DRAMA), for diagnosing diabetic retinopathy (DR) across multisource heterogeneous datasets and aimed at improving the diagnostic accuracy and efficiency.
This was a cross-sectional study conducted at Zhejiang University Eye Hospital and approved by the ethics committee.
The study included 1500 retinal images from 957 participants aged 18 to 83 years. The dataset was divided into 3 subdatasets: color fundus photography, ultra-widefield imaging, and portable fundus camera. Images were annotated by 3 experienced ophthalmologists.
The AI system was built using EfficientNet-B2, pretrained on the ImageNet dataset. It performed 11 multilabel tasks, including image type identification, quality assessment, lesion detection, and diabetic macular edema (DME) detection. The model used LabelSmoothingCrossEntropy and AdamP optimizer to enhance robustness and convergence. The system's performance was evaluated using metrics such as accuracy, sensitivity, specificity, and area under the curve (AUC). External validation was conducted using datasets from different clinical centers.
The primary outcomes measured were the accuracy, sensitivity, specificity, and AUC of the AI system in diagnosing DR.
After excluding 218 poor-quality images, DRAMA demonstrated high diagnostic accuracy, with EfficientNet-B2 achieving 87.02% accuracy in quality assessment and 91.60% accuracy in lesion detection. Area under the curves were >0.95 for most tasks, with 0.93 for grading and DME detection. External validation showed slightly lower accuracy in some tasks but outperformed in identifying hemorrhages and DME. Diabetic Retinopathy Analysis Model Assistant diagnosed the entire test set in 86 ms, significantly faster than the 90 to 100 minutes required by humans.
Diabetic Retinopathy Analysis Model Assistant, an AI-based multitask model, showed high potential for clinical integration, significantly improving the diagnostic efficiency and accuracy, particularly in resource-limited settings.
The author(s) have no proprietary or commercial interest in any materials discussed in this article.
开发并验证一种基于人工智能（AI）的系统——糖尿病视网膜病变分析模型助手（DRAMA），用于跨多源异构数据集诊断糖尿病视网膜病变（DR），旨在提高诊断准确性和效率。
这是一项在浙江大学眼科医院进行的横断面研究，并获得伦理委员会批准。
该研究纳入了957名年龄在18至83岁之间参与者的1500张视网膜图像。数据集分为3个子数据集：彩色眼底照相、超广角成像和便携式眼底相机。图像由3名经验丰富的眼科医生进行标注。
AI系统使用在ImageNet数据集上预训练的EfficientNet-B2构建。它执行11个多标签任务，包括图像类型识别、质量评估、病变检测和糖尿病性黄斑水肿（DME）检测。该模型使用标签平滑交叉熵和AdamP优化器来增强鲁棒性和收敛性。使用准确率、灵敏度、特异性和曲线下面积（AUC）等指标评估系统性能。使用来自不同临床中心的数据集进行外部验证。
测量的主要结果是AI系统诊断DR的准确率、灵敏度、特异性和AUC。
在排除218张质量不佳的图像后，DRAMA显示出较高的诊断准确性，EfficientNet-B2在质量评估中的准确率达到87.02%，在病变检测中的准确率达到91.60%。大多数任务的曲线下面积>0.95，分级和DME检测的曲线下面积为0.93。外部验证显示在某些任务中准确率略低，但在识别出血和DME方面表现更优。糖尿病视网膜病变分析模型助手在86毫秒内诊断了整个测试集，明显快于人类所需的90至100分钟。
糖尿病视网膜病变分析模型助手，一种基于AI的多任务模型，显示出很高的临床整合潜力，显著提高了诊断效率和准确性，特别是在资源有限的环境中。
作者对本文讨论的任何材料均无所有权或商业利益。
