Data Sheet 8_A deep-learning pipeline for the diagnosis and grading of common blinding ophthalmic diseases based on lesion-focused classification model.pdf

BackgroundGlaucoma (GLAU), Age-related Macular Degeneration (AMD), Retinal Vein Occlusion (RVO), and Diabetic Retinopathy (DR) are common blinding ophthalmic diseases worldwide.
PurposeThis approach is expected to enhance the early detection and treatment of common blinding ophthalmic diseases, contributing to the reduction of individual and economic burdens associated with these conditions.
MethodsWe propose an effective deep-learning pipeline that combine both segmentation model and classification model for diagnosis and grading of four common blinding ophthalmic diseases and normal retinal fundus.
ResultsIn total, 102,786 fundus images of 75,682 individuals were used for training validation and external validation purposes. We test our model on internal validation data set, the micro Area Under the Receiver Operating Characteristic curve (AUROC) of which reached 0.995. Then, we fine-tuned the diagnosis model to classify each of the four disease into early and late stage, respectively, which achieved AUROCs of 0.597 (GL), 0.877 (AMD), 0.972 (RVO), and 0.961 (DR) respectively. To test the generalization of our model, we conducted two external validation experiments on Neimeng and Guangxi cohort, all of which maintained high accuracy.
ConclusionOur algorithm demonstrates accurate artificial intelligence diagnosis pipeline for common blinding ophthalmic diseases based on Lesion-Focused fundus that overcomes the low-accuracy of the traditional classification method that based on raw retinal images, which has good generalization ability on diverse cases in different regions.

背景 青光眼（Glaucoma, GLAU）、年龄相关性黄斑变性（Age-related Macular Degeneration, AMD）、视网膜静脉阻塞（Retinal Vein Occlusion, RVO）以及糖尿病视网膜病变（Diabetic Retinopathy, DR）是全球范围内常见的致盲性眼科疾病。
目的 本研究旨在提升此类常见致盲性眼科疾病的早期检出与干预水平，助力减轻此类病症给患者个体及社会经济带来的双重负担。
方法 我们提出了一款高效的深度学习流水线，该流水线融合了分割模型与分类模型，可针对四种常见致盲性眼科疾病及正常视网膜眼底图像开展诊断与分级任务。
结果 本研究共纳入75682名受试者的102786张眼底图像，用于模型训练、验证及外部验证。我们在内部验证数据集上测试模型性能，其微平均受试者工作特征曲线下面积（micro Area Under the Receiver Operating Characteristic curve, AUROC）达到0.995。随后，我们对诊断模型进行微调，以分别将四种疾病划分为早期与晚期阶段，对应的AUROC分别为0.597（GL，青光眼）、0.877（AMD，年龄相关性黄斑变性）、0.972（RVO，视网膜静脉阻塞）及0.961（DR，糖尿病视网膜病变）。为验证模型的泛化能力，我们分别在内蒙古队列与广西队列中开展了两项外部验证实验，所有实验均保持了较高的准确率。
结论 本算法基于病灶聚焦型眼底图像，构建了精准的常见致盲性眼科疾病人工智能诊断流水线，解决了传统基于原始视网膜图像的分类方法准确率偏低的问题，且在不同地区的多样化病例中展现出良好的泛化能力。