R&D Department, Fraunhofer Portugal AICOS, Porto, Portugal,
Faculty of Medicine of the University of Porto, Porto, Portugal,
Ophthalmologica. 2021;244(3):250-257. doi: 10.1159/000512638. Epub 2020 Oct 29.
To evaluate the diagnostic accuracy of a diagnostic system software for the automated screening of diabetic retinopathy (DR) on digital colour fundus photographs, the 2019 Convolutional Neural Network (CNN) model with Inception-V3.
In this cross-sectional study, 295 fundus images were analysed by the CNN model and compared to a panel of ophthalmologists. Images were obtained from a dataset acquired within a screening programme. Diagnostic accuracy measures and respective 95% CI were calculated.
The sensitivity and specificity of the CNN model in diagnosing referable DR was 81% (95% CI 66-90%) and 97% (95% CI 95-99%), respectively. Positive predictive value was 86% (95% CI 72-94%) and negative predictive value 96% (95% CI 93-98%). The positive likelihood ratio was 33 (95% CI 15-75) and the negative was 0.20 (95% CI 0.11-0.35). Its clinical impact is demonstrated by the change observed in the pre-test probability of referable DR (assuming a prevalence of 16%) to a post-test probability for a positive test result of 86% and for a negative test result of 4%.
A CNN model negative test result safely excludes DR, and its use may significantly reduce the burden of ophthalmologists at reading centres.
评估一款基于卷积神经网络（CNN）的 Inception-V3 模型的糖尿病视网膜病变（DR）自动筛查诊断系统软件的诊断准确性。
本研究为一项横断面研究，共分析了 295 张眼底图像，这些图像由 CNN 模型分析，并与一组眼科医生进行了比较。图像来自筛查项目中获得的数据集。计算了诊断准确性测量指标及其 95%置信区间（CI）。
CNN 模型诊断有临床意义的 DR 的敏感性和特异性分别为 81%（95%CI 66-90%）和 97%（95%CI 95-99%）。阳性预测值为 86%（95%CI 72-94%），阴性预测值为 96%（95%CI 93-98%）。阳性似然比为 33（95%CI 15-75），阴性似然比为 0.20（95%CI 0.11-0.35）。其临床影响表现为参考 DR 的术前概率（假设患病率为 16%）观察到的变化，即阳性测试结果的术后概率为 86%，阴性测试结果的术后概率为 4%。
CNN 模型的阴性测试结果可安全排除 DR，其应用可能会显著减轻阅片中心眼科医生的负担。
