文献速递眼底病与葡萄膜炎

深度学习在苏格兰糖尿病眼病筛查项目中对糖尿病视网膜病变的检测

Deep learning detection of diabetic retinopathy in Scotland's diabetic eye screening programme.
PubMed 文献 · Br J Ophthalmol · 2024-06-20

该研究利用2006至2016年苏格兰国家糖尿病视网膜病变筛查项目中179944名患者的视网膜图像、质量保证数据和常规分级,开发基于深度学习的自动分级算法,检测任一眼是否存在不可分级图像或任何糖尿病视网膜病变。在质量保证图像上与人工分级者和iGradingM相比,深度学习在相同敏感度下特异度更优(p<0.001)。按筛查最终分级,检测任何糖尿病视网膜病变的敏感度为89.19%(270392/303154),特异度为77.41%(500945/647158);检测可观察病变和需转诊病变的敏感度分别为96.58%(16613/17201)和98.48%(22600/22948);总体43.84%的筛查批次需人工分级。

要点

  • 深度学习在相同敏感度下检测不可分级或糖尿病视网膜病变图像的特异度优于人工分级者和iGradingM(p<0.001)。
  • 按筛查最终分级检测任何糖尿病视网膜病变的敏感度为89.19%(270392/303154),特异度为77.41%(500945/647158)。
  • 检测可观察病变和需转诊病变的敏感度分别为96.58%和98.48%,总体43.84%的筛查批次需人工分级。

核心结论

  • 深度学习分级系统在苏格兰国家糖尿病视网膜病变筛查项目的质量保证数据和11年图像中完成评估,覆盖50%参加筛查的人群。
  • 与现有自动分级系统相比,该系统可在相同敏感度下减少人工分级工作量。

研究设计与样本

  • 研究获取2006至2016年苏格兰国家数据集179944名患者的视网膜图像、质量保证数据和常规糖尿病视网膜病变分级。
  • 质量保证分级可用于744张图像。
  • 开发深度学习算法检测任一眼是否包含不可分级图像或任何糖尿病视网膜病变,并对照共识质量保证分级和常规分级评估敏感度与特异度。

主要发现

  • 质量保证图像中不可分级或伴糖尿病视网膜病变的图像,深度学习在相同敏感度下特异度优于人工分级者(p<0.001)和iGradingM(p<0.001)。
  • 按筛查最终分级检测任何糖尿病视网膜病变的敏感度为89.19%(270392/303154),特异度为77.41%(500945/647158)。
  • 检测可观察病变的敏感度为96.58%(16613/17201)。
  • 检测需转诊病变的敏感度为98.48%(22600/22948)。
  • 总体43.84%的筛查批次需人工分级。

关键数值与推荐

  • 检测任何糖尿病视网膜病变:敏感度89.19%(270392/303154),特异度77.41%(500945/647158)。
  • 检测可观察病变:敏感度96.58%(16613/17201)。
  • 检测需转诊病变:敏感度98.48%(22600/22948)。
  • 需人工分级的筛查批次占43.84%。

临床怎么用

  • 原文结论指出,与现有自动分级系统相比,该系统可在相同敏感度下减少人工分级工作量。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND/AIMS: Support vector machine-based automated grading (known as iGradingM) has been shown to be safe, cost-effective and robust in the diabetic retinopathy (DR) screening (DES) programme in Scotland. It triages screening episodes as gradable with no DR versus manual grading required. The study aim was to develop a deep learning-based autograder using images and gradings from DES and to compare its performance with that of iGradingM. METHODS: Retinal images, quality assurance (QA) data and routine DR grades were obtained from national datasets in 179 944 patients for years 2006-2016. QA grades were available for 744 images. We developed a deep learning-based algorithm to detect whether either eye contained ungradable images or any DR. The sensitivity and specificity were evaluated against consensus QA grades and routine grades. RESULTS: Images used in QA which were ungradable or with DR were detected by deep learning with better specificity compared with manual graders (p<0.001) and with iGradingM (p<0.001) at the same sensitivities. Any DR according to the DES final grade was detected with 89.19% (270 392/303 154) sensitivity and 77.41% (500 945/647 158) specificity. Observable disease and referable disease were detected with sensitivities of 96.58% (16 613/17 201) and 98.48% (22 600/22 948), respectively. Overall, 43.84% of screening episodes would require manual grading. CONCLUSION: A deep learning-based system for DR grading was evaluated in QA data and images from 11 years in 50% of people attending a national DR screening programme. The system could reduce the manual grading workload at the same sensitivity compared with the current automated grading system.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Fleming AD, Mellor J, McGurnaghan SJ, et al. Deep learning detection of diabetic retinopathy in Scotland's diabetic eye screening programme. Br J Ophthalmol. 2024. PMID: 37704266. doi:10.1136/bjo-2023-323395

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。