在苏格兰筛查项目中使用视网膜图像深度学习预测视网膜病变进展
该研究基于苏格兰筛查项目中21346例1型糖尿病和247233例2型糖尿病患者数据,利用深度学习从眼底图像预测筛查间期内进展为需转诊糖尿病视网膜病变。与现有视网膜病变分级相比,深度学习预测器将1型糖尿病AUC从0.809提升至0.87、2型糖尿病从0.825提升至0.87,并使预期滞留时间分别缩短3.4周和2.7周。
要点
- 深度学习预测器将1型糖尿病需转诊视网膜病变预测AUC从0.809提升至0.87。
- 深度学习预测器将2型糖尿病需转诊视网膜病变预测AUC从0.825提升至0.87。
- 深度学习策略下预期滞留时间较现行召回策略在1型糖尿病缩短3.4周、2型糖尿病缩短2.7周。
核心结论
- 与使用当前视网膜病变分级相比,眼底图像深度学习显著改善了下次筛查前发生需转诊视网膜病变的预测。
- 这可对筛查召回间期政策产生积极影响,例如在固定工作量下减少需转诊疾病的预期时间,也可用于在固定滞留时间下优化工作量。
研究设计与样本
- 研究纳入苏格兰筛查项目中21346例1型糖尿病患者和247233例2型糖尿病患者。
- 1型糖尿病患者平均贡献4.8个筛查间期,其中1339个间期以需转诊筛查 episode 结束。
- 2型糖尿病患者平均贡献4.4个筛查间期,其中4675个间期以需转诊筛查 episode 结束。
- 利用深度学习从眼底图像提取信息预测间期末需转诊状态,并与筛查分配的视网膜病变分级预测价值进行比较。
主要发现
- 与使用当前视网膜病变分级的预测器相比,深度学习预测器将1型糖尿病AUC从0.809提升至0.87。
- 与使用当前视网膜病变分级的预测器相比,深度学习预测器将2型糖尿病AUC从0.825提升至0.87。
- 深度学习衍生策略下预期滞留时间较现行召回策略在1型糖尿病缩短3.4周、在2型糖尿病缩短2.7周。
临床怎么用
- 原文结论指出深度学习可对筛查召回间期政策产生积极影响,但未据此给出具体临床推荐。
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: National guidelines of many countries set screening intervals for diabetic retinopathy (DR) based on grading of the last screening retinal images. We explore the potential of deep learning (DL) on images to predict progression to referable DR beyond DR grading, and the potential impact on assigned screening intervals, within the Scottish screening programme. METHODS: We consider 21 346 and 247 233 people with type 1 diabetes mellitus (T1DM) and type 2 diabetes mellitus (T2DM), respectively, each contributing on average 4.8 and 4.4 screening intervals of which 1339 and 4675 intervals concluded with a referable screening episode. Information extracted from fundus images using DL was used to predict referable status at the end of interval and its predictive value in comparison to screening-assigned DR grade was assessed. RESULTS: The DL predictor increased the area under the receiver operating characteristic curve in comparison to a predictor using current DR grades from 0.809 to 0.87 for T1DM and from 0.825 to 0.87 for T2DM. Expected sojourn time-the time from becoming referable to being rescreened-was found to be 3.4 (T1DM) and 2.7 (T2DM) weeks less for a DL-derived policy compared with the current recall policy. CONCLUSIONS: We showed that, compared with using the current retinopathy grade, DL of fundus images significantly improves the prediction of incident referable retinopathy before the next screening episode. This can impact screening recall interval policy positively, for example, by reducing the expected time with referable disease for a fixed workload-which we show as an exemplar. Additionally, it could be used to optimise workload for a fixed sojourn time.
引用
- Mellor J, Jiang W, Fleming A, et al. Prediction of retinopathy progression using deep learning on retinal images within the Scottish screening programme. Br J Ophthalmol. 2024. PMID: 38316534. doi:10.1136/bjo-2023-323400
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。