机器学习与人工分级师基于眼底图像诊断青光眼的比较:面向人群筛查
本研究基于EPIC-Norfolk眼研究6304名参与者,比较机器学习与人工分级师测量的垂直杯盘比(VCDR)对青光眼的预测效能。结果显示机器学习VCDR的AUROC显著高于人工分级,提示ML支持的人群青光眼筛查策略具有潜力。
要点
- 机器学习VCDR预测青光眼状态的AUROC在左眼为88%、右眼为90%,均高于人工分级。
- 机器学习VCDR解释青光眼状态方差的比例在左眼为31%、右眼为35%,优于人工分级。
- 机器学习VCDR预测效能也优于AutoMorph模型和HRT。
核心结论
- 在基于人群的设置中,机器学习从眼底图像预测专家确诊的青光眼状态远优于训练有素的人工分级师。
研究设计与样本
- 基于人群的横断面分析,纳入EPIC-Norfolk眼研究中6304名双眼彩色眼底图像可被人工和机器学习分级的研究对象。
主要发现
- 左眼人工VCDR和机器学习VCDR分别解释17%(95%CI 14.7-20.4)和31%(95%CI 27.9-33.9)的青光眼状态方差,AUROC分别为79%(95%CI 76.8-81.2)和88%(95%CI 86.3-89.1)。
- 右眼人工VCDR和机器学习VCDR分别解释20%(95%CI 16.9-22.6)和35%(95%CI 32.4-37.9)的方差,AUROC分别为81%(95%CI 78.6-82.5)和90%(95%CI 88.7-91.0)。
- 机器学习VCDR在预测青光眼状态方面也优于AutoMorph和HRT。
关键数值与推荐
- 青光眼状态由三级中心专家检查确定。
临床怎么用
- 机器学习VCDR可作为一种有前景的工具用于人群青光眼筛查,辅助识别需转诊的患者。
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
PURPOSE: To compare the accuracy of vertical cup-disc ratios (VCDRs), ascertained by machine learning (ML) versus human graders, from fundus images for glaucoma detection. This study uses population-based data, with a disease prevalence and case mix that is more reflective of an unselected patient population than conventional case-control studies, with the aim of developing improved glaucoma screening tests. DESIGN: Cross-sectional analysis of a population-based study. PARTICIPANTS: A total of 6304 participants of the European Prospective Investigation of Cancer (EPIC)-Norfolk Eye Study with color fundus images gradable by humans and ML in both eyes. METHODS: Vertical cup-disc ratio was independently estimated from 2-dimensional fundus images of EPIC-Norfolk Eye Study participants by trained human graders (human-derived VCDR [H-VCDR]) and an externally trained, open-access ML model (ML-derived VCDR [ML-VCDR]). A neural network trained on 81 830 ophthalmologist-labeled images was used to generate pseudo-labels for over 100 000 UK Biobank images, on which ML-VCDR was subsequently trained. Glaucoma status was ascertained by tertiary-center specialist examination. Predictive performance of VCDR for glaucoma status was examined using logistic regression. Machine learning-derived VCDR estimates were additionally compared with a popular open-source ML model (AutoMorph) and scanning laser ophthalmoscopy (Heidelberg Retinal Tomography [HRT]). MAIN OUTCOME MEASURES: Area under the receiver operating characteristic curve (AUROC) explained variance (McFadden's pseudo-R2). RESULTS: Of 6304 participants (mean age, 68 years; 57% women), 696 had glaucoma or suspect status in at least 1 eye. For left eyes, H-VCDR and ML-VCDR explained 17% (95% confidence interval [CI], 14.7-20.4) and 31% (95% CI, 27.9-33.9) of glaucoma status variance and had an AUROC of 79% (95% CI, 76.8-81.2) and 88% (95% CI, 86.3-89.1), respectively. Right eye H-VCDR and ML-VCDR explained 20% (95% CI, 16.9-22.6) and 35% (95% CI, 32.4-37.9) of the variance and had an AUROC of 81% (95% CI, 78.6-82.5) and 90% (95% CI, 88.7-91.0), respectively. Machine learning-derived VCDR also performed better than AutoMorph and HRT at predicting glaucoma status from VCDR estimations. CONCLUSIONS: In this population-based setting, ML far outperformed trained human graders at predicting specialist-ascertained glaucoma status from fundus images. This provides promise for ML-supported strategies for glaucoma population screening. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
引用
- Taylor TRP, Khasentino J, Luben RN, et al. A Comparison of Machine Learning and Human Graders for Glaucoma Diagnosis from Fundus Images for Population Screening. Ophthalmology. 2026. PMID: 42575300. doi:10.1016/j.ophtha.2026.07.043
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。