文献速递医学人工智能与信息学基础与转化研究

人工智能从眼底照片检测视乳头水肿

Artificial Intelligence to Detect Papilledema from Ocular Fundus Photographs.
PubMed 文献 · N Engl J Med · 2020-04-14

本研究训练、验证并外部测试了一个深度学习系统,基于15846张药物散瞳后采集的眼底照片,将视盘分类为正常、视乳头水肿或其他异常。外部测试集1505张照片中,检测视乳头水肿的AUC为0.96,敏感度96.4%,特异度84.7%。

要点

  • 深度学习系统可从散瞳眼底照片区分视乳头水肿、正常视盘及其他异常。
  • 外部测试检测视乳头水肿AUC 0.96,敏感度96.4%,特异度84.7%。
  • 该系统有望辅助非眼科医生识别视乳头水肿。

核心结论

  • 深度学习系统利用药物散瞳眼底照片可区分视乳头水肿、正常视盘和非视乳头水肿异常。

研究设计与样本

  • 回顾性收集15846张药物散瞳眼底照片,来自多个民族人群和多种数字相机。
  • 14341张来自11个国家19个站点用于训练和验证,1505张来自5个其他站点用于外部测试。
  • 以神经眼科医生临床诊断为参考标准,计算AUC、敏感度和特异度。

主要发现

  • 训练和验证集来自6779例患者共14341张照片:正常视盘9156张,视乳头水肿2148张,其他异常3037张。
  • 各站点分类为正常的比例范围为9.8%至100%,分类为视乳头水肿的比例范围为0至59.5%。
  • 验证集中,系统区分视乳头水肿与正常视盘及非视乳头水肿异常的AUC为0.99(95%CI 0.98至0.99)。
  • 验证集中,系统区分正常与异常视盘的AUC为0.99(95%CI 0.99至0.99)。
  • 外部测试集1505张照片中,检测视乳头水肿的AUC为0.96(95%CI 0.95至0.97),敏感度96.4%(95%CI 93.9至98.3),特异度84.7%(95%CI 82.3至87.1)。

临床怎么用

  • 可辅助非眼科医生从散瞳眼底照片中识别视乳头水肿,减少对直接检眼镜的依赖。

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: Nonophthalmologist physicians do not confidently perform direct ophthalmoscopy. The use of artificial intelligence to detect papilledema and other optic-disk abnormalities from fundus photographs has not been well studied. METHODS: We trained, validated, and externally tested a deep-learning system to classify optic disks as being normal or having papilledema or other abnormalities from 15,846 retrospectively collected ocular fundus photographs that had been obtained with pharmacologic pupillary dilation and various digital cameras in persons from multiple ethnic populations. Of these photographs, 14,341 from 19 sites in 11 countries were used for training and validation, and 1505 photographs from 5 other sites were used for external testing. Performance at classifying the optic-disk appearance was evaluated by calculating the area under the receiver-operating-characteristic curve (AUC), sensitivity, and specificity, as compared with a reference standard of clinical diagnoses by neuro-ophthalmologists. RESULTS: The training and validation data sets from 6779 patients included 14,341 photographs: 9156 of normal disks, 2148 of disks with papilledema, and 3037 of disks with other abnormalities. The percentage classified as being normal ranged across sites from 9.8 to 100%; the percentage classified as having papilledema ranged across sites from zero to 59.5%. In the validation set, the system discriminated disks with papilledema from normal disks and disks with nonpapilledema abnormalities with an AUC of 0.99 (95% confidence interval [CI], 0.98 to 0.99) and normal from abnormal disks with an AUC of 0.99 (95% CI, 0.99 to 0.99). In the external-testing data set of 1505 photographs, the system had an AUC for the detection of papilledema of 0.96 (95% CI, 0.95 to 0.97), a sensitivity of 96.4% (95% CI, 93.9 to 98.3), and a specificity of 84.7% (95% CI, 82.3 to 87.1). CONCLUSIONS: A deep-learning system using fundus photographs with pharmacologically dilated pupils differentiated among optic disks with papilledema, normal disks, and disks with nonpapilledema abnormalities. (Funded by the Singapore National Medical Research Council and the SingHealth Duke-NUS Ophthalmology and Visual Sciences Academic Clinical Program.).

来源:N Engl J Med,查看原文。版权归原作者所有。

引用

  1. Milea D, Najjar RP, Zhubo J, et al. Artificial Intelligence to Detect Papilledema from Ocular Fundus Photographs. N Engl J Med. 2020. PMID: 32286748. doi:10.1056/NEJMoa1917130

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。