基于OCT图像的高近视视力威胁病变深度学习筛查系统开发与验证
本研究利用1048例高近视患者的5505张OCT黄斑图像开发深度学习系统,用于识别视网膜劈裂、黄斑裂孔、视网膜脱离和病理性近视脉络膜新生血管。在91例患者的412张独立测试图像中,各病变AUC达0.961至0.999,敏感度不劣于视网膜专家且特异度大于90%。
要点
- 基于OCT黄斑图像训练四个CNN模型识别高近视四种视力威胁病变。
- 独立测试集中各病变AUC为0.961至0.999,特异度均大于90%。
- AI系统敏感度等于或优于视网膜专家,并可提供热图解释。
核心结论
- 深度学习系统基于OCT黄斑图像可可靠识别高近视患者的视力威胁病变,敏感度与视网膜专家相当且特异度高。
研究设计与样本
- 横断面前瞻性研究,开发集为2012至2017年中山眼科中心1048例高近视患者的5505张合格OCT黄斑图像。
- 独立测试集为2019年1月至5月中山眼科中心招募的91例高近视患者的412张图像。
- 采用InceptionResnetV2架构训练四个独立CNN模型,使用Focal Loss处理类别不平衡,按Youden指数确定最佳操作阈值。
主要发现
- 独立测试集中四种病变的ROC曲线下面积均较高,范围为0.961至0.999。
- AI系统敏感度等于或优于视网膜专家,特异度均大于90%。
- AI系统通过热图提供透明且可解释的诊断。
关键数值与推荐
- 四个CNN模型分别识别视网膜劈裂、黄斑裂孔、视网膜脱离和病理性近视脉络膜新生血管。
- 独立测试集各病变AUC为0.961至0.999,特异度大于90%。
临床怎么用
- 该AI系统可能应用于大规模高近视筛查和患者随访。
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: To apply deep learning technology to develop an artificial intelligence (AI) system that can identify vision-threatening conditions in high myopia patients based on optical coherence tomography (OCT) macular images. METHODS: In this cross-sectional, prospective study, a total of 5505 qualified OCT macular images obtained from 1048 high myopia patients admitted to Zhongshan Ophthalmic Centre (ZOC) from 2012 to 2017 were selected for the development of the AI system. The independent test dataset included 412 images obtained from 91 high myopia patients recruited at ZOC from January 2019 to May 2019. We adopted the InceptionResnetV2 architecture to train four independent convolutional neural network (CNN) models to identify the following four vision-threatening conditions in high myopia: retinoschisis, macular hole, retinal detachment and pathological myopic choroidal neovascularisation. Focal Loss was used to address class imbalance, and optimal operating thresholds were determined according to the Youden Index. RESULTS: In the independent test dataset, the areas under the receiver operating characteristic curves were high for all conditions (0.961 to 0.999). Our AI system achieved sensitivities equal to or even better than those of retina specialists as well as high specificities (greater than 90%). Moreover, our AI system provided a transparent and interpretable diagnosis with heatmaps. CONCLUSIONS: We used OCT macular images for the development of CNN models to identify vision-threatening conditions in high myopia patients. Our models achieved reliable sensitivities and high specificities, comparable to those of retina specialists and may be applied for large-scale high myopia screening and patient follow-up.
引用
- Li Y, Feng W, Zhao X, et al. Development and validation of a deep learning system to screen vision-threatening conditions in high myopia using optical coherence tomography images. Br J Ophthalmol. 2020. PMID: 33355150. doi:10.1136/bjophthalmol-2020-317825
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。