Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center and Department of Ophthalmology, Duke University, Durham, NC, USA.
Glaucoma Service, Department of Ophthalmology, University of Campinas, Campinas, São Paulo, Brazil.
Transl Vis Sci Technol. 2021 Jan 7;10(1):12. doi: 10.1167/tvst.10.1.12. eCollection 2021 Jan.
To assess whether age can be predicted from deep learning analysis of peripapillary spectral-domain optical coherence tomography (SD-OCT) B-scans and to determine the importance of specific retinal areas on the predictions.
Deep learning (DL) convolutional neural networks were developed to predict chronological age in healthy subjects using peripapillary SD-OCT B-scan images. Models were built using the whole B-scan, as well as using specific regions through image ablation. Cross-validation was used for training and testing the model. Mean absolute error (MAE) and correlations between predicted and observed age were used to evaluate model performance.
A total of 7271 images from 542 eyes of 278 healthy subjects were included. DL predictions of age using the whole B-scan were strongly correlated with chronological age (MAE = 5.82 years; = 0.860, < 0.001). The model also accurately discriminated between the lowest and highest tertiles of age, with an area under the receiver operating characteristic curve of 0.962. In general, class activation maps tended to show a diffuse pattern of activation throughout the scan image. For specific structures of the B-scan, the layers with the strongest correlations with chronological age were the choroid and vitreous (both = 0.736), whereas retinal nerve fiber layer had the lowest correlation ( = 0.492).
A DL algorithm was able to accurately predict age from whole peripapillary SD-OCT B-scans.
DL models applied to SD-OCT scans suggest that aging appears to affect several layers in the posterior eye segment.
评估深度学习分析视盘周围谱域光相干断层扫描（SD-OCT）B 扫描是否可以预测年龄，并确定特定视网膜区域对预测的重要性。
使用视盘周围 SD-OCT B 扫描图像，开发深度学习（DL）卷积神经网络来预测健康受试者的实际年龄。使用整个 B 扫描以及通过图像消融来构建模型。使用交叉验证来训练和测试模型。使用平均绝对误差（MAE）和预测年龄与实际年龄之间的相关性来评估模型性能。
共纳入了 7271 张来自 278 名健康受试者 542 只眼的图像。使用整个 B 扫描的 DL 预测年龄与实际年龄密切相关（MAE=5.82 岁； =0.860，<0.001）。该模型还能准确区分年龄的最低和最高三分位数，受试者工作特征曲线下面积为 0.962。一般来说，类激活图倾向于在整个扫描图像中显示出弥漫性激活模式。对于 B 扫描的特定结构，与实际年龄相关性最强的是脉络膜和玻璃体（均为 =0.736），而视网膜神经纤维层的相关性最低（ =0.492）。
DL 算法能够准确地从整个视盘周围 SD-OCT B 扫描中预测年龄。
AI 医生
