Lo Julian, Yu Timothy T, Ma Da, Zang Pengxiao, Owen Julia P, Zhang Qinqin, Wang Ruikang K, Beg Mirza Faisal, Lee Aaron Y, Jia Yali, Sarunic Marinko V
School of Engineering Science, Simon Fraser University, Burnaby, Canada.
Casey Eye Institute, Oregon Health and Science University, Portland, Oregon.
Ophthalmol Sci. 2021 Oct 8;1(4):100069. doi: 10.1016/j.xops.2021.100069. eCollection 2021 Dec.
To evaluate the performance of a federated learning framework for deep neural network-based retinal microvasculature segmentation and referable diabetic retinopathy (RDR) classification using OCT and OCT angiography (OCTA).
Retrospective analysis of clinical OCT and OCTA scans of control participants and patients with diabetes.
The 153 OCTA en face images used for microvasculature segmentation were acquired from 4 OCT instruments with fields of view ranging from 2 × 2-mm to 6 × 6-mm. The 700 eyes used for RDR classification consisted of OCTA en face images and structural OCT projections acquired from 2 commercial OCT systems.
OCT angiography images used for microvasculature segmentation were delineated manually and verified by retina experts. Diabetic retinopathy (DR) severity was evaluated by retinal specialists and was condensed into 2 classes: non-RDR and RDR. The federated learning configuration was demonstrated via simulation using 4 clients for microvasculature segmentation and was compared with other collaborative training methods. Subsequently, federated learning was applied over multiple institutions for RDR classification and was compared with models trained and tested on data from the same institution (internal models) and different institutions (external models).
For microvasculature segmentation, we measured the accuracy and Dice similarity coefficient (DSC). For severity classification, we measured accuracy, area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, balanced accuracy, F1 score, sensitivity, and specificity.
For both applications, federated learning achieved similar performance as internal models. Specifically, for microvasculature segmentation, the federated learning model achieved similar performance (mean DSC across all test sets, 0.793) as models trained on a fully centralized dataset (mean DSC, 0.807). For RDR classification, federated learning achieved a mean AUROC of 0.954 and 0.960; the internal models attained a mean AUROC of 0.956 and 0.973. Similar results are reflected in the other calculated evaluation metrics.
Federated learning showed similar results to traditional deep learning in both applications of segmentation and classification, while maintaining data privacy. Evaluation metrics highlight the potential of collaborative learning for increasing domain diversity and the generalizability of models used for the classification of OCT data.
使用光学相干断层扫描（OCT）和光学相干断层扫描血管造影（OCTA），评估基于深度神经网络的视网膜微血管分割和可参考性糖尿病视网膜病变（RDR）分类的联邦学习框架的性能。
对对照参与者和糖尿病患者的临床OCT和OCTA扫描进行回顾性分析。
用于微血管分割的153张OCTA正面图像是从4台OCT仪器获取的，视野范围从2×2毫米到6×6毫米。用于RDR分类的700只眼睛包括从2个商用OCT系统获取的OCTA正面图像和结构性OCT投影。
用于微血管分割的OCT血管造影图像由视网膜专家手动勾勒并验证。糖尿病视网膜病变（DR）的严重程度由视网膜专家评估，并浓缩为2类：非RDR和RDR。通过使用4个客户端进行微血管分割的模拟展示了联邦学习配置，并与其他协作训练方法进行比较。随后，在多个机构应用联邦学习进行RDR分类，并与在同一机构（内部模型）和不同机构（外部模型）的数据上训练和测试的模型进行比较。
对于微血管分割，我们测量了准确率和骰子相似系数（DSC）。对于严重程度分类，我们测量了准确率、受试者工作特征曲线下面积（AUROC）、精确召回率曲线下面积、平衡准确率、F1分数、敏感性和特异性。
对于这两种应用，联邦学习取得了与内部模型相似的性能。具体而言，对于微血管分割，联邦学习模型取得了与在完全集中的数据集上训练的模型相似的性能（所有测试集的平均DSC，0.793）（平均DSC，0.807）。对于RDR分类，联邦学习的平均AUROC为0.954和0.960；内部模型的平均AUROC为0.956和0.973。其他计算的评估指标也反映了类似的结果。
在分割和分类的两种应用中，联邦学习显示出与传统深度学习相似的结果，同时保持了数据隐私。评估指标突出了协作学习在增加领域多样性和用于OCT数据分类的模型的通用性方面的潜力。
