biostudies-literatureUnknown1(4)Lo J<h4>Purpose</h4>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).<h4>Design</h4>Retrospective analysis of clinical OCT and OCTA scans of control participants and patients with diabetes.<h4>Participants</h4>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.<h4>Methods</h4>OCT angiography images used for microvasculature segmentation were delineated manually and verified bOphthalmology science100069https://www.ebi.ac.uk/biostudies/studies/S-EPMC9559956biostudies-literatureFederated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data.PMC9559956Lee AYSarunic MVWang RKJia YLo JOwen JPBeg MFMa DZang PZhang QYu TTfalseFederated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data.<h4>Purpose</h4>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).<h4>Design</h4>Retrospective analysis of clinical OCT and OCTA scans of control participants and patients with diabetes.<h4>Participants</h4>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.<h4>Methods</h4>OCT angiography images used for microvasculature segmentation were delineated manually and verified b2021-01-01T00:00:00Z2021 Dec2025-04-19T06:48:19.303Z2025-04-19T06:48:19.303ZS-EPMC95599563624694410.1016/j.xops.2021.100069