{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["1(4)"],"submitter":["Lo J"],"pubmed_abstract":["<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 b"],"journal":["Ophthalmology science"],"pagination":["100069"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9559956"],"repository":["biostudies-literature"],"pubmed_title":["Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data."],"pmcid":["PMC9559956"],"pubmed_authors":["Lee AY","Sarunic MV","Wang RK","Jia Y","Lo J","Owen JP","Beg MF","Ma D","Zang P","Zhang Q","Yu TT"],"additional_accession":[]},"is_claimable":false,"name":"Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data.","description":"<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 b","dates":{"release":"2021-01-01T00:00:00Z","publication":"2021 Dec","modification":"2025-04-19T06:48:19.303Z","creation":"2025-04-19T06:48:19.303Z"},"accession":"S-EPMC9559956","cross_references":{"pubmed":["36246944"],"doi":["10.1016/j.xops.2021.100069"]}}