Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data

Purpose: 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). Design: Retrospective analysis of clinical OCT and OCTA scans of co...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Julian Lo, MASc, Timothy T. Yu, BASc, Da Ma, PhD, Pengxiao Zang, MEng, Julia P. Owen, PhD, Qinqin Zhang, PhD, Ruikang K. Wang, PhD, Mirza Faisal Beg, PhD, Aaron Y. Lee, MD, MSc, Yali Jia, PhD, Marinko V. Sarunic, PhD, MBA
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Diabetic retinopathy Federated learning Machine learning Neural network OCT Ophthalmology RE1-994
Acceso en línea:	https://doaj.org/article/303b9dd4d0f94ee3a1e8c6c74867b0df
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:303b9dd4d0f94ee3a1e8c6c74867b0df
record_format	dspace
spelling	oai:doaj.org-article:303b9dd4d0f94ee3a1e8c6c74867b0df2021-11-10T04:43:10ZFederated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data2666-914510.1016/j.xops.2021.100069https://doaj.org/article/303b9dd4d0f94ee3a1e8c6c74867b0df2021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666914521000671https://doaj.org/toc/2666-9145Purpose: 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). Design: Retrospective analysis of clinical OCT and OCTA scans of control participants and patients with diabetes. Participants: 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. Methods: 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). Main Outcome Measures: 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. Results: 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. Conclusions: 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.Julian Lo, MAScTimothy T. Yu, BAScDa Ma, PhDPengxiao Zang, MEngJulia P. Owen, PhDQinqin Zhang, PhDRuikang K. Wang, PhDMirza Faisal Beg, PhDAaron Y. Lee, MD, MScYali Jia, PhDMarinko V. Sarunic, PhD, MBAElsevierarticleDiabetic retinopathyFederated learningMachine learningNeural networkOCTOphthalmologyRE1-994ENOphthalmology Science, Vol 1, Iss 4, Pp 100069- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Diabetic retinopathy Federated learning Machine learning Neural network OCT Ophthalmology RE1-994
spellingShingle	Diabetic retinopathy Federated learning Machine learning Neural network OCT Ophthalmology RE1-994 Julian Lo, MASc Timothy T. Yu, BASc Da Ma, PhD Pengxiao Zang, MEng Julia P. Owen, PhD Qinqin Zhang, PhD Ruikang K. Wang, PhD Mirza Faisal Beg, PhD Aaron Y. Lee, MD, MSc Yali Jia, PhD Marinko V. Sarunic, PhD, MBA Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data
description	Purpose: 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). Design: Retrospective analysis of clinical OCT and OCTA scans of control participants and patients with diabetes. Participants: 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. Methods: 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). Main Outcome Measures: 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. Results: 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. Conclusions: 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.
format	article
author	Julian Lo, MASc Timothy T. Yu, BASc Da Ma, PhD Pengxiao Zang, MEng Julia P. Owen, PhD Qinqin Zhang, PhD Ruikang K. Wang, PhD Mirza Faisal Beg, PhD Aaron Y. Lee, MD, MSc Yali Jia, PhD Marinko V. Sarunic, PhD, MBA
author_facet	Julian Lo, MASc Timothy T. Yu, BASc Da Ma, PhD Pengxiao Zang, MEng Julia P. Owen, PhD Qinqin Zhang, PhD Ruikang K. Wang, PhD Mirza Faisal Beg, PhD Aaron Y. Lee, MD, MSc Yali Jia, PhD Marinko V. Sarunic, PhD, MBA
author_sort	Julian Lo, MASc
title	Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data
title_short	Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data
title_full	Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data
title_fullStr	Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data
title_full_unstemmed	Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data
title_sort	federated learning for microvasculature segmentation and diabetic retinopathy classification of oct data
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/303b9dd4d0f94ee3a1e8c6c74867b0df
work_keys_str_mv	AT julianlomasc federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata AT timothytyubasc federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata AT damaphd federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata AT pengxiaozangmeng federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata AT juliapowenphd federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata AT qinqinzhangphd federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata AT ruikangkwangphd federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata AT mirzafaisalbegphd federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata AT aaronyleemdmsc federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata AT yalijiaphd federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata AT marinkovsarunicphdmba federatedlearningformicrovasculaturesegmentationanddiabeticretinopathyclassificationofoctdata
_version_	1718440540654010368

Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data

Ejemplares similares