Evaluating the impact of vitreomacular adhesion on anti-VEGF therapy for retinal vein occlusion using machine learning

Abstract Vitreomacular adhesion (VMA) represents a prognostic biomarker in the management of exudative macular disease using anti-vascular endothelial growth factor (VEGF) agents. However, manual evaluation of VMA in 3D optical coherence tomography (OCT) is laborious and data on its impact on therap...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sebastian M. Waldstein, Alessio Montuoro, Dominika Podkowinski, Ana-Maria Philip, Bianca S. Gerendas, Hrvoje Bogunovic, Ursula Schmidt-Erfurth
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/a30f128685a44e5e8d2e91b490234b53
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a30f128685a44e5e8d2e91b490234b53
record_format	dspace
spelling	oai:doaj.org-article:a30f128685a44e5e8d2e91b490234b532021-12-02T15:05:04ZEvaluating the impact of vitreomacular adhesion on anti-VEGF therapy for retinal vein occlusion using machine learning10.1038/s41598-017-02971-y2045-2322https://doaj.org/article/a30f128685a44e5e8d2e91b490234b532017-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-02971-yhttps://doaj.org/toc/2045-2322Abstract Vitreomacular adhesion (VMA) represents a prognostic biomarker in the management of exudative macular disease using anti-vascular endothelial growth factor (VEGF) agents. However, manual evaluation of VMA in 3D optical coherence tomography (OCT) is laborious and data on its impact on therapy of retinal vein occlusion (RVO) are limited. The aim of this study was to (1) develop a fully automated segmentation algorithm for the posterior vitreous boundary and (2) to study the effect of VMA on anti-VEGF therapy for RVO. A combined machine learning/graph cut segmentation algorithm for the posterior vitreous boundary was designed and evaluated. 391 patients with central/branch RVO under standardized ranibizumab treatment for 6/12 months were included in a systematic post-hoc analysis. VMA (70%) was automatically differentiated from non-VMA (30%) using the developed method combined with unsupervised clustering. In this proof-of-principle study, eyes with VMA showed larger BCVA gains than non-VMA eyes (BRVO: 15 ± 12 vs. 11 ± 11 letters, p = 0.02; CRVO: 18 ± 14 vs. 9 ± 13 letters, p < 0.01) and received a similar number of retreatments. However, this association diminished after adjustment for baseline BCVA, also when using more fine-grained VMA classes. Our study illustrates that machine learning represents a promising path to assess imaging biomarkers in OCT.Sebastian M. WaldsteinAlessio MontuoroDominika PodkowinskiAna-Maria PhilipBianca S. GerendasHrvoje BogunovicUrsula Schmidt-ErfurthNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-11 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Sebastian M. Waldstein Alessio Montuoro Dominika Podkowinski Ana-Maria Philip Bianca S. Gerendas Hrvoje Bogunovic Ursula Schmidt-Erfurth Evaluating the impact of vitreomacular adhesion on anti-VEGF therapy for retinal vein occlusion using machine learning
description	Abstract Vitreomacular adhesion (VMA) represents a prognostic biomarker in the management of exudative macular disease using anti-vascular endothelial growth factor (VEGF) agents. However, manual evaluation of VMA in 3D optical coherence tomography (OCT) is laborious and data on its impact on therapy of retinal vein occlusion (RVO) are limited. The aim of this study was to (1) develop a fully automated segmentation algorithm for the posterior vitreous boundary and (2) to study the effect of VMA on anti-VEGF therapy for RVO. A combined machine learning/graph cut segmentation algorithm for the posterior vitreous boundary was designed and evaluated. 391 patients with central/branch RVO under standardized ranibizumab treatment for 6/12 months were included in a systematic post-hoc analysis. VMA (70%) was automatically differentiated from non-VMA (30%) using the developed method combined with unsupervised clustering. In this proof-of-principle study, eyes with VMA showed larger BCVA gains than non-VMA eyes (BRVO: 15 ± 12 vs. 11 ± 11 letters, p = 0.02; CRVO: 18 ± 14 vs. 9 ± 13 letters, p < 0.01) and received a similar number of retreatments. However, this association diminished after adjustment for baseline BCVA, also when using more fine-grained VMA classes. Our study illustrates that machine learning represents a promising path to assess imaging biomarkers in OCT.
format	article
author	Sebastian M. Waldstein Alessio Montuoro Dominika Podkowinski Ana-Maria Philip Bianca S. Gerendas Hrvoje Bogunovic Ursula Schmidt-Erfurth
author_facet	Sebastian M. Waldstein Alessio Montuoro Dominika Podkowinski Ana-Maria Philip Bianca S. Gerendas Hrvoje Bogunovic Ursula Schmidt-Erfurth
author_sort	Sebastian M. Waldstein
title	Evaluating the impact of vitreomacular adhesion on anti-VEGF therapy for retinal vein occlusion using machine learning
title_short	Evaluating the impact of vitreomacular adhesion on anti-VEGF therapy for retinal vein occlusion using machine learning
title_full	Evaluating the impact of vitreomacular adhesion on anti-VEGF therapy for retinal vein occlusion using machine learning
title_fullStr	Evaluating the impact of vitreomacular adhesion on anti-VEGF therapy for retinal vein occlusion using machine learning
title_full_unstemmed	Evaluating the impact of vitreomacular adhesion on anti-VEGF therapy for retinal vein occlusion using machine learning
title_sort	evaluating the impact of vitreomacular adhesion on anti-vegf therapy for retinal vein occlusion using machine learning
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/a30f128685a44e5e8d2e91b490234b53
work_keys_str_mv	AT sebastianmwaldstein evaluatingtheimpactofvitreomacularadhesiononantivegftherapyforretinalveinocclusionusingmachinelearning AT alessiomontuoro evaluatingtheimpactofvitreomacularadhesiononantivegftherapyforretinalveinocclusionusingmachinelearning AT dominikapodkowinski evaluatingtheimpactofvitreomacularadhesiononantivegftherapyforretinalveinocclusionusingmachinelearning AT anamariaphilip evaluatingtheimpactofvitreomacularadhesiononantivegftherapyforretinalveinocclusionusingmachinelearning AT biancasgerendas evaluatingtheimpactofvitreomacularadhesiononantivegftherapyforretinalveinocclusionusingmachinelearning AT hrvojebogunovic evaluatingtheimpactofvitreomacularadhesiononantivegftherapyforretinalveinocclusionusingmachinelearning AT ursulaschmidterfurth evaluatingtheimpactofvitreomacularadhesiononantivegftherapyforretinalveinocclusionusingmachinelearning
_version_	1718388974907555840

Evaluating the impact of vitreomacular adhesion on anti-VEGF therapy for retinal vein occlusion using machine learning

Ejemplares similares