Cargando…

Deep iterative vessel segmentation in OCT angiography

This paper addresses retinal vessel segmentation on optical coherence tomography angiography (OCT-A) images of the human retina. Our approach is motivated by the need for high precision image-guided delivery of regenerative therapies in vitreo-retinal surgery. OCT-A visualizes macular vasculature, t...

Descripción completa

Detalles Bibliográficos
Autores principales: Pissas, Theodoros, Bloch, Edward, Cardoso, M. Jorge, Flores, Blanca, Georgiadis, Odysseas, Jalali, Sepehr, Ravasio, Claudio, Stoyanov, Danail, Da Cruz, Lyndon, Bergeles, Christos
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Optical Society of America 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7249805/
https://www.ncbi.nlm.nih.gov/pubmed/32499939
http://dx.doi.org/10.1364/BOE.384919
_version_ 1783538660636884992
author Pissas, Theodoros
Bloch, Edward
Cardoso, M. Jorge
Flores, Blanca
Georgiadis, Odysseas
Jalali, Sepehr
Ravasio, Claudio
Stoyanov, Danail
Da Cruz, Lyndon
Bergeles, Christos
author_facet Pissas, Theodoros
Bloch, Edward
Cardoso, M. Jorge
Flores, Blanca
Georgiadis, Odysseas
Jalali, Sepehr
Ravasio, Claudio
Stoyanov, Danail
Da Cruz, Lyndon
Bergeles, Christos
author_sort Pissas, Theodoros
collection PubMed
description This paper addresses retinal vessel segmentation on optical coherence tomography angiography (OCT-A) images of the human retina. Our approach is motivated by the need for high precision image-guided delivery of regenerative therapies in vitreo-retinal surgery. OCT-A visualizes macular vasculature, the main landmark of the surgically targeted area, at a level of detail and spatial extent unattainable by other imaging modalities. Thus, automatic extraction of detailed vessel maps can ultimately inform surgical planning. We address the task of delineation of the Superficial Vascular Plexus in 2D Maximum Intensity Projections (MIP) of OCT-A using convolutional neural networks that iteratively refine the quality of the produced vessel segmentations. We demonstrate that the proposed approach compares favourably to alternative network baselines and graph-based methodologies through extensive experimental analysis, using data collected from 50 subjects, including both individuals that underwent surgery for structural macular abnormalities and healthy subjects. Additionally, we demonstrate generalization to 3D segmentation and narrower field-of-view OCT-A. In the future, the extracted vessel maps will be leveraged for surgical planning and semi-automated intraoperative navigation in vitreo-retinal surgery.
format Online
Article
Text
id pubmed-7249805
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Optical Society of America
record_format MEDLINE/PubMed
spelling pubmed-72498052020-06-03 Deep iterative vessel segmentation in OCT angiography Pissas, Theodoros Bloch, Edward Cardoso, M. Jorge Flores, Blanca Georgiadis, Odysseas Jalali, Sepehr Ravasio, Claudio Stoyanov, Danail Da Cruz, Lyndon Bergeles, Christos Biomed Opt Express Article This paper addresses retinal vessel segmentation on optical coherence tomography angiography (OCT-A) images of the human retina. Our approach is motivated by the need for high precision image-guided delivery of regenerative therapies in vitreo-retinal surgery. OCT-A visualizes macular vasculature, the main landmark of the surgically targeted area, at a level of detail and spatial extent unattainable by other imaging modalities. Thus, automatic extraction of detailed vessel maps can ultimately inform surgical planning. We address the task of delineation of the Superficial Vascular Plexus in 2D Maximum Intensity Projections (MIP) of OCT-A using convolutional neural networks that iteratively refine the quality of the produced vessel segmentations. We demonstrate that the proposed approach compares favourably to alternative network baselines and graph-based methodologies through extensive experimental analysis, using data collected from 50 subjects, including both individuals that underwent surgery for structural macular abnormalities and healthy subjects. Additionally, we demonstrate generalization to 3D segmentation and narrower field-of-view OCT-A. In the future, the extracted vessel maps will be leveraged for surgical planning and semi-automated intraoperative navigation in vitreo-retinal surgery. Optical Society of America 2020-04-10 /pmc/articles/PMC7249805/ /pubmed/32499939 http://dx.doi.org/10.1364/BOE.384919 Text en Published by The Optical Society under the terms of the Creative Commons Attribution 4.0 License. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI. Published by The Optical Society under the terms of the Creative Commons Attribution 4.0 License (http://creativecommons.org/licenses/by/4.0/) . Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.
spellingShingle Article
Pissas, Theodoros
Bloch, Edward
Cardoso, M. Jorge
Flores, Blanca
Georgiadis, Odysseas
Jalali, Sepehr
Ravasio, Claudio
Stoyanov, Danail
Da Cruz, Lyndon
Bergeles, Christos
Deep iterative vessel segmentation in OCT angiography
title Deep iterative vessel segmentation in OCT angiography
title_full Deep iterative vessel segmentation in OCT angiography
title_fullStr Deep iterative vessel segmentation in OCT angiography
title_full_unstemmed Deep iterative vessel segmentation in OCT angiography
title_short Deep iterative vessel segmentation in OCT angiography
title_sort deep iterative vessel segmentation in oct angiography
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7249805/
https://www.ncbi.nlm.nih.gov/pubmed/32499939
http://dx.doi.org/10.1364/BOE.384919
work_keys_str_mv AT pissastheodoros deepiterativevesselsegmentationinoctangiography
AT blochedward deepiterativevesselsegmentationinoctangiography
AT cardosomjorge deepiterativevesselsegmentationinoctangiography
AT floresblanca deepiterativevesselsegmentationinoctangiography
AT georgiadisodysseas deepiterativevesselsegmentationinoctangiography
AT jalalisepehr deepiterativevesselsegmentationinoctangiography
AT ravasioclaudio deepiterativevesselsegmentationinoctangiography
AT stoyanovdanail deepiterativevesselsegmentationinoctangiography
AT dacruzlyndon deepiterativevesselsegmentationinoctangiography
AT bergeleschristos deepiterativevesselsegmentationinoctangiography