King's College London

Research portal

Deep Iterative Vessel Segmentation in OCT Angiography

Research output: Contribution to journalArticle

Standard

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.

In: Biomedical Optics Express, Vol. 11, No. 5, 01.05.2020, p. 2490-2510.

Research output: Contribution to journalArticle

Harvard

Pissas, T, Bloch, E, Cardoso, MJ, Flores, B, Georgiadis, O, Jalali, S, Ravasio, C, Stoyanov, D, Da Cruz, L & Bergeles, C 2020, 'Deep Iterative Vessel Segmentation in OCT Angiography', Biomedical Optics Express, vol. 11, no. 5, pp. 2490-2510. https://doi.org/10.1364/BOE.384919

APA

Pissas, T., Bloch, E., Cardoso, M. J., Flores, B., Georgiadis, O., Jalali, S., Ravasio, C., Stoyanov, D., Da Cruz, L., & Bergeles, C. (2020). Deep Iterative Vessel Segmentation in OCT Angiography. Biomedical Optics Express, 11(5), 2490-2510. https://doi.org/10.1364/BOE.384919

Vancouver

Pissas T, Bloch E, Cardoso MJ, Flores B, Georgiadis O, Jalali S et al. Deep Iterative Vessel Segmentation in OCT Angiography. Biomedical Optics Express. 2020 May 1;11(5):2490-2510. https://doi.org/10.1364/BOE.384919

Author

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. In: Biomedical Optics Express. 2020 ; Vol. 11, No. 5. pp. 2490-2510.

Bibtex Download

@article{270eab2a52b7487c9537cf2f450f42fe,
title = "Deep Iterative Vessel Segmentation in OCT Angiography",
abstract = "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 Plexusin2D 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 from50subjects, including both individuals that underwent surgery for structural macular abnormalities and healthy subjects. Additionally, we demonstrate generalization to3Dsegmentation 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.",
author = "Theodoros Pissas and Edward Bloch and Cardoso, {M. Jorge} and Blanca Flores and Odysseas Georgiadis and Sepehr Jalali and Claudio Ravasio and Danail Stoyanov and {Da Cruz}, Lyndon and Christos Bergeles",
year = "2020",
month = may,
day = "1",
doi = "10.1364/BOE.384919",
language = "English",
volume = "11",
pages = "2490--2510",
journal = "Biomedical Optics Express",
issn = "2156-7085",
publisher = "The Optical Society",
number = "5",

}

RIS (suitable for import to EndNote) Download

TY - JOUR

T1 - Deep Iterative Vessel Segmentation in OCT Angiography

AU - Pissas, Theodoros

AU - Bloch, Edward

AU - Cardoso, M. Jorge

AU - Flores, Blanca

AU - Georgiadis, Odysseas

AU - Jalali, Sepehr

AU - Ravasio, Claudio

AU - Stoyanov, Danail

AU - Da Cruz, Lyndon

AU - Bergeles, Christos

PY - 2020/5/1

Y1 - 2020/5/1

N2 - 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 Plexusin2D 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 from50subjects, including both individuals that underwent surgery for structural macular abnormalities and healthy subjects. Additionally, we demonstrate generalization to3Dsegmentation 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.

AB - 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 Plexusin2D 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 from50subjects, including both individuals that underwent surgery for structural macular abnormalities and healthy subjects. Additionally, we demonstrate generalization to3Dsegmentation 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.

UR - http://www.scopus.com/inward/record.url?scp=85084680470&partnerID=8YFLogxK

U2 - 10.1364/BOE.384919

DO - 10.1364/BOE.384919

M3 - Article

AN - SCOPUS:85084680470

VL - 11

SP - 2490

EP - 2510

JO - Biomedical Optics Express

JF - Biomedical Optics Express

SN - 2156-7085

IS - 5

ER -

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454