Deep learning approaches for segmenting Bruch’s membrane opening from OCT volumes

Dominika Sułot; David Alonso-Caneiro; D. Robert Iskander; Michael J. Collins

doi:10.1364/OSAC.403102

Back

Deep learning approaches for segmenting Bruch’s membrane opening from OCT volumes

Journal article

Open access

Peer reviewed

Deep learning approaches for segmenting Bruch’s membrane opening from OCT volumes

Dominika Sułot, David Alonso-Caneiro, D. Robert Iskander and Michael J. Collins

OSA Continuum, Vol.3(12), pp.3351-3364

2020

DOI: https://doi.org/10.1364/OSAC.403102

Files and links (1)

pdf

osac-3-12-33514.68 MBDownload View

Published Version Open Access

Abstract

Automated segmentation of the eye’s morphological features in OCT datasets is fundamental to support rapid clinical decision making and to avoid time-consuming manual segmentation of the images. In recent years, deep learning (DL) techniques have become a commonly employed approach to tackle image analysis problems. This study provides a description of the development of automated DL segmentation methods of the Bruch’s membrane opening (BMO) from a series of OCT cross-sectional scans. A range of DL techniques are systematically evaluated, with the secondary goal to understand the effect of the network input size on the model performance. The results indicate that a fully semantic approach, in which the whole B-scan is considered with data augmentation, results in the best performance, achieving high levels of similarity metrics with a dice coefficient of 0.995 and BMO boundary localization with a mean absolute error of 1.15 pixels. The work further highlights the importance of fully semantic methods over patch-based techniques in the classification of OCT regions.

Details

Title: Deep learning approaches for segmenting Bruch’s membrane opening from OCT volumes
Authors: Dominika Sułot (Corresponding Author) - Wrocław University of Science and Technology
David Alonso-Caneiro (Author) - Queensland University of Technology
D. Robert Iskander (Author) - Wrocław University of Science and Technology
Michael J. Collins (Author) - Queensland University of Technology
Publication details: OSA Continuum, Vol.3(12), pp.3351-3364
Publisher: Optica
Date published: 2020
DOI: 10.1364/OSAC.403102
ISSN: 2578-7519
Copyright note: © 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
Organisation Unit: School of Science, Technology and Engineering
Language: English
Record Identifier: 99973596502621
Output Type: Journal article

Metrics

26 Record Views

4 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Web Of Science research areas: Optics

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites