Enhanced OCT chorio-retinal segmentation in low-data settings with semi-supervised GAN augmentation using cross-localisation

Jason Kugelman; David Alonso-Caneiro; Scott A. Read; Stephen J. Vincent; Michael J. Collins

doi:10.1016/j.cviu.2023.103852

Back

Enhanced OCT chorio-retinal segmentation in low-data settings with semi-supervised GAN augmentation using cross-localisation

Journal article

Open access

Peer reviewed

Enhanced OCT chorio-retinal segmentation in low-data settings with semi-supervised GAN augmentation using cross-localisation

Jason Kugelman, David Alonso-Caneiro, Scott A. Read, Stephen J. Vincent and Michael J. Collins

Computer Vision and Image Understanding, Vol.237, pp.1-11

2023

DOI: https://doi.org/10.1016/j.cviu.2023.103852

Files and links (2)

pdf

preproof2.68 MBDownload View

Published VersionCC BY V4.0, Open Access

url

https://doi.org/10.1016/j.cviu.2023.103852View

Published Version

Abstract

Data augmentation

Deep learning

GANs

Generative adversarial networks

Machine learning

OCT

Semi-supervised learning

Training deep learning methods for optical coherence tomography (OCT) retinal and choroidal layer segmentation is a challenge when data is scarce. In medical image analysis, this is often the case with a lack of data sharing due to confidentiality agreements and data privacy concerns which is further exacerbated in cases of rare pathologies. Even where OCT data is readily available, performing the requisite annotations is time consuming, costly, and error-prone. Data augmentation and semi-supervised learning (SSL) are two techniques employed in deep learning to enhance training in these situations. In this study, we extend our previous work proposing an enhanced StyleGAN2-based data augmentation method for OCT images by employing SSL through a novel cross-localisation technique. The technique increases the diversity of the synthetic data by automatically incorporating styles from unlabeled data with those from labelled data. The method can be used to extend StyleGAN2 as the core idea is simple, yet highly performant. In this work, we optimize the method through a set of ablations and propose the use of a targeted task-specific model selection technique for more optimal generator selection, further boosting performance. The method is applied to OCT retinal and choroidal layer segmentation, demonstrating its effectiveness through substantial patch classification performance improvements as well as significant reductions in choroidal layer segmentation error.

Details

Title: Enhanced OCT chorio-retinal segmentation in low-data settings with semi-supervised GAN augmentation using cross-localisation
Authors: Jason Kugelman (Corresponding Author) - Queensland University of Technology
David Alonso-Caneiro (Author) - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Scott A. Read (Author) - Queensland University of Technology
Stephen J. Vincent (Author) - Queensland University of Technology
Michael J. Collins (Author) - Queensland University of Technology
Publication details: Computer Vision and Image Understanding, Vol.237, pp.1-11
Publisher: Academic Press
Date published: 2023
DOI: 10.1016/j.cviu.2023.103852
ISSN: 1090-235X; 1077-3142
Data Availability: The authors do not have permission to share data.
Organisation Unit: University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering
Language: English
Record Identifier: 99971194602621
Output Type: Journal article

Metrics

4 File views/ downloads

33 Record Views