MFGAN: OCT Image Super-resolution and Enhancement with Blind Degradation and Multi-frame Fusion

He, Z; Xiao, Z; Xu, Z; Li, Y; Song, Z; Leighton, C; Wang, L; Liu, S; Wong, SY; Huang, W; Jia, W; Lam, KM

MFGAN: OCT Image Super-resolution and Enhancement with Blind Degradation and Multi-frame Fusion

He, Z Xiao, Z Xu, Z Li, Y Song, Z Leighton, C Wang, L Liu, S Wong, SY Huang, W Jia, W

Lam, KM

Permalink

Publisher:: SPIE, the international society for optics and photonics
Publication Type:: Conference Proceeding
Citation:: Proceedings of SPIE the International Society for Optical Engineering, 2025, 13510, pp. 1351005-1351005-6
Issue Date:: 2025-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted versionAdobe PDF (2.07 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	He, Z
dc.contributor.author	Xiao, Z
dc.contributor.author	Xu, Z
dc.contributor.author	Li, Y
dc.contributor.author	Song, Z
dc.contributor.author	Leighton, C
dc.contributor.author	Wang, L
dc.contributor.author	Liu, S
dc.contributor.author	Wong, SY
dc.contributor.author	Huang, W
dc.contributor.author	Jia, W https://orcid.org/0000-0002-0940-3338
dc.contributor.author	Lam, KM
dc.contributor.editor	Kim, J-G
dc.contributor.editor	Yeh, C-H
dc.contributor.editor	Qian, K
dc.contributor.editor	Nakajima, M
dc.contributor.editor	Chang, C-Y
dc.contributor.editor	Lau, PY
dc.date	2025-01-06
dc.date.accessioned	2025-08-11T04:06:08Z
dc.date.available	2025-08-11T04:06:08Z
dc.date.issued	2025-01-01
dc.identifier.citation	Proceedings of SPIE the International Society for Optical Engineering, 2025, 13510, pp. 1351005-1351005-6
dc.identifier.issn	0277-786X
dc.identifier.issn	1996-756X
dc.identifier.uri	http://hdl.handle.net/10453/189366
dc.description.abstract	Optical coherence tomography (OCT) is crucial in medical imaging, especially for retinal diagnostics.However, its effectiveness is often limited by imaging devices, resulting in high noise levels, low resolution, and reduced sampling rates, which hinder OCT image diagnosis.This paper proposes a generative adversarial network (GAN) based OCT image super-resolution framework that leverages a blind degradation and Multi-frame Fusion mechanism, namely MFGAN, for retinal OCT image super-resolution.Our method jointly performs denoising, blind super-resolution, and multi-frame fusion, which can reconstruct high quality OCT images without requiring paired ground-truth data.We employ a blind degradation model to handle OCT image degradation and a denoising prior to effectively process noisy inputs.Experimental results on the PKU37 dataset and the VIP Cup 2024 dataset demonstrate that MFGAN excels in both visual quality and quantitative performance, outperforming existing OCT image super-resolution methods.
dc.language	en
dc.publisher	SPIE, the international society for optics and photonics
dc.relation.ispartof	Proceedings of SPIE the International Society for Optical Engineering
dc.relation.ispartof	International Workshop on Advanced Imaging Technology (IWAIT) 2025
dc.relation.isbasedon	10.1117/12.3057230
dc.rights	info:eu-repo/semantics/openAccess
dc.subject.classification	4006 Communications engineering
dc.subject.classification	4009 Electronics, sensors and digital hardware
dc.subject.classification	5102 Atomic, molecular and optical physics
dc.title	MFGAN: OCT Image Super-resolution and Enhancement with Blind Degradation and Multi-frame Fusion
dc.type	Conference Proceeding
utslib.citation.volume	13510
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Global Big Data Technologies Centre (GBDTC)
utslib.copyright.status	open_access	*
dc.date.updated	2025-08-11T04:06:07Z
pubs.finish-date	2025-01-08
pubs.publication-status	Published
pubs.start-date	2025-01-06
pubs.volume	13510

Abstract:

Optical coherence tomography (OCT) is crucial in medical imaging, especially for retinal diagnostics.However, its effectiveness is often limited by imaging devices, resulting in high noise levels, low resolution, and reduced sampling rates, which hinder OCT image diagnosis.This paper proposes a generative adversarial network (GAN) based OCT image super-resolution framework that leverages a blind degradation and Multi-frame Fusion mechanism, namely MFGAN, for retinal OCT image super-resolution.Our method jointly performs denoising, blind super-resolution, and multi-frame fusion, which can reconstruct high quality OCT images without requiring paired ground-truth data.We employ a blind degradation model to handle OCT image degradation and a denoising prior to effectively process noisy inputs.Experimental results on the PKU37 dataset and the VIP Cup 2024 dataset demonstrate that MFGAN excels in both visual quality and quantitative performance, outperforming existing OCT image super-resolution methods.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/189366