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

Zongqi He; Zhe Xiao; Zhuoning Xu; Yunze Li; Zelin Song; Calvin Leighton; Li Wang; Shanru Liu; Shiun Yee Wong; Wenfeng Huang; Wenjing Jia; Kin Man Lam

doi:10.1117/12.3057230

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

Zongqi He
, Zhe Xiao
, Zhuoning Xu
, Yunze Li
, Zelin Song
, Calvin Leighton
, Li Wang
, Shanru Liu
, Shiun Yee Wong
, Wenfeng Huang
, Wenjing Jia
, Kin Man Lam

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

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.

Original language	English
Title of host publication	International Workshop on Advanced Imaging Technology, IWAIT 2025
Editors	Masayuki Nakajima, Chuan-Yu Chang, Chia-Hung Yeh, Jae-Gon Kim, Kemao Qian, Phooi Yee Lau
Publisher	SPIE
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781510688124
DOIs	https://doi.org/10.1117/12.3057230
Publication status	Published - Feb 2025
Event	2025 International Workshop on Advanced Imaging Technology, IWAIT 2025 - Douliu City, Taiwan Duration: 6 Jan 2025 → 8 Jan 2025

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	13510
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	2025 International Workshop on Advanced Imaging Technology, IWAIT 2025
Country/Territory	Taiwan
City	Douliu City
Period	6/01/25 → 8/01/25

Keywords

Blind Degradation
Image Enhancement
Multi-frame Fusion
OCT Image Super-resolution

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

More information

10.1117/12.3057230

Cite this

He, Z., Xiao, Z., Xu, Z., Li, Y., Song, Z., Leighton, C., Wang, L., Liu, S., Wong, S. Y., Huang, W., Jia, W., & Lam, K. M. (2025). MFGAN: OCT Image Super-resolution and Enhancement with Blind Degradation and Multi-frame Fusion. In M. Nakajima, C.-Y. Chang, C.-H. Yeh, J.-G. Kim, K. Qian, & P. Y. Lau (Eds.), International Workshop on Advanced Imaging Technology, IWAIT 2025 (pp. 1-6). Article 1351005 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13510). SPIE. https://doi.org/10.1117/12.3057230

He, Zongqi ; Xiao, Zhe ; Xu, Zhuoning et al. / MFGAN: OCT Image Super-resolution and Enhancement with Blind Degradation and Multi-frame Fusion. International Workshop on Advanced Imaging Technology, IWAIT 2025. editor / Masayuki Nakajima ; Chuan-Yu Chang ; Chia-Hung Yeh ; Jae-Gon Kim ; Kemao Qian ; Phooi Yee Lau. SPIE, 2025. pp. 1-6 (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{03a4ad8a2ff34551bb9760ffea6ef613,

title = "MFGAN: OCT Image Super-resolution and Enhancement with Blind Degradation and Multi-frame Fusion",

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.",

keywords = "Blind Degradation, Image Enhancement, Multi-frame Fusion, OCT Image Super-resolution",

author = "Zongqi He and Zhe Xiao and Zhuoning Xu and Yunze Li and Zelin Song and Calvin Leighton and Li Wang and Shanru Liu and Wong, \{Shiun Yee\} and Wenfeng Huang and Wenjing Jia and Lam, \{Kin Man\}",

note = "Publisher Copyright: {\textcopyright} 2024 SPIE.; 2025 International Workshop on Advanced Imaging Technology, IWAIT 2025 ; Conference date: 06-01-2025 Through 08-01-2025",

year = "2025",

month = feb,

doi = "10.1117/12.3057230",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

pages = "1--6",

editor = "Masayuki Nakajima and Chuan-Yu Chang and Chia-Hung Yeh and Jae-Gon Kim and Kemao Qian and Lau, \{Phooi Yee\}",

booktitle = "International Workshop on Advanced Imaging Technology, IWAIT 2025",

address = "United States",

}

He, Z , Xiao, Z , Xu, Z , Li, Y , Song, Z, Leighton, C, Wang, L, Liu, S, Wong, SY, Huang, W, Jia, W & Lam, KM 2025, MFGAN: OCT Image Super-resolution and Enhancement with Blind Degradation and Multi-frame Fusion. in M Nakajima, C-Y Chang, C-H Yeh, J-G Kim, K Qian & PY Lau (eds), International Workshop on Advanced Imaging Technology, IWAIT 2025., 1351005, Proceedings of SPIE - The International Society for Optical Engineering, vol. 13510, SPIE, pp. 1-6, 2025 International Workshop on Advanced Imaging Technology, IWAIT 2025, Douliu City, Taiwan, 6/01/25. https://doi.org/10.1117/12.3057230

MFGAN: OCT Image Super-resolution and Enhancement with Blind Degradation and Multi-frame Fusion. / He, Zongqi ; Xiao, Zhe ; Xu, Zhuoning et al.
International Workshop on Advanced Imaging Technology, IWAIT 2025. ed. / Masayuki Nakajima; Chuan-Yu Chang; Chia-Hung Yeh; Jae-Gon Kim; Kemao Qian; Phooi Yee Lau. SPIE, 2025. p. 1-6 1351005 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13510).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - MFGAN: OCT Image Super-resolution and Enhancement with Blind Degradation and Multi-frame Fusion

AU - He, Zongqi

AU - Xiao, Zhe

AU - Xu, Zhuoning

AU - Li, Yunze

AU - Song, Zelin

AU - Leighton, Calvin

AU - Wang, Li

AU - Liu, Shanru

AU - Wong, Shiun Yee

AU - Huang, Wenfeng

AU - Jia, Wenjing

AU - Lam, Kin Man

PY - 2025/2

Y1 - 2025/2

N2 - 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.

AB - 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.

KW - Blind Degradation

KW - Image Enhancement

KW - Multi-frame Fusion

KW - OCT Image Super-resolution

UR - https://www.scopus.com/pages/publications/85218350553

U2 - 10.1117/12.3057230

DO - 10.1117/12.3057230

M3 - Conference article published in proceeding or book

AN - SCOPUS:85218350553

T3 - Proceedings of SPIE - The International Society for Optical Engineering

SP - 1

EP - 6

BT - International Workshop on Advanced Imaging Technology, IWAIT 2025

A2 - Nakajima, Masayuki

A2 - Chang, Chuan-Yu

A2 - Yeh, Chia-Hung

A2 - Kim, Jae-Gon

A2 - Qian, Kemao

A2 - Lau, Phooi Yee

PB - SPIE

T2 - 2025 International Workshop on Advanced Imaging Technology, IWAIT 2025

Y2 - 6 January 2025 through 8 January 2025

ER -

He Z , Xiao Z , Xu Z , Li Y , Song Z, Leighton C et al. MFGAN: OCT Image Super-resolution and Enhancement with Blind Degradation and Multi-frame Fusion. In Nakajima M, Chang CY, Yeh CH, Kim JG, Qian K, Lau PY, editors, International Workshop on Advanced Imaging Technology, IWAIT 2025. SPIE. 2025. p. 1-6. 1351005. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.3057230

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

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this