Cargando…
Joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images
Background: Ultra-Wide-Field (UWF) fundus imaging is an essential diagnostic tool for identifying ophthalmologic diseases, as it captures detailed retinal structures within a wider field of view (FOV). However, the presence of eyelashes along the edge of the eyelids can cast shadows and obscure the...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10196374/ https://www.ncbi.nlm.nih.gov/pubmed/37215081 http://dx.doi.org/10.3389/fcell.2023.1181305 |
_version_ | 1785044338643828736 |
---|---|
author | Zhang, Jiong Sha, Dengfeng Ma, Yuhui Zhang, Dan Tan, Tao Xu, Xiayu Yi, Quanyong Zhao, Yitian |
author_facet | Zhang, Jiong Sha, Dengfeng Ma, Yuhui Zhang, Dan Tan, Tao Xu, Xiayu Yi, Quanyong Zhao, Yitian |
author_sort | Zhang, Jiong |
collection | PubMed |
description | Background: Ultra-Wide-Field (UWF) fundus imaging is an essential diagnostic tool for identifying ophthalmologic diseases, as it captures detailed retinal structures within a wider field of view (FOV). However, the presence of eyelashes along the edge of the eyelids can cast shadows and obscure the view of fundus imaging, which hinders reliable interpretation and subsequent screening of fundus diseases. Despite its limitations, there are currently no effective methods or datasets available for removing eyelash artifacts from UWF fundus images. This research aims to develop an effective approach for eyelash artifact removal and thus improve the visual quality of UWF fundus images for accurate analysis and diagnosis. Methods: To address this issue, we first constructed two UWF fundus datasets: the paired synthetic eyelashes (PSE) dataset and the unpaired real eyelashes (uPRE) dataset. Then we proposed a deep learning architecture called Joint Conditional Generative Adversarial Networks (JcGAN) to remove eyelash artifacts from UWF fundus images. JcGAN employs a shared generator with two discriminators for joint learning of both real and synthetic eyelash artifacts. Furthermore, we designed a background refinement module that refines background information and is trained with the generator in an end-to-end manner. Results: Experimental results on both PSE and uPRE datasets demonstrate the superiority of the proposed JcGAN over several state-of-the-art deep learning approaches. Compared with the best existing method, JcGAN improves PSNR and SSIM by 4.82% and 0.23%, respectively. In addition, we also verified that eyelash artifact removal via JcGAN could significantly improve vessel segmentation performance in UWF fundus images. Assessment via vessel segmentation illustrates that the sensitivity, Dice coefficient and area under curve (AUC) of ResU-Net have respectively increased by 3.64%, 1.54%, and 1.43% after eyelash artifact removal using JcGAN. Conclusion: The proposed JcGAN effectively removes eyelash artifacts in UWF images, resulting in improved visibility of retinal vessels. Our method can facilitate better processing and analysis of retinal vessels and has the potential to improve diagnostic outcomes. |
format | Online Article Text |
id | pubmed-10196374 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-101963742023-05-20 Joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images Zhang, Jiong Sha, Dengfeng Ma, Yuhui Zhang, Dan Tan, Tao Xu, Xiayu Yi, Quanyong Zhao, Yitian Front Cell Dev Biol Cell and Developmental Biology Background: Ultra-Wide-Field (UWF) fundus imaging is an essential diagnostic tool for identifying ophthalmologic diseases, as it captures detailed retinal structures within a wider field of view (FOV). However, the presence of eyelashes along the edge of the eyelids can cast shadows and obscure the view of fundus imaging, which hinders reliable interpretation and subsequent screening of fundus diseases. Despite its limitations, there are currently no effective methods or datasets available for removing eyelash artifacts from UWF fundus images. This research aims to develop an effective approach for eyelash artifact removal and thus improve the visual quality of UWF fundus images for accurate analysis and diagnosis. Methods: To address this issue, we first constructed two UWF fundus datasets: the paired synthetic eyelashes (PSE) dataset and the unpaired real eyelashes (uPRE) dataset. Then we proposed a deep learning architecture called Joint Conditional Generative Adversarial Networks (JcGAN) to remove eyelash artifacts from UWF fundus images. JcGAN employs a shared generator with two discriminators for joint learning of both real and synthetic eyelash artifacts. Furthermore, we designed a background refinement module that refines background information and is trained with the generator in an end-to-end manner. Results: Experimental results on both PSE and uPRE datasets demonstrate the superiority of the proposed JcGAN over several state-of-the-art deep learning approaches. Compared with the best existing method, JcGAN improves PSNR and SSIM by 4.82% and 0.23%, respectively. In addition, we also verified that eyelash artifact removal via JcGAN could significantly improve vessel segmentation performance in UWF fundus images. Assessment via vessel segmentation illustrates that the sensitivity, Dice coefficient and area under curve (AUC) of ResU-Net have respectively increased by 3.64%, 1.54%, and 1.43% after eyelash artifact removal using JcGAN. Conclusion: The proposed JcGAN effectively removes eyelash artifacts in UWF images, resulting in improved visibility of retinal vessels. Our method can facilitate better processing and analysis of retinal vessels and has the potential to improve diagnostic outcomes. Frontiers Media S.A. 2023-05-05 /pmc/articles/PMC10196374/ /pubmed/37215081 http://dx.doi.org/10.3389/fcell.2023.1181305 Text en Copyright © 2023 Zhang, Sha, Ma, Zhang, Tan, Xu, Yi and Zhao. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Cell and Developmental Biology Zhang, Jiong Sha, Dengfeng Ma, Yuhui Zhang, Dan Tan, Tao Xu, Xiayu Yi, Quanyong Zhao, Yitian Joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images |
title | Joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images |
title_full | Joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images |
title_fullStr | Joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images |
title_full_unstemmed | Joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images |
title_short | Joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images |
title_sort | joint conditional generative adversarial networks for eyelash artifact removal in ultra-wide-field fundus images |
topic | Cell and Developmental Biology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10196374/ https://www.ncbi.nlm.nih.gov/pubmed/37215081 http://dx.doi.org/10.3389/fcell.2023.1181305 |
work_keys_str_mv | AT zhangjiong jointconditionalgenerativeadversarialnetworksforeyelashartifactremovalinultrawidefieldfundusimages AT shadengfeng jointconditionalgenerativeadversarialnetworksforeyelashartifactremovalinultrawidefieldfundusimages AT mayuhui jointconditionalgenerativeadversarialnetworksforeyelashartifactremovalinultrawidefieldfundusimages AT zhangdan jointconditionalgenerativeadversarialnetworksforeyelashartifactremovalinultrawidefieldfundusimages AT tantao jointconditionalgenerativeadversarialnetworksforeyelashartifactremovalinultrawidefieldfundusimages AT xuxiayu jointconditionalgenerativeadversarialnetworksforeyelashartifactremovalinultrawidefieldfundusimages AT yiquanyong jointconditionalgenerativeadversarialnetworksforeyelashartifactremovalinultrawidefieldfundusimages AT zhaoyitian jointconditionalgenerativeadversarialnetworksforeyelashartifactremovalinultrawidefieldfundusimages |