Synthesizing multi-frame high-resolution fluorescein angiography images from retinal fundus images using generative adversarial networks

Fundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular circulation in the fundus. As FA may pose a risk to patients, generative adversarial networks have been used to convert retinal fundus images into fluorescein an...

Full description

Saved in:
Bibliographic Details
Published inBiomedical engineering online Vol. 22; no. 1; pp. 16 - 15
Main Authors Li, Ping, He, Yi, Wang, Pinghe, Wang, Jing, Shi, Guohua, Chen, Yiwei
Format Journal Article
LanguageEnglish
Published England BioMed Central Ltd 21.02.2023
BioMed Central
BMC
Subjects
Ablation
Angiography
Attention
Blood vessels
Classification
Coders
Cross correlation
Datasets
Deep learning
Diabetic retinopathy
Diagnosis
Fluorescein
Fluorescein Angiography
Fluorescein angiography images
Fluorescence angiography
Fundus Oculi
Generative adversarial network
Generative adversarial networks
Generators
High resolution
Humans
Image Processing, Computer-Assisted - methods
Image resolution
Image segmentation
Liquors
Medical examination
Medical imaging
Methods
Multi-frame
Neural networks
Performance evaluation
Retina
Retinal diseases
Retinal fundus images
Signal to noise ratio
Similarity
Unsupervised learning
China
High-resolution
Fluorescein angiography images
Multi-frame
Retinal fundus images
Generative adversarial network
Online AccessGet full text

Cover

Abstract Fundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular circulation in the fundus. As FA may pose a risk to patients, generative adversarial networks have been used to convert retinal fundus images into fluorescein angiography images. However, the available methods focus on generating FA images of a single phase, and the resolution of the generated FA images is low, being unsuitable for accurately diagnosing fundus diseases. We propose a network that generates multi-frame high-resolution FA images. This network consists of a low-resolution GAN (LrGAN) and a high-resolution GAN (HrGAN), where LrGAN generates low-resolution and full-size FA images with global intensity information, HrGAN takes the FA images generated by LrGAN as input to generate multi-frame high-resolution FA patches. Finally, the FA patches are merged into full-size FA images. Our approach combines supervised and unsupervised learning methods and achieves better quantitative and qualitative results than using either method alone. Structural similarity (SSIM), normalized cross-correlation (NCC) and peak signal-to-noise ratio (PSNR) were used as quantitative metrics to evaluate the performance of the proposed method. The experimental results show that our method achieves better quantitative results with structural similarity of 0.7126, normalized cross-correlation of 0.6799, and peak signal-to-noise ratio of 15.77. In addition, ablation experiments also demonstrate that using a shared encoder and residual channel attention module in HrGAN is helpful for the generation of high-resolution images. Overall, our method has higher performance for generating retinal vessel details and leaky structures in multiple critical phases, showing a promising clinical diagnostic value.
AbstractList Fundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular circulation in the fundus. As FA may pose a risk to patients, generative adversarial networks have been used to convert retinal fundus images into fluorescein angiography images. However, the available methods focus on generating FA images of a single phase, and the resolution of the generated FA images is low, being unsuitable for accurately diagnosing fundus diseases.BACKGROUNDFundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular circulation in the fundus. As FA may pose a risk to patients, generative adversarial networks have been used to convert retinal fundus images into fluorescein angiography images. However, the available methods focus on generating FA images of a single phase, and the resolution of the generated FA images is low, being unsuitable for accurately diagnosing fundus diseases.We propose a network that generates multi-frame high-resolution FA images. This network consists of a low-resolution GAN (LrGAN) and a high-resolution GAN (HrGAN), where LrGAN generates low-resolution and full-size FA images with global intensity information, HrGAN takes the FA images generated by LrGAN as input to generate multi-frame high-resolution FA patches. Finally, the FA patches are merged into full-size FA images.METHODSWe propose a network that generates multi-frame high-resolution FA images. This network consists of a low-resolution GAN (LrGAN) and a high-resolution GAN (HrGAN), where LrGAN generates low-resolution and full-size FA images with global intensity information, HrGAN takes the FA images generated by LrGAN as input to generate multi-frame high-resolution FA patches. Finally, the FA patches are merged into full-size FA images.Our approach combines supervised and unsupervised learning methods and achieves better quantitative and qualitative results than using either method alone. Structural similarity (SSIM), normalized cross-correlation (NCC) and peak signal-to-noise ratio (PSNR) were used as quantitative metrics to evaluate the performance of the proposed method. The experimental results show that our method achieves better quantitative results with structural similarity of 0.7126, normalized cross-correlation of 0.6799, and peak signal-to-noise ratio of 15.77. In addition, ablation experiments also demonstrate that using a shared encoder and residual channel attention module in HrGAN is helpful for the generation of high-resolution images.RESULTSOur approach combines supervised and unsupervised learning methods and achieves better quantitative and qualitative results than using either method alone. Structural similarity (SSIM), normalized cross-correlation (NCC) and peak signal-to-noise ratio (PSNR) were used as quantitative metrics to evaluate the performance of the proposed method. The experimental results show that our method achieves better quantitative results with structural similarity of 0.7126, normalized cross-correlation of 0.6799, and peak signal-to-noise ratio of 15.77. In addition, ablation experiments also demonstrate that using a shared encoder and residual channel attention module in HrGAN is helpful for the generation of high-resolution images.Overall, our method has higher performance for generating retinal vessel details and leaky structures in multiple critical phases, showing a promising clinical diagnostic value.CONCLUSIONSOverall, our method has higher performance for generating retinal vessel details and leaky structures in multiple critical phases, showing a promising clinical diagnostic value.
Fundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular circulation in the fundus. As FA may pose a risk to patients, generative adversarial networks have been used to convert retinal fundus images into fluorescein angiography images. However, the available methods focus on generating FA images of a single phase, and the resolution of the generated FA images is low, being unsuitable for accurately diagnosing fundus diseases. We propose a network that generates multi-frame high-resolution FA images. This network consists of a low-resolution GAN (LrGAN) and a high-resolution GAN (HrGAN), where LrGAN generates low-resolution and full-size FA images with global intensity information, HrGAN takes the FA images generated by LrGAN as input to generate multi-frame high-resolution FA patches. Finally, the FA patches are merged into full-size FA images. Our approach combines supervised and unsupervised learning methods and achieves better quantitative and qualitative results than using either method alone. Structural similarity (SSIM), normalized cross-correlation (NCC) and peak signal-to-noise ratio (PSNR) were used as quantitative metrics to evaluate the performance of the proposed method. The experimental results show that our method achieves better quantitative results with structural similarity of 0.7126, normalized cross-correlation of 0.6799, and peak signal-to-noise ratio of 15.77. In addition, ablation experiments also demonstrate that using a shared encoder and residual channel attention module in HrGAN is helpful for the generation of high-resolution images. Overall, our method has higher performance for generating retinal vessel details and leaky structures in multiple critical phases, showing a promising clinical diagnostic value.
Abstract Background Fundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular circulation in the fundus. As FA may pose a risk to patients, generative adversarial networks have been used to convert retinal fundus images into fluorescein angiography images. However, the available methods focus on generating FA images of a single phase, and the resolution of the generated FA images is low, being unsuitable for accurately diagnosing fundus diseases. Methods We propose a network that generates multi-frame high-resolution FA images. This network consists of a low-resolution GAN (LrGAN) and a high-resolution GAN (HrGAN), where LrGAN generates low-resolution and full-size FA images with global intensity information, HrGAN takes the FA images generated by LrGAN as input to generate multi-frame high-resolution FA patches. Finally, the FA patches are merged into full-size FA images. Results Our approach combines supervised and unsupervised learning methods and achieves better quantitative and qualitative results than using either method alone. Structural similarity (SSIM), normalized cross-correlation (NCC) and peak signal-to-noise ratio (PSNR) were used as quantitative metrics to evaluate the performance of the proposed method. The experimental results show that our method achieves better quantitative results with structural similarity of 0.7126, normalized cross-correlation of 0.6799, and peak signal-to-noise ratio of 15.77. In addition, ablation experiments also demonstrate that using a shared encoder and residual channel attention module in HrGAN is helpful for the generation of high-resolution images. Conclusions Overall, our method has higher performance for generating retinal vessel details and leaky structures in multiple critical phases, showing a promising clinical diagnostic value.
Fundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular circulation in the fundus. As FA may pose a risk to patients, generative adversarial networks have been used to convert retinal fundus images into fluorescein angiography images. However, the available methods focus on generating FA images of a single phase, and the resolution of the generated FA images is low, being unsuitable for accurately diagnosing fundus diseases. We propose a network that generates multi-frame high-resolution FA images. This network consists of a low-resolution GAN (LrGAN) and a high-resolution GAN (HrGAN), where LrGAN generates low-resolution and full-size FA images with global intensity information, HrGAN takes the FA images generated by LrGAN as input to generate multi-frame high-resolution FA patches. Finally, the FA patches are merged into full-size FA images. Our approach combines supervised and unsupervised learning methods and achieves better quantitative and qualitative results than using either method alone. Structural similarity (SSIM), normalized cross-correlation (NCC) and peak signal-to-noise ratio (PSNR) were used as quantitative metrics to evaluate the performance of the proposed method. The experimental results show that our method achieves better quantitative results with structural similarity of 0.7126, normalized cross-correlation of 0.6799, and peak signal-to-noise ratio of 15.77. In addition, ablation experiments also demonstrate that using a shared encoder and residual channel attention module in HrGAN is helpful for the generation of high-resolution images. Overall, our method has higher performance for generating retinal vessel details and leaky structures in multiple critical phases, showing a promising clinical diagnostic value.
Background Fundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular circulation in the fundus. As FA may pose a risk to patients, generative adversarial networks have been used to convert retinal fundus images into fluorescein angiography images. However, the available methods focus on generating FA images of a single phase, and the resolution of the generated FA images is low, being unsuitable for accurately diagnosing fundus diseases. Methods We propose a network that generates multi-frame high-resolution FA images. This network consists of a low-resolution GAN (LrGAN) and a high-resolution GAN (HrGAN), where LrGAN generates low-resolution and full-size FA images with global intensity information, HrGAN takes the FA images generated by LrGAN as input to generate multi-frame high-resolution FA patches. Finally, the FA patches are merged into full-size FA images. Results Our approach combines supervised and unsupervised learning methods and achieves better quantitative and qualitative results than using either method alone. Structural similarity (SSIM), normalized cross-correlation (NCC) and peak signal-to-noise ratio (PSNR) were used as quantitative metrics to evaluate the performance of the proposed method. The experimental results show that our method achieves better quantitative results with structural similarity of 0.7126, normalized cross-correlation of 0.6799, and peak signal-to-noise ratio of 15.77. In addition, ablation experiments also demonstrate that using a shared encoder and residual channel attention module in HrGAN is helpful for the generation of high-resolution images. Conclusions Overall, our method has higher performance for generating retinal vessel details and leaky structures in multiple critical phases, showing a promising clinical diagnostic value. Keywords: Retinal fundus images, Fluorescein angiography images, Multi-frame, High-resolution, Generative adversarial network
BackgroundFundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular circulation in the fundus. As FA may pose a risk to patients, generative adversarial networks have been used to convert retinal fundus images into fluorescein angiography images. However, the available methods focus on generating FA images of a single phase, and the resolution of the generated FA images is low, being unsuitable for accurately diagnosing fundus diseases.MethodsWe propose a network that generates multi-frame high-resolution FA images. This network consists of a low-resolution GAN (LrGAN) and a high-resolution GAN (HrGAN), where LrGAN generates low-resolution and full-size FA images with global intensity information, HrGAN takes the FA images generated by LrGAN as input to generate multi-frame high-resolution FA patches. Finally, the FA patches are merged into full-size FA images.ResultsOur approach combines supervised and unsupervised learning methods and achieves better quantitative and qualitative results than using either method alone. Structural similarity (SSIM), normalized cross-correlation (NCC) and peak signal-to-noise ratio (PSNR) were used as quantitative metrics to evaluate the performance of the proposed method. The experimental results show that our method achieves better quantitative results with structural similarity of 0.7126, normalized cross-correlation of 0.6799, and peak signal-to-noise ratio of 15.77. In addition, ablation experiments also demonstrate that using a shared encoder and residual channel attention module in HrGAN is helpful for the generation of high-resolution images.ConclusionsOverall, our method has higher performance for generating retinal vessel details and leaky structures in multiple critical phases, showing a promising clinical diagnostic value.
ArticleNumber 16
Audience Academic
Author He, Yi
Wang, Jing
Li, Ping
Wang, Pinghe
Shi, Guohua
Chen, Yiwei
Author_xml – sequence: 1
  givenname: Ping
  surname: Li
  fullname: Li, Ping
– sequence: 2
  givenname: Yi
  surname: He
  fullname: He, Yi
– sequence: 3
  givenname: Pinghe
  surname: Wang
  fullname: Wang, Pinghe
– sequence: 4
  givenname: Jing
  surname: Wang
  fullname: Wang, Jing
– sequence: 5
  givenname: Guohua
  surname: Shi
  fullname: Shi, Guohua
– sequence: 6
  givenname: Yiwei
  surname: Chen
  fullname: Chen, Yiwei
BackLink https://www.ncbi.nlm.nih.gov/pubmed/36810105$$D View this record in MEDLINE/PubMed
BookMark eNp9kttuFSEUhiemxh70Bbwwk3hTL6bCwDBwY9I0Hpo0MbGaeEfW5jCbOgMVmOr2CXxs2d1t7W6M4QJYfP8PrPz71Y4P3lTVc4yOMObsdcKtILxBLWkQRj1q2KNqD9O-a0Tbfd25t96t9lO6QKhFiIkn1S5hHBdJt1f9Pl_5vDTJ_XJ-qKd5zK6xESZTL92wbKJJYZyzC7624xzKVhnna_CDC0OEy-WqdhMMJtU2hqmOJjsPY21nr-d0ezSntfdgvImQ3ZWpQV-ZmCC6gnqTf4T4LT2tHlsYk3l2Mx9UX969_XzyoTn7-P705PisUZ3oc6M5hrazAD3GViEOiilNAZjVvdZACBW4ZZ3gxLSCEqCMG0O4Xmja9ZYbclCdbnx1gAt5Gcsb40oGcPK6EOIgIWanRiM1sUZRLVirBBUUeK8EMEIp4WqB8drrzcbrcl5MRivjc4Rxy3T7xLulHMKVFIJ2jKNicHhjEMP32aQsJ1c6PI7gTZiTbPteEMoYEgV9-QC9CHMszV5TnNO-Jbj7Sw1QPuC8DeVetTaVxz3hmJUA8EId_YMqQ5vJqRIy60p9S_BqS1CYbH7mAeaU5On5p232xf2m3HXjNnMFaDeAiiGlaOwdgpFcB1tugi1LsOV1sCUrIv5ApFyGdTDL0934P-kf-Df_Mw
CitedBy_id crossref_primary_10_3390_biomedicines13020284
crossref_primary_10_1007_s11517_024_03191_z
crossref_primary_10_1080_17434440_2023_2294364
crossref_primary_10_3389_fonc_2024_1287995
crossref_primary_10_3390_app15063084
crossref_primary_10_1038_s41746_024_01018_7
crossref_primary_10_3390_info15010012
crossref_primary_10_1142_S1793545824500032
crossref_primary_10_1145_3653456
crossref_primary_10_1016_j_jconrel_2025_113650
Cites_doi 10.1109/TPAMI.2019.2913372
10.1109/CVPR.2018.00917
10.1109/ICCV.2017.244
10.1109/TBME.2018.2814538
10.1117/12.2512549
10.1109/TMI.2017.2759102
10.1109/CVPR.2017.683
10.1109/JBHI.2018.2872813
10.1109/ICPR48806.2021.9412428
10.1016/j.knosys.2019.03.016
10.1109/TMI.2018.2794988
10.1007/978-3-030-00928-1_37
10.1109/TIP.2003.819861
10.1109/IJCNN.2019.8852082
10.1109/CVPR.2018.00916
10.1109/CVPR.2016.90
10.1590/S0004-27492007000400011
10.1186/s12938-019-0682-x
10.1016/j.compbiomed.2019.103485
10.1109/ICPR.2010.579
10.1109/CVPR.2017.632
10.1016/j.preteyeres.2011.05.001
10.1016/j.neucom.2018.09.013
10.1007/978-3-319-46487-9_43
10.1111/j.1755-3768.1986.tb06919.x
10.1109/ISBI45749.2020.9098742
10.1007/978-3-030-87592-3_11
10.1109/ISBI.2019.8759417
10.1109/TMI.2019.2899910
10.1007/978-3-030-32226-7_13
10.1109/ICCVW54120.2021.00362
10.48550/arXiv.2006.10216
10.1007/978-3-319-46475-6_43
10.1109/TMI.2018.2791488
10.1109/ISBI.2019.8759414
10.1016/j.neucom.2018.10.103
10.3109/08820539809056052
10.1016/j.ophtha.2018.02.037
10.1002/mp.14075
10.1007/978-3-030-25886-3_22
ContentType Journal Article
Copyright 2023. The Author(s).
COPYRIGHT 2023 BioMed Central Ltd.
2023. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
The Author(s) 2023
Copyright_xml – notice: 2023. The Author(s).
– notice: COPYRIGHT 2023 BioMed Central Ltd.
– notice: 2023. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: The Author(s) 2023
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
ISR
3V.
7QO
7X7
7XB
88E
8FD
8FE
8FG
8FH
8FI
8FJ
8FK
ABJCF
ABUWG
AFKRA
AZQEC
BBNVY
BENPR
BGLVJ
BHPHI
CCPQU
DWQXO
FR3
FYUFA
GHDGH
GNUQQ
HCIFZ
K9.
L6V
LK8
M0S
M1P
M7P
M7S
P64
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
7X8
5PM
DOA
DOI 10.1186/s12938-023-01070-6
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Gale In Context: Science
ProQuest Central (Corporate)
Biotechnology Research Abstracts
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Medical Database (Alumni Edition)
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Natural Science Journals
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials
Biological Science Collection
ProQuest Central
ProQuest Technology Collection
Natural Science Collection
ProQuest One
ProQuest Central
Engineering Research Database
Proquest Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
ProQuest SciTech Premium Collection
ProQuest Health & Medical Complete (Alumni)
ProQuest Engineering Collection
Biological Sciences
ProQuest Health & Medical Collection
Medical Database
Biological Science Database
Engineering Database
Biotechnology and BioEngineering Abstracts
ProQuest Central Premium
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering collection
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Publicly Available Content Database
ProQuest Central Student
Technology Collection
Technology Research Database
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Natural Science Collection
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Health & Medical Research Collection
ProQuest Engineering Collection
Health Research Premium Collection
Biotechnology Research Abstracts
Health and Medicine Complete (Alumni Edition)
Natural Science Collection
ProQuest Central Korea
Health & Medical Research Collection
Biological Science Collection
ProQuest Central (New)
ProQuest Medical Library (Alumni)
Engineering Collection
Engineering Database
ProQuest Biological Science Collection
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
ProQuest Technology Collection
Health Research Premium Collection (Alumni)
Biological Science Database
ProQuest SciTech Collection
ProQuest Hospital Collection (Alumni)
Biotechnology and BioEngineering Abstracts
ProQuest Health & Medical Complete
ProQuest Medical Library
ProQuest One Academic UKI Edition
Materials Science & Engineering Collection
Engineering Research Database
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic


MEDLINE


Publicly Available Content Database
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 4
  dbid: 8FG
  name: ProQuest Technology Collection
  url: https://search.proquest.com/technologycollection1
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Engineering
EISSN 1475-925X
EndPage 15
ExternalDocumentID oai_doaj_org_article_d3fec4d962c9494a87c9a634438cb11e
PMC9945680
A738160068
36810105
10_1186_s12938_023_01070_6
Genre Journal Article
GeographicLocations China
GeographicLocations_xml – name: China
GrantInformation_xml – fundername: Jiangsu Provincial Key Research and Development Program
  grantid: BE2019682
– fundername: National Natural Science Foundation of China
  grantid: 62075235
– fundername: National Natural Science Foundation of China
  grantid: 61605210
– fundername: National Natural Science Foundation of China
  grantid: 61675226
– fundername: ;
  grantid: BE2019682
– fundername: ;
  grantid: 61605210; 61675226; 62075235
GroupedDBID ---
0R~
23N
2WC
53G
5GY
5VS
6J9
6PF
7X7
88E
8FE
8FG
8FH
8FI
8FJ
AAFWJ
AAJSJ
AASML
AAWTL
AAYXX
ABDBF
ABJCF
ABUWG
ACGFO
ACGFS
ACIHN
ACIWK
ACPRK
ACUHS
ADBBV
ADMLS
ADRAZ
ADUKV
AEAQA
AENEX
AFKRA
AFPKN
AFRAH
AHBYD
AHMBA
AHYZX
ALIPV
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMTXH
AOIJS
BAPOH
BAWUL
BBNVY
BCNDV
BENPR
BFQNJ
BGLVJ
BHPHI
BMC
BPHCQ
BVXVI
C6C
CCPQU
CITATION
CS3
DIK
E3Z
EAD
EAP
EAS
EBD
EBLON
EBS
EMB
EMK
EMOBN
ESX
F5P
FRP
FYUFA
GROUPED_DOAJ
GX1
HCIFZ
HMCUK
HYE
I-F
IAO
IGS
IHR
INH
INR
ISR
ITC
KQ8
L6V
LK8
M1P
M48
M7P
M7S
MK~
ML~
M~E
O5R
O5S
OK1
OVT
P2P
PGMZT
PHGZM
PHGZT
PIMPY
PQQKQ
PROAC
PSQYO
PTHSS
RBZ
RNS
ROL
RPM
RSV
SEG
SOJ
SV3
TR2
TUS
UKHRP
W2D
WOQ
WOW
XSB
CGR
CUY
CVF
ECM
EIF
NPM
PMFND
3V.
7QO
7XB
8FD
8FK
AZQEC
DWQXO
FR3
GNUQQ
K9.
P64
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQUKI
PRINS
7X8
5PM
PUEGO
ID FETCH-LOGICAL-c597t-d81a25faa711fc08ac6cd4aa6fd7dda33491265983e2943a468ee38dbd457f8e3
IEDL.DBID M48
ISSN 1475-925X
IngestDate Wed Aug 27 01:33:00 EDT 2025
Thu Aug 21 18:38:02 EDT 2025
Tue Aug 05 11:33:42 EDT 2025
Fri Jul 25 19:10:31 EDT 2025
Tue Jun 17 20:47:14 EDT 2025
Tue Jun 10 20:25:48 EDT 2025
Fri Jun 27 06:03:50 EDT 2025
Thu Apr 03 07:07:53 EDT 2025
Thu Apr 24 23:10:06 EDT 2025
Tue Jul 01 00:34:39 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords High-resolution
Fluorescein angiography images
Multi-frame
Retinal fundus images
Generative adversarial network
Language English
License 2023. The Author(s).
Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c597t-d81a25faa711fc08ac6cd4aa6fd7dda33491265983e2943a468ee38dbd457f8e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
OpenAccessLink http://journals.scholarsportal.info/openUrl.xqy?doi=10.1186/s12938-023-01070-6
PMID 36810105
PQID 2788472315
PQPubID 42562
PageCount 15
ParticipantIDs doaj_primary_oai_doaj_org_article_d3fec4d962c9494a87c9a634438cb11e
pubmedcentral_primary_oai_pubmedcentral_nih_gov_9945680
proquest_miscellaneous_2779346609
proquest_journals_2788472315
gale_infotracmisc_A738160068
gale_infotracacademiconefile_A738160068
gale_incontextgauss_ISR_A738160068
pubmed_primary_36810105
crossref_primary_10_1186_s12938_023_01070_6
crossref_citationtrail_10_1186_s12938_023_01070_6
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2023-02-21
PublicationDateYYYYMMDD 2023-02-21
PublicationDate_xml – month: 02
  year: 2023
  text: 2023-02-21
  day: 21
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
– name: London
PublicationTitle Biomedical engineering online
PublicationTitleAlternate Biomed Eng Online
PublicationYear 2023
Publisher BioMed Central Ltd
BioMed Central
BMC
Publisher_xml – name: BioMed Central Ltd
– name: BioMed Central
– name: BMC
References K Palaniappan (1070_CR18) 2019
Z Wang (1070_CR36) 2004; 13
H Fu (1070_CR5) 2018; 37
P Costa (1070_CR13) 2018; 37
D Nie (1070_CR25) 2018; 65
1070_CR8
F Schiffers (1070_CR27) 2018
1070_CR26
M Qi (1070_CR17) 2020; 47
J Hu (1070_CR42) 2020; 42
1070_CR29
1070_CR41
1070_CR40
1070_CR23
1070_CR45
Z Yu (1070_CR24) 2019; 18
1070_CR44
1070_CR43
SS Hayreh (1070_CR20) 2011; 30
L Dai (1070_CR1) 2018; 37
S Wang (1070_CR6) 2019; 38
Z Yan (1070_CR3) 2019; 23
X Wang (1070_CR11) 2019
R Brancato (1070_CR19) 1998; 13
R Lira (1070_CR21) 2007; 70
U Karhunen (1070_CR22) 1986; 64
1070_CR38
1070_CR4
1070_CR37
1070_CR35
M Frid-Adar (1070_CR16) 2018; 321
1070_CR39
S Liu (1070_CR7) 2019; 115
1070_CR30
W Zhang (1070_CR9) 2019; 175
F Grassmann (1070_CR10) 2018; 125
Y Zhou (1070_CR14) 2019
D Nie (1070_CR15) 2018; 65
1070_CR12
W Li (1070_CR28) 2020
1070_CR34
1070_CR33
1070_CR32
S Guo (1070_CR2) 2020; 392
1070_CR31
References_xml – volume: 42
  start-page: 2011
  issue: 8
  year: 2020
  ident: 1070_CR42
  publication-title: IEEE T Pattern Anal
  doi: 10.1109/TPAMI.2019.2913372
– ident: 1070_CR43
  doi: 10.1109/CVPR.2018.00917
– ident: 1070_CR38
  doi: 10.1109/ICCV.2017.244
– volume: 65
  start-page: 2720
  issue: 12
  year: 2018
  ident: 1070_CR25
  publication-title: IEEE T Bio-Med Eng
  doi: 10.1109/TBME.2018.2814538
– ident: 1070_CR31
  doi: 10.1117/12.2512549
– volume-title: Synthetic fundus fluorescein angiography using deep neural networks. In Bildverarbeitung für die Medizin
  year: 2018
  ident: 1070_CR27
– volume: 65
  start-page: 2720
  year: 2018
  ident: 1070_CR15
  publication-title: IEEE Trans Biomed Eng
  doi: 10.1109/TBME.2018.2814538
– volume: 37
  start-page: 781
  year: 2018
  ident: 1070_CR13
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2017.2759102
– ident: 1070_CR41
  doi: 10.1109/CVPR.2017.683
– volume: 23
  start-page: 1427
  year: 2019
  ident: 1070_CR3
  publication-title: IEEE J Biomed Health Inform
  doi: 10.1109/JBHI.2018.2872813
– start-page: 505
  volume-title: High-resolution diabetic retinopathy image synthesis manipulated by grading and lesions. Lecture notes in computer science
  year: 2019
  ident: 1070_CR14
– ident: 1070_CR30
  doi: 10.1109/ICPR48806.2021.9412428
– ident: 1070_CR35
– volume: 175
  start-page: 12
  year: 2019
  ident: 1070_CR9
  publication-title: Knowl Based Syst
  doi: 10.1016/j.knosys.2019.03.016
– volume: 37
  start-page: 1149
  year: 2018
  ident: 1070_CR1
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2018.2794988
– ident: 1070_CR26
  doi: 10.1007/978-3-030-00928-1_37
– volume: 13
  start-page: 600
  issue: 4
  year: 2004
  ident: 1070_CR36
  publication-title: IEEE T Image Process
  doi: 10.1109/TIP.2003.819861
– ident: 1070_CR33
  doi: 10.1109/IJCNN.2019.8852082
– ident: 1070_CR34
  doi: 10.1109/CVPR.2018.00916
– ident: 1070_CR40
  doi: 10.1109/CVPR.2016.90
– volume: 70
  start-page: 615
  issue: 4
  year: 2007
  ident: 1070_CR21
  publication-title: Arq Bras Oftalmol
  doi: 10.1590/S0004-27492007000400011
– volume: 18
  start-page: 1
  issue: 1
  year: 2019
  ident: 1070_CR24
  publication-title: Biomed Eng Online
  doi: 10.1186/s12938-019-0682-x
– volume: 115
  start-page: 103485
  year: 2019
  ident: 1070_CR7
  publication-title: Comput Biol Med
  doi: 10.1016/j.compbiomed.2019.103485
– ident: 1070_CR37
  doi: 10.1109/ICPR.2010.579
– ident: 1070_CR45
  doi: 10.1109/CVPR.2017.632
– volume: 30
  start-page: 359
  issue: 5
  year: 2011
  ident: 1070_CR20
  publication-title: Prog Retin Eye Res
  doi: 10.1016/j.preteyeres.2011.05.001
– start-page: 30
  volume-title: Retinal abnormalities recognition using regional multitask learning. Lecture notes in computer science
  year: 2019
  ident: 1070_CR11
– volume: 321
  start-page: 321
  year: 2018
  ident: 1070_CR16
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.09.013
– ident: 1070_CR39
  doi: 10.1007/978-3-319-46487-9_43
– volume: 64
  start-page: 282
  issue: 3
  year: 1986
  ident: 1070_CR22
  publication-title: Acta Ophthalmol
  doi: 10.1111/j.1755-3768.1986.tb06919.x
– ident: 1070_CR4
  doi: 10.1109/ISBI45749.2020.9098742
– ident: 1070_CR29
  doi: 10.1007/978-3-030-87592-3_11
– ident: 1070_CR8
  doi: 10.1109/ISBI.2019.8759417
– volume: 38
  start-page: 2485
  year: 2019
  ident: 1070_CR6
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2019.2899910
– ident: 1070_CR32
  doi: 10.1007/978-3-030-32226-7_13
– ident: 1070_CR23
  doi: 10.1109/ICCVW54120.2021.00362
– year: 2020
  ident: 1070_CR28
  publication-title: arXiv preprint
  doi: 10.48550/arXiv.2006.10216
– ident: 1070_CR44
  doi: 10.1007/978-3-319-46475-6_43
– volume: 37
  start-page: 1597
  year: 2018
  ident: 1070_CR5
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2018.2791488
– ident: 1070_CR12
  doi: 10.1109/ISBI.2019.8759414
– volume: 392
  start-page: 314
  year: 2020
  ident: 1070_CR2
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.10.103
– volume: 13
  start-page: 189
  issue: 4
  year: 1998
  ident: 1070_CR19
  publication-title: Semin Ophthalmol
  doi: 10.3109/08820539809056052
– volume: 125
  start-page: 1410
  year: 2018
  ident: 1070_CR10
  publication-title: Ophthalmology
  doi: 10.1016/j.ophtha.2018.02.037
– volume: 47
  start-page: 1880
  year: 2020
  ident: 1070_CR17
  publication-title: Med Phys
  doi: 10.1002/mp.14075
– start-page: 543
  volume-title: Ocular fluid dynamics
  year: 2019
  ident: 1070_CR18
  doi: 10.1007/978-3-030-25886-3_22
SSID ssj0020069
Score 2.3994563
Snippet Fundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular circulation in the...
Background Fundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular...
BackgroundFundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular...
Abstract Background Fundus fluorescein angiography (FA) can be used to diagnose fundus diseases by observing dynamic fluorescein changes that reflect vascular...
SourceID doaj
pubmedcentral
proquest
gale
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 16
SubjectTerms Ablation
Angiography
Attention
Blood vessels
Classification
Coders
Cross correlation
Datasets
Deep learning
Diabetic retinopathy
Diagnosis
Fluorescein
Fluorescein Angiography
Fluorescein angiography images
Fluorescence angiography
Fundus Oculi
Generative adversarial network
Generative adversarial networks
Generators
High resolution
Humans
Image Processing, Computer-Assisted - methods
Image resolution
Image segmentation
Liquors
Medical examination
Medical imaging
Methods
Multi-frame
Neural networks
Performance evaluation
Retina
Retinal diseases
Retinal fundus images
Signal to noise ratio
Similarity
Unsupervised learning
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZQDwgOCMorUJBBSByQ1SR2HPtYEFVBKgdKpd4sx49lpZJFzebQ_gJ-NjOOd7UREly47kySjefzPJSZz4S84RGSVmE7ZlWQTOiSs042HfNlaZV1MfJEmX_6RZ6ci88XzcXOUV_YEzbRA08Ld-h5DE54LWunhRZWtU5byYXgynVVFdD7QszbFFO51EIC3s2IjJKHA0Y1xSA-QekMIGdyFoYSW_-fPnknKM0bJnci0PF9ci-njvRo-ssPyK3Q75O7O4SC--T2af5U_pD8OrvuIbkbljcgoalvkEXsxKLIUMygys6go_FyXF0hq9Oypxbulkms6fIH-JqB4gAKxVlHfDiEQT8OGxE2zS_oIjFXo9ukFo93HiyCmvZTg_nwiJwff_z24YTlYxeYg-pizbyqbN1Ea9uqiq4Ei0nnhbUy-tZ7y7nQVS0brXioteBWSBUCV77zommjCvwx2etXfXhKqO5qrQK409aBxTy3vPOd9i3cx3Mhu4JUGysYlznJ8WiMS5NqEyXNZDkDljPJckYW5N32mp8TI8dftd-jcbeayKadfgCMmYwx8y-MFeQ1QsMgX0aPDTkLOw6D-XT21Ry1-OUVB20K8jYrxRW8g7N5vgFWAim2ZpoHM03Y0G4u3iDQZIcymLpVkEdAMt4U5NVWjFdik1wfViPqgLMVUpa6IE8mwG7fmyPvHOTSBWlnUJ4tzFzSL78nunGtIclW5bP_sZLPyZ067cKa1dUB2VtfjeEFZHXr7mXawL8BhJJMqw
  priority: 102
  providerName: Directory of Open Access Journals
– databaseName: Health & Medical Collection
  dbid: 7X7
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb9QwELagSAgOCMorUJBBSByQ1SR2HPuECqIqSOVAqbQ3y_FjWakkZbM5wC_gZzOT9W43Quo1M3nOeB7xzDeEvOERglZhG2ZVkEzonLNGVg3zeW6VdTHyETL_9Ks8ORdfZtUs_XDrU1nlxiaOhtp3Dv-RH5aQq4kaopHq_eUvhlOjcHc1jdC4SW4hdBmWdNWzq4QLYXg3jTJKHvbo2xQDLwUJNKg6kxNnNGL2_2-Zd1zTtGxyxw8d3yf3UgBJj9YSf0BuhHaf3N2BFdwnt0_ThvlD8vfsdwshXr_4AxQ6Vg-yiPVYFHGKGeTaSfVovBi6JWI7LVpq4WoJypoufoLF6Sm2oVDseMSbgzP0Q78hYen8nM5H_Go0ntTikOfeomrTdl1m3j8i58efvn88YWn4AnOQY6yYV4Utq2htXRTR5SA36bywVkZfe285F7ooZaUVD6UW3AqpQuDKN15UdVSBPyZ7bdeGp4TqptQqgFGtHRfCc8sb32hfw3U8F7LJSLGRgnEJmRwHZFyYMUNR0qwlZ0ByZpSckRl5tz3nco3LcS33BxTulhMxtccD3XJu0hI1nsfghNeydFpoYVXttJXwxFy5pihCRl6jahhEzWixLGduh743n8--maMa91-x3SYjbxNT7OAdnE1dDvAlEGhrwnkw4YRl7abkjQaaZFZ6c7UIMvJqS8YzsVSuDd2APGByhZS5zsiTtcJu35sj-hxE1BmpJ6o8-TBTSrv4MYKOaw2htsqfXf9Yz8mdclxfJSuLA7K3Wg7hBURtq-bluDT_AYX_RAQ
  priority: 102
  providerName: ProQuest
Title Synthesizing multi-frame high-resolution fluorescein angiography images from retinal fundus images using generative adversarial networks
URI https://www.ncbi.nlm.nih.gov/pubmed/36810105
https://www.proquest.com/docview/2788472315
https://www.proquest.com/docview/2779346609
https://pubmed.ncbi.nlm.nih.gov/PMC9945680
https://doaj.org/article/d3fec4d962c9494a87c9a634438cb11e
Volume 22
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3di9NAEF_uA0QfRM-v6FlWEXyQ1SS72Y8HkTu5ego95M6Dvi2bbFILNdWmBc-_wD_bmW1SGjwEX_LQnWySnZmdme7Mbwh5wStwWoXLmdOlZMLEnOUyy5mPY6ddUVU8QOaPzuTppfg0zsY7pGt31C5gc21oh_2kLhez1z9_XL0DhX8bFF7LNw3aLM3A-kBgDCLM5C7ZB8ukUFFHYnOqgNGzCdVGKmMmzcZdEc21c_QMVcDz_3vX3jJb_ZTKLRs1vENut84lPVpLw12yU9YH5NYW5OABuTFqD9Pvkd8XVzW4f830F4zQkFnIKszVoohhzCAOb8WSVrPVfIG4T9OaOpithbmm02-wGzUUS1QoVkPiw8FQ-lXTDWFa_YROArY1bqzUYQPoxqHY03qdgt7cJ5fDky_vT1nbmIEVEH8smdeJS7PKOZUkVREDT2XhhXOy8sp7x7kwSSozo3mZGsGdkLosufa5F5mqdMkfkL16XpePCDV5anQJG64quBCeO5773HgF83guZB6RpOOCLVrUcmyeMbMhetHSrjlngXM2cM7KiLza3PN9jdnxT-pjZO6GEvG2ww_zxcS26ms9r8pCeCPTwggjnFaFcRLemOsiT5IyIs9RNCwiatSYsjNxq6axHy_O7ZHCs1ksxYnIy5aomsM3FK6tgICVQBCuHuVhjxJUvugPdxJoO42xqdLgaYC7nkXk2WYY78Q0urqcr5AGtmMhZWwi8nAtsJvv5ohMB952RFRPlHsL0x-pp18DILkx4Ibr-PF_rfsTcjMN6payNDkke8vFqnwKDt4yH5BdNVZw1cMPA7J_fHL2-XwQ_iwZBH3-A2dIUUc
linkProvider Scholars Portal
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLbGkLg8IBi3wACDQDxM1pLYdewHhMZlatnlgW1S34xjO6XSSEfTCo1fwK_hN3JOmnSNkPa21_rETXLu8TnfIeQ1LyBoFTZnVgXJhI45y2UvZz6OrbKuKHgNmX9wKPsn4suwN1wjf9teGCyrbG1ibaj9xOE38u0UcjWRQTTSe3_2k-HUKDxdbUdoLMRiL5z_gpStejf4BPx9k6a7n48_9lkzVYA5CJ5nzKvEpr3C2ixJChfDDUnnhbWy8Jn3lnOhk1T2tOIh1YJbIVUIXPnci15WqMBh32vkOjjeGDUqG14keAj72zbmKLldoS9VDLwiJOygWkx2nF89I-B_T7DiCrtlmit-b_cuudMErHRnIWH3yFooN8jtFRjDDXLjoDmgv0_-HJ2XEFJW49-wQutqRVZg_RdFXGQGuX0j6rQ4nU-miCU1LqmF3RrobDr-ARauotj2QrHDEv8cnK-fV-0SluqP6KjGy0ZjTS0Ola4sqhItF2Xt1QNyciVseUjWy0kZHhOq81SrAEY8c1wIzy3Pfa59Bvt4LmQekaTlgnENEjoO5Dg1dUakpFlwzgDnTM05IyOytbzmbIEDcin1B2TukhIxvOsfJtORaUyC8bwITngtU6eFFlZlTlsJd8yVy5MkROQVioZBlI4Sy4BGdl5VZnD01exkeN6L7T0RedsQFRN4Bmebrgp4Ewjs1aHc7FCCGXHd5VYCTWPGKnOhdBF5uVzGK7E0rwyTOdKAiRdSxjoijxYCu3xujmh3EMFHJOuIcufFdFfK8fca5FxrCO1V_OTy23pBbvaPD_bN_uBw7ym5lda6lrI02STrs-k8PIOIcZY_r9WUkm9XbRf-AaoJgek
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Synthesizing+multi-frame+high-resolution+fluorescein+angiography+images+from+retinal+fundus+images+using+generative+adversarial+networks&rft.jtitle=Biomedical+engineering+online&rft.au=Li%2C+Ping&rft.au=He%2C+Yi&rft.au=Wang%2C+Pinghe&rft.au=Wang%2C+Jing&rft.date=2023-02-21&rft.issn=1475-925X&rft.eissn=1475-925X&rft.volume=22&rft.issue=1&rft_id=info:doi/10.1186%2Fs12938-023-01070-6&rft.externalDBID=n%2Fa&rft.externalDocID=10_1186_s12938_023_01070_6
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1475-925X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1475-925X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1475-925X&client=summon