Drusen‐aware model for age‐related macular degeneration recognition

Introduction The purpose of this study was to build an automated age‐related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age‐related changes by using drusen masks for spatial feature supervision. Metho...

Full description

Saved in:
Bibliographic Details
Published inOphthalmic & physiological optics Vol. 43; no. 4; pp. 668 - 679
Main Authors Pan, Junjun, Ho, Sharon, Ly, Angelica, Kalloniatis, Michael, Sowmya, Arcot
Format Journal Article
LanguageEnglish
Published England Wiley Subscription Services, Inc 01.07.2023
John Wiley and Sons Inc
Subjects
Online AccessGet full text
ISSN0275-5408
1475-1313
1475-1313
DOI10.1111/opo.13108

Cover

Abstract Introduction The purpose of this study was to build an automated age‐related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age‐related changes by using drusen masks for spatial feature supervision. Methods A range of clinical sources were used to acquire 7588 CFPs. Contrast limited adaptive histogram equalisation was used for pre‐processing. ResNet50 was used as the backbone network, and a spatial attention block was added to integrate prior knowledge of drusen features into the backbone. The evaluation metrics used were sensitivity, specificity and F1 score, which is the harmonic mean of precision and recall (sensitivity) and area under the receiver‐operating characteristic (AUC). Fivefold cross‐validation was performed, and the results compared with four other methods. Results Excellent discrimination results were obtained with the algorithm. On the public dataset (n = 6565), the proposed method achieved a mean (SD) sensitivity of 0.54 (0.09), specificity of 0.99 (0.00), F1 score of 0.62 (0.06) and AUC of 0.92 (0.02). On the private dataset (n = 1023), the proposed method achieved a sensitivity of 0.92 (0.02), specificity of 0.98 (0.01), F1 score of 0.92 (0.01) and AUC of 0.98 (0.01). Conclusion The proposed drusen‐aware model outperformed baseline and other vessel feature‐based methods in F1 and AUC on the AMD/normal CFP classification task and achieved comparable results on datasets that included other diseases that often confound classification. The method also improved results when a five‐category grading protocol was used, thereby reflecting discriminative ability of the algorithm within a real‐life clinical setting.
AbstractList The purpose of this study was to build an automated age-related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age-related changes by using drusen masks for spatial feature supervision.INTRODUCTIONThe purpose of this study was to build an automated age-related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age-related changes by using drusen masks for spatial feature supervision.A range of clinical sources were used to acquire 7588 CFPs. Contrast limited adaptive histogram equalisation was used for pre-processing. ResNet50 was used as the backbone network, and a spatial attention block was added to integrate prior knowledge of drusen features into the backbone. The evaluation metrics used were sensitivity, specificity and F1 score, which is the harmonic mean of precision and recall (sensitivity) and area under the receiver-operating characteristic (AUC). Fivefold cross-validation was performed, and the results compared with four other methods.METHODSA range of clinical sources were used to acquire 7588 CFPs. Contrast limited adaptive histogram equalisation was used for pre-processing. ResNet50 was used as the backbone network, and a spatial attention block was added to integrate prior knowledge of drusen features into the backbone. The evaluation metrics used were sensitivity, specificity and F1 score, which is the harmonic mean of precision and recall (sensitivity) and area under the receiver-operating characteristic (AUC). Fivefold cross-validation was performed, and the results compared with four other methods.Excellent discrimination results were obtained with the algorithm. On the public dataset (n = 6565), the proposed method achieved a mean (SD) sensitivity of 0.54 (0.09), specificity of 0.99 (0.00), F1 score of 0.62 (0.06) and AUC of 0.92 (0.02). On the private dataset (n = 1023), the proposed method achieved a sensitivity of 0.92 (0.02), specificity of 0.98 (0.01), F1 score of 0.92 (0.01) and AUC of 0.98 (0.01).RESULTSExcellent discrimination results were obtained with the algorithm. On the public dataset (n = 6565), the proposed method achieved a mean (SD) sensitivity of 0.54 (0.09), specificity of 0.99 (0.00), F1 score of 0.62 (0.06) and AUC of 0.92 (0.02). On the private dataset (n = 1023), the proposed method achieved a sensitivity of 0.92 (0.02), specificity of 0.98 (0.01), F1 score of 0.92 (0.01) and AUC of 0.98 (0.01).The proposed drusen-aware model outperformed baseline and other vessel feature-based methods in F1 and AUC on the AMD/normal CFP classification task and achieved comparable results on datasets that included other diseases that often confound classification. The method also improved results when a five-category grading protocol was used, thereby reflecting discriminative ability of the algorithm within a real-life clinical setting.CONCLUSIONThe proposed drusen-aware model outperformed baseline and other vessel feature-based methods in F1 and AUC on the AMD/normal CFP classification task and achieved comparable results on datasets that included other diseases that often confound classification. The method also improved results when a five-category grading protocol was used, thereby reflecting discriminative ability of the algorithm within a real-life clinical setting.
The purpose of this study was to build an automated age-related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age-related changes by using drusen masks for spatial feature supervision. A range of clinical sources were used to acquire 7588 CFPs. Contrast limited adaptive histogram equalisation was used for pre-processing. ResNet50 was used as the backbone network, and a spatial attention block was added to integrate prior knowledge of drusen features into the backbone. The evaluation metrics used were sensitivity, specificity and F1 score, which is the harmonic mean of precision and recall (sensitivity) and area under the receiver-operating characteristic (AUC). Fivefold cross-validation was performed, and the results compared with four other methods. Excellent discrimination results were obtained with the algorithm. On the public dataset (n = 6565), the proposed method achieved a mean (SD) sensitivity of 0.54 (0.09), specificity of 0.99 (0.00), F1 score of 0.62 (0.06) and AUC of 0.92 (0.02). On the private dataset (n = 1023), the proposed method achieved a sensitivity of 0.92 (0.02), specificity of 0.98 (0.01), F1 score of 0.92 (0.01) and AUC of 0.98 (0.01). The proposed drusen-aware model outperformed baseline and other vessel feature-based methods in F1 and AUC on the AMD/normal CFP classification task and achieved comparable results on datasets that included other diseases that often confound classification. The method also improved results when a five-category grading protocol was used, thereby reflecting discriminative ability of the algorithm within a real-life clinical setting.
Introduction The purpose of this study was to build an automated age‐related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age‐related changes by using drusen masks for spatial feature supervision. Methods A range of clinical sources were used to acquire 7588 CFPs. Contrast limited adaptive histogram equalisation was used for pre‐processing. ResNet50 was used as the backbone network, and a spatial attention block was added to integrate prior knowledge of drusen features into the backbone. The evaluation metrics used were sensitivity, specificity and F1 score, which is the harmonic mean of precision and recall (sensitivity) and area under the receiver‐operating characteristic (AUC). Fivefold cross‐validation was performed, and the results compared with four other methods. Results Excellent discrimination results were obtained with the algorithm. On the public dataset (n = 6565), the proposed method achieved a mean (SD) sensitivity of 0.54 (0.09), specificity of 0.99 (0.00), F1 score of 0.62 (0.06) and AUC of 0.92 (0.02). On the private dataset (n = 1023), the proposed method achieved a sensitivity of 0.92 (0.02), specificity of 0.98 (0.01), F1 score of 0.92 (0.01) and AUC of 0.98 (0.01). Conclusion The proposed drusen‐aware model outperformed baseline and other vessel feature‐based methods in F1 and AUC on the AMD/normal CFP classification task and achieved comparable results on datasets that included other diseases that often confound classification. The method also improved results when a five‐category grading protocol was used, thereby reflecting discriminative ability of the algorithm within a real‐life clinical setting.
IntroductionThe purpose of this study was to build an automated age‐related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age‐related changes by using drusen masks for spatial feature supervision.MethodsA range of clinical sources were used to acquire 7588 CFPs. Contrast limited adaptive histogram equalisation was used for pre‐processing. ResNet50 was used as the backbone network, and a spatial attention block was added to integrate prior knowledge of drusen features into the backbone. The evaluation metrics used were sensitivity, specificity and F1 score, which is the harmonic mean of precision and recall (sensitivity) and area under the receiver‐operating characteristic (AUC). Fivefold cross‐validation was performed, and the results compared with four other methods.ResultsExcellent discrimination results were obtained with the algorithm. On the public dataset (n = 6565), the proposed method achieved a mean (SD) sensitivity of 0.54 (0.09), specificity of 0.99 (0.00), F1 score of 0.62 (0.06) and AUC of 0.92 (0.02). On the private dataset (n = 1023), the proposed method achieved a sensitivity of 0.92 (0.02), specificity of 0.98 (0.01), F1 score of 0.92 (0.01) and AUC of 0.98 (0.01).ConclusionThe proposed drusen‐aware model outperformed baseline and other vessel feature‐based methods in F1 and AUC on the AMD/normal CFP classification task and achieved comparable results on datasets that included other diseases that often confound classification. The method also improved results when a five‐category grading protocol was used, thereby reflecting discriminative ability of the algorithm within a real‐life clinical setting.
Author Pan, Junjun
Ho, Sharon
Ly, Angelica
Sowmya, Arcot
Kalloniatis, Michael
AuthorAffiliation 3 School of Optometry and Vision Science University of New South Wales Kensington New South Wales Australia
4 School of Medicine (Optometry) Deakin University Waurn Ponds Victoria Australia
1 School of Computer Science and Engineering University of New South Wales Kensington New South Wales Australia
2 Centre for Eye Health University of New South Wales Kensington New South Wales Australia
AuthorAffiliation_xml – name: 4 School of Medicine (Optometry) Deakin University Waurn Ponds Victoria Australia
– name: 3 School of Optometry and Vision Science University of New South Wales Kensington New South Wales Australia
– name: 1 School of Computer Science and Engineering University of New South Wales Kensington New South Wales Australia
– name: 2 Centre for Eye Health University of New South Wales Kensington New South Wales Australia
Author_xml – sequence: 1
  givenname: Junjun
  surname: Pan
  fullname: Pan, Junjun
  organization: University of New South Wales
– sequence: 2
  givenname: Sharon
  orcidid: 0000-0002-1975-828X
  surname: Ho
  fullname: Ho, Sharon
  organization: University of New South Wales
– sequence: 3
  givenname: Angelica
  orcidid: 0000-0001-7881-1522
  surname: Ly
  fullname: Ly, Angelica
  organization: University of New South Wales
– sequence: 4
  givenname: Michael
  orcidid: 0000-0002-5264-4639
  surname: Kalloniatis
  fullname: Kalloniatis, Michael
  organization: Deakin University
– sequence: 5
  givenname: Arcot
  orcidid: 0000-0001-9236-5063
  surname: Sowmya
  fullname: Sowmya, Arcot
  email: a.sowmya@unsw.edu.au
  organization: University of New South Wales
BackLink https://www.ncbi.nlm.nih.gov/pubmed/36786498$$D View this record in MEDLINE/PubMed
BookMark eNp9kc1uEzEUhS1URNPCghdAI7EBpLT22GN7VggVKEiVwqJ768ZzJ7jy2MGeIcqOR-AZeRKcJvxVgDe-1_7O0fXxCTkKMSAhjxk9Y2Wdx3U8Y5xRfY_MmFDNvDT8iMxoXepGUH1MTnK-oZQqpfQDcsyl0lK0ekYuX6cpY_j25StsIGE1xA591cdUwQrLaUIPI3bVAHbykKoOVxgwwehiqBLauApuVz8k93vwGR8d9lNy_fbN9cW7-dXi8v3Fq6u5FULoeaNQiaVs-VL0VlumGkUbhBoEb5bYNpbxXgO0HWjJoKZWt1ZaqjoQFrqWn5IXe9sprGG7Ae_NOrkB0tYwanZhmBKGuQ2jwC_38HpaDthZDGOCX4IIzvx5E9xHs4qfi1UrpGI7h2cHhxQ_TZhHM7hs0XsIGKdsaqVkw1opeUGf3kFv4pRCycLUuq650pqrQj35faSfs_z4kAKc7wGbYs4Je2PdeJt2mdD5v77y-R3F_xI5uG-cx-2_QbP4sNgrvgOUyry8
CitedBy_id crossref_primary_10_1080_08164622_2023_2235346
Cites_doi 10.1016/j.cie.2020.106559
10.1109/CVPR.2016.319
10.31577/cai_2021_5_957
10.1016/S2214-109X(20)30488-5
10.1007/978-3-319-67558-9_28
10.1007/978-981-16-1086-8_31
10.1109/ACCESS.2020.3040275
10.1007/978-3-030-20351-1_62
10.3390/s21113865
10.1109/TEVC.2019.2890858
10.1109/ICCVW.2019.00049
10.1016/j.jfranklin.2008.04.009
10.3390/diagnostics10110904
10.1109/EMBC46164.2021.9629607
10.1109/AICAS.2019.8771609
10.1155/2020/7493419
10.1016/j.ophtha.2018.11.015
10.1016/j.ajo.2006.05.028
10.1016/S0197-2456(99)00031-8
10.1167/iovs.12-11449
10.1109/ICIP40778.2020.9190800
10.3390/electronics9101617
10.1258/jrsm.2009.080298
10.1109/ICMLA.2017.00-75
10.1364/BOE.7.004928
10.1007/978-981-16-1089-9_60
10.1016/j.ophtha.2012.10.036
10.1109/ICBSII51839.2021.9445134
10.1080/08164622.2021.1878821
10.1016/j.compbiomed.2017.01.018
10.1109/JBHI.2021.3092339
10.1111/ceo.12466
10.1167/iovs.17-23076
10.1109/TMI.2021.3075244
ContentType Journal Article
Copyright 2023 The Authors. published by John Wiley & Sons Ltd on behalf of College of Optometrists.
2023 The Authors. Ophthalmic and Physiological Optics published by John Wiley & Sons Ltd on behalf of College of Optometrists.
2023. This article is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2023 The Authors. published by John Wiley & Sons Ltd on behalf of College of Optometrists.
– notice: 2023 The Authors. Ophthalmic and Physiological Optics published by John Wiley & Sons Ltd on behalf of College of Optometrists.
– notice: 2023. This article is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 24P
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7QG
7T5
7TK
H94
7X8
5PM
ADTOC
UNPAY
DOI 10.1111/opo.13108
DatabaseName Wiley Online Library Open Access
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Animal Behavior Abstracts
Immunology Abstracts
Neurosciences Abstracts
AIDS and Cancer Research Abstracts
MEDLINE - Academic
PubMed Central (Full Participant titles)
Unpaywall for CDI: Periodical Content
Unpaywall
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
AIDS and Cancer Research Abstracts
Immunology Abstracts
Neurosciences Abstracts
Animal Behavior Abstracts
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE

AIDS and Cancer Research Abstracts
Database_xml – sequence: 1
  dbid: 24P
  name: Wiley Online Library Open Access
  url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  sourceTypes: Publisher
– 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: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Physics
DocumentTitleAlternate DRUSEN‐AWARE MODEL FOR AMD RECOGNITION
EISSN 1475-1313
EndPage 679
ExternalDocumentID 10.1111/opo.13108
PMC10946718
36786498
10_1111_opo_13108
OPO13108
Genre researchArticle
Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: NH&MRC Ideas grant
  funderid: #1186915
– fundername: Guide Dogs NSW/ACT
– fundername: NH&MRC Ideas grant
  grantid: #1186915
GroupedDBID ---
--K
.3N
.GA
.Y3
05W
0R~
10A
123
1B1
1OB
1OC
1~5
24P
29N
31~
33P
36B
3SF
4.4
4G.
50Y
50Z
51W
51X
52M
52N
52O
52P
52R
52S
52T
52U
52V
52W
52X
53G
5HH
5LA
5VS
66C
7-5
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A01
A03
AAEDT
AAESR
AAEVG
AAHHS
AAHQN
AAIPD
AALRI
AAMNL
AANHP
AANLZ
AAONW
AAQFI
AAQXK
AASGY
AAXRX
AAXUO
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABEML
ABJNI
ABMAC
ABPVW
ABQWH
ABWVN
ABXGK
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACGFO
ACGFS
ACGOF
ACMXC
ACNCT
ACPOU
ACPRK
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADBTR
ADEOM
ADIZJ
ADKYN
ADMGS
ADMUD
ADNMO
ADOZA
ADXAS
ADZMN
AEEZP
AEIGN
AEIMD
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFEBI
AFFPM
AFGKR
AFPWT
AFWVQ
AFZJQ
AHBTC
AHEFC
AIACR
AIAGR
AITYG
AIURR
AIWBW
AJBDE
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ASPBG
ATUGU
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMXJE
BROTX
BRXPI
BY8
C45
CAG
COF
D-6
D-7
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRMAN
DRSTM
DU5
DUUFO
EAD
EAP
EBC
EBD
EBS
EJD
EMB
EMK
EMOBN
EPS
ESX
EX3
F00
F01
F04
F5P
FDB
FEDTE
FGOYB
FUBAC
G-S
G.N
GODZA
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
IHE
IX1
J0M
K48
KBYEO
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
M41
MEWTI
MK4
MRFUL
MRMAN
MRSTM
MSFUL
MSMAN
MSSTM
MXFUL
MXMAN
MXSTM
N04
N05
N9A
NF~
NQ-
O66
O9-
OVD
P2P
P2W
P2X
P2Z
P4B
P4D
PALCI
Q.N
Q11
QB0
R.K
R2-
RIWAO
RJQFR
ROL
RPZ
RX1
SAMSI
SEW
SSZ
SUPJJ
SV3
TEORI
TUS
UB1
UHS
V8K
W8V
W99
WBKPD
WH7
WHWMO
WIH
WIJ
WIK
WOHZO
WOW
WQJ
WRC
WUP
WVDHM
WXI
WXSBR
XG1
YFH
YUY
ZZTAW
~IA
~WT
AAMMB
AAYXX
ACVFH
ADCNI
AEFGJ
AEUPX
AEYWJ
AFPUW
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7QG
7T5
7TK
H94
7X8
5PM
ADTOC
UNPAY
ID FETCH-LOGICAL-c4448-57e74b693b4fc8c175705ea2a435be95c13f8aa9da861a20c89c6c07da4cad93
IEDL.DBID UNPAY
ISSN 0275-5408
1475-1313
IngestDate Sun Oct 26 03:51:23 EDT 2025
Thu Aug 21 18:34:47 EDT 2025
Thu Oct 02 09:46:22 EDT 2025
Wed Aug 13 02:44:04 EDT 2025
Thu Apr 03 07:06:18 EDT 2025
Wed Oct 01 03:00:31 EDT 2025
Thu Apr 24 22:56:14 EDT 2025
Wed Jan 22 16:22:48 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords deep learning
image classification
drusen
machine learning
age-related macular degeneration
artificial intelligence
automated recognition
Language English
License Attribution-NonCommercial-NoDerivs
2023 The Authors. Ophthalmic and Physiological Optics published by John Wiley & Sons Ltd on behalf of College of Optometrists.
This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc-nd/4.0/ License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made.
cc-by-nc-nd
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c4448-57e74b693b4fc8c175705ea2a435be95c13f8aa9da861a20c89c6c07da4cad93
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-5264-4639
0000-0002-1975-828X
0000-0001-7881-1522
0000-0001-9236-5063
OpenAccessLink https://proxy.k.utb.cz/login?url=https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/opo.13108
PMID 36786498
PQID 2822378837
PQPubID 2045120
PageCount 12
ParticipantIDs unpaywall_primary_10_1111_opo_13108
pubmedcentral_primary_oai_pubmedcentral_nih_gov_10946718
proquest_miscellaneous_2776519663
proquest_journals_2822378837
pubmed_primary_36786498
crossref_citationtrail_10_1111_opo_13108
crossref_primary_10_1111_opo_13108
wiley_primary_10_1111_opo_13108_OPO13108
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate July 2023
PublicationDateYYYYMMDD 2023-07-01
PublicationDate_xml – month: 07
  year: 2023
  text: July 2023
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
– name: London
– name: Hoboken
PublicationTitle Ophthalmic & physiological optics
PublicationTitleAlternate Ophthalmic Physiol Opt
PublicationYear 2023
Publisher Wiley Subscription Services, Inc
John Wiley and Sons Inc
Publisher_xml – name: Wiley Subscription Services, Inc
– name: John Wiley and Sons Inc
References 2021; 9
2019; 11492
2021; 26
2021; 1376
2021; 21
2017; 82
2021; 104
2021; 204
2019; 126
1999; 20
2020; 145
2008; 345
2017; 10553
2013; 120
2020; 10
2020; 8
2016; 7
2020; 2020
2013; 54
2017; 58
2021
2020
2019; 23
2015; 43
2020; 9
2019
2009; 102
2006; 142
2017
2016
2014
2021; 40
2018; 59
e_1_2_12_4_1
e_1_2_12_3_1
e_1_2_12_6_1
e_1_2_12_5_1
e_1_2_12_19_1
e_1_2_12_18_1
e_1_2_12_2_1
e_1_2_12_17_1
e_1_2_12_16_1
e_1_2_12_38_1
e_1_2_12_39_1
e_1_2_12_20_1
e_1_2_12_21_1
e_1_2_12_22_1
e_1_2_12_23_1
e_1_2_12_24_1
e_1_2_12_25_1
e_1_2_12_26_1
e_1_2_12_40_1
e_1_2_12_27_1
e_1_2_12_28_1
e_1_2_12_29_1
e_1_2_12_30_1
Saha SK (e_1_2_12_35_1) 2017; 58
e_1_2_12_31_1
e_1_2_12_32_1
e_1_2_12_33_1
e_1_2_12_34_1
e_1_2_12_36_1
e_1_2_12_37_1
e_1_2_12_15_1
e_1_2_12_14_1
e_1_2_12_13_1
e_1_2_12_12_1
e_1_2_12_8_1
e_1_2_12_11_1
e_1_2_12_7_1
e_1_2_12_10_1
e_1_2_12_9_1
References_xml – volume: 40
  start-page: 2284
  year: 2021
  end-page: 94
  article-title: Rotation‐oriented collaborative self‐supervised learning for retinal disease diagnosis
  publication-title: IEEE Trans Med Imaging
– volume: 126
  start-page: 565
  year: 2019
  end-page: 75
  article-title: DeepSeeNet: a deep learning model for automated classification of patient‐based age‐related macular degeneration severity from color fundus photographs
  publication-title: Ophthalmology
– volume: 26
  start-page: 115
  year: 2021
  end-page: 26
  article-title: Joint optimization of CycleGAN and CNN classifier for detection and localization of retinal pathologies on color fundus photographs
  publication-title: IEEE J Biomed Health Inform
– volume: 9
  year: 2020
  article-title: Automatic drusen segmentation for age‐related macular degeneration in fundus images using deep learning
  publication-title: Electronics
– start-page: 199
  year: 2019
  end-page: 200
– volume: 54
  start-page: 3019
  year: 2013
  end-page: 27
  article-title: Automatic drusen quantification and risk assessment of age‐related macular degeneration on color fundus images
  publication-title: Invest Ophthalmol Vis Sci
– volume: 10553
  year: 2017
– volume: 102
  start-page: 56
  year: 2009
  end-page: 61
  article-title: Age‐related macular degeneration
  publication-title: J R Soc Med
– volume: 10
  year: 2020
  article-title: CSID: a novel multimodal image fusion algorithm for enhanced clinical diagnosis
  publication-title: Diagnostics
– start-page: 3514
  year: 2021
  end-page: 3517
– volume: 82
  start-page: 80
  year: 2017
  end-page: 6
  article-title: Comparing humans and deep learning performance for grading AMD: a study in using universal deep features and transfer learning for automated AMD analysis
  publication-title: Comput Biol Med
– volume: 104
  start-page: 795
  year: 2021
  end-page: 804
  article-title: Clinical outcomes of the Centre for Eye Health: an intra‐professional optometry‐led collaborative eye care clinic in Australia
  publication-title: Clin Exp Optom
– year: 2016
– volume: 11492
  year: 2019
– volume: 9
  start-page: e489
  year: 2021
  end-page: 551
  article-title: The Lancet global health commission on global eye health: vision beyond 2020
  publication-title: Lancet Glob Health
– volume: 23
  start-page: 828
  year: 2019
  end-page: 41
  article-title: One pixel attack for fooling deep neural networks
  publication-title: IEEE Trans Evol Comput
– year: 2014
– start-page: 320
  year: 2020
  end-page: 324
– volume: 43
  start-page: 308
  year: 2015
  end-page: 19
  article-title: Clinical model assisting with the collaborative care of glaucoma patients and suspects
  publication-title: Clin Experiment Ophthalmol
– volume: 1376
  year: 2021
– volume: 142
  start-page: 688
  year: 2006
  end-page: 9
  article-title: Retinal vascular abnormalities and prevalence of age‐related macular degeneration in adult Chinese: the Beijing eye study
  publication-title: Am J Ophthalmol
– volume: 58
  start-page: 25
  year: 2017
  article-title: Deep learning based decision support system for automated diagnosis of age‐related macular degeneration (AMD)
  publication-title: Invest Ophthalmol Vis Sci
– volume: 145
  year: 2020
  article-title: A mayfly optimization algorithm
  publication-title: Comput Ind Eng
– volume: 345
  start-page: 748
  year: 2008
  end-page: 65
  article-title: Enhancement of blood vessels in digital fundus photographs via the application of multiscale line operators
  publication-title: J Franklin Inst
– volume: 8
  start-page: 212499
  year: 2020
  end-page: 508
  article-title: Multi‐label classification of fundus images with efficientnet
  publication-title: IEEE Access
– start-page: 1
  year: 2021
  end-page: 5
– volume: 21
  year: 2021
  article-title: Hemorrhage detection based on 3D CNN deep learning framework and feature fusion for evaluating retinal abnormality in diabetic patients
  publication-title: Sensors
– volume: 40
  start-page: 957
  year: 2021
  end-page: 87
  article-title: Detection of macula and recognition of aged‐related macular degeneration in retinal fundus images
  publication-title: Comput Inform
– year: 2020
– volume: 120
  start-page: 844
  year: 2013
  end-page: 51
  article-title: Clinical classification of age‐related macular degeneration
  publication-title: Ophthalmology
– volume: 20
  start-page: 573
  year: 1999
  end-page: 600
  article-title: The age‐related eye disease study (AREDS): design implications AREDS report no. 1
  publication-title: Control Clin Trials
– volume: 204
  year: 2021
– start-page: 716
  year: 2017
  end-page: 720
– volume: 59
  start-page: 1790
  year: 2018
  end-page: 9
  article-title: Multispectral pattern recognition reveals a diversity of clinical signs in intermediate age‐related macular degeneration
  publication-title: Invest Ophthalmol Vis Sci
– volume: 2020
  year: 2020
  article-title: Multimodal retinal image analysis via deep learning for the diagnosis of intermediate dry age‐related macular degeneration: a feasibility study
  publication-title: J Ophthalmol
– volume: 7
  start-page: 4928
  year: 2016
  end-page: 40
  article-title: Machine learning based detection of age‐related macular degeneration (AMD) and diabetic macular edema (DME) from optical coherence tomography (OCT) images
  publication-title: Biomed Opt Express
– year: 2019
– ident: e_1_2_12_8_1
  doi: 10.1016/j.cie.2020.106559
– ident: e_1_2_12_18_1
  doi: 10.1109/CVPR.2016.319
– ident: e_1_2_12_13_1
  doi: 10.31577/cai_2021_5_957
– ident: e_1_2_12_3_1
  doi: 10.1016/S2214-109X(20)30488-5
– ident: e_1_2_12_26_1
  doi: 10.1007/978-3-319-67558-9_28
– ident: e_1_2_12_16_1
– ident: e_1_2_12_40_1
  doi: 10.1007/978-981-16-1086-8_31
– ident: e_1_2_12_38_1
  doi: 10.1109/ACCESS.2020.3040275
– ident: e_1_2_12_25_1
  doi: 10.1007/978-3-030-20351-1_62
– ident: e_1_2_12_21_1
  doi: 10.3390/s21113865
– ident: e_1_2_12_19_1
  doi: 10.1109/TEVC.2019.2890858
– ident: e_1_2_12_10_1
  doi: 10.1109/ICCVW.2019.00049
– ident: e_1_2_12_15_1
  doi: 10.1016/j.jfranklin.2008.04.009
– ident: e_1_2_12_23_1
  doi: 10.3390/diagnostics10110904
– ident: e_1_2_12_39_1
  doi: 10.1109/EMBC46164.2021.9629607
– ident: e_1_2_12_5_1
  doi: 10.1109/AICAS.2019.8771609
– ident: e_1_2_12_31_1
  doi: 10.1155/2020/7493419
– ident: e_1_2_12_11_1
  doi: 10.1016/j.ophtha.2018.11.015
– ident: e_1_2_12_24_1
  doi: 10.1016/j.ajo.2006.05.028
– ident: e_1_2_12_14_1
  doi: 10.1016/S0197-2456(99)00031-8
– ident: e_1_2_12_27_1
  doi: 10.1167/iovs.12-11449
– ident: e_1_2_12_9_1
  doi: 10.1109/ICIP40778.2020.9190800
– ident: e_1_2_12_37_1
  doi: 10.3390/electronics9101617
– ident: e_1_2_12_2_1
  doi: 10.1258/jrsm.2009.080298
– ident: e_1_2_12_33_1
  doi: 10.1109/ICMLA.2017.00-75
– ident: e_1_2_12_7_1
  doi: 10.1364/BOE.7.004928
– ident: e_1_2_12_34_1
  doi: 10.1007/978-981-16-1089-9_60
– ident: e_1_2_12_4_1
  doi: 10.1016/j.ophtha.2012.10.036
– ident: e_1_2_12_6_1
  doi: 10.1109/ICBSII51839.2021.9445134
– ident: e_1_2_12_29_1
  doi: 10.1080/08164622.2021.1878821
– ident: e_1_2_12_32_1
  doi: 10.1016/j.compbiomed.2017.01.018
– ident: e_1_2_12_36_1
  doi: 10.1109/JBHI.2021.3092339
– ident: e_1_2_12_22_1
– ident: e_1_2_12_30_1
  doi: 10.1111/ceo.12466
– volume: 58
  start-page: 25
  year: 2017
  ident: e_1_2_12_35_1
  article-title: Deep learning based decision support system for automated diagnosis of age‐related macular degeneration (AMD)
  publication-title: Invest Ophthalmol Vis Sci
– ident: e_1_2_12_20_1
  doi: 10.1167/iovs.17-23076
– ident: e_1_2_12_12_1
  doi: 10.1109/TMI.2021.3075244
– ident: e_1_2_12_17_1
– ident: e_1_2_12_28_1
SSID ssj0007778
Score 2.3493898
Snippet Introduction The purpose of this study was to build an automated age‐related macular degeneration (AMD) colour fundus photography (CFP) recognition method that...
The purpose of this study was to build an automated age-related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates...
IntroductionThe purpose of this study was to build an automated age‐related macular degeneration (AMD) colour fundus photography (CFP) recognition method that...
SourceID unpaywall
pubmedcentral
proquest
pubmed
crossref
wiley
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 668
SubjectTerms Age
age‐related macular degeneration
Algorithms
artificial intelligence
automated recognition
Classification
deep learning
drusen
Eye diseases
Humans
image classification
machine learning
Macular degeneration
Macular Degeneration - diagnosis
Original
Photography
Retina
Retinal Drusen - diagnosis
ROC Curve
SummonAdditionalLinks – databaseName: Wiley Online Library Open Access
  dbid: 24P
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9RADLZKEdBLBYXS0ILC49BL0CbzjHqqgFIhlfZQpN4iz2RCkZZktdtV1Vt_Qn9jfwmeSXbEqoC4RRnnIXtsf57x2ADvikZJ6XxaueGYkfXDTEvJM-Ta5rYxzAp_OPnoqzz8xr-cibMV2FuchenrQ8QFN68ZwV57BUcz-03Ju0n3Pidwou_B_ZxwjJ_eBT-JZlip3gwXSvjdfz2UFfJpPPHRZWd0B2HeTZR8NG8neHWJ4_EymA3e6OAxrA8wMt3v5f4EVly7AQ-Pho3yDXgQMjvt7Cl8_jj1qyy31zd4iVOXhtY3KUHVlCwJ3Q2HWVyd_sSQkZrW7nuoRO0Flsb0oq59BqcHn04_HGZD94TMcoq5MqGc4kaWzPDGEuOVUCPhsEACSMaVwuas0YhljVrmWIysLq20I1Ujt1iXbBNW2651W5Ci8C2sGFdcOM6sRiXy2jQUmgmjmBwlsLvgYmWHyuK-wcW4WkQYxPAqMDyBN5F00pfT-BPRzkIU1aBRs8qnu_ra90wl8DoOky74DQ5sXTcnGqUkIVICUQk87yUXv8LIK0te0sv1kkwjga-zvTzS_jgP9bZzCoEl-fAE3kbx_-vvd8PE-DtFdXxyHC5e_D_pNqz5Rvd9ovAOrF5M5-4lwaEL8ypM-194wAd1
  priority: 102
  providerName: Wiley-Blackwell
Title Drusen‐aware model for age‐related macular degeneration recognition
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fopo.13108
https://www.ncbi.nlm.nih.gov/pubmed/36786498
https://www.proquest.com/docview/2822378837
https://www.proquest.com/docview/2776519663
https://pubmed.ncbi.nlm.nih.gov/PMC10946718
https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/opo.13108
UnpaywallVersion publishedVersion
Volume 43
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVEBS
  databaseName: EBSCOhost Academic Search Ultimate
  customDbUrl: https://search.ebscohost.com/login.aspx?authtype=ip,shib&custid=s3936755&profile=ehost&defaultdb=asn
  eissn: 1475-1313
  dateEnd: 20241103
  omitProxy: true
  ssIdentifier: ssj0007778
  issn: 1475-1313
  databaseCode: ABDBF
  dateStart: 20030101
  isFulltext: true
  titleUrlDefault: https://search.ebscohost.com/direct.asp?db=asn
  providerName: EBSCOhost
– providerCode: PRVWIB
  databaseName: Wiley Online Library - Core collection (SURFmarket)
  issn: 1475-1313
  databaseCode: DR2
  dateStart: 19970101
  customDbUrl:
  isFulltext: true
  eissn: 1475-1313
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0007778
  providerName: Wiley-Blackwell
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB7RrYBeeJRCU0oVHodestrEr-RYUUqF1HaFWqmcwthxALFkV9tdVXDiJ_Ab-0sYOw8pFBASlyhKJg_bM_Y39vgbgBdJqaS0Lqxcc4yo98MolZJHyFMTm1IzI9zm5KNjeXjG35yL8ybPqdsLU_NDdBNuzjJ8f-0MfFaUdT_fmjr5ldNhTAAlXYFVKQiMD2D17Hi8987PrCjhlv39ZjhO5yTIGm6h3rP9EekazLweLXl7Wc3w6yVOJn1E64ekg7vwvi1MHYnyebhc6KH59gvP43-U9h7caeBquFfr1324Yat1uHXULMivw00fQWouHsDr_bmbzbn6_gMvcW5Dn2InJEgcUo9FV_2mGVuEX9BHvoaF_eAZr51ihF0Y07TagNODV6cvD6MmS0NkOPl2kVBWcS0zpnlpqIGVUCNhMUECYtpmwsSsTBGzAlMZYzIyaWakGakCucEiYw9hUE0ruwkhCpcqi3HFheXMpKhEXOiSXEChFZOjAHbbhspNw2DuEmlM8taToRrKfQ0F8KwTndW0Hb8T2m5bO28s9yJ3YbWOY5-pAJ52t8nm3EIKVna6JBmlJCFfAmsBPKqVo_sKo9Ff8oxenvbUphNwfN79O9Wnj57XOyZXWxJWCOB5p2F_-_tdrzB_lshPxif-ZOufXvgY1hJCcHUs8jYMFvOlfUKIa6F3YCXhYzruv012Ggv7CYRxLaM
linkProvider Unpaywall
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9RADLZKEZRLBQVK-oDwOPSSapN5RuKCKGWBbtvDIvUWOZMJRVqS1barqjd-Ar-RX4Jnkh2xKiBuUeI8ZMeezzPf2ACvslpJaR2tvOSYUPTDREvJE-TapKYumRFuc_LoWA4_849n4mwFXi_2wnT1IcKEm_MMH6-dg7sJ6d-8vJ22-ymhE30LbnOZSpd6Zfw0xGGlujicKeGW_3VfV8jxeMKty6PRDYh5kym5Nm-meH2Fk8kymvXD0eF9WO9xZPymM_wDWLHNBtwd9SvlG3DHUzvNxUN4fzBz0yw_v__AK5zZ2Pe-iQmrxhRK6KzfzWKr-Bt6Smpc2S--FLWzWBz4RW3zCMaH78Zvh0nfPiExnJKuRCireClzVvLakOaVUANhMUNCSKXNhUlZrRHzCrVMMRsYnRtpBqpCbrDK2WNYbdrGPoEYhethxbjiwnJmNCqRVmVNuZkoFZODCPYWWixMX1rcdbiYFIsUgxReeIVH8CKITrt6Gn8S2lmYouhd6qJwfFdX_J6pCJ6Hy-QMboUDG9vOSUYpSZCUUFQEm53lwlsYDcuS5_RwvWTTIOAKbS9fab6e-4LbKeXAkgbxCF4G8__r6_f8j_F3ieLk9MQfbP2_6DNYG45HR8XRh-NP23DPdb3vWMM7sHo5m9tdwkaX5VPvAr8AqdIK4Q
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Jb9QwFH4qRRQuLGULFAjLoZeMJvEaiQtiGMrSRahIvaDoxXFaxJCMpjOq4MRP4DfyS3h2FhgKCHGL4pfF9nv2Z_vzZ4BHSamktI5WnnOMqPXDSEvJI-TaxKbMmRFuc_L2jtx6y18eiIMVeNzthWn0IfoJNxcZvr12AW6nRflTlNfTehATOtFn4CwXqXaEvtGbH-JRSjXtcKKEW_7Xra6Q4_H0jy73Rqcg5mmm5PlFNcVPJziZLKNZ3x2NL8G7LiMNC-XDYDHPB-bzLxqP_5vTy3Cxxanhk8axrsCKrdZhbbtdiV-Hc546ao6vwvPRzE3jfPvyFU9wZkN_tk5IWDikporu-t0ytgg_oqe8hoU99FLXziPCnr9UV9dgf_xs_-lW1B7PEBlOg7pIKKt4LlOW89JQzSqhhsJigoTAcpsKE7NSI6YFahljMjQ6NdIMVYHcYJGy67Ba1ZW9CSEKd0YW44oLy5nRqERc5CWN_USumBwGsNnVUmZa6XJ3gsYk64YwVEKZL6EAHvSm00av43dGG11VZ23IHmeOT-vE9ZkK4H6fTMHmVlCwsvWCbJSSBHkJpQVwo_GM_iuMun3JU3q5XvKZ3sAJeS-nVO-PvKB3TGNsSSAhgIe9e_3t7ze9t_zZItvd2_UXt_7d9B6s7Y3G2esXO69uw4WEoFxDSt6A1flsYe8Q9Jrnd32EfQe1Aisl
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT9wwEB7RRX1cSkspTUur9HHgktVm_UqOqC2gSjwOINFTOnYcQCzZ1bIrBCd-Ar-xv6Rj5yEF2qpSb1Y8eTiesb-xx98AfBoWSkrrwso1x4hGP4wSKXmEPDGxKTQzwh1O3tmV24f825E4qvOcurMwFT9Eu-DmLMOP187AJ3lRjfONqZNfOe7HBFCSB7AoBYHxHiwe7u5vfPcrK0q4bX9_GI5TmQRZzS3Uubc7I92DmfejJR_PywleXeJo1EW0fkraXIIfTWOqSJSz_nym--b6Ds_jf7T2GTyt4Wq4UenXc1iw5TI82qk35JfhoY8gNRcvYOvL1K3m_Ly5xUuc2tCn2AkJEoc0YtFVf2jG5uE5-sjXMLfHnvHaKUbYhjGNyxU42Px68Hk7qrM0RIaTbxcJZRXXMmWaF4Y6WAk1EBaHSEBM21SYmBUJYppjImMcDkySGmkGKkduME_ZS-iV49K-ghCFS5XFuOLCcmYSVCLOdUEuoNCKyUEA601HZaZmMHeJNEZZ48nQH8r8HwrgQys6qWg7fie01vR2VlvuRebCah3HPlMBvG-ryebcRgqWdjwnGaUkIV8CawGsVsrRvoXR7C95Sg9POmrTCjg-725NeXrieb1jcrUlYYUAPrYa9revX_cK82eJbG9_zxde_9MD38CTISG4KhZ5DXqz6dy-JcQ10-9qq_oFcnUr4w
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=Drusen%E2%80%90aware+model+for+age%E2%80%90related+macular+degeneration+recognition&rft.jtitle=Ophthalmic+%26+physiological+optics&rft.au=Pan%2C+Junjun&rft.au=Ho%2C+Sharon&rft.au=Ly%2C+Angelica&rft.au=Kalloniatis%2C+Michael&rft.date=2023-07-01&rft.pub=John+Wiley+and+Sons+Inc&rft.issn=0275-5408&rft.eissn=1475-1313&rft.volume=43&rft.issue=4&rft.spage=668&rft.epage=679&rft_id=info:doi/10.1111%2Fopo.13108&rft_id=info%3Apmid%2F36786498&rft.externalDocID=PMC10946718
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0275-5408&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0275-5408&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0275-5408&client=summon