Development and validation of a deep‐learning algorithm for the detection of neovascular age‐related macular degeneration from colour fundus photographs
Importance Detection of early onset neovascular age‐related macular degeneration (AMD) is critical to protecting vision. Background To describe the development and validation of a deep‐learning algorithm (DLA) for the detection of neovascular age‐related macular degeneration. Design Development and...
Gespeichert in:
| Veröffentlicht in: | Clinical & experimental ophthalmology Jg. 47; H. 8; S. 1009 - 1018 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Melbourne
John Wiley & Sons Australia, Ltd
01.11.2019
Wiley Subscription Services, Inc |
| Schlagworte: | |
| ISSN: | 1442-6404, 1442-9071, 1442-9071 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Importance
Detection of early onset neovascular age‐related macular degeneration (AMD) is critical to protecting vision.
Background
To describe the development and validation of a deep‐learning algorithm (DLA) for the detection of neovascular age‐related macular degeneration.
Design
Development and validation of a DLA using retrospective datasets.
Participants
We developed and trained the DLA using 56 113 retinal images and an additional 86 162 images from an independent dataset to externally validate the DLA. All images were non‐stereoscopic and retrospectively collected.
Methods
The internal validation dataset was derived from real‐world clinical settings in China. Gold standard grading was assigned when consensus was reached by three individual ophthalmologists. The DLA classified 31 247 images as gradable and 24 866 as ungradable (poor quality or poor field definition). These ungradable images were used to create a classification model for image quality. Efficiency and diagnostic accuracy were tested using 86 162 images derived from the Melbourne Collaborative Cohort Study. Neovascular AMD and/or ungradable outcome in one or both eyes was considered referable.
Main Outcome Measures
Area under the receiver operating characteristic curve (AUC), sensitivity and specificity.
Results
In the internal validation dataset, the AUC, sensitivity and specificity of the DLA for neovascular AMD was 0.995, 96.7%, 96.4%, respectively. Testing against the independent external dataset achieved an AUC, sensitivity and specificity of 0.967, 100% and 93.4%, respectively. More than 60% of false positive cases displayed other macular pathologies. Amongst the false negative cases (internal validation dataset only), over half (57.2%) proved to be undetected detachment of the neurosensory retina or RPE layer.
Conclusions and Relevance
This DLA shows robust performance for the detection of neovascular AMD amongst retinal images from a multi‐ethnic sample and under different imaging protocols. Further research is warranted to investigate where this technology could be best utilized within screening and research settings. |
|---|---|
| AbstractList | Importance
Detection of early onset neovascular age‐related macular degeneration (AMD) is critical to protecting vision.
Background
To describe the development and validation of a deep‐learning algorithm (DLA) for the detection of neovascular age‐related macular degeneration.
Design
Development and validation of a DLA using retrospective datasets.
Participants
We developed and trained the DLA using 56 113 retinal images and an additional 86 162 images from an independent dataset to externally validate the DLA. All images were non‐stereoscopic and retrospectively collected.
Methods
The internal validation dataset was derived from real‐world clinical settings in China. Gold standard grading was assigned when consensus was reached by three individual ophthalmologists. The DLA classified 31 247 images as gradable and 24 866 as ungradable (poor quality or poor field definition). These ungradable images were used to create a classification model for image quality. Efficiency and diagnostic accuracy were tested using 86 162 images derived from the Melbourne Collaborative Cohort Study. Neovascular AMD and/or ungradable outcome in one or both eyes was considered referable.
Main Outcome Measures
Area under the receiver operating characteristic curve (AUC), sensitivity and specificity.
Results
In the internal validation dataset, the AUC, sensitivity and specificity of the DLA for neovascular AMD was 0.995, 96.7%, 96.4%, respectively. Testing against the independent external dataset achieved an AUC, sensitivity and specificity of 0.967, 100% and 93.4%, respectively. More than 60% of false positive cases displayed other macular pathologies. Amongst the false negative cases (internal validation dataset only), over half (57.2%) proved to be undetected detachment of the neurosensory retina or RPE layer.
Conclusions and Relevance
This DLA shows robust performance for the detection of neovascular AMD amongst retinal images from a multi‐ethnic sample and under different imaging protocols. Further research is warranted to investigate where this technology could be best utilized within screening and research settings. Detection of early onset neovascular age-related macular degeneration (AMD) is critical to protecting vision.IMPORTANCEDetection of early onset neovascular age-related macular degeneration (AMD) is critical to protecting vision.To describe the development and validation of a deep-learning algorithm (DLA) for the detection of neovascular age-related macular degeneration.BACKGROUNDTo describe the development and validation of a deep-learning algorithm (DLA) for the detection of neovascular age-related macular degeneration.Development and validation of a DLA using retrospective datasets.DESIGNDevelopment and validation of a DLA using retrospective datasets.We developed and trained the DLA using 56 113 retinal images and an additional 86 162 images from an independent dataset to externally validate the DLA. All images were non-stereoscopic and retrospectively collected.PARTICIPANTSWe developed and trained the DLA using 56 113 retinal images and an additional 86 162 images from an independent dataset to externally validate the DLA. All images were non-stereoscopic and retrospectively collected.The internal validation dataset was derived from real-world clinical settings in China. Gold standard grading was assigned when consensus was reached by three individual ophthalmologists. The DLA classified 31 247 images as gradable and 24 866 as ungradable (poor quality or poor field definition). These ungradable images were used to create a classification model for image quality. Efficiency and diagnostic accuracy were tested using 86 162 images derived from the Melbourne Collaborative Cohort Study. Neovascular AMD and/or ungradable outcome in one or both eyes was considered referable.METHODSThe internal validation dataset was derived from real-world clinical settings in China. Gold standard grading was assigned when consensus was reached by three individual ophthalmologists. The DLA classified 31 247 images as gradable and 24 866 as ungradable (poor quality or poor field definition). These ungradable images were used to create a classification model for image quality. Efficiency and diagnostic accuracy were tested using 86 162 images derived from the Melbourne Collaborative Cohort Study. Neovascular AMD and/or ungradable outcome in one or both eyes was considered referable.Area under the receiver operating characteristic curve (AUC), sensitivity and specificity.MAIN OUTCOME MEASURESArea under the receiver operating characteristic curve (AUC), sensitivity and specificity.In the internal validation dataset, the AUC, sensitivity and specificity of the DLA for neovascular AMD was 0.995, 96.7%, 96.4%, respectively. Testing against the independent external dataset achieved an AUC, sensitivity and specificity of 0.967, 100% and 93.4%, respectively. More than 60% of false positive cases displayed other macular pathologies. Amongst the false negative cases (internal validation dataset only), over half (57.2%) proved to be undetected detachment of the neurosensory retina or RPE layer.RESULTSIn the internal validation dataset, the AUC, sensitivity and specificity of the DLA for neovascular AMD was 0.995, 96.7%, 96.4%, respectively. Testing against the independent external dataset achieved an AUC, sensitivity and specificity of 0.967, 100% and 93.4%, respectively. More than 60% of false positive cases displayed other macular pathologies. Amongst the false negative cases (internal validation dataset only), over half (57.2%) proved to be undetected detachment of the neurosensory retina or RPE layer.This DLA shows robust performance for the detection of neovascular AMD amongst retinal images from a multi-ethnic sample and under different imaging protocols. Further research is warranted to investigate where this technology could be best utilized within screening and research settings.CONCLUSIONS AND RELEVANCEThis DLA shows robust performance for the detection of neovascular AMD amongst retinal images from a multi-ethnic sample and under different imaging protocols. Further research is warranted to investigate where this technology could be best utilized within screening and research settings. ImportanceDetection of early onset neovascular age‐related macular degeneration (AMD) is critical to protecting vision.BackgroundTo describe the development and validation of a deep‐learning algorithm (DLA) for the detection of neovascular age‐related macular degeneration.DesignDevelopment and validation of a DLA using retrospective datasets.ParticipantsWe developed and trained the DLA using 56 113 retinal images and an additional 86 162 images from an independent dataset to externally validate the DLA. All images were non‐stereoscopic and retrospectively collected.MethodsThe internal validation dataset was derived from real‐world clinical settings in China. Gold standard grading was assigned when consensus was reached by three individual ophthalmologists. The DLA classified 31 247 images as gradable and 24 866 as ungradable (poor quality or poor field definition). These ungradable images were used to create a classification model for image quality. Efficiency and diagnostic accuracy were tested using 86 162 images derived from the Melbourne Collaborative Cohort Study. Neovascular AMD and/or ungradable outcome in one or both eyes was considered referable.Main Outcome MeasuresArea under the receiver operating characteristic curve (AUC), sensitivity and specificity.ResultsIn the internal validation dataset, the AUC, sensitivity and specificity of the DLA for neovascular AMD was 0.995, 96.7%, 96.4%, respectively. Testing against the independent external dataset achieved an AUC, sensitivity and specificity of 0.967, 100% and 93.4%, respectively. More than 60% of false positive cases displayed other macular pathologies. Amongst the false negative cases (internal validation dataset only), over half (57.2%) proved to be undetected detachment of the neurosensory retina or RPE layer.Conclusions and RelevanceThis DLA shows robust performance for the detection of neovascular AMD amongst retinal images from a multi‐ethnic sample and under different imaging protocols. Further research is warranted to investigate where this technology could be best utilized within screening and research settings. Detection of early onset neovascular age-related macular degeneration (AMD) is critical to protecting vision. To describe the development and validation of a deep-learning algorithm (DLA) for the detection of neovascular age-related macular degeneration. Development and validation of a DLA using retrospective datasets. We developed and trained the DLA using 56 113 retinal images and an additional 86 162 images from an independent dataset to externally validate the DLA. All images were non-stereoscopic and retrospectively collected. The internal validation dataset was derived from real-world clinical settings in China. Gold standard grading was assigned when consensus was reached by three individual ophthalmologists. The DLA classified 31 247 images as gradable and 24 866 as ungradable (poor quality or poor field definition). These ungradable images were used to create a classification model for image quality. Efficiency and diagnostic accuracy were tested using 86 162 images derived from the Melbourne Collaborative Cohort Study. Neovascular AMD and/or ungradable outcome in one or both eyes was considered referable. Area under the receiver operating characteristic curve (AUC), sensitivity and specificity. In the internal validation dataset, the AUC, sensitivity and specificity of the DLA for neovascular AMD was 0.995, 96.7%, 96.4%, respectively. Testing against the independent external dataset achieved an AUC, sensitivity and specificity of 0.967, 100% and 93.4%, respectively. More than 60% of false positive cases displayed other macular pathologies. Amongst the false negative cases (internal validation dataset only), over half (57.2%) proved to be undetected detachment of the neurosensory retina or RPE layer. This DLA shows robust performance for the detection of neovascular AMD amongst retinal images from a multi-ethnic sample and under different imaging protocols. Further research is warranted to investigate where this technology could be best utilized within screening and research settings. |
| Author | Li, Zhixi Scheetz, Jane Chang, Robert Makeyeva, Galina Meng, Wei Keel, Stuart Phung, James Liu, Chi He, Mingguang Yan, Xixi Aung, KhinZaw Guymer, Robyn Robman, Liubov |
| Author_xml | – sequence: 1 givenname: Stuart orcidid: 0000-0001-6756-348X surname: Keel fullname: Keel, Stuart organization: University of Melbourne – sequence: 2 givenname: Zhixi surname: Li fullname: Li, Zhixi organization: Zhongshan Ophthalmic Center, Sun Yat‐Sen University – sequence: 3 givenname: Jane orcidid: 0000-0003-0523-1927 surname: Scheetz fullname: Scheetz, Jane organization: University of Melbourne – sequence: 4 givenname: Liubov surname: Robman fullname: Robman, Liubov organization: Monash University Melbourne – sequence: 5 givenname: James surname: Phung fullname: Phung, James organization: Monash University Melbourne – sequence: 6 givenname: Galina surname: Makeyeva fullname: Makeyeva, Galina organization: University of Melbourne – sequence: 7 givenname: KhinZaw surname: Aung fullname: Aung, KhinZaw organization: University of Melbourne – sequence: 8 givenname: Chi surname: Liu fullname: Liu, Chi organization: Healgoo Interactive Medical Technology Co. Ltd – sequence: 9 givenname: Xixi surname: Yan fullname: Yan, Xixi organization: University of Melbourne – sequence: 10 givenname: Wei surname: Meng fullname: Meng, Wei organization: Healgoo Interactive Medical Technology Co. Ltd – sequence: 11 givenname: Robyn surname: Guymer fullname: Guymer, Robyn organization: University of Melbourne – sequence: 12 givenname: Robert surname: Chang fullname: Chang, Robert organization: Byers Eye Institute at Stanford University – sequence: 13 givenname: Mingguang surname: He fullname: He, Mingguang email: mingguang.he@unimelb.edu.au organization: Zhongshan Ophthalmic Center, Sun Yat‐Sen University |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/31215760$$D View this record in MEDLINE/PubMed |
| BookMark | eNp1kctu1DAUhi1URC-w4AWQJTawmNa3OMkSDeUiVeoG1pYTH2dSOXawnUHd8Qg8AE_Hk2CamU0F3vjI-v7_HJ__HJ344AGhl5Rc0nKuegiXlFd19QSdUSHYpiU1PTnUUhBxis5TuiOEVIzLZ-iUU0arWpIz9Os97MGFeQKfsfYG77Ubjc5j8DhYrLEBmH__-OlARz_6AWs3hDjm3YRtiDjvoBAZ-qPAQ9jr1C9OR6wHKMoITmcweNLrq4EBPMS1hY1hwn1wYYnYLt4sCc-7kMMQ9bxLz9FTq12CF4f7An39cP1l-2lzc_vx8_bdzabnTVNt6qYiVBjZkK6WtBINEdBYXhvatDXrpOGV6VtZ2Y63tpXUdB0jglHLSakt8Av0ZvWdY_i2QMpqGlMPzunynSUpxgQXLWWMFPT1I_SuzO7LdIpxzlvOaSML9epALd0ERs1xnHS8V8e9F-BqBfoYUopgVT_mh5XkqEenKFF_k1UlWfWQbFG8faQ4mv6LPbh_Hx3c_x9U2-vbVfEHpLe17w |
| CitedBy_id | crossref_primary_10_1038_s41433_024_03085_2 crossref_primary_10_1371_journal_pone_0237352 crossref_primary_10_1016_j_preteyeres_2020_100900 crossref_primary_10_1002_14651858_CD015522_pub2 crossref_primary_10_1097_IIO_0000000000000334 crossref_primary_10_1136_bmjhci_2023_100757 crossref_primary_10_1007_s11548_021_02498_8 crossref_primary_10_1038_s41746_020_00350_y crossref_primary_10_1038_s41746_021_00438_z crossref_primary_10_1136_bjo_2025_327447 crossref_primary_10_1097_ICU_0000000000000676 crossref_primary_10_1097_ICU_0000000000000679 crossref_primary_10_1007_s11831_022_09720_z crossref_primary_10_1016_j_ijmedinf_2020_104363 crossref_primary_10_1038_s41598_023_38610_y crossref_primary_10_3390_diagnostics13182965 crossref_primary_10_1016_j_bspc_2024_106263 crossref_primary_10_1038_s41598_021_94178_5 crossref_primary_10_1371_journal_pone_0290278 crossref_primary_10_3389_fmed_2021_710329 crossref_primary_10_3390_diagnostics12010134 crossref_primary_10_1055_a_2413_6782 crossref_primary_10_1186_s40662_022_00285_3 crossref_primary_10_1016_j_cmpb_2023_107358 crossref_primary_10_3928_23258160_20220817_01 crossref_primary_10_1016_j_preteyeres_2025_101353 crossref_primary_10_3390_life12070973 crossref_primary_10_1016_j_oret_2020_03_007 crossref_primary_10_1186_s40662_024_00385_2 crossref_primary_10_1097_APO_0000000000000301 crossref_primary_10_1111_ceo_13881 crossref_primary_10_1038_s41746_024_01018_7 crossref_primary_10_1111_ceo_13968 crossref_primary_10_1097_IAE_0000000000003878 crossref_primary_10_1080_08164622_2021_2022961 crossref_primary_10_1097_OPX_0000000000001845 crossref_primary_10_1111_jce_15171 crossref_primary_10_1016_j_xcrm_2025_102187 crossref_primary_10_1038_s41746_025_01768_y crossref_primary_10_1080_02713683_2023_2215984 crossref_primary_10_1186_s40942_024_00554_4 crossref_primary_10_1080_08820538_2021_1889617 crossref_primary_10_3389_fmed_2023_1115032 crossref_primary_10_1111_ceo_14147 crossref_primary_10_1097_APO_0000000000000404 crossref_primary_10_1016_j_cmpb_2021_106048 crossref_primary_10_1007_s10462_024_10883_3 crossref_primary_10_1007_s10278_023_00775_3 crossref_primary_10_1038_s41746_022_00571_3 |
| Cites_doi | 10.1016/j.ophtha.2016.11.014 10.1001/jamaophthalmol.2018.4118 10.1038/538020a 10.1016/j.ophtha.2018.01.023 10.1167/iovs.12-9576 10.1093/ije/dyx085 10.3109/09286586.2015.1010688 10.1167/iovs.10-7075 10.1016/S2214-109X(13)70145-1 10.1016/j.compbiomed.2014.07.015 10.1001/jamaophthalmol.2017.3782 10.1038/s41598-018-22612-2 10.1001/jama.2016.17563 10.1371/journal.pone.0133628 10.1001/archopht.1984.01040031330019 10.1016/S0140-6736(07)61104-0 10.1016/j.ophtha.2012.10.036 10.1016/j.ophtha.2018.11.015 10.1001/jama.2017.18152 10.2337/dc18-0147 10.1016/j.compbiomed.2017.01.018 10.1016/j.ophtha.2018.02.037 10.1080/09286580902864419 10.1016/S0140-6736(12)60282-7 10.1001/jama.2016.17216 |
| ContentType | Journal Article |
| Copyright | 2019 Royal Australian and New Zealand College of Ophthalmologists 2019 Royal Australian and New Zealand College of Ophthalmologists. |
| Copyright_xml | – notice: 2019 Royal Australian and New Zealand College of Ophthalmologists – notice: 2019 Royal Australian and New Zealand College of Ophthalmologists. |
| DBID | AAYXX CITATION NPM 7TK K9. 7X8 |
| DOI | 10.1111/ceo.13575 |
| DatabaseName | CrossRef PubMed Neurosciences Abstracts ProQuest Health & Medical Complete (Alumni) MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed ProQuest Health & Medical Complete (Alumni) Neurosciences Abstracts MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic ProQuest Health & Medical Complete (Alumni) PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1442-9071 |
| EndPage | 1018 |
| ExternalDocumentID | 31215760 10_1111_ceo_13575 CEO13575 |
| Genre | article Journal Article |
| GroupedDBID | --- .3N .GA .Y3 05W 0R~ 10A 1OC 29B 31~ 33P 36B 3SF 4.4 50Y 50Z 51W 51X 52M 52N 52O 52P 52R 52S 52T 52U 52V 52W 52X 53G 5GY 5HH 5LA 5VS 66C 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 930 A01 A03 AAESR AAEVG AAHHS AAHQN AAIPD AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABDBF ABEML ABJNI ABPVW ABQWH ABXGK ACAHQ ACBWZ ACCFJ ACCZN ACGFS ACGOF ACIWK ACMXC ACPOU ACPRK ACRPL ACSCC ACUHS ACXBN ACXQS ACYXJ ADBBV ADBTR ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN ADZOD AEEZP AEIGN AEIMD AENEX AEQDE AEUQT AEUYR AFBPY AFEBI AFFPM AFGKR AFPWT AFRAH AFWVQ AFZJQ AHBTC AHMBA AIACR AITYG AIURR AIWBW AJBDE ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ATUGU AZBYB AZFZN AZVAB BAFTC BDRZF BFHJK BHBCM BMXJE BROTX BRXPI BY8 C45 CAG COF CS3 D-6 D-7 D-E D-F DCZOG DPXWK DR2 DRFUL DRMAN DRSTM DU5 EAD EAP EBC EBD EJD EMB EMK EMOBN ESX EX3 F00 F01 F04 F5P FEDTE FUBAC G-S G.N GODZA H.X HF~ HGLYW HVGLF HZI HZ~ IHE IX1 J0M K48 KBYEO KTM LATKE LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES MEWTI MK4 MRFUL MRMAN MRSTM MSFUL MSMAN MSSTM MXFUL MXMAN MXSTM N04 N05 N9A NF~ O66 O9- OIG OVD P2P P2W P2X P2Z P4B P4D PQQKQ Q.N Q11 QB0 R.K ROL RX1 SUPJJ SV3 TEORI TUS UB1 W8V W99 WBKPD WHWMO WIH WIJ WIK WOHZO WOQ WOW WQJ WRC WVDHM WXI WXSBR XG1 YFH ZZTAW ~IA ~WT AAMMB AAYXX AEFGJ AEYWJ AGHNM AGQPQ AGXDD AGYGG AIDQK AIDYY CITATION O8X NPM 7TK K9. 7X8 |
| ID | FETCH-LOGICAL-c3885-785014d680b76154804e8f37d18972b6d35dc965fb39f961dbb20421f301dbfe3 |
| IEDL.DBID | DRFUL |
| ISICitedReferencesCount | 61 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000479387700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1442-6404 1442-9071 |
| IngestDate | Wed Oct 01 14:58:58 EDT 2025 Sat Nov 29 15:09:12 EST 2025 Thu Apr 03 07:05:57 EDT 2025 Tue Nov 18 21:57:38 EST 2025 Sat Nov 29 03:30:33 EST 2025 Wed Jan 22 16:37:02 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 8 |
| Keywords | age-related macular degeneration deep-learning algorithm retinal-imaging |
| Language | English |
| License | 2019 Royal Australian and New Zealand College of Ophthalmologists. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3885-785014d680b76154804e8f37d18972b6d35dc965fb39f961dbb20421f301dbfe3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 ObjectType-Undefined-3 |
| ORCID | 0000-0003-0523-1927 0000-0001-6756-348X |
| OpenAccessLink | https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/ceo.13575 |
| PMID | 31215760 |
| PQID | 2333933186 |
| PQPubID | 1006520 |
| PageCount | 10 |
| ParticipantIDs | proquest_miscellaneous_2243491220 proquest_journals_2333933186 pubmed_primary_31215760 crossref_citationtrail_10_1111_ceo_13575 crossref_primary_10_1111_ceo_13575 wiley_primary_10_1111_ceo_13575_CEO13575 |
| PublicationCentury | 2000 |
| PublicationDate | November 2019 2019-11-00 2019-Nov 20191101 |
| PublicationDateYYYYMMDD | 2019-11-01 |
| PublicationDate_xml | – month: 11 year: 2019 text: November 2019 |
| PublicationDecade | 2010 |
| PublicationPlace | Melbourne |
| PublicationPlace_xml | – name: Melbourne – name: Australia – name: Surry Hills |
| PublicationTitle | Clinical & experimental ophthalmology |
| PublicationTitleAlternate | Clin Exp Ophthalmol |
| PublicationYear | 2019 |
| Publisher | John Wiley & Sons Australia, Ltd Wiley Subscription Services, Inc |
| Publisher_xml | – name: John Wiley & Sons Australia, Ltd – name: Wiley Subscription Services, Inc |
| References | 2017; 318 2018; 8 2017; 82 2014; 2 2007; 370 1984; 102 2016; 538 2016; 316 2017; 46 2015; 22 2018; 125 2018; 136 2015; 10 2019; 126 2011; 52 2018; 41 2013; 120 2012; 379 2017; 135 2017; 124 2009; 16 2012; 53 2014; 53 e_1_2_8_24_1 e_1_2_8_25_1 e_1_2_8_26_1 e_1_2_8_27_1 e_1_2_8_3_1 e_1_2_8_2_1 e_1_2_8_5_1 e_1_2_8_4_1 e_1_2_8_7_1 e_1_2_8_6_1 e_1_2_8_9_1 e_1_2_8_8_1 e_1_2_8_20_1 e_1_2_8_21_1 e_1_2_8_22_1 e_1_2_8_23_1 e_1_2_8_17_1 e_1_2_8_18_1 e_1_2_8_19_1 e_1_2_8_13_1 e_1_2_8_14_1 e_1_2_8_15_1 e_1_2_8_16_1 e_1_2_8_10_1 e_1_2_8_11_1 e_1_2_8_12_1 |
| References_xml | – volume: 120 start-page: 844 year: 2013 end-page: 851 article-title: Clinical classification of age‐related macular degeneration publication-title: Ophthalmology – volume: 126 start-page: 565 year: 2019 end-page: 575 – volume: 10 year: 2015 article-title: The clinical effectiveness and cost‐effectiveness of screening for age‐related macular degeneration in Japan: a Markov modeling study publication-title: PLoS One – volume: 316 start-page: 2402 year: 2016 end-page: 2410 article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs publication-title: JAMA – volume: 318 start-page: 2211 year: 2017 end-page: 2223 article-title: Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes publication-title: JAMA – volume: 316 start-page: 2366 year: 2016 end-page: 2367 article-title: Artificial intelligence with deep learning technology looks into diabetic retinopathy screening publication-title: JAMA – volume: 52 start-page: 5862 year: 2011 end-page: 5871 article-title: Automatic detection of diabetic retinopathy and age‐related macular degeneration in digital fundus images publication-title: Invest Ophthalmol Vis Sci – volume: 379 start-page: 1728 year: 2012 end-page: 1738 article-title: Age‐related macular degeneration publication-title: Lancet – volume: 8 start-page: 4330 year: 2018 article-title: Feasibility and patient acceptability of a novel artificial intelligence‐based screening model for diabetic retinopathy at endocrinology outpatient services: a pilot study publication-title: Sci Rep – volume: 16 start-page: 254 year: 2009 end-page: 261 article-title: Non‐mydriatic digital macular photography: how good is the second eye photograph? publication-title: Ophthalmic Epidemiol – volume: 22 start-page: 75 year: 2015 end-page: 84 article-title: Age‐related macular degeneration in ethnically diverse Australia: Melbourne collaborative cohort study publication-title: Ophthalmic Epidemiol – volume: 53 start-page: 55 year: 2014 end-page: 64 article-title: Automated diagnosis of age‐related macular degeneration using greyscale features from digital fundus images publication-title: Comput Biol Med – volume: 46 start-page: 1757 year: 2017 end-page: 1757i article-title: Cohort profile: the Melbourne collaborative cohort study (health 2020) publication-title: Int J Epidemiol – volume: 8 start-page: 4330 year: 2018 article-title: Feasibility and patient acceptability of a novel artificial intelligence‐based screening model for diabetic retinopathy at endocrinology outpatient services: a pilot study publication-title: Scientific Rep – volume: 41 start-page: 2509 year: 2018 end-page: 2516 article-title: An automated grading system for detection of vision‐threatening referable diabetic retinopathy on the basis of color fundus photographs publication-title: Diabetes Care – volume: 124 start-page: 343 year: 2017 end-page: 351 article-title: Automated diabetic retinopathy image assessment software: diagnostic accuracy and cost‐effectiveness compared with human graders publication-title: Ophthalmology – volume: 370 start-page: 204 year: 2007 end-page: 206 article-title: Clinical update: new treatments for age‐related macular degeneration publication-title: Lancet – volume: 2 year: 2014 end-page: e116 article-title: Global prevalence of age‐related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta‐analysis publication-title: Lancet Glob Health – volume: 135 start-page: 1170 year: 2017 end-page: 1176 article-title: Automated grading of age‐related macular degeneration from color fundus images using deep convolutional neural networks publication-title: JAMA Ophthalmol – volume: 53 start-page: 8310 year: 2012 end-page: 8318 article-title: Automated "disease/no disease" grading of age‐related macular degeneration by an image mining approach publication-title: Invest Ophthalmol Vis Sci – volume: 102 start-page: 1640 year: 1984 end-page: 1642 article-title: Age‐related macular degeneration and blindness due to neovascular maculopathy publication-title: Arch Ophthalmol – volume: 125 start-page: 1199 year: 2018 end-page: 1206 article-title: Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs publication-title: Ophthalmology – volume: 82 start-page: 80 year: 2017 end-page: 86 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: 136 start-page: 1359 year: 2018 end-page: 1366 – volume: 538 start-page: 20 year: 2016 – volume: 125 start-page: 1410 year: 2018 end-page: 1420 article-title: A deep learning algorithm for prediction of age‐related eye disease study severity scale for age‐related macular degeneration from color fundus photography publication-title: Ophthalmology – ident: e_1_2_8_9_1 doi: 10.1016/j.ophtha.2016.11.014 – ident: e_1_2_8_21_1 doi: 10.1001/jamaophthalmol.2018.4118 – ident: e_1_2_8_22_1 doi: 10.1038/538020a – ident: e_1_2_8_11_1 doi: 10.1016/j.ophtha.2018.01.023 – ident: e_1_2_8_19_1 doi: 10.1167/iovs.12-9576 – ident: e_1_2_8_14_1 doi: 10.1093/ije/dyx085 – ident: e_1_2_8_16_1 doi: 10.3109/09286586.2015.1010688 – ident: e_1_2_8_17_1 doi: 10.1167/iovs.10-7075 – ident: e_1_2_8_2_1 doi: 10.1016/S2214-109X(13)70145-1 – ident: e_1_2_8_18_1 doi: 10.1016/j.compbiomed.2014.07.015 – ident: e_1_2_8_5_1 doi: 10.1001/jamaophthalmol.2017.3782 – ident: e_1_2_8_25_1 doi: 10.1038/s41598-018-22612-2 – ident: e_1_2_8_27_1 doi: 10.1038/s41598-018-22612-2 – ident: e_1_2_8_23_1 doi: 10.1001/jama.2016.17563 – ident: e_1_2_8_24_1 doi: 10.1371/journal.pone.0133628 – ident: e_1_2_8_3_1 doi: 10.1001/archopht.1984.01040031330019 – ident: e_1_2_8_8_1 doi: 10.1016/S0140-6736(07)61104-0 – ident: e_1_2_8_13_1 doi: 10.1016/j.ophtha.2012.10.036 – ident: e_1_2_8_20_1 doi: 10.1016/j.ophtha.2018.11.015 – ident: e_1_2_8_12_1 doi: 10.1001/jama.2017.18152 – ident: e_1_2_8_26_1 doi: 10.2337/dc18-0147 – ident: e_1_2_8_4_1 doi: 10.1016/j.compbiomed.2017.01.018 – ident: e_1_2_8_6_1 doi: 10.1016/j.ophtha.2018.02.037 – ident: e_1_2_8_15_1 doi: 10.1080/09286580902864419 – ident: e_1_2_8_7_1 doi: 10.1016/S0140-6736(12)60282-7 – ident: e_1_2_8_10_1 doi: 10.1001/jama.2016.17216 |
| SSID | ssj0005236 |
| Score | 2.4901323 |
| Snippet | Importance
Detection of early onset neovascular age‐related macular degeneration (AMD) is critical to protecting vision.
Background
To describe the development... Detection of early onset neovascular age-related macular degeneration (AMD) is critical to protecting vision. To describe the development and validation of a... ImportanceDetection of early onset neovascular age‐related macular degeneration (AMD) is critical to protecting vision.BackgroundTo describe the development... Detection of early onset neovascular age-related macular degeneration (AMD) is critical to protecting vision.IMPORTANCEDetection of early onset neovascular... |
| SourceID | proquest pubmed crossref wiley |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1009 |
| SubjectTerms | Age age‐related macular degeneration Algorithms Datasets Deep learning deep‐learning algorithm Macular degeneration Retina retinal‐imaging |
| Title | Development and validation of a deep‐learning algorithm for the detection of neovascular age‐related macular degeneration from colour fundus photographs |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fceo.13575 https://www.ncbi.nlm.nih.gov/pubmed/31215760 https://www.proquest.com/docview/2333933186 https://www.proquest.com/docview/2243491220 |
| Volume | 47 |
| WOSCitedRecordID | wos000479387700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1442-9071 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0005236 issn: 1442-6404 databaseCode: DRFUL dateStart: 20000101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NbtQwEB61W4S48P-zUCqDOPQSaWMnsS1OqHTFoRSEKNpbZMf2dqU2WW2yPfcReACejidhbGejrQAJiVsUz8iRPTMeZ2a-AXjjfOzF0CrJU0eTTKJKaZPKRHEnmNOTzIa6tW8n_PRUzGby8w683dTCRHyI4Yeb14xgr72CK91uKXllG9-0gee7sEdRbvMR7L3_Mj072crwYLG4KKNJkU2yHljIJ_IMzDePo998zJsuazhzpvf-62vvw93e1STvomw8gB1bP4TbH_tg-iP4sZUwRFRtCArdIrZYIo0jihhrlz-vv_eNJeZEXcyb1aI7vyTo6RL0HJGiC6lcgaG2Q14rQSuFnKFQxhpyqeJbY-cB5Tpw-MIW4jGz1yuCp6tZt2R53nQRQrt9DGfT469HH5K-WUNSMSHyhAsfoTSFmGhe-HsQbrNwjJtUSE51YVhuKlnkTjPpZJEarSkajNShhTHaWfYERnVT22dAKuN4YYV0yuVZJYSqXKaFkJprmRrjxnC42bOy6pHMfUONi3Jzo8HVLsNqj-H1QLqM8B1_ItrfbHzZa3BbUsaYZGjxijG8GoZR93xAReGKrpGGZiyTKaWTMTyNAjPMwjxsBy9w5DDIxd-nL4-OP4WH5_9O-gLuoOcmY1HkPoy61dq-hFvVVbdoVwewy2fioFeHX6uOEOw |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NbtQwEB6VFgEXfgssFDCIQy-RNrbjH4kLKl0VsV0QalFvURzb25XaZLWb5cwj8AA8HU_C2MlGWwESErcomZEje2Y89sx8A_Dah9iLpWWSpZ4mXKNKGZvqpJBeMW-G3MW6tS9jOZmoszP9aQverGthWnyI_sItaEa010HBw4X0hpaXrg5dG2R2DXY4ihHK9867z6PT8UaKB2urizhNBB_yDlkoZPL0zFf3o9-czKs-a9x0Rnf-73fvwu3O2SRvW-m4B1uuug83jrtw-gP4sZEyRIrKEhS7WdtkidSeFMQ6N__57XvXWmJKiotpvZg155cEfV2CviNSNDGZKzJUrs9sJWinkDOWyjhLLov2rXXTiHMdOUJpCwmo2asFwf3VrpZkfl43LYj2chdOR4cnB0dJ164hKZlSWSJViFFaoYZGinASwoVWnkmbKi2pEZZlttQi84Zpr0VqjaFoMlKPNsYa79hD2K7qyj0GUlovhVPaFz7jpVJF6blRShtpdGqtH8D-etHyssMyDy01LvL1mQZnO4-zPYBXPem8BfD4E9HeeuXzToeXOWWMaYY2TwzgZf8ZtS-EVAqc0RXSUM64TikdDuBRKzH9KCwAd0iBX_ajYPx9-Pzg8GN8ePLvpC_g5tHJ8Tgfv598eAq30I_TbYnkHmw3i5V7BtfLr81suXjeacUvfk4T9A |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9NAEB6VFFVceD8CBRbEoRdL8e56HxIX1DYCEUKFKOrN8r7SSK0dJQ5nfgI_gF_HL2EfjpUKkJC4Wd4ZrbU7MzvrmfkG4JULsReDdVbkDmdUepVSJpdZxZ0gTo2ojXVrXyZ8OhVnZ_JkB15vamESPkT_wy1oRrTXQcHtwrgtLde2CV0beHENdmloIjOA3aNP49PJVooHSdVFFGeMjmiHLBQyeXrmq-fRb07mVZ81HjrjW__3ubfhZudsojdJOu7Ajq3vwt6HLpx-D35spQyhqjbIi908NVlCjUMVMtYufn773rWWmKHqYtYs5-35JfK-LvK-o6doYzJXZKhtn9mKvJ3ynLFUxhp0WaW3xs4iznXkCKUtKKBmr5fIn69mvUKL86ZNINqr-3A6Pv58-Dbr2jVkmghRZFyEGKVhYqQ4Czchv9HCEW5yITlWzJDCaMkKp4h0kuVGKexNRu68jTHKWfIABnVT20eAtHGcWSFd5Qqqhai0o0oIqbiSuTFuCAebTSt1h2UeWmpclJs7jV_tMq72EF72pIsE4PEnov3NzpedDq9KTAiRxNs8NoQX_bDXvhBSqfyKrj0NpoTKHOPREB4mielnIQG4gzM_chAF4-_Tl4fHH-PD438nfQ57J0fjcvJu-v4J3PBunEwVkvswaJdr-xSu66_tfLV81inFL-5UE28 |
| 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=Development+and+validation+of+a+deep-learning+algorithm+for+the+detection+of+neovascular+age-related+macular+degeneration+from+colour+fundus+photographs&rft.jtitle=Clinical+%26+experimental+ophthalmology&rft.au=Keel%2C+Stuart&rft.au=Li%2C+Zhixi&rft.au=Scheetz%2C+Jane&rft.au=Robman%2C+Liubov&rft.date=2019-11-01&rft.issn=1442-9071&rft.eissn=1442-9071&rft.volume=47&rft.issue=8&rft.spage=1009&rft_id=info:doi/10.1111%2Fceo.13575&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1442-6404&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1442-6404&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1442-6404&client=summon |