Multidisease Deep Learning Neural Network for the Diagnosis of Corneal Diseases
To report a multidisease deep learning diagnostic network (MDDN) of common corneal diseases: dry eye syndrome (DES), Fuchs endothelial dystrophy (FED), and keratoconus (KCN) using anterior segment optical coherence tomography (AS-OCT) images. Development of a deep learning neural network diagnosis a...
Saved in:
| Published in | American journal of ophthalmology Vol. 226; pp. 252 - 261 |
|---|---|
| Main Authors | , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Elsevier Inc
01.06.2021
Elsevier Limited |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | To report a multidisease deep learning diagnostic network (MDDN) of common corneal diseases: dry eye syndrome (DES), Fuchs endothelial dystrophy (FED), and keratoconus (KCN) using anterior segment optical coherence tomography (AS-OCT) images.
Development of a deep learning neural network diagnosis algorithm.
A total of 158,220 AS-OCT images from 879 eyes of 478 subjects were used to develop and validate a classification deep network. After a quality check, the network was trained and validated using 134,460 images. We tested the network using a test set of consecutive patients involving 23,760 AS-OCT images of 132 eyes of 69 patients. The area under receiver operating characteristic curve (AUROC), area under precision-recall curve (AUPRC), and F1 score and 95% confidence intervals (CIs) were computed.
The MDDN achieved eye-level AUROCs >0.99 (95% CI: 0.90, 1.0), AUPRCs > 0.96 (95% CI: 0.90, 1.0), and F1 scores > 0.90 (95% CI: 0.81, 1.0) for DES, FED, and KCN, respectively.
MDDN is a novel diagnostic tool for corneal diseases that can be used to automatically diagnose KCN, FED, and DES using only AS-OCT images. |
|---|---|
| AbstractList | PurposeTo report a multidisease deep learning diagnostic network (MDDN) of common corneal diseases: dry eye syndrome (DES), Fuchs endothelial dystrophy (FED), and keratoconus (KCN) using anterior segment optical coherence tomography (AS-OCT) images.Study DesignDevelopment of a deep learning neural network diagnosis algorithm.MethodsA total of 158,220 AS-OCT images from 879 eyes of 478 subjects were used to develop and validate a classification deep network. After a quality check, the network was trained and validated using 134,460 images. We tested the network using a test set of consecutive patients involving 23,760 AS-OCT images of 132 eyes of 69 patients. The area under receiver operating characteristic curve (AUROC), area under precision-recall curve (AUPRC), and F1 score and 95% confidence intervals (CIs) were computed.ResultsThe MDDN achieved eye-level AUROCs >0.99 (95% CI: 0.90, 1.0), AUPRCs > 0.96 (95% CI: 0.90, 1.0), and F1 scores > 0.90 (95% CI: 0.81, 1.0) for DES, FED, and KCN, respectively.ConclusionsMDDN is a novel diagnostic tool for corneal diseases that can be used to automatically diagnose KCN, FED, and DES using only AS-OCT images. To report a multidisease deep learning diagnostic network (MDDN) of common corneal diseases: dry eye syndrome (DES), Fuchs endothelial dystrophy (FED), and keratoconus (KCN) using anterior segment optical coherence tomography (AS-OCT) images. Development of a deep learning neural network diagnosis algorithm. A total of 158,220 AS-OCT images from 879 eyes of 478 subjects were used to develop and validate a classification deep network. After a quality check, the network was trained and validated using 134,460 images. We tested the network using a test set of consecutive patients involving 23,760 AS-OCT images of 132 eyes of 69 patients. The area under receiver operating characteristic curve (AUROC), area under precision-recall curve (AUPRC), and F1 score and 95% confidence intervals (CIs) were computed. The MDDN achieved eye-level AUROCs >0.99 (95% CI: 0.90, 1.0), AUPRCs > 0.96 (95% CI: 0.90, 1.0), and F1 scores > 0.90 (95% CI: 0.81, 1.0) for DES, FED, and KCN, respectively. MDDN is a novel diagnostic tool for corneal diseases that can be used to automatically diagnose KCN, FED, and DES using only AS-OCT images. To report a multidisease deep learning diagnostic network (MDDN) of common corneal diseases: dry eye syndrome (DES), Fuchs endothelial dystrophy (FED), and keratoconus (KCN) using anterior segment optical coherence tomography (AS-OCT) images.PURPOSETo report a multidisease deep learning diagnostic network (MDDN) of common corneal diseases: dry eye syndrome (DES), Fuchs endothelial dystrophy (FED), and keratoconus (KCN) using anterior segment optical coherence tomography (AS-OCT) images.Development of a deep learning neural network diagnosis algorithm.STUDY DESIGNDevelopment of a deep learning neural network diagnosis algorithm.A total of 158,220 AS-OCT images from 879 eyes of 478 subjects were used to develop and validate a classification deep network. After a quality check, the network was trained and validated using 134,460 images. We tested the network using a test set of consecutive patients involving 23,760 AS-OCT images of 132 eyes of 69 patients. The area under receiver operating characteristic curve (AUROC), area under precision-recall curve (AUPRC), and F1 score and 95% confidence intervals (CIs) were computed.METHODSA total of 158,220 AS-OCT images from 879 eyes of 478 subjects were used to develop and validate a classification deep network. After a quality check, the network was trained and validated using 134,460 images. We tested the network using a test set of consecutive patients involving 23,760 AS-OCT images of 132 eyes of 69 patients. The area under receiver operating characteristic curve (AUROC), area under precision-recall curve (AUPRC), and F1 score and 95% confidence intervals (CIs) were computed.The MDDN achieved eye-level AUROCs >0.99 (95% CI: 0.90, 1.0), AUPRCs > 0.96 (95% CI: 0.90, 1.0), and F1 scores > 0.90 (95% CI: 0.81, 1.0) for DES, FED, and KCN, respectively.RESULTSThe MDDN achieved eye-level AUROCs >0.99 (95% CI: 0.90, 1.0), AUPRCs > 0.96 (95% CI: 0.90, 1.0), and F1 scores > 0.90 (95% CI: 0.81, 1.0) for DES, FED, and KCN, respectively.MDDN is a novel diagnostic tool for corneal diseases that can be used to automatically diagnose KCN, FED, and DES using only AS-OCT images.CONCLUSIONSMDDN is a novel diagnostic tool for corneal diseases that can be used to automatically diagnose KCN, FED, and DES using only AS-OCT images. |
| Author | Elsawy, Amr Feuer, William Abdel-Mottaleb, Mohamed Abou Shousha, Mohamed Eleiwa, Taher Chase, Collin Ozcan, Eyup Tolba, Mohamed |
| Author_xml | – sequence: 1 givenname: Amr surname: Elsawy fullname: Elsawy, Amr organization: Bascom Palmer Eye institute, Miller School of Medicine, University of Miami, Miami – sequence: 2 givenname: Taher orcidid: 0000-0003-3107-2106 surname: Eleiwa fullname: Eleiwa, Taher organization: Bascom Palmer Eye institute, Miller School of Medicine, University of Miami, Miami – sequence: 3 givenname: Collin orcidid: 0000-0002-8839-3245 surname: Chase fullname: Chase, Collin organization: Bascom Palmer Eye institute, Miller School of Medicine, University of Miami, Miami – sequence: 4 givenname: Eyup surname: Ozcan fullname: Ozcan, Eyup organization: Bascom Palmer Eye institute, Miller School of Medicine, University of Miami, Miami – sequence: 5 givenname: Mohamed surname: Tolba fullname: Tolba, Mohamed organization: Bascom Palmer Eye institute, Miller School of Medicine, University of Miami, Miami – sequence: 6 givenname: William surname: Feuer fullname: Feuer, William organization: Bascom Palmer Eye institute, Miller School of Medicine, University of Miami, Miami – sequence: 7 givenname: Mohamed surname: Abdel-Mottaleb fullname: Abdel-Mottaleb, Mohamed organization: Electrical and Computer Engineering, University of Miami, Coral Gables – sequence: 8 givenname: Mohamed surname: Abou Shousha fullname: Abou Shousha, Mohamed email: Mshousha@med.miami.edu, m.aboushousha@med.miami.edu, mshoushamd@gmail.com organization: Bascom Palmer Eye institute, Miller School of Medicine, University of Miami, Miami |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33529589$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkU1rGzEQhkVJaZy0P6CXstBLL-tK2pVWoqfi9CPgJJf2LGRplGqzllxJm5J_XxmnPfiQwMAw8DzDMO8ZOgkxAEJvCV4STPjHcanHuKSYkiXel3iBFkQMsiVCkhO0wBjTVnayP0VnOY915EM_vEKnXceoZEIu0M3VPBVvfQadobkA2DVr0Cn4cNtcw5z0VFv5E9Nd42Jqyq8KeX0bYva5ia5ZxRSgQheHDfk1eun0lOHNYz9HP79--bH63q5vvl2uPq9b08uhtBvOCNkQw7lmApjurAAhDOXCMcspEY5qQ52UTltrwTjCmOh7oLgDTEF25-jDYe8uxd8z5KK2PhuYJh0gzlnRXnDSs46Qir4_Qsc4p1CvU5QxzAlnXV-pd4_UvNmCVbvktzo9qH-vqgA5ACbFnBO4_wjBah-HGlWNQ-3jUHhfojrDkWN80cXHUJL205Pmp4MJ9Yn3HpLKxkMwYH0CU5SN_klbHtlm8sEbPd3BwzPuX9mkteg |
| CitedBy_id | crossref_primary_10_3390_diagnostics12123167 crossref_primary_10_3389_fopht_2024_1380701 crossref_primary_10_1097_ICO_0000000000003626 crossref_primary_10_1136_bmjopen_2023_077859 crossref_primary_10_1097_ICO_0000000000003467 crossref_primary_10_1109_TBME_2021_3082152 crossref_primary_10_1097_ICO_0000000000003343 crossref_primary_10_3389_fmed_2023_1309097 crossref_primary_10_1002_14651858_CD014911_pub2 crossref_primary_10_1016_j_jfo_2024_104242 crossref_primary_10_1167_tvst_12_5_14 crossref_primary_10_1186_s40662_024_00376_3 crossref_primary_10_3389_fmed_2021_724902 crossref_primary_10_1007_s40778_023_00229_0 crossref_primary_10_3390_diagnostics13203165 crossref_primary_10_2147_OPTH_S321764 crossref_primary_10_3390_diagnostics14232696 crossref_primary_10_3390_jcm11092528 crossref_primary_10_1016_j_clae_2024_102284 crossref_primary_10_1016_j_jtos_2021_11_004 crossref_primary_10_1038_s41597_024_03464_0 crossref_primary_10_1097_ICU_0000000000000885 crossref_primary_10_1167_tvst_14_3_17 crossref_primary_10_1038_s41598_024_71480_6 crossref_primary_10_1007_s00417_023_06154_6 crossref_primary_10_1016_j_ajo_2023_04_008 crossref_primary_10_1016_j_compbiomed_2022_105471 crossref_primary_10_1038_s41598_024_75518_7 crossref_primary_10_3390_bioengineering11101005 |
| Cites_doi | 10.1016/j.survophthal.2018.09.002 10.1038/nature14539 10.1016/j.jtos.2015.11.002 10.1016/j.ophtha.2013.05.027 10.1016/S0161-6420(94)31313-3 10.1371/journal.pone.0205998 10.1167/iovs.14-14346 10.1136/bmjopen-2019-031313 10.1016/j.jcrs.2015.09.020 10.3109/08820538.2013.825283 10.1111/aos.13613 10.1001/jamaophthalmol.2015.4776 10.1007/978-3-319-10590-1_53 10.1038/s41433-019-0592-y 10.1016/j.ajo.2017.02.026 10.1097/ICO.0000000000001776 10.1364/BOE.9.001545 10.1145/3065386 10.1016/j.ophtha.2016.05.029 10.1371/journal.pone.0207891 10.1001/jama.2016.17216 10.1016/j.psym.2016.02.013 10.1016/j.ajo.2017.09.027 10.1016/j.ophtha.2020.01.021 10.1097/ICO.0000000000001194 10.1136/bjophthalmol-2011-300539 10.1097/ICL.0000000000000469 10.1016/0002-9394(86)90817-2 10.1016/j.ophtha.2017.02.008 10.1371/journal.pone.0037711 10.1097/TP.0000000000001281 10.1136/bjophthalmol-2018-313173 10.1001/jamaophthalmol.2017.3782 10.1201/9781003522560-16 10.1016/j.ophtha.2018.11.015 10.1016/j.preteyeres.2019.04.003 10.1167/iovs.16-19963 10.1016/j.transproceed.2004.04.093 10.1016/j.jtos.2017.05.003 |
| ContentType | Journal Article |
| Copyright | 2021 Copyright © 2021. Published by Elsevier Inc. Copyright Elsevier Limited Jun 2021 |
| Copyright_xml | – notice: 2021 – notice: Copyright © 2021. Published by Elsevier Inc. – notice: Copyright Elsevier Limited Jun 2021 |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM K9. NAPCQ 7X8 |
| DOI | 10.1016/j.ajo.2021.01.018 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed ProQuest Health & Medical Complete (Alumni) Nursing & Allied Health Premium MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) ProQuest Health & Medical Complete (Alumni) Nursing & Allied Health Premium MEDLINE - Academic |
| DatabaseTitleList | ProQuest Health & Medical Complete (Alumni) MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 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: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine Public Health |
| EISSN | 1879-1891 |
| EndPage | 261 |
| ExternalDocumentID | 33529589 10_1016_j_ajo_2021_01_018 S0002939421000398 |
| Genre | Validation Study Research Support, Non-U.S. Gov't Journal Article Research Support, N.I.H., Extramural |
| GeographicLocations | United States--US |
| GeographicLocations_xml | – name: United States--US |
| GrantInformation_xml | – fundername: NEI NIH HHS grantid: K23 EY026118 |
| GroupedDBID | --- --K --M -~X .1- .55 .FO .GJ .~1 0R~ 1B1 1CY 1P~ 1~. 1~5 23M 4.4 457 4G. 53G 5GY 5RE 5VS 6J9 7-5 71M 8P~ AABNK AAEDT AAEDW AAHTB AAIKJ AAKOC AALRI AAOAW AAQFI AAQQT AAQXK AATTM AAWTL AAXKI AAXUO AAYWO ABBQC ABCQX ABDPE ABFNM ABFRF ABJNI ABLJU ABMAC ABMZM ABOCM ABPEJ ABWVN ABXDB ACDAQ ACGFO ACGFS ACIEU ACIUM ACNCT ACRLP ACRPL ACVFH ADBBV ADCNI ADEZE ADFRT ADMUD ADNMO AEBSH AEFWE AEIPS AEKER AENEX AEUPX AEVXI AFFNX AFJKZ AFPUW AFRHN AFTJW AFXIZ AGCQF AGHFR AGQPQ AGUBO AGYEJ AHMBA AI. AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX APXCP ASPBG AVWKF AXJTR AZFZN BKEYQ BKOJK BLXMC BNPGV BPHCQ BVXVI CS3 EBS EFJIC EFKBS EJD EMOBN EO8 EO9 EP2 EP3 EX3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA HVGLF HZ~ IHE J1W J5H K-O KOM L7B M41 MO0 N4W N9A O-L O9- OAUVE OF- OPF OQ~ OZT P-8 P-9 P2P PC. PQQKQ PROAC Q38 R2- ROL RPZ SCC SDF SDG SDP SEL SES SPCBC SSH SSZ SV3 T5K UNMZH UV1 VH1 WH7 WOW X7M XPP Z5R ZGI ZXP ~G- 3V. 7RV 7X7 8FI AACTN AAIAV ABLVK ABYKQ AFCTW AFKRA AFKWA AHPSJ AJBFU AJOXV AMFUW AZQEC BENPR EFLBG FYUFA G8K GUQSH LCYCR M1P M2O RIG ZA5 AAYXX AGRNS CITATION CGR CUY CVF ECM EIF NPM PKN K9. NAPCQ 7X8 |
| ID | FETCH-LOGICAL-c497t-b6511b1c66a58e5a3d8e88c268f5d6218f2ac2f99fadddecf155844e203e02e93 |
| IEDL.DBID | .~1 |
| ISSN | 0002-9394 1879-1891 |
| IngestDate | Tue Aug 05 09:33:32 EDT 2025 Sat Jul 26 02:09:34 EDT 2025 Wed Feb 19 02:25:09 EST 2025 Thu Apr 24 23:11:07 EDT 2025 Tue Jul 01 03:25:37 EDT 2025 Fri Feb 23 02:44:46 EST 2024 Tue Aug 26 16:33:43 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | Copyright © 2021. Published by Elsevier Inc. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c497t-b6511b1c66a58e5a3d8e88c268f5d6218f2ac2f99fadddecf155844e203e02e93 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 ObjectType-Undefined-3 |
| ORCID | 0000-0002-8839-3245 0000-0003-3107-2106 |
| PMID | 33529589 |
| PQID | 2550616534 |
| PQPubID | 41749 |
| PageCount | 10 |
| ParticipantIDs | proquest_miscellaneous_2486145311 proquest_journals_2550616534 pubmed_primary_33529589 crossref_primary_10_1016_j_ajo_2021_01_018 crossref_citationtrail_10_1016_j_ajo_2021_01_018 elsevier_sciencedirect_doi_10_1016_j_ajo_2021_01_018 elsevier_clinicalkey_doi_10_1016_j_ajo_2021_01_018 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | June 2021 2021-06-00 20210601 |
| PublicationDateYYYYMMDD | 2021-06-01 |
| PublicationDate_xml | – month: 06 year: 2021 text: June 2021 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: Chicago |
| PublicationTitle | American journal of ophthalmology |
| PublicationTitleAlternate | Am J Ophthalmol |
| PublicationYear | 2021 |
| Publisher | Elsevier Inc Elsevier Limited |
| Publisher_xml | – name: Elsevier Inc – name: Elsevier Limited |
| References | Ting, Peng, Varadarajan (bib0038) 2019; 72 Asaoka, Murata, Iwase, Araie (bib0034) 2016; 123 Fujimoto, Swanson (bib0031) 2016; 57 Abou Shousha, Yoo, Sayed (bib0025) 2017; 178 Kamiya, Ayatsuka, Kato (bib0022) 2019; 9 Huang D. Future direction of anterior segment optical coherence tomography. 2008:165-172. Krizhevsky, Sutskever, Hinton (bib0026) 2017; 60 Nanda, Alone (bib0029) 2019; 25 Gulshan, Peng, Coram (bib0036) 2016; 316 Yousefi, Yousefi, Takahashi (bib0039) 2018; 13 Windsor, Sun, Frick, Swanson, Rosenfeld, Huang (bib0042) 2018; 185 Hamill, Schmedt, Jurkunas (bib0008) 2013; 28 Stapleton, Alves, Bunya (bib0005) 2017; 15 Kennedy, Bourne, Dyer (bib0010) 1986; 101 Peng, Dharssi, Chen (bib0035) 2019; 126 Venhuizen, van Ginneken, Liefers (bib0037) 2018; 9 Burlina, Joshi, Pekala, Pacheco, Freund, Bressler (bib0032) 2017; 135 Tuft, Moodaley, Gregory, Davison, Buckley (bib0030) 1994; 101 Abuksis, Orenstein, Hershko (bib0001) 2004; 36 Sandali, El Sanharawi, Temstet (bib0012) 2013; 120 McDonald, Patel, Keith, Snedecor (bib0028) 2016; 14 Treder, Lauermann, Alnawaiseh, Eter (bib0020) 2019; 38 Swanson, Huang (bib0041) 2011; 8 LeCun, Bengio, Hinton (bib0016) 2015; 521 Ruiz Hidalgo, Rozema, Saad (bib0023) 2017; 36 Iovino, Fossarello, Giannaccare (bib0014) 2018; 13 Ting, Pasquale, Peng (bib0017) 2019; 103 Gain, Jullienne, He (bib0006) 2016; 134 Kapoor, Whigham, Al-Aswad (bib0018) 2019; 8 Matthaei, Sandhaeger, Hermel (bib0009) 2017; 101 Gargeya, Leng (bib0033) 2017; 124 Drzyzga, Krupka-Matuszczyk, Drzyzga, Mrukwa-Kominek, Kucia (bib0011) 2016; 57 Zeiler M., Fergus R. Visualizing and understanding convolutional networks. arXiv, 2013. Abou Shousha, Wang, Kontadakis (bib0013) 2020; 34 Xu, Dupps, Srivastava, Ehlers (bib0040) 2014; 55 van der Heijden, Abramoff, Verbraak, van Hecke, Liem, Nijpels (bib0019) 2018; 96 Kovacs, Mihaltz, Kranitz (bib0021) 2016; 42 Pascolini, Mariotti (bib0003) 2012; 96 Sarnicola, Farooq, Colby (bib0007) 2019; 45 Kapoor, Walters, Al-Aswad (bib0015) 2019; 64 McColgan (bib0002) 2009; 19 Waduthantri, Yong, Tan (bib0004) 2012; 7 Eleiwa, Elsawy, Tolba, Feuer, Yoo, Shousha (bib0043) 2020; 127 Burlina (10.1016/j.ajo.2021.01.018_bib0032) 2017; 135 McColgan (10.1016/j.ajo.2021.01.018_bib0002) 2009; 19 Pascolini (10.1016/j.ajo.2021.01.018_bib0003) 2012; 96 McDonald (10.1016/j.ajo.2021.01.018_bib0028) 2016; 14 Ting (10.1016/j.ajo.2021.01.018_bib0017) 2019; 103 Nanda (10.1016/j.ajo.2021.01.018_bib0029) 2019; 25 Kamiya (10.1016/j.ajo.2021.01.018_bib0022) 2019; 9 Venhuizen (10.1016/j.ajo.2021.01.018_bib0037) 2018; 9 Yousefi (10.1016/j.ajo.2021.01.018_bib0039) 2018; 13 Abou Shousha (10.1016/j.ajo.2021.01.018_bib0025) 2017; 178 Kapoor (10.1016/j.ajo.2021.01.018_bib0018) 2019; 8 Ruiz Hidalgo (10.1016/j.ajo.2021.01.018_bib0023) 2017; 36 Kovacs (10.1016/j.ajo.2021.01.018_bib0021) 2016; 42 Swanson (10.1016/j.ajo.2021.01.018_bib0041) 2011; 8 Sandali (10.1016/j.ajo.2021.01.018_bib0012) 2013; 120 LeCun (10.1016/j.ajo.2021.01.018_bib0016) 2015; 521 Matthaei (10.1016/j.ajo.2021.01.018_bib0009) 2017; 101 Iovino (10.1016/j.ajo.2021.01.018_bib0014) 2018; 13 10.1016/j.ajo.2021.01.018_bib0027 Gulshan (10.1016/j.ajo.2021.01.018_bib0036) 2016; 316 Hamill (10.1016/j.ajo.2021.01.018_bib0008) 2013; 28 10.1016/j.ajo.2021.01.018_bib0024 Kapoor (10.1016/j.ajo.2021.01.018_bib0015) 2019; 64 Abuksis (10.1016/j.ajo.2021.01.018_bib0001) 2004; 36 Abou Shousha (10.1016/j.ajo.2021.01.018_bib0013) 2020; 34 Asaoka (10.1016/j.ajo.2021.01.018_bib0034) 2016; 123 Stapleton (10.1016/j.ajo.2021.01.018_bib0005) 2017; 15 Kennedy (10.1016/j.ajo.2021.01.018_bib0010) 1986; 101 Drzyzga (10.1016/j.ajo.2021.01.018_bib0011) 2016; 57 Ting (10.1016/j.ajo.2021.01.018_bib0038) 2019; 72 Sarnicola (10.1016/j.ajo.2021.01.018_bib0007) 2019; 45 Eleiwa (10.1016/j.ajo.2021.01.018_bib0043) 2020; 127 Gargeya (10.1016/j.ajo.2021.01.018_bib0033) 2017; 124 Krizhevsky (10.1016/j.ajo.2021.01.018_bib0026) 2017; 60 Treder (10.1016/j.ajo.2021.01.018_bib0020) 2019; 38 Waduthantri (10.1016/j.ajo.2021.01.018_bib0004) 2012; 7 Fujimoto (10.1016/j.ajo.2021.01.018_bib0031) 2016; 57 Peng (10.1016/j.ajo.2021.01.018_bib0035) 2019; 126 Tuft (10.1016/j.ajo.2021.01.018_bib0030) 1994; 101 Gain (10.1016/j.ajo.2021.01.018_bib0006) 2016; 134 Windsor (10.1016/j.ajo.2021.01.018_bib0042) 2018; 185 van der Heijden (10.1016/j.ajo.2021.01.018_bib0019) 2018; 96 Xu (10.1016/j.ajo.2021.01.018_bib0040) 2014; 55 |
| References_xml | – volume: 45 start-page: 1 year: 2019 end-page: 10 ident: bib0007 article-title: Fuchs endothelial corneal dystrophy: update on pathogenesis and future directions publication-title: Eye Contact Lens – volume: 28 start-page: 281 year: 2013 end-page: 286 ident: bib0008 article-title: Fuchs endothelial cornea dystrophy: a review of the genetics behind disease development publication-title: Semin Ophthalmol – volume: 13 year: 2018 ident: bib0014 article-title: Corneal endothelium features in Fuchs' endothelial corneal dystrophy: a preliminary 3D anterior segment optical coherence tomography study publication-title: PLoS One – reference: Huang D. Future direction of anterior segment optical coherence tomography. 2008:165-172. – volume: 8 start-page: 187 year: 2019 end-page: 194 ident: bib0018 article-title: Artificial intelligence and optical coherence tomography imaging publication-title: Asia Pac J Ophthalmol (Phila) – volume: 36 start-page: 1249 year: 2004 end-page: 1252 ident: bib0001 article-title: Cornea recipients: are their opinions and attitudes toward organ donation different from those of the general population? publication-title: Transplant Proc – volume: 120 start-page: 2403 year: 2013 end-page: 2412 ident: bib0012 article-title: Fourier-domain optical coherence tomography imaging in keratoconus: a corneal structural classification publication-title: Ophthalmology – volume: 135 start-page: 1170 year: 2017 end-page: 1176 ident: bib0032 article-title: Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks publication-title: JAMA Ophthalmol – volume: 13 year: 2018 ident: bib0039 article-title: Keratoconus severity identification using unsupervised machine learning publication-title: PLoS One – volume: 101 start-page: 267 year: 1986 end-page: 273 ident: bib0010 article-title: A 48-year clinical and epidemiologic study of keratoconus publication-title: Am J Ophthalmol – volume: 34 start-page: 915 year: 2020 end-page: 922 ident: bib0013 article-title: Corneal epithelial thickness profile in dry-eye disease publication-title: Eye (Lond) – volume: 60 start-page: 84 year: 2017 end-page: 90 ident: bib0026 article-title: ImageNet classification with deep convolutional neural networks publication-title: Commun ACM – volume: 9 start-page: 1545 year: 2018 end-page: 1569 ident: bib0037 article-title: Deep learning approach for the detection and quantification of intraretinal cystoid fluid in multivendor optical coherence tomography publication-title: Biomed Opt Express – volume: 72 year: 2019 ident: bib0038 article-title: Deep learning in ophthalmology: the technical and clinical considerations publication-title: Prog Retin Eye Res – volume: 57 start-page: 414 year: 2016 end-page: 422 ident: bib0011 article-title: Quality of life and mental state after sight restoration by corneal transplantation publication-title: Psychosomatics – volume: 178 start-page: 27 year: 2017 end-page: 37 ident: bib0025 article-title: In vivo characteristics of corneal endothelium/Descemet membrane complex for the diagnosis of corneal graft rejection publication-title: Am J Ophthalmol – volume: 101 start-page: 1387 year: 2017 end-page: 1399 ident: bib0009 article-title: Changing indications in penetrating keratoplasty: a systematic review of 34 years of global reporting publication-title: Transplantation – volume: 19 start-page: 51 year: 2009 end-page: 54 ident: bib0002 article-title: Corneal transplant surgery publication-title: J Perioper Pract – volume: 64 start-page: 233 year: 2019 end-page: 240 ident: bib0015 article-title: The current state of artificial intelligence in ophthalmology publication-title: Surv Ophthalmol – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: bib0016 article-title: Deep learning publication-title: Nature – volume: 57 start-page: OCT1 year: 2016 end-page: OCT13 ident: bib0031 article-title: The development, commercialization, and impact of optical coherence tomography publication-title: Invest Ophthalmol Vis Sci – volume: 103 start-page: 167 year: 2019 end-page: 175 ident: bib0017 article-title: Artificial intelligence and deep learning in ophthalmology publication-title: Br J Ophthalmol – volume: 14 start-page: 144 year: 2016 end-page: 167 ident: bib0028 article-title: Economic and humanistic burden of dry eye disease in Europe, North America, and Asia: a systematic literature review publication-title: Ocular Surface – volume: 101 start-page: 439 year: 1994 end-page: 447 ident: bib0030 article-title: Prognostic factors for the progression of keratoconus publication-title: Ophthalmology – volume: 124 start-page: 962 year: 2017 end-page: 969 ident: bib0033 article-title: Automated identification of diabetic retinopathy using deep learning publication-title: Ophthalmology – volume: 9 year: 2019 ident: bib0022 article-title: Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study publication-title: BMJ Open – volume: 126 start-page: 565 year: 2019 end-page: 575 ident: bib0035 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: 8 year: 2011 ident: bib0041 article-title: Ophthalmic OCT reaches $1 billion per year publication-title: Retinal Physician – volume: 96 start-page: 614 year: 2012 end-page: 618 ident: bib0003 article-title: Global estimates of visual impairment: 2010 publication-title: Br J Ophthalmol – volume: 42 start-page: 275 year: 2016 end-page: 283 ident: bib0021 article-title: Accuracy of machine learning classifiers using bilateral data from a Scheimpflug camera for identifying eyes with preclinical signs of keratoconus publication-title: J Cataract Refract Surg – volume: 7 start-page: e37711 year: 2012 ident: bib0004 article-title: Cost of dry eye treatment in an Asian clinic setting publication-title: PLoS One – volume: 38 start-page: 157 year: 2019 end-page: 161 ident: bib0020 article-title: Using deep learning in automated detection of graft detachment in Descemet membrane endothelial keratoplasty: a pilot study publication-title: Cornea – volume: 36 start-page: 689 year: 2017 end-page: 695 ident: bib0023 article-title: Validation of an objective keratoconus detection system implemented in a Scheimpflug tomographer and comparison with other methods publication-title: Cornea – volume: 127 start-page: 874 year: 2020 end-page: 887 ident: bib0043 article-title: Diagnostic performance of 3-dimensional thickness of the endothelium-Descemet complex in Fuchs' endothelial cell corneal dystrophy publication-title: Ophthalmology – volume: 134 start-page: 167 year: 2016 end-page: 173 ident: bib0006 article-title: Global survey of corneal transplantation and eye banking publication-title: JAMA Ophthalmol – volume: 15 start-page: 334 year: 2017 end-page: 365 ident: bib0005 article-title: TFOS DEWS II epidemiology report publication-title: Ocul Surf – volume: 316 start-page: 2402 year: 2016 end-page: 2410 ident: bib0036 article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs publication-title: JAMA – reference: Zeiler M., Fergus R. Visualizing and understanding convolutional networks. arXiv, 2013. – volume: 25 start-page: 295 year: 2019 end-page: 310 ident: bib0029 article-title: REVIEW: current understanding of the pathogenesis of Fuchs' endothelial corneal dystrophy publication-title: Mol Vis – volume: 185 start-page: 115 year: 2018 end-page: 122 ident: bib0042 article-title: Estimating public and patient savings from basic research—a study of optical coherence tomography in managing antiangiogenic therapy publication-title: Am J Ophthalmol – volume: 55 start-page: 5610 year: 2014 end-page: 5615 ident: bib0040 article-title: Automated volumetric analysis of interface fluid in Descemet stripping automated endothelial keratoplasty using intraoperative optical coherence tomography publication-title: Invest Ophthalmol Vis Sci – volume: 96 start-page: 63 year: 2018 end-page: 68 ident: bib0019 article-title: Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System publication-title: Acta Ophthalmol – volume: 123 start-page: 1974 year: 2016 end-page: 1980 ident: bib0034 article-title: Detecting preperimetric glaucoma with standard automated perimetry using a deep learning classifier publication-title: Ophthalmology – volume: 64 start-page: 233 year: 2019 ident: 10.1016/j.ajo.2021.01.018_bib0015 article-title: The current state of artificial intelligence in ophthalmology publication-title: Surv Ophthalmol doi: 10.1016/j.survophthal.2018.09.002 – volume: 521 start-page: 436 year: 2015 ident: 10.1016/j.ajo.2021.01.018_bib0016 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 14 start-page: 144 year: 2016 ident: 10.1016/j.ajo.2021.01.018_bib0028 article-title: Economic and humanistic burden of dry eye disease in Europe, North America, and Asia: a systematic literature review publication-title: Ocular Surface doi: 10.1016/j.jtos.2015.11.002 – volume: 120 start-page: 2403 year: 2013 ident: 10.1016/j.ajo.2021.01.018_bib0012 article-title: Fourier-domain optical coherence tomography imaging in keratoconus: a corneal structural classification publication-title: Ophthalmology doi: 10.1016/j.ophtha.2013.05.027 – volume: 101 start-page: 439 year: 1994 ident: 10.1016/j.ajo.2021.01.018_bib0030 article-title: Prognostic factors for the progression of keratoconus publication-title: Ophthalmology doi: 10.1016/S0161-6420(94)31313-3 – volume: 8 start-page: 187 year: 2019 ident: 10.1016/j.ajo.2021.01.018_bib0018 article-title: Artificial intelligence and optical coherence tomography imaging publication-title: Asia Pac J Ophthalmol (Phila) – volume: 13 year: 2018 ident: 10.1016/j.ajo.2021.01.018_bib0039 article-title: Keratoconus severity identification using unsupervised machine learning publication-title: PLoS One doi: 10.1371/journal.pone.0205998 – volume: 55 start-page: 5610 year: 2014 ident: 10.1016/j.ajo.2021.01.018_bib0040 article-title: Automated volumetric analysis of interface fluid in Descemet stripping automated endothelial keratoplasty using intraoperative optical coherence tomography publication-title: Invest Ophthalmol Vis Sci doi: 10.1167/iovs.14-14346 – volume: 9 year: 2019 ident: 10.1016/j.ajo.2021.01.018_bib0022 article-title: Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study publication-title: BMJ Open doi: 10.1136/bmjopen-2019-031313 – volume: 42 start-page: 275 year: 2016 ident: 10.1016/j.ajo.2021.01.018_bib0021 article-title: Accuracy of machine learning classifiers using bilateral data from a Scheimpflug camera for identifying eyes with preclinical signs of keratoconus publication-title: J Cataract Refract Surg doi: 10.1016/j.jcrs.2015.09.020 – volume: 28 start-page: 281 year: 2013 ident: 10.1016/j.ajo.2021.01.018_bib0008 article-title: Fuchs endothelial cornea dystrophy: a review of the genetics behind disease development publication-title: Semin Ophthalmol doi: 10.3109/08820538.2013.825283 – volume: 96 start-page: 63 year: 2018 ident: 10.1016/j.ajo.2021.01.018_bib0019 article-title: Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System publication-title: Acta Ophthalmol doi: 10.1111/aos.13613 – volume: 134 start-page: 167 year: 2016 ident: 10.1016/j.ajo.2021.01.018_bib0006 article-title: Global survey of corneal transplantation and eye banking publication-title: JAMA Ophthalmol doi: 10.1001/jamaophthalmol.2015.4776 – ident: 10.1016/j.ajo.2021.01.018_bib0027 doi: 10.1007/978-3-319-10590-1_53 – volume: 34 start-page: 915 year: 2020 ident: 10.1016/j.ajo.2021.01.018_bib0013 article-title: Corneal epithelial thickness profile in dry-eye disease publication-title: Eye (Lond) doi: 10.1038/s41433-019-0592-y – volume: 178 start-page: 27 year: 2017 ident: 10.1016/j.ajo.2021.01.018_bib0025 article-title: In vivo characteristics of corneal endothelium/Descemet membrane complex for the diagnosis of corneal graft rejection publication-title: Am J Ophthalmol doi: 10.1016/j.ajo.2017.02.026 – volume: 38 start-page: 157 year: 2019 ident: 10.1016/j.ajo.2021.01.018_bib0020 article-title: Using deep learning in automated detection of graft detachment in Descemet membrane endothelial keratoplasty: a pilot study publication-title: Cornea doi: 10.1097/ICO.0000000000001776 – volume: 9 start-page: 1545 year: 2018 ident: 10.1016/j.ajo.2021.01.018_bib0037 article-title: Deep learning approach for the detection and quantification of intraretinal cystoid fluid in multivendor optical coherence tomography publication-title: Biomed Opt Express doi: 10.1364/BOE.9.001545 – volume: 60 start-page: 84 year: 2017 ident: 10.1016/j.ajo.2021.01.018_bib0026 article-title: ImageNet classification with deep convolutional neural networks publication-title: Commun ACM doi: 10.1145/3065386 – volume: 123 start-page: 1974 year: 2016 ident: 10.1016/j.ajo.2021.01.018_bib0034 article-title: Detecting preperimetric glaucoma with standard automated perimetry using a deep learning classifier publication-title: Ophthalmology doi: 10.1016/j.ophtha.2016.05.029 – volume: 13 year: 2018 ident: 10.1016/j.ajo.2021.01.018_bib0014 article-title: Corneal endothelium features in Fuchs' endothelial corneal dystrophy: a preliminary 3D anterior segment optical coherence tomography study publication-title: PLoS One doi: 10.1371/journal.pone.0207891 – volume: 316 start-page: 2402 year: 2016 ident: 10.1016/j.ajo.2021.01.018_bib0036 article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs publication-title: JAMA doi: 10.1001/jama.2016.17216 – volume: 57 start-page: 414 year: 2016 ident: 10.1016/j.ajo.2021.01.018_bib0011 article-title: Quality of life and mental state after sight restoration by corneal transplantation publication-title: Psychosomatics doi: 10.1016/j.psym.2016.02.013 – volume: 185 start-page: 115 year: 2018 ident: 10.1016/j.ajo.2021.01.018_bib0042 article-title: Estimating public and patient savings from basic research—a study of optical coherence tomography in managing antiangiogenic therapy publication-title: Am J Ophthalmol doi: 10.1016/j.ajo.2017.09.027 – volume: 127 start-page: 874 year: 2020 ident: 10.1016/j.ajo.2021.01.018_bib0043 article-title: Diagnostic performance of 3-dimensional thickness of the endothelium-Descemet complex in Fuchs' endothelial cell corneal dystrophy publication-title: Ophthalmology doi: 10.1016/j.ophtha.2020.01.021 – volume: 36 start-page: 689 year: 2017 ident: 10.1016/j.ajo.2021.01.018_bib0023 article-title: Validation of an objective keratoconus detection system implemented in a Scheimpflug tomographer and comparison with other methods publication-title: Cornea doi: 10.1097/ICO.0000000000001194 – volume: 96 start-page: 614 year: 2012 ident: 10.1016/j.ajo.2021.01.018_bib0003 article-title: Global estimates of visual impairment: 2010 publication-title: Br J Ophthalmol doi: 10.1136/bjophthalmol-2011-300539 – volume: 45 start-page: 1 year: 2019 ident: 10.1016/j.ajo.2021.01.018_bib0007 article-title: Fuchs endothelial corneal dystrophy: update on pathogenesis and future directions publication-title: Eye Contact Lens doi: 10.1097/ICL.0000000000000469 – volume: 101 start-page: 267 year: 1986 ident: 10.1016/j.ajo.2021.01.018_bib0010 article-title: A 48-year clinical and epidemiologic study of keratoconus publication-title: Am J Ophthalmol doi: 10.1016/0002-9394(86)90817-2 – volume: 124 start-page: 962 year: 2017 ident: 10.1016/j.ajo.2021.01.018_bib0033 article-title: Automated identification of diabetic retinopathy using deep learning publication-title: Ophthalmology doi: 10.1016/j.ophtha.2017.02.008 – volume: 7 start-page: e37711 year: 2012 ident: 10.1016/j.ajo.2021.01.018_bib0004 article-title: Cost of dry eye treatment in an Asian clinic setting publication-title: PLoS One doi: 10.1371/journal.pone.0037711 – volume: 19 start-page: 51 year: 2009 ident: 10.1016/j.ajo.2021.01.018_bib0002 article-title: Corneal transplant surgery publication-title: J Perioper Pract – volume: 101 start-page: 1387 year: 2017 ident: 10.1016/j.ajo.2021.01.018_bib0009 article-title: Changing indications in penetrating keratoplasty: a systematic review of 34 years of global reporting publication-title: Transplantation doi: 10.1097/TP.0000000000001281 – volume: 103 start-page: 167 year: 2019 ident: 10.1016/j.ajo.2021.01.018_bib0017 article-title: Artificial intelligence and deep learning in ophthalmology publication-title: Br J Ophthalmol doi: 10.1136/bjophthalmol-2018-313173 – volume: 135 start-page: 1170 year: 2017 ident: 10.1016/j.ajo.2021.01.018_bib0032 article-title: Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks publication-title: JAMA Ophthalmol doi: 10.1001/jamaophthalmol.2017.3782 – ident: 10.1016/j.ajo.2021.01.018_bib0024 doi: 10.1201/9781003522560-16 – volume: 126 start-page: 565 year: 2019 ident: 10.1016/j.ajo.2021.01.018_bib0035 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 doi: 10.1016/j.ophtha.2018.11.015 – volume: 25 start-page: 295 year: 2019 ident: 10.1016/j.ajo.2021.01.018_bib0029 article-title: REVIEW: current understanding of the pathogenesis of Fuchs' endothelial corneal dystrophy publication-title: Mol Vis – volume: 72 year: 2019 ident: 10.1016/j.ajo.2021.01.018_bib0038 article-title: Deep learning in ophthalmology: the technical and clinical considerations publication-title: Prog Retin Eye Res doi: 10.1016/j.preteyeres.2019.04.003 – volume: 57 start-page: OCT1 year: 2016 ident: 10.1016/j.ajo.2021.01.018_bib0031 article-title: The development, commercialization, and impact of optical coherence tomography publication-title: Invest Ophthalmol Vis Sci doi: 10.1167/iovs.16-19963 – volume: 36 start-page: 1249 year: 2004 ident: 10.1016/j.ajo.2021.01.018_bib0001 article-title: Cornea recipients: are their opinions and attitudes toward organ donation different from those of the general population? publication-title: Transplant Proc doi: 10.1016/j.transproceed.2004.04.093 – volume: 15 start-page: 334 year: 2017 ident: 10.1016/j.ajo.2021.01.018_bib0005 article-title: TFOS DEWS II epidemiology report publication-title: Ocul Surf doi: 10.1016/j.jtos.2017.05.003 – volume: 8 year: 2011 ident: 10.1016/j.ajo.2021.01.018_bib0041 article-title: Ophthalmic OCT reaches $1 billion per year publication-title: Retinal Physician |
| SSID | ssj0006747 |
| Score | 2.4893844 |
| Snippet | To report a multidisease deep learning diagnostic network (MDDN) of common corneal diseases: dry eye syndrome (DES), Fuchs endothelial dystrophy (FED), and... PurposeTo report a multidisease deep learning diagnostic network (MDDN) of common corneal diseases: dry eye syndrome (DES), Fuchs endothelial dystrophy (FED),... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 252 |
| SubjectTerms | Algorithms Area Under Curve Artificial intelligence Automation Classification Cornea Corneal Diseases - diagnosis Deep Learning Diabetes Diabetic retinopathy Diagnosis, Computer-Assisted Disease Dry Eye Syndromes - diagnosis FDA approval Female Fuchs' Endothelial Dystrophy - diagnosis Health care Humans Keratoconus - diagnosis Male Medical diagnosis Middle Aged Neural networks Neural Networks, Computer Patients Prospective Studies Public health Quality of life ROC Curve Tomography Tomography, Optical Coherence Transplants & implants |
| Title | Multidisease Deep Learning Neural Network for the Diagnosis of Corneal Diseases |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S0002939421000398 https://dx.doi.org/10.1016/j.ajo.2021.01.018 https://www.ncbi.nlm.nih.gov/pubmed/33529589 https://www.proquest.com/docview/2550616534 https://www.proquest.com/docview/2486145311 |
| Volume | 226 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1RSxwxEB5EQXwprdb2Wisp9Kmwuptks8mjnMq1xetLBd9CNpuUE9k7vPPV3-7MbvakUBWEfdndzJKdTGa-kG8mAN8ExyDhG1ypRt1kkjueOS9FFqpQO-G84Q0tFC-manIpf16VVxswHnJhiFaZfH_v0ztvnZ4cJ20eL2YzyvHNMVYZyYsuw5QSfqWsyMqP7h9pHqqS1QCBqfWws9lxvNw15f_xoqvcSed-_D82PYU9uxh0_hbeJPDITvr-vYON0O7C9kXaHt-D3106bdpzYachLFiqn_qXURUOlJ32tG-GWJUh9mOnPdVutmTzyMbz2xaBIz7svrB8D5fnZ3_GkyydmJB5aapVVivET3XhlXKlDqUTjQ5ae650LBuF0Txy53k0JqJba4KPiCa0lIHnIuQ8GLEPm-28DR-BIVIwTSyDqzGAEyNNuMJ7HSMiEmU4H0E-6Mr6VE6cTrW4sQNv7Nqiei2p1-Z06RF8X4ss-loazzXmwwDYIUkU3ZpFT_-ckFwL_WNFL4kdDCNs0xReWlxroRmrUsgRfF2_xslHOyquDfM7bCM1aUcUxQg-9Jax_jNKZjOlNp9e16fPsEN3PSvtADZXt3fhC-KfVX3YGfghbJ38-DWZPgB0PQH- |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dT9swED9BJw1eJvYBdIPNSDxNCiS249qPU6HqNlpeQOLNchwbtUJpRcsrfzvnxClC4kNCypPti5Lz-e5n3RfAIaNoJGyJN1Uvy4RTQxNjOUtczxWGGatoGS6Ko7EYXvJ_V_nVGvTbXJgQVhl1f6PTa20dR44jN4_nk0nI8U3RVilOszrDVK7DB47HN7QxOLp_jPMQPd5rMXBY3ro26yAvMw0JgDSrS3eGxh_PG6eXwGdthAZb8CmiR_Kn-cDPsOaqL_BxFP3jX-G8zqeNThdy4tycxAKq1ySU4UDacRP3TRCsEgR_5KSJtZssyMyT_uy2QuSIg_UbFt_gcnB60R8msWVCYrnqLZNCIIAqMiuEyaXLDSulk9JSIX1eCjTnnhpLvVIe9VrprEc4ITl3NGUupU6xbehUs8rtAkGooEqfO1OgBQ8hacxk1krvEZIIRWkX0pZX2sZ64qGtxY1uA8emGtmrA3t1Gh7Zhd8rknlTTOO1xbTdAN1miaJe06jqXyPiK6InYvQW2V67wzqe4YXGyxbKscgZ78LBahpPX3CpmMrN7nANl4E7LMu6sNNIxurPQjabyqX6_r5v-gUbw4vRmT77O_7_AzbDTBOitged5e2d20cwtCx-1sL-AEm3A4w |
| 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=Multidisease+Deep+Learning+Neural+Network+for+the+Diagnosis+of+Corneal+Diseases&rft.jtitle=American+journal+of+ophthalmology&rft.au=Elsawy%2C+Amr&rft.au=Eleiwa%2C+Taher&rft.au=Chase%2C+Collin&rft.au=Ozcan%2C+Eyup&rft.date=2021-06-01&rft.eissn=1879-1891&rft.volume=226&rft.spage=252&rft_id=info:doi/10.1016%2Fj.ajo.2021.01.018&rft_id=info%3Apmid%2F33529589&rft.externalDocID=33529589 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0002-9394&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0002-9394&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0002-9394&client=summon |