57084 Combining artificial intelligence and robotics: a novel fully automated optical coherence tomography-based approach for eye disease screening

ABSTRACT IMPACT: Despite its importance in systemic diseases such as diabetes, the eye is notably difficult to examine for non-specialists; this study introduces a fully automated approach for eye disease screening, coupling a deep learning algorithm with a robotically-aligned optical coherence tomo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of clinical and translational science Jg. 5; H. s1; S. 122
Hauptverfasser: Song, Ailin, Ortiz, Pablo, Draelos, Mark, Schuman, Stefanie G., Jaffe, Glenn J., Farsiu, Sina, Izatt, Joseph A., McNabb, Ryan P., Kuo, Anthony N.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cambridge, UK Cambridge University Press 01.03.2021
Schlagworte:
ISSN:2059-8661, 2059-8661
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract ABSTRACT IMPACT: Despite its importance in systemic diseases such as diabetes, the eye is notably difficult to examine for non-specialists; this study introduces a fully automated approach for eye disease screening, coupling a deep learning algorithm with a robotically-aligned optical coherence tomography system to improve eye care in non-ophthalmology settings. OBJECTIVES/GOALS: This study aims to develop and test a deep learning (DL) method to classify images acquired from a robotically-aligned optical coherence tomography (OCT) system as normal vs. abnormal. The long-term goal of our study is to integrate artificial intelligence and robotic eye imaging to fully automate eye disease screening in diverse clinical settings. METHODS/STUDY POPULATION: Between August and October 2020, patients seen at the Duke Eye Center and healthy volunteers (age ≥18) were imaged with a custom, robotically-aligned OCT (RAOCT) system following routine eye exam. Using transfer learning, we adapted a preexisting convolutional neural network to train a DL algorithm to classify OCT images as normal vs. abnormal. The model was trained and validated on two publicly available OCT datasets and two of our own RAOCT volumes. For external testing, the top-performing model based on validation was applied to a representative averaged B-scan from each of the remaining RAOCT volumes. The model’s performance was evaluated against a reference standard of clinical diagnoses by retina specialists. Saliency maps were created to visualize the areas contributing most to the model predictions. RESULTS/ANTICIPATED RESULTS: The training and validation datasets included 87,697 OCT images, of which 59,743 were abnormal. The top-performing DL model had a training accuracy of 96% and a validation accuracy of 99%. For external testing, 43 eyes of 27 subjects were imaged with the robotically-aligned OCT system. Compared to clinical diagnoses, the model correctly labeled 18 out of 22 normal averaged B-scans and 18 out of 21 abnormal averaged B-scans. Overall, in the testing set, the model had an AUC for the detection of pathology of 0.92, an accuracy of 84%, a sensitivity of 86%, and a specificity of 82%. For the correctly predicted scans, saliency maps identified the areas contributing most to the DL algorithm’s predictions, which matched the regions of greatest clinical importance. DISCUSSION/SIGNIFICANCE OF FINDINGS: This is the first study to develop and apply a DL model to images acquired from a self-aligning OCT system, demonstrating the potential of integrating DL and robotic eye imaging to automate eye disease screening. We are working to translate this technology for use in emergency departments and primary care, where it will have the greatest impact.
AbstractList ABSTRACT IMPACT: Despite its importance in systemic diseases such as diabetes, the eye is notably difficult to examine for non-specialists; this study introduces a fully automated approach for eye disease screening, coupling a deep learning algorithm with a robotically-aligned optical coherence tomography system to improve eye care in non-ophthalmology settings. OBJECTIVES/GOALS: This study aims to develop and test a deep learning (DL) method to classify images acquired from a robotically-aligned optical coherence tomography (OCT) system as normal vs. abnormal. The long-term goal of our study is to integrate artificial intelligence and robotic eye imaging to fully automate eye disease screening in diverse clinical settings. METHODS/STUDY POPULATION: Between August and October 2020, patients seen at the Duke Eye Center and healthy volunteers (age ≥18) were imaged with a custom, robotically-aligned OCT (RAOCT) system following routine eye exam. Using transfer learning, we adapted a preexisting convolutional neural network to train a DL algorithm to classify OCT images as normal vs. abnormal. The model was trained and validated on two publicly available OCT datasets and two of our own RAOCT volumes. For external testing, the top-performing model based on validation was applied to a representative averaged B-scan from each of the remaining RAOCT volumes. The model’s performance was evaluated against a reference standard of clinical diagnoses by retina specialists. Saliency maps were created to visualize the areas contributing most to the model predictions. RESULTS/ANTICIPATED RESULTS: The training and validation datasets included 87,697 OCT images, of which 59,743 were abnormal. The top-performing DL model had a training accuracy of 96% and a validation accuracy of 99%. For external testing, 43 eyes of 27 subjects were imaged with the robotically-aligned OCT system. Compared to clinical diagnoses, the model correctly labeled 18 out of 22 normal averaged B-scans and 18 out of 21 abnormal averaged B-scans. Overall, in the testing set, the model had an AUC for the detection of pathology of 0.92, an accuracy of 84%, a sensitivity of 86%, and a specificity of 82%. For the correctly predicted scans, saliency maps identified the areas contributing most to the DL algorithm’s predictions, which matched the regions of greatest clinical importance. DISCUSSION/SIGNIFICANCE OF FINDINGS: This is the first study to develop and apply a DL model to images acquired from a self-aligning OCT system, demonstrating the potential of integrating DL and robotic eye imaging to automate eye disease screening. We are working to translate this technology for use in emergency departments and primary care, where it will have the greatest impact.
Author Song, Ailin
Kuo, Anthony N.
Farsiu, Sina
McNabb, Ryan P.
Draelos, Mark
Ortiz, Pablo
Izatt, Joseph A.
Jaffe, Glenn J.
Schuman, Stefanie G.
AuthorAffiliation 2 Duke University, Department of Biomedical Engineering
3 Duke University, Department of Ophthalmology
1 Duke University School of Medicine
AuthorAffiliation_xml – name: 3 Duke University, Department of Ophthalmology
– name: 1 Duke University School of Medicine
– name: 2 Duke University, Department of Biomedical Engineering
Author_xml – sequence: 1
  givenname: Ailin
  surname: Song
  fullname: Song, Ailin
– sequence: 2
  givenname: Pablo
  surname: Ortiz
  fullname: Ortiz, Pablo
– sequence: 3
  givenname: Mark
  surname: Draelos
  fullname: Draelos, Mark
– sequence: 4
  givenname: Stefanie G.
  surname: Schuman
  fullname: Schuman, Stefanie G.
– sequence: 5
  givenname: Glenn J.
  surname: Jaffe
  fullname: Jaffe, Glenn J.
– sequence: 6
  givenname: Sina
  surname: Farsiu
  fullname: Farsiu, Sina
– sequence: 7
  givenname: Joseph A.
  surname: Izatt
  fullname: Izatt, Joseph A.
– sequence: 8
  givenname: Ryan P.
  surname: McNabb
  fullname: McNabb, Ryan P.
– sequence: 9
  givenname: Anthony N.
  surname: Kuo
  fullname: Kuo, Anthony N.
BookMark eNpVkdFqHCEUhqWk0HSbuz6AD9DZ6jjq2ItCWZo2EMhNey1H58ysYVYHnQ3sc_SF62ZLSa4Uf_-Pw_nek6uYIhLykbMtZ1x_9mvZtqzlW83bN-S6ZdI0vVL86sX9Hbkp5ZExxvtWKSGuyR-pWd_RXTq4EEOcKOQ1jMEHmGmIK85zmDB6pBAHmpNLa_DlCwUa0xPOdDzO84nCcU0HWHGgaal5rfq0x_zcq0maMiz7U-Og1C-wLDmB39MxZYonpEMoWBNafEY8z_CBvB1hLnjz79yQ37fff-1-NvcPP-523-4bz41qm94MnIuOS8Y6Bspx1zLjBmcADEeQozTaaMF69Epp30sx9MaoQWqnO2VQbMjdhTskeLRLDgfIJ5sg2OeHlCd73oaf0UrwxgvnpRPYVRjUlaKE0TmtnBGusr5eWMvRHXDwGNcM8yvo6ySGvZ3Sk-37VpvqYkM-XQA-p1Iyjv-7nNmzYFsF27NgWwWLv5Zpnpc
ContentType Journal Article
Copyright The Association for Clinical and Translational Science 2021 2021 The Association for Clinical and Translational Science
Copyright_xml – notice: The Association for Clinical and Translational Science 2021 2021 The Association for Clinical and Translational Science
DBID AAYXX
CITATION
5PM
DOA
DOI 10.1017/cts.2021.712
DatabaseName CrossRef
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
EISSN 2059-8661
EndPage 122
ExternalDocumentID oai_doaj_org_article_5ac9c3bc5b3e467ca205e5afbb76b93b
PMC8827966
10_1017_cts_2021_712
GroupedDBID 09C
09E
0R~
8FE
8FH
AABES
AABWE
AAGFV
AAKTX
AASVR
AAYXX
ABGDZ
ABQTM
ABROB
ABVZP
ABXHF
ACAJB
ACBEK
ACDLN
ACGFS
ACUIJ
ADAZD
ADBBV
ADDNB
ADKIL
ADOVH
ADVJH
AEBAK
AEHGV
AEMTJ
AEYHU
AFFHD
AFKQG
AFKRA
AFLVW
AFZFC
AGABE
AGJUD
AHIPN
AHQXX
AHRGI
AIGNW
AIHIV
AIOIP
AJCYY
AKMAY
ALMA_UNASSIGNED_HOLDINGS
ANPSP
AQJOH
ARCSS
AUXHV
AZGZS
BBLKV
BBNVY
BCNDV
BENPR
BHPHI
BLZWO
BMAJL
BRIRG
CBIIA
CCPQU
CCQAD
CFAFE
CITATION
CJCSC
DOHLZ
GROUPED_DOAJ
HCIFZ
HYE
IKXGN
IOEEP
IPYYG
JHPGK
JKPOH
JQKCU
JVRFK
KCGVB
KFECR
LK8
M7P
M~E
NIKVX
OK1
PHGZM
PHGZT
PQGLB
RCA
ROL
RPM
S6U
SAAAG
T9M
WFFJZ
ZYDXJ
5PM
ID FETCH-LOGICAL-c1962-89d1134150040a6b1b209bdb9aa91ea5f59797308ec667c853d8996d57b7469e3
IEDL.DBID DOA
ISSN 2059-8661
IngestDate Tue Oct 14 19:08:48 EDT 2025
Tue Nov 04 01:53:01 EST 2025
Sat Nov 29 01:40:29 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue s1
Language English
License http://creativecommons.org/licenses/by/4.0
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c1962-89d1134150040a6b1b209bdb9aa91ea5f59797308ec667c853d8996d57b7469e3
OpenAccessLink https://doaj.org/article/5ac9c3bc5b3e467ca205e5afbb76b93b
PageCount 1
ParticipantIDs doaj_primary_oai_doaj_org_article_5ac9c3bc5b3e467ca205e5afbb76b93b
pubmedcentral_primary_oai_pubmedcentral_nih_gov_8827966
crossref_primary_10_1017_cts_2021_712
PublicationCentury 2000
PublicationDate 2021-03-01
PublicationDateYYYYMMDD 2021-03-01
PublicationDate_xml – month: 03
  year: 2021
  text: 2021-03-01
  day: 01
PublicationDecade 2020
PublicationPlace Cambridge, UK
PublicationPlace_xml – name: Cambridge, UK
PublicationTitle Journal of clinical and translational science
PublicationYear 2021
Publisher Cambridge University Press
Publisher_xml – name: Cambridge University Press
SSID ssj0001826633
Score 2.1358294
Snippet ABSTRACT IMPACT: Despite its importance in systemic diseases such as diabetes, the eye is notably difficult to examine for non-specialists; this study...
SourceID doaj
pubmedcentral
crossref
SourceType Open Website
Open Access Repository
Index Database
StartPage 122
SubjectTerms Data Science/Biostatistics/Informatics
Translational Science, Policy, & Health Outcomes Science
Title 57084 Combining artificial intelligence and robotics: a novel fully automated optical coherence tomography-based approach for eye disease screening
URI https://pubmed.ncbi.nlm.nih.gov/PMC8827966
https://doaj.org/article/5ac9c3bc5b3e467ca205e5afbb76b93b
Volume 5
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAEN
  databaseName: Cambridge University Press Wholly Gold Open Access Journals
  customDbUrl:
  eissn: 2059-8661
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001826633
  issn: 2059-8661
  databaseCode: IKXGN
  dateStart: 20170201
  isFulltext: true
  titleUrlDefault: http://journals.cambridge.org/action/login
  providerName: Cambridge University Press
– providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2059-8661
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001826633
  issn: 2059-8661
  databaseCode: DOA
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2059-8661
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001826633
  issn: 2059-8661
  databaseCode: M~E
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Biological Science Database
  customDbUrl:
  eissn: 2059-8661
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001826633
  issn: 2059-8661
  databaseCode: M7P
  dateStart: 20170201
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/biologicalscijournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2059-8661
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001826633
  issn: 2059-8661
  databaseCode: BENPR
  dateStart: 20170201
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwELVQxcCCQIAoX7oBxkASx3HMBqgVA1QMIHWLfLajVkJJVdpKXfgT_GHOSYpaFhaWDHHkOPdyvnvO5ZmxywgdBVlrA2m1IYJieJBR2AkUsefYYmbQ1SKuT3IwyIZD9bK21ZevCWvkgRvD3QhtlOFoBHJHTm10HAondIEoU1Qc_exLWc8amapXVyhrTjlvK929RrSZeXHuOLqWUbwRg2qp_t8lkWsxpr_HdtvkEO6aQe2zLVcesC8hwywBclysN3MAP-ZG9wHGa4KaoEsL0worL7x8CxrKauHewa-vL0HPZxXlps5CNalXr8FUo-ZPP6CWVrc68DHNwkpnHCihBbd00H7FAZpiiPbSGA7ZW7_3-vAYtFspBIZcjOY8ZSMv3Sa80-oUI4xDhRaV1ipyWhTEKxQ5e-ZMSkamGG6JiKVWSJREoB0_Yp2yKt0xA53KUGjBEyOjRHOO3GQZFlgU1K9KVJddrYybTxrFjLwpJZM5gZB7EHICocvuveV_rvE61_UJQj9v0c__Qr_L5AZuG71ttpTjUa2eTZRCEsc7-Y_bn7Id_zhNTdoZ68ymc3fOts1iNv6YXtSvJB2fP3vfcZ3umQ
linkProvider Directory of Open Access Journals
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=57084+Combining+artificial+intelligence+and+robotics%3A+a+novel+fully+automated+optical+coherence+tomography-based+approach+for+eye+disease+screening&rft.jtitle=Journal+of+clinical+and+translational+science&rft.au=Song%2C+Ailin&rft.au=Ortiz%2C+Pablo&rft.au=Draelos%2C+Mark&rft.au=Schuman%2C+Stefanie+G.&rft.date=2021-03-01&rft.pub=Cambridge+University+Press&rft.eissn=2059-8661&rft.volume=5&rft.issue=Suppl+1&rft.spage=122&rft.epage=122&rft_id=info:doi/10.1017%2Fcts.2021.712&rft.externalDocID=PMC8827966
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2059-8661&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2059-8661&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2059-8661&client=summon