Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities
Issued Date
2023-06-01
Resource Type
ISSN
10708022
eISSN
15365166
Scopus ID
2-s2.0-85159737109
Pubmed ID
36719740
Journal Title
Journal of Neuro-Ophthalmology
Volume
43
Issue
2
Start Page
159
End Page
167
Rights Holder(s)
SCOPUS
Bibliographic Citation
Journal of Neuro-Ophthalmology Vol.43 No.2 (2023) , 159-167
Suggested Citation
Vasseneix C., Nusinovici S., Xu X., Hwang J.M., Hamann S., Chen J.J., Loo J.L., Milea L., Tan K.B.K., Ting D.S.W., Liu Y., Newman N.J., Biousse V., Wong T.Y., Milea D., Najjar R.P., Gohier P., Miller N., Vanikieti K., La Morgia C., Rougier M.B., Ambika S., Fonseca P., Lagrèze W.A., Sanda N., Chiquet C., Yang H., Chan C.K.M., Cheung C.Y., Chau T.T.H., Jurkute N., Yu-Wai-Man P., Kho R., Jonas J.B., Vignal-Clermont C., Kim D.H., Yang H.K., Aung T., Singhal S., Tow S., Nongpiur M.E., Perera S., Narayanaswamy A., Thirugnanam U.N., Fraser C.L., Mejico L.J., Fard M.A. Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities. Journal of Neuro-Ophthalmology Vol.43 No.2 (2023) , 159-167. 167. doi:10.1097/WNO.0000000000001800 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/83025
Title
Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities
Author(s)
Vasseneix C.
Nusinovici S.
Xu X.
Hwang J.M.
Hamann S.
Chen J.J.
Loo J.L.
Milea L.
Tan K.B.K.
Ting D.S.W.
Liu Y.
Newman N.J.
Biousse V.
Wong T.Y.
Milea D.
Najjar R.P.
Gohier P.
Miller N.
Vanikieti K.
La Morgia C.
Rougier M.B.
Ambika S.
Fonseca P.
Lagrèze W.A.
Sanda N.
Chiquet C.
Yang H.
Chan C.K.M.
Cheung C.Y.
Chau T.T.H.
Jurkute N.
Yu-Wai-Man P.
Kho R.
Jonas J.B.
Vignal-Clermont C.
Kim D.H.
Yang H.K.
Aung T.
Singhal S.
Tow S.
Nongpiur M.E.
Perera S.
Narayanaswamy A.
Thirugnanam U.N.
Fraser C.L.
Mejico L.J.
Fard M.A.
Nusinovici S.
Xu X.
Hwang J.M.
Hamann S.
Chen J.J.
Loo J.L.
Milea L.
Tan K.B.K.
Ting D.S.W.
Liu Y.
Newman N.J.
Biousse V.
Wong T.Y.
Milea D.
Najjar R.P.
Gohier P.
Miller N.
Vanikieti K.
La Morgia C.
Rougier M.B.
Ambika S.
Fonseca P.
Lagrèze W.A.
Sanda N.
Chiquet C.
Yang H.
Chan C.K.M.
Cheung C.Y.
Chau T.T.H.
Jurkute N.
Yu-Wai-Man P.
Kho R.
Jonas J.B.
Vignal-Clermont C.
Kim D.H.
Yang H.K.
Aung T.
Singhal S.
Tow S.
Nongpiur M.E.
Perera S.
Narayanaswamy A.
Thirugnanam U.N.
Fraser C.L.
Mejico L.J.
Fard M.A.
Author's Affiliation
Farabi Eye Hospital
Istituto delle Scienze Neurologiche di Bologna
Seoul National University Bundang Hospital
Duke-NUS Medical School
Universidade de Coimbra, Faculdade de Medicina
Fondation Adolphe de Rothschild
Alma Mater Studiorum Università di Bologna
NUS Yong Loo Lin School of Medicine
Medical Research Foundation, Chennai
Universität Freiburg
University of California, Berkeley
Singapore Eye Research Institute
Universite Catholique de Lille
Sun Yat-Sen University
Centro Hospitalar e Universitário de Coimbra
SUNY Upstate Medical University
Singapore General Hospital
Universität Heidelberg
Moorfields Eye Hospital NHS Foundation Trust
Faculty of Medicine Ramathibodi Hospital, Mahidol University
Hong Kong Eye Hospital
Save Sight Institute
UCL Institute of Ophthalmology
Hôpitaux Universitaires de Genève
CHU Angers
Singapore National Eye Centre
Rigshospitalet
Centre Hospitalier Universitaire de Grenoble
Mayo Clinic
A-Star, Institute of High Performance Computing
Groupe Hospitalier Pellegrin
Chinese University of Hong Kong
Emory University School of Medicine
Johns Hopkins School of Medicine
American Eye Center
Istituto delle Scienze Neurologiche di Bologna
Seoul National University Bundang Hospital
Duke-NUS Medical School
Universidade de Coimbra, Faculdade de Medicina
Fondation Adolphe de Rothschild
Alma Mater Studiorum Università di Bologna
NUS Yong Loo Lin School of Medicine
Medical Research Foundation, Chennai
Universität Freiburg
University of California, Berkeley
Singapore Eye Research Institute
Universite Catholique de Lille
Sun Yat-Sen University
Centro Hospitalar e Universitário de Coimbra
SUNY Upstate Medical University
Singapore General Hospital
Universität Heidelberg
Moorfields Eye Hospital NHS Foundation Trust
Faculty of Medicine Ramathibodi Hospital, Mahidol University
Hong Kong Eye Hospital
Save Sight Institute
UCL Institute of Ophthalmology
Hôpitaux Universitaires de Genève
CHU Angers
Singapore National Eye Centre
Rigshospitalet
Centre Hospitalier Universitaire de Grenoble
Mayo Clinic
A-Star, Institute of High Performance Computing
Groupe Hospitalier Pellegrin
Chinese University of Hong Kong
Emory University School of Medicine
Johns Hopkins School of Medicine
American Eye Center
Other Contributor(s)
Abstract
Background: The examination of the optic nerve head (optic disc) is mandatory in patients with headache, hypertension, or any neurological symptoms, yet it is rarely or poorly performed in general clinics. We recently developed a brain and optic nerve study with artificial intelligence-deep learning system (BONSAI-DLS) capable of accurately detecting optic disc abnormalities including papilledema (swelling due to elevated intracranial pressure) on digital fundus photographs with a comparable classification performance to expert neuro-ophthalmologists, but its performance compared to first-line clinicians remains unknown. Methods: In this international, cross-sectional multicenter study, the DLS, trained on 14,341 fundus photographs, was tested on a retrospectively collected convenience sample of 800 photographs (400 normal optic discs, 201 papilledema and 199 other abnormalities) from 454 patients with a robust ground truth diagnosis provided by the referring expert neuro-ophthalmologists. The areas under the receiver-operating-characteristic curves were calculated for the BONSAI-DLS. Error rates, accuracy, sensitivity, and specificity of the algorithm were compared with those of 30 clinicians with or without ophthalmic training (6 general ophthalmologists, 6 optometrists, 6 neurologists, 6 internists, 6 emergency department [ED] physicians) who graded the same testing set of images. Results: With an error rate of 15.3%, the DLS outperformed all clinicians (average error rates 24.4%, 24.8%, 38.2%, 44.8%, 47.9% for general ophthalmologists, optometrists, neurologists, internists and ED physicians, respectively) in the overall classification of optic disc appearance. The DLS displayed significantly higher accuracies than 100%, 86.7% and 93.3% of clinicians (n = 30) for the classification of papilledema, normal, and other disc abnormalities, respectively. Conclusions: The performance of the BONSAI-DLS to classify optic discs on fundus photographs was superior to that of clinicians with or without ophthalmic training. A trained DLS may offer valuable diagnostic aid to clinicians from various clinical settings for the screening of optic disc abnormalities harboring potentially sight- or life-threatening neurological conditions.