Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities

Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities Publisher Pubmed

Vasseneix C¹ ; Nusinovici S¹ ; Xu X³ ; Hwang JM⁴ ; Hamann S⁵ ; Chen JJ⁶ ; Loo JL⁷ ; Milea L⁸ ; Tan KBK⁹ ; Ting DSW^{1, 2, 7} ; Liu Y³ ; Newman NJ¹⁰ ; Biousse V¹⁰ ; Wong TY^{1, 2, 7} Show All Authors

Vasseneix C¹
Nusinovici S¹
Xu X³
Hwang JM⁴
Hamann S⁵
Chen JJ⁶
Loo JL⁷
Milea L⁸
Tan KBK⁹
Ting DSW^{1, 2, 7}
Liu Y³
Newman NJ¹⁰
Biousse V¹⁰
Wong TY^{1, 2, 7}
Milea D^{2, 7}
Najjar RP^{1, 2, 11}
Gohier P¹²
Miller N¹³
Vanikieti K¹⁴
La Morgia C^{15, 16}
Rougier MB¹⁷
Ambika S¹⁸
Fonseca P^{19, 20}
Lagreze WA²¹
Sanda N²²
Chiquet C²³
Yang H²⁴
Chan CKM^{25, 26}
Cheung CY^{25, 26}
Chau TTH²⁷
Jurkute N^{28, 29}
Yuwaiman P^{28, 29}
Kho R³⁰
Jonas JB³¹
Vignalclermont C³²
Kim DH³³
Yang HK³³
Aung T^{34, 35, 36}
Singhal S^{34, 35, 36}
Tow S^{34, 35, 36}
Nongpiur ME^{34, 35, 36}
Perera S^{34, 35, 36}
Narayanaswamy A^{34, 35, 36}
Thirugnanam UN^{34, 35, 36}
Fraser CL³⁷
Mejico LJ³⁸
Fard MA³⁹

Show Affiliations

1. Visual Neuroscience Group, Singapore Eye Research Institute, Singapore, Singapore
2. Duke NUS Medical School, National University of Singapore, Singapore, Singapore
3. Institute of High Performance Computing Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
4. Department of Ophthalmology, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam-si, South Korea
5. Department of Ophthalmology, Rigshospitalet, University of Copenhagen, Kobenhavn, Denmark
6. Departments of Ophthalmology and Neurology, Mayo Clinic, Rochester, MN, United States
7. Singapore National Eye Centre, Singapore, Singapore
8. Berkeley University, Berkeley, CA, United States
9. Department of Emergency Medicine, Singapore General Hospital, Singapore, Singapore
10. Departments of Ophthalmology, Neurology and Neurological Surgery, Emory University School of Medicine, Atlanta, GA, United States
11. Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
12. Department of Ophthalmology, University Hospital Angers, Angers, France
13. Department of Ophthalmology, Neurology and Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, MD, United States
14. Department of Ophthalmology, Faculty of Medicine Ramathibodi Hospital, Mahidol University, Bangkok, Thailand
15. Istituto delle Scienze Neurologiche di Bologna, UOC Clinica Neurologica, Bologna, Italy
16. Dipartimento di Scienze Biomediche e Neuromotorie, Universita degli Studi di Bologna, Bologna, Italy
17. Service dâ€™Ophtalmologie., Unite Retine - Uveites - Neuro-Ophtalmologie, Hopital Pellegrin, CHU de Bordeaux, Bordeaux, France
18. Department of Neuro-ophthalmology, Sankara Nethralaya-A Unit of Medical Research, Foundation, Chennai, India
19. Department of Ophthalmology, Centro Hospitalar e Universitario de Coimbra (CHUC), Coimbra, Portugal
20. Coimbra Institute for Biomedical Imaging and Translational Research (CIBIT), Faculty of Medicine University of Coimbra (FMUC), Coimbra, Portugal
21. Eye Center, Medical Center, Medical Faculty, University Freiburg Germany, Freiburg, Germany
22. Clinical Neuroscience Department, Geneva University Hospital, Geneva, Switzerland
23. Department of Ophthalmology, University Hospital of Grenoble-Alpes, Grenoble-Alpes University, HP2 Laboratory, INSERM U1042, Grenoble, France
24. Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
25. Department of Ophthalmology and Visual Sciences, Chinese University of Hong Kong, Hong Kong, Hong Kong
26. Hong Kong Eye Hospital, Hong Kong, Hong Kong
27. Department of Ophthalmology, Lille Catholic Hospital, Lille Catholic University, Inserm U1171, Lille, France
28. Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom
29. UCL Institute of Ophthalmology, University College London, London, United Kingdom
30. American Eye Center, Mandaluyong City, Manila, Philippines
31. Department of Ophthalmology, Medical Faculty Mannheim of the Ruprecht-Karls-University of Heidelberg, Mannheim, Germany
32. Fondation Adolphe de Rothschild, Paris, France
33. Ophthalmology Department, Seoul National University College of Medicine, Seoul National University Bundang Hospital, South Korea
34. Singapore National Eye Centre, Singapore Eye Research Institute, Singapore, Singapore
35. Duke-NUS Medical School, Singapore, Singapore
36. Yong Loo Lin School of Medicine, National University of Singapore, Singapore General Hospital, Singapore, Singapore
37. Save Sight Institute, Faculty of Health and Medicine, University of Sydney, NSW, Australia
38. Department of Neurology, SUNY Upstate Medical University, Syracuse, NY, United States
39. Farabi Eye Hospital, Tehran University of Medical Science, Tehran, Iran

Source: Journal of Neuro-Ophthalmology Published:2023

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. © 2023 by North American Neuro-Ophthalmology Society.

Related Docs

1. Artificial Intelligence to Detect Papilledema From Ocular Fundus Photographs, New England Journal of Medicine (2020)

2. Application of a Deep Learning System to Detect Papilledema on Nonmydriatic Ocular Fundus Photographs in an Emergency Department, American Journal of Ophthalmology (2024)

3. Artificial Intelligence in Retinal Image Analysis: Development, Advances, and Challenges, Survey of Ophthalmology (2023)

4. From the Diagnosis of Infectious Keratitis to Discriminating Fungal Subtypes; a Deep Learning-Based Study, Scientific Reports (2023)

5. Differentiating Glaucomatous Optic Neuropathy From Non-Glaucomatous Optic Neuropathies Using Deep Learning Algorithms, American Journal of Ophthalmology (2023)

6. Deep Learning-Based Classification of Subtypes of Primary Angle-Closure Disease With Anterior Segment Optical Coherence Tomography, Journal of Glaucoma (2023)

7. Artificial Intelligence in Rheumatoid Arthritis: Current Status and Future Perspectives: A State-Of-The-Art Review, Rheumatology and Therapy (2022)

8. Deep Learning for Diagnosis of Head and Neck Cancers Through Radiographic Data: A Systematic Review and Meta-Analysis, Oral Radiology (2024)

Experts (# of related papers)

View all Related Experts

Masoud Aghsaei Fard (2)

Mona Seyed Safizadeh (1)

Style	Citing Format
MLA	Vasseneix C, et al.. "Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities." Journal of Neuro-Ophthalmology, vol. 43, no. 2, 2023, pp. 159-167.
APA	Vasseneix C, Nusinovici S, Xu X, Hwang JM, Hamann S, Chen JJ, Loo JL, Milea L, Tan KBK, Ting DSW, Liu Y, Newman NJ, Biousse V, Wong TY, Milea D, Najjar RP, Gohier P, Miller N, Vanikieti K, ... Fard MA (2023). Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities. Journal of Neuro-Ophthalmology, 43(2), 159-167.
Chicago	Vasseneix C, Nusinovici S, Xu X, Hwang JM, Hamann S, Chen JJ, Loo JL, et al.. "Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities." Journal of Neuro-Ophthalmology 43, no. 2 (2023): 159-167.
Harvard	Vasseneix C et al. (2023) 'Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities', Journal of Neuro-Ophthalmology, 43(2), pp. 159-167.
Vancouver	Vasseneix C, Nusinovici S, Xu X, Hwang JM, Hamann S, Chen JJ, et al.. Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities. Journal of Neuro-Ophthalmology. 2023;43(2):159-167.
BibTex	@article{ author = {Vasseneix C and Nusinovici S and Xu X and Hwang JM and Hamann S and Chen JJ and Loo JL and Milea L and Tan KBK and Ting DSW and Liu Y and Newman NJ and Biousse V and Wong TY and Milea D and Najjar RP and Gohier P and Miller N and Vanikieti K and La Morgia C and Rougier MB and Ambika S and Fonseca P and Lagreze WA and Sanda N and Chiquet C and Yang H and Chan CKM and Cheung CY and Chau TTH and Jurkute N and Yuwaiman P and Kho R and Jonas JB and Vignalclermont C and Kim DH and Yang HK and Aung T and Singhal S and Tow S and Nongpiur ME and Perera S and Narayanaswamy A and Thirugnanam UN and Fraser CL and Mejico LJ and Fard MA}, title = {Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities}, journal = {Journal of Neuro-Ophthalmology}, volume = {43}, number = {2}, pages = {159-167}, year = {2023} }
RIS	TY - JOUR AU - Vasseneix C AU - Nusinovici S AU - Xu X AU - Hwang JM AU - Hamann S AU - Chen JJ AU - Loo JL AU - Milea L AU - Tan KBK AU - Ting DSW AU - Liu Y AU - Newman NJ AU - Biousse V AU - Wong TY AU - Milea D AU - Najjar RP AU - Gohier P AU - Miller N AU - Vanikieti K AU - La Morgia C AU - Rougier MB AU - Ambika S AU - Fonseca P AU - Lagreze WA AU - Sanda N AU - Chiquet C AU - Yang H AU - Chan CKM AU - Cheung CY AU - Chau TTH AU - Jurkute N AU - Yuwaiman P AU - Kho R AU - Jonas JB AU - Vignalclermont C AU - Kim DH AU - Yang HK AU - Aung T AU - Singhal S AU - Tow S AU - Nongpiur ME AU - Perera S AU - Narayanaswamy A AU - Thirugnanam UN AU - Fraser CL AU - Mejico LJ AU - Fard MA TI - Deep Learning System Outperforms Clinicians in Identifying Optic Disc Abnormalities JO - Journal of Neuro-Ophthalmology VL - 43 IS - 2 SP - 159 EP - 167 PY - 2023 ER -

Science Communicator Platform

Authors

Authors Affiliations

Abstract