Performance of a Deep Learning System and Performance of Optometrists for the Detection of Glaucomatous Optic Neuropathy Using Colour Retinal Photographs
The AI system exhibited lower performance than optometrists in detecting referable glaucoma. Our findings suggest that while AI can serve as a screening tool, both AI and optometrists have suboptimal performance for the nuanced diagnosis of glaucoma using fundus photographs alone. Enhanced training with diverse populations for AI is essential for improving GON detection and addressing the significant challenge of undiagnosed cases.
Authors
- Christian Davey (ORCID: https://orcid.org/0000-0003-3097-9769)
- Algis J. Vingrys (ORCID: https://orcid.org/0000-0001-5920-4604)
- Randall S. Stafford (ORCID: https://orcid.org/0000-0003-1805-1271)
- Catherine Jan (ORCID: https://orcid.org/0000-0001-7383-8208)
- Peter van Wijngaarden (ORCID: https://orcid.org/0000-0002-8800-7834)
- Jennifer C. Fan Gaskin (ORCID: https://orcid.org/0000-0003-2782-9700)
- Xianwen Shang (ORCID: https://orcid.org/0000-0001-6143-9349)
- Mingguang He (ORCID: https://orcid.org/0000-0002-6664-3442)
- George Y. X. Kong (ORCID: https://orcid.org/0000-0003-0522-3046)
- Jacqueline Henwood
- Bernardo P. Soares Bezerra
Institutions
- Hong Kong Polytechnic University (HK)
- The University of Melbourne (AU)
- Vision Australia (AU)
- Australian College of Optometry (AU)
- Centre for Eye Research Australia (AU)
- Stanford University (US)
Publication Details
- Journal
- Bioengineering
- Published
- 2024-11-13
- DOI
- https://doi.org/10.3390/bioengineering11111139
- Citations
- 1
- Primary Topic
- Glaucoma and retinal disorders
- Type
- article
- Field-Weighted Citation Impact
- 0.54
Funders
- Australian Government
- State Government of Victoria
- National Health and Medical Research Council