Grading of diabetic retinopathy using a pre‐segmenting deep learning classification model: Validation of an automated algorithm
While the autonomous DL algorithm for DR classification only performed on par with a human grader for some measures in a high-risk population, extrapolations to a real-world population demonstrated an excellent 92% NPV, which could make it clinically feasible to use autonomously to identify non-DR patients.
Authors
- Jakob Grauslund (ORCID: https://orcid.org/0000-0001-5019-0736)
- J. Andersen (ORCID: https://orcid.org/0000-0003-3238-868X)
- Sebastian Dinesen (ORCID: https://orcid.org/0000-0002-7367-9398)
- Thiusius Rajeeth Savarimuthu (ORCID: https://orcid.org/0000-0002-2478-8694)
- Dyllan Edson Similié
Institutions
- Steno Diabetes Centers (DK)
- University of Southern Denmark (DK)
- Maersk (Denmark) (DK)
- Odense University Hospital (DK)
- Sykehuset i Vestfold (NO)
Publication Details
- Journal
- Acta Ophthalmologica
- Published
- 2024-10-19
- DOI
- https://doi.org/10.1111/aos.16781
- Citations
- 3
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 1.21