Analyzing clinical variables indicative of uveal melanoma to determine how they affect decisions made by an artificial intelligence classifier
The results from this study demonstrate that the FN classifications for CML fundus image classifications from our AI model are not associated with the presence of imaging risk factors for UM but are influenced by thinness of the lesion.
Authors
- Emad A. Mohammed (ORCID: https://orcid.org/0000-0001-8722-4856)
- Behrouz H. Far (ORCID: https://orcid.org/0000-0003-1589-8039)
- Rachel Curtis (ORCID: https://orcid.org/0000-0002-4997-6034)
- Trafford Crump (ORCID: https://orcid.org/0000-0001-6690-1926)
- Ezekiel Weis (ORCID: https://orcid.org/0000-0002-6862-0850)
- Esmaeil Shakeri (ORCID: https://orcid.org/0000-0002-8146-1874)
- Antoine Sylvestre-Bouchard
- Emily Laycock
Institutions
- University of Calgary (CA)
- Queen's University (CA)
- Wilfrid Laurier University (CA)
Publication Details
- Journal
- Canadian Journal of Ophthalmology
- Published
- 2025-03-30
- DOI
- https://doi.org/10.1016/j.jcjo.2025.02.012
- Primary Topic
- Ocular Oncology and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00