A Convolutional Neural Network Using Anterior Segment Photos for Infectious Keratitis Identification
Convolutional neural networks with ensemble techniques provided the best performance in discriminating bacterial keratitis, fungal keratitis, non-infectious corneal lesions, and normal corneas. Our models can be used as a screening tool for non-ophthalmic health care providers and ophthalmologists for rapid provisional diagnosis of infectious keratitis.
Authors
- Thanachaporn Kittipibul (ORCID: https://orcid.org/0000-0001-5814-2413)
- Vannarut Satitpitakul (ORCID: https://orcid.org/0000-0002-1020-6833)
- Ngamjit Kasetsuwan (ORCID: https://orcid.org/0000-0003-1926-4666)
- Vilavun Puangsricharern (ORCID: https://orcid.org/0000-0002-0725-456X)
- Usanee Reinprayoon (ORCID: https://orcid.org/0000-0002-3660-3538)
- Apiwit Puangsricharern
- Surachet Yuktiratna
- Yossapon Jaisarn
- Keeratika Sangsao
Institutions
- PTT Public Company Limited (Thailand) (TH)
- Thai Red Cross Society (TH)
- Chulalongkorn University (TH)
- King Chulalongkorn Memorial Hospital (TH)
Publication Details
- Journal
- Clinical ophthalmology
- Published
- 2025-01-01
- DOI
- https://doi.org/10.2147/opth.s496552
- Citations
- 1
- Primary Topic
- Digital Imaging for Blood Diseases
- Type
- article
- Field-Weighted Citation Impact
- 1.28
Funders
- Thailand Science Research and Innovation