Evaluating Text-to-Image Generation in Pediatric Ophthalmology
Text-to-image generators are poor at generating images of common pediatric ophthalmology pathologies. They can serve as adequate supplemental tools for generating high-quality accurate textual information, but care must be taken to tailor generated text to be readable by users.
Authors
- Christina Scelfo (ORCID: https://orcid.org/0000-0001-8261-7431)
- Sarah Jill de Jong
- Mohamed M. Khodeiry (ORCID: https://orcid.org/0000-0003-0109-5331)
- Ahmad Alzein (ORCID: https://orcid.org/0000-0002-5369-9033)
- Abdelrahman M. Elhusseiny (ORCID: https://orcid.org/0000-0003-1412-375X)
- Qais A. Dihan (ORCID: https://orcid.org/0009-0005-1471-288X)
Institutions
- University of Louisville (US)
- Rosalind Franklin University of Medicine and Science (US)
- University of Illinois Chicago (US)
- Arkansas Cardiology (US)
- Arkansas Baptist College (US)
- Arkansas Department of Agriculture (US)
- University of Arkansas for Medical Sciences (US)
Publication Details
- Journal
- Journal of Pediatric Ophthalmology & Strabismus
- Published
- 2025-09-26
- DOI
- https://doi.org/10.3928/01913913-20250724-03
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.65