Image Generation of Common Dermatological Diagnoses by Artificial Intelligence: Evaluation Study of the Potential for Education and Training Purposes
AI-generated images of common dermatological conditions are becoming more accurate. This holds great implications for education but should be used with caution as further research is needed with more advanced, specific, and inclusive training data. Limitations include the use of AI image generators created by a single parent company as well as the use of a limited set of diagnoses.
Authors
- Gabriela Cobos
- Subin Lim
- Sarah Kooper-Johnson
- Daniel S. Loo (ORCID: https://orcid.org/0000-0002-3479-4991)
- Joshua Mervis (ORCID: https://orcid.org/0000-0002-4395-8871)
- Andrew Robinson (ORCID: https://orcid.org/0000-0003-3403-4674)
- Jumana Aldhalaan (ORCID: https://orcid.org/0000-0002-6243-9575)
- Vijay Kodumudi (ORCID: https://orcid.org/0000-0002-2498-2489)
- Bichchau Michelle Nguyen (ORCID: https://orcid.org/0000-0002-4751-1559)
- Mauro Petrillo (ORCID: https://orcid.org/0000-0002-6782-4704)
Institutions
- Tufts Medical Center (US)
Publication Details
- Journal
- JMIR Dermatology
- Published
- 2025-08-26
- DOI
- https://doi.org/10.2196/72371
- Primary Topic
- Cutaneous Melanoma Detection and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00