Facial Aesthetics in Artificial Intelligence: First Investigation Comparing Results in a Generative AI Study.
Certain AI models outperformed others in generating the images, with evaluator opinions varying on their realism and clinical value. Some images reasonably depicted the target area and the expected outcome; however, many images displayed inappropriate postsurgical outcomes or provoked the uncanny valley effect with their lack of realism. The authors stress the need for AI improvement to produce better pre- and postoperative images, and plan for further research comparing AI-generated visuals with actual surgical results.
Authors
- Anthony Colon
- Ashley Ignatiuk (ORCID: https://orcid.org/0000-0003-4074-6280)
- Arya Akhavan (ORCID: https://orcid.org/0000-0001-7119-9123)
- Soheyb Ayad (ORCID: https://orcid.org/0000-0002-6876-7254)
- Arsany Yassa (ORCID: https://orcid.org/0009-0009-1474-4346)
- Olivia Ayad (ORCID: https://orcid.org/0009-0005-6406-6433)
Institutions
- Rutgers, The State University of New Jersey (US)
- Ain Shams University (EG)
- Rutgers New Jersey Medical School (US)
- University of Reggio Calabria (IT)
Publication Details
- Journal
- PubMed
- Published
- 2025-01-01
- Primary Topic
- Body Image and Dysmorphia Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00