Skip to main content

Spring Deadline: Sunday, March 1 @ 11:59pm PT. Click here to apply.

Back to Research
Accepted to JID 2025 (Oral Presentation)

SkinGPT-4 provides a generalizable foundation for fair and customizable skin disease classification models

Kiran Nijjer, Ryan Bui, Adnan Ahmed, Derek Jiu, Peter Wang

Abstract

SkinGPT-4 is an interactive dermatology diagnostic system powered by an advanced visual large language model. Leveraging a fine-tuned version of MiniGPT-4, trained on an extensive collection of skin disease images (comprising 52,929 images) along with clinical concepts and doctors' notes, SkinGPT-4 can autonomously evaluate skin photos, identify characteristics and categories of skin conditions, perform in-depth analysis, and provide interactive treatment recommendations. [arXiv link TBA]

Citation

Kiran Nijjer, Ryan Bui, Adnan Ahmed, Derek Jiu, Peter Wang. "SkinGPT-4 provides a generalizable foundation for fair and customizable skin disease classification models". Accepted to JID 2025 (Oral Presentation).

Resources

Details

Conference
Accepted to JID 2025 (Oral Presentation)
Authors
5 authors

Publish Your Research

Join Algoverse and work with world-class mentors to publish at top AI conferences.

Start Your Application