Reliable Vision-Language Dermatology AI to Help Detect Skin Cancer Early
Official title: Building Reliable Vision-Language Assistant for Dermatology AI through Modeling Uncertainties in Multimodal LLMs
Funded at Rochester Institute of Technology · NIH-11394774 · Data updated 2026-11-12
A study to build an AI assistant that analyzes skin images and chats with patients to support early melanoma diagnosis and skin care.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Rochester Institute of Technology NIH-funded |
| Lab location | 1 site (Rochester, United States) |
| Project start | August 12, 2025 |
| Project end | June 30, 2029 |
| Funding year | 2026 |
| Award (this year) | $186,875 |
| NIH project number | 5R16GM159146-02 |
| Project ID | NIH-11394774 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults at risk for or concerned about skin cancer who have digital skin images or questions about skin lesions.
✕Less likely to help
Individuals without skin concerns or access to digital image data may not benefit directly from this AI tool.
What this research studies
This project aims to create a conversational, image‑aware AI agent for dermatology that can interpret digital skin photos and provide clear, patient‑friendly text advice. By fine‑tuning large language models to reason over visual skin cues, the AI will offer interactive guidance and information to patients, potentially speeding up access to dermatology care. The work focuses on reliability, interpretability, and safe, accessible remote support for people who may have limited dermatologist access.
Why it matters
Potential benefit: If successful, patients could receive quicker preliminary insights and guidance for skin changes, potentially speeding up diagnosis and improving teledermatology access.
How similar studies have gone: Prior dermatology AI work has shown promise in image recognition; integrating visual and textual guidance is an emerging area with limited clinical validation.
Where this research is happening
-
Rochester Institute of Technology
Rochester, United States Active
Researchers
- Principal investigator: Tao, Zhiqiang — Rochester Institute of Technology
- Study coordinator: Tao, Zhiqiang
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.