Keeping AI tools in radiation therapy safe and reliable
Quality assurance for safe use of AI systems in radiotherapy
['FUNDING_R01'] · WASHINGTON UNIVERSITY · NIH-11306619
This project builds automatic checks to help ensure AI used in radiation treatment images and plans works safely for patients receiving radiation therapy.
Quick facts
| Phase | ['FUNDING_R01'] |
|---|---|
| Study type | Nih_funding |
| Sex | All |
| Sponsor | WASHINGTON UNIVERSITY (nih funded) |
| Locations | 1 site (SAINT LOUIS, UNITED STATES) |
| Trial ID | NIH-11306619 on ClinicalTrials.gov |
What this research studies
This project will create automated monitors that watch the images and AI outputs used in my radiation treatments and flag changes caused by scanner updates, protocol shifts, or equipment replacement. The team is designing these checks to work with commercial, closed-source AI systems so hospitals can verify safety without needing the AI source code. They will test the detectors using real clinical imaging and radiation oncology workflows to find situations where AI performance can degrade. The goal is to give my clinic practical tools and guidelines to continuously watch AI tools so they don't silently drift and affect my care.
Who could benefit from this research
Good fit: Patients receiving radiation therapy at centers that use AI for imaging, auto-segmentation, synthetic CT, or treatment planning would be the most relevant population for these QA tools.
Not a fit: People not undergoing radiation therapy or treated at clinics that do not use AI tools are unlikely to see direct benefit from this project.
Why it matters
Potential benefit: If successful, these QA tools could reduce AI-related errors in radiation therapy and make treatments safer and more reliable for patients.
How similar studies have performed: Prior work has shown that AI can fail when clinical data shifts, but robust, clinically practical QA methods for AI are relatively new and this approach is somewhat novel.
Where this research is happening
SAINT LOUIS, UNITED STATES
- WASHINGTON UNIVERSITY — SAINT LOUIS, UNITED STATES (ACTIVE)
Researchers
- Principal investigator: HUGO, GEOFFREY D — WASHINGTON UNIVERSITY
- Study coordinator: HUGO, GEOFFREY D
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 below.