Using past and present PET/CT scans to improve lymphoma imaging
Multimodal Learning for Contextually-Aware Longitudinal PET/CT image analysis
Creating AI that reads multiple PET/CT scans over time to help doctors more accurately find and track lymphoma in adults.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Wisconsin-Madison NIH-funded |
| Lab location | 1 site (Madison, United States) |
| Project ID | NIH-11230216 on NIH RePORTER |
What this research studies
This project builds AI that looks at FDG PET/CT images from more than one time point so the algorithm can use earlier scans and clinical notes as context for later images. The models combine PET and CT images with clinical text using multimodal vision-language techniques to detect low-level residual lymphoma that can be hard to tell apart from normal or treatment-related uptake. The goal is to produce fast, whole-body quantitative measurements and reduce differences between readers. The team trains and validates the approach using adult lymphoma PET/CT images from clinical sites.
Who could benefit from this research
Good fit: Adults with lymphoma who have baseline and follow-up FDG PET/CT scans (typically age 21 and older) are the most relevant candidates for this work.
Not a fit: People without lymphoma, pediatric patients, or patients who do not have serial FDG PET/CT imaging are unlikely to benefit directly from this project.
Why it matters
Potential benefit: If successful, this could make PET/CT readings more accurate and consistent, leading to better treatment decisions and faster results for patients with lymphoma.
How similar studies have performed: Deep learning has shown promise for single-timepoint PET/CT analysis, but using longitudinal, context-aware multimodal models for lymphoma imaging is newer and less tested.
Where this research is happening
Madison, United States
- University of Wisconsin-Madison — Madison, United States (Active)
Researchers
- Principal investigator: Bradshaw, Tyler J — University of Wisconsin-Madison
- Study coordinator: Bradshaw, Tyler J
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.