Better brain PET scans using AI
Next Generation Brain PET Imaging
This project uses artificial intelligence to create high-quality brain FDG PET images from ultra-low-dose PET or from MRI alone to help people needing scans for tumor recurrence, dementia, or epilepsy.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Stanford University NIH-funded |
| Lab location | 1 site (Stanford, United States) |
| Project ID | NIH-11170581 on NIH RePORTER |
What this research studies
If you take part, you would have simultaneous PET and MRI scans while researchers train AI models to turn very-low-dose PET plus MRI into images that look like standard PET. The team will test the approach for three common uses of brain FDG PET—tumor recurrence, dementia, and epilepsy—by comparing AI images to routine scans and by having doctors read them without knowing which are real. They will also try to produce PET-like images using only MRI data to remove radiation entirely for some patients. Finally, researchers will explore whether adding clinical and genetic information improves the AI images and helps predict future imaging-based markers.
Who could benefit from this research
Good fit: Ideal participants are people referred for brain FDG PET for tumor recurrence, dementia evaluation, or epilepsy who can undergo MRI and PET scanning.
Not a fit: People who require PET with tracers other than FDG, cannot have MRI, or have conditions not represented in the study data may not benefit from these AI methods.
Why it matters
Potential benefit: If successful, this could provide PET-quality brain images with much less or no radiation, making scans safer, faster, and more available.
How similar studies have performed: Earlier small studies have shown promising results for AI-based PET denoising and MR-to-PET image synthesis, but replacing PET with MR-only approaches remains experimental.
Where this research is happening
Stanford, United States
- Stanford University — Stanford, United States (Active)
Researchers
- Principal investigator: Zaharchuk, Gregory George — Stanford University
- Study coordinator: Zaharchuk, Gregory George
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.