AI to make PET scans clearer for each patient

Multi-Center Academic-Industrial Partnership for Personalized Al-Enabled High Count PET

NIH-funded research Yale University · NIH-11320723

This project uses artificial intelligence to turn routine PET scans into higher-count, less noisy images so people getting PET scans can have clearer results.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionYale University NIH-funded
Lab location1 site (New Haven, United States)
Project IDNIH-11320723 on NIH RePORTER

What this research studies

If I get a PET scan at one of the participating centers, researchers will use deep-learning software to reduce image noise and produce images that look like higher-count scans. The team collected many real PET images from different hospitals and scanners to train the AI so it works across machines and settings. Partner hospitals and an imaging company will test the software on clinical scans and work to integrate it into routine reading. The goal is to make images clearer without changing how my scan is done.

Who could benefit from this research

Good fit: People scheduled for routine PET imaging (for example for cancer diagnosis, staging, or monitoring) at participating centers are the most likely candidates for this work.

Not a fit: Patients who do not receive PET scans, whose scans are already very high-count/low-noise, or who are scanned at non-participating sites may not experience benefit.

Why it matters

Potential benefit: Clearer, higher-quality PET images could lower false positives, reduce unnecessary follow-up tests or procedures, and increase diagnostic confidence.

How similar studies have performed: Deep-learning noise reduction for low-count PET has shown promise in prior work, but converting routine clinical PET to consistently higher-count images across many scanners is a newer and less-tested approach.

Where this research is happening

New Haven, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.