AI that combines MRI and PET brain scans to map different Alzheimer's patterns

Advanced machine learning algorithms that integrate multi-modal neuroimaging to quantify the heterogeneity in Alzheimer's Disease

NIH-funded research University of Pennsylvania · NIH-11473306

This project builds AI that looks at MRI and PET brain scans to spot and describe different forms of Alzheimer's disease in people with memory concerns or early dementia.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionUniversity of Pennsylvania NIH-funded
Lab location1 site (Philadelphia, United States)
Project IDNIH-11473306 on NIH RePORTER

What this research studies

You would be part of work that uses artificial intelligence to bring together multiple types of brain scans—like structural MRI and PET scans that show amyloid and tau—to understand brain changes. First, the team will map normal age-related brain changes using scans from healthy older adults to set a baseline. Then they will use a semi-supervised AI method to find distinct patterns of Alzheimer’s-related changes across people with preclinical or symptomatic disease. The goal is to describe the different ways Alzheimer’s can affect the brain so care can be better tailored to each person.

Who could benefit from this research

Good fit: Ideal candidates are older adults with memory concerns, mild cognitive impairment, early Alzheimer's disease, or people at higher risk who can undergo MRI and PET imaging.

Not a fit: People who cannot have MRI or PET scans, those unwilling to travel to imaging centers, or those with very advanced disease where imaging would not change care may not benefit directly.

Why it matters

Potential benefit: If successful, this could help doctors recognize different Alzheimer's subtypes earlier and guide more personalized care or future targeted treatments.

How similar studies have performed: Previous machine-learning work has helped detect Alzheimer’s signals, but combining multiple scan types in unsupervised and semi-supervised ways is relatively new and remains experimental.

Where this research is happening

Philadelphia, 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.