AI that makes faster, clearer high-resolution brain MRIs from very little reference data
Robust and Efficient Learning of High-Resolution Brain MRI Reconstruction from Small Referenceless Data
This project uses artificial intelligence to produce high-resolution brain MRI images more quickly and without needing large reference scans, aiming to help people who need detailed brain imaging.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Minnesota NIH-funded |
| Lab location | 1 site (Minneapolis, United States) |
| Project ID | NIH-11324499 on NIH RePORTER |
What this research studies
Researchers are building AI methods that can reconstruct very detailed brain MRI pictures from smaller amounts of raw scan data so that scanning can be faster. They train and test new deep-learning algorithms designed to work without large reference databases, and optimize them to reduce artifacts and preserve anatomical detail for anatomical, functional, and diffusion MRI. The team will validate these methods using brain imaging datasets and advanced reconstruction techniques to ensure images are reliable for research and clinical use. If the algorithms work well, clinics could obtain higher-resolution brain images with shorter scan times and fewer repeated scans.
Who could benefit from this research
Good fit: People scheduled for brain MRI for neurological, psychiatric, or research reasons who can safely undergo MRI would be the most directly relevant participants or data sources.
Not a fit: Patients who do not need brain MRI, who cannot have MRI (e.g., incompatible implants), or whose care depends on other imaging types may not benefit directly from this work.
Why it matters
Potential benefit: Could shorten MRI scan times while producing clearer brain images, helping doctors diagnose and monitor neurological and psychiatric conditions more accurately.
How similar studies have performed: Deep learning has already improved MRI reconstruction in many settings, but applying referenceless, high-resolution methods to whole-brain imaging is newer and still being validated.
Where this research is happening
Minneapolis, United States
- University of Minnesota — Minneapolis, United States (Active)
Researchers
- Principal investigator: Akcakaya, Mehmet — University of Minnesota
- Study coordinator: Akcakaya, Mehmet
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.