Improving MRI image quality using machine learning techniques
Official title: Machine Learning-Based Adaptation of Data Sampling and Reconstruction for Efficient Dynamic MRI
Funded at Michigan State University · NIH-10705033 · Data updated 2026-11-12
This study is exploring how to make MRI scans clearer and more detailed by using smart computer technology to improve the way images are taken and put together, so patients can get better diagnoses and care.
Quick facts
| Grant type | R21 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Michigan State University NIH-funded |
| Lab location | 1 site (East Lansing, United States) |
| Project start | September 30, 2022 |
| Project end | July 31, 2025 |
| Funding year | 2023 |
| Award (this year) | $188,556 |
| NIH project number | 5R21EB030762-02 |
| Project ID | NIH-10705033 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research include patients undergoing MRI scans for various medical conditions, particularly those requiring dynamic imaging of moving organs like the heart.
✕Less likely to help
Patients who do not require MRI imaging or those with conditions that do not involve dynamic imaging may not benefit from this research.
What this research studies
This research focuses on enhancing the quality of magnetic resonance imaging (MRI) by utilizing machine learning to optimize how data is collected and reconstructed. Traditional MRI methods often result in low-resolution images due to fixed data sampling patterns and nonadaptive algorithms. By implementing a machine learning-based system, the research aims to tailor data acquisition to specific clinical tasks and patient characteristics, potentially leading to clearer and more accurate images. The study will involve testing various sampling strategies and reconstruction methods using large datasets to determine the most effective approaches.
Why it matters
Potential benefit: If successful, this research could significantly improve the diagnostic accuracy of MRI scans for patients.
How similar studies have gone: Previous research has shown promise in using machine learning for image reconstruction in medical imaging, indicating that this approach could lead to significant advancements.
Where this research is happening
-
Michigan State University
East Lansing, United States Active
Researchers
- Principal investigator: Ravishankar, Saiprasad — Michigan State University
- Study coordinator: Ravishankar, Saiprasad
Related research
Other NIH-funded projects on the same topics.
-
Understanding how octopuses integrate sensory information and make decisions
This study is exploring how octopuses use their arms to grip things by looking closely at their nervous system and movements, which could help us understand their amazing abilities better.
-
Stabilizing the tear film to relieve evaporative dry eye
This project tests new ways to stabilize the tear film in people with evaporative dry eye, with the goal of longer-lasting comfort.
-
Cell-type specific brain stimulation: new methods to map and predict ICMS effects
A study using targeted brain stimulation and advanced gene mapping to understand how different brain cell types respond to electrical stimulation and how this affects behavior.
-
Expanded program to monitor work injuries and illnesses in Michigan
A nationwide-style occupational health surveillance program will be continued and expanded in Michigan to track injuries, illnesses, and related hazards among workers.
-
Identifying protective antibody responses to malaria in children
Young children in Africa may develop antibodies that protect against malaria; this project maps which antibody features help prevent severe disease.
-
Understanding how viral fusion proteins cause membranes to fuse
Scientists are studying how the envelope proteins of AIDS-causing viruses help them fuse with human cells, with the aim of guiding new antiviral strategies.
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.