AI-powered MRI tool to map soft palate and throat-valve movement

Development of an MRI Guided Machine Learning Algorithm to Assess the Velopharyngeal Mechanism

NIH-funded research University of Virginia · NIH-11228412

This project will use MRI scans plus artificial intelligence to build 3D pictures of how the soft palate and throat valve work in children with cleft palate or related conditions.

Quick facts

Grant typeR21 grant
Study typeNIH-funded research
Funding institutionUniversity of Virginia NIH-funded
Lab location1 site (Charlottesville, United States)
Project IDNIH-11228412 on NIH RePORTER

What this research studies

Researchers will take MRI images of the velopharyngeal area (the soft palate and the back of the throat) in young children and create 3D models showing how those parts move during speech and breathing. They will train machine learning algorithms on those images to speed up analysis and find patterns that are hard to see by eye. The goal is to produce objective, patient-specific measurements that surgeons can use when planning repairs. Eventually the team hopes these measurements will help predict which surgical approaches are most likely to succeed and reduce the need for repeat operations.

Who could benefit from this research

Good fit: Children (typically infants through about 11 years old) with repaired cleft palate, craniofacial conditions, or suspected velopharyngeal dysfunction and related speech problems would be the ideal candidates.

Not a fit: Children without structural velopharyngeal problems (for example, speech differences caused purely by learning/neurologic issues) may not get direct benefit from this imaging tool.

Why it matters

Potential benefit: If successful, this could help surgeons tailor operations to a child's specific anatomy and lower the chance of failed or repeat surgeries, improving speech outcomes.

How similar studies have performed: Previous MRI research has shown promise in visualizing velopharyngeal anatomy but has been limited by small datasets and slow analysis, and applying AI to this problem is relatively new and not yet proven.

Where this research is happening

Charlottesville, 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.