Kazlin Mason
University of Virginia, VA·Medicine & Clinical Research
Many children born with cleft palate or other craniofacial conditions develop velopharyngeal dysfunction (VPD). In VPD, the soft palate and throat walls cannot close off the nose during speech, so speech sounds hypernasal.
- Fields
Medicine & Clinical Research
Biomedical Engineering
Computer Science
- Topics
velopharyngeal dysfunction
cleft palate
craniofacial conditions
- Grants
- 1 known grant, through Nov 2026
What they work on
- Develop a deep learning framework that automatically segments velopharyngeal structures in 3D and measures them in 2D from MRI scans of children with velopharyngeal anomalies.
- Build a large MRI dataset to test hypotheses about how velopharyngeal anatomy relates to speech resonance and hypernasality.
- Assess whether automated MRI-based anatomic analysis can be feasibly built into the clinical workflow for evaluating patients before surgery.
More about the research
Surgery is often needed, but up to 32% of these operations fail, and every revision is less likely to succeed. Part of the problem is that clinicians cannot objectively measure the velopharyngeal anatomy before surgery. As a result, it is poorly understood what separates anatomy that works from anatomy that does not.
Why it matters
Children with cleft palate and craniofacial conditions who develop hypernasal speech could benefit from objective, automated MRI-based assessment before surgery. This approach could support patient-specific surgical planning, raise surgical success rates and reduce repeat operations. The goal is better speech, communication and quality of life.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Lisa Gfrerer
Weill Medical College of Cornell University, NY·Medicine & Clinical Research
Further develop NerveAI, an artificial intelligence algorithm that identifies nerve pain patterns from patients' pain drawings in real time, to diagnose occipital neuralgia at the initial point of care.
Ronald Stanley
Missouri University of Science and Technology, MO·Engineering
Build an online platform with the International Skin Imaging Collaborative (ISIC) where experts worldwide annotate, segment and validate critical structures in dermoscopic skin lesion images.
Jeanne Shen
Stanford University, CA·Medicine & Clinical Research
Build a publicly available, expert-annotated multimodal colorectal cancer dataset. It will combine pathology whole-slide images, preoperative CT and MRI scans, and structured electronic medical record data.
The school
University of Virginia: 43 labs on PI Pages, $814M a year on research, 413 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.