Development of an MRI Guided Machine Learning Algorithm to Assess the Velopharyngeal Mechanism - PROJECT SUMMARY More than 25-35% of children with velopharyngeal (VP) or palatal anomalies, such as those associated with repaired cleft palate and/or craniofacial conditions, will develop velopharyngeal dysfunction (VPD) as evidenced by hypernasal speech. This can negatively impact quality of life and communication abilities across the lifespan if not corrected during childhood. VPD often requires surgical management to achieve an anatomy capable of producing normal speech and balanced resonance. However, an extremely high failure rate (up to 32%) is reported for these surgical procedures, and numerous revision surgeries are necessary. With each revision surgery, the likelihood for success further decreases. Furthermore, although the consequences of VPD are well established, the fundamental anatomic underpinnings for what constitutes functional VP anatomy from non-functional anatomy is poorly understood due to the inability for clinicians to objectively quantify the VP mechanism and consider patient-specific variables in the pre-operative assessment process. Recent work utilizing MRI has emerged as a methodology to facilitate improved understanding of the VP anatomy. However, previous efforts to understand the VP mechanism have been significantly limited by small sample sizes and time-intensive analytic methods. What is needed is a major technological advancement in our ability to quantify the VP anatomy and utilize this information to integrate patient-specific measurements into the clinical decision-making process. The main objectives of this R21 project are to deliver a cutting-edge, artificial intelligence/deep learning framework for automated 3D segmentation and 2D measurement of VP structures (Aim 1), to develop a large dataset to test foundational hypotheses on the relationships between velopharyngeal anatomy and speech resonance (Aim 2), and assess feasibility for integration of anatomic analyses in a clinical workflow (Aim 3). These advancements will lay a critical foundation by developing a clinically feasible method for accurate, pre- operative assessment of the VP mechanism, which will accelerate clinical translation and development of precision medicine approaches. This will lead to exciting opportunities for patient-specific surgical planning and operation with a higher success rate. This will ultimately improve communication outcomes and quality of life for children with VPD.
