S8A-06 SESSION 8A: METOPIC SYNOSTOSIS QUANTIFYING THE SEVERITY OF METOPIC CRANIOSYNOSTOSIS: A PILOT STUDY IN APPLICATION OF ADVANCED MACHINE LEARNING IN CRANIOFACIAL SURGERY

Abstract

Introduction: Metopic Craniosynostosis refers to early fusion of the metopic suture. It can cause head shape anomalies and symptoms of elevated intracranial pressure. While the current standard for diagnosing the condition utilizes CT imaging and physical exam, there is no standardized method for predicting disease severity. Previous studies using interfrontal angles have looked at differences in specific skull landmarks, however these measurements are difficult to readily ascertain in clinical practice and fail to assess the complete skull contour. This pilot project employs machine learning algorithms to combine statistical shape information with expert ratings to generate a user-friendly method of measuring the severity of metopic craniosynostosis. Methods: Expert ratings of normal and metopic skull CT images were collected. Skull-shape analysis was conducted using ShapeWorks software. Advanced machine-learning was used to combine the expert ratings with our shape analysis model to predict the severity of metopic CS using CT images. Our model was then compared to the gold standard using interfrontal angles. Results: 17 metopic and 65 non-affected skull CT images of patients 5–15 months old were assigned a severity by 18 craniofacial surgeons. Our model accurately correlated the level of skull deformity with severity (p<0.10) and predicted the severity of metopic CS more often than models using interfrontal angles (χ2=5.46, p=0.019). Conclusion: This is the first study that combines shape information with expert ratings to generate an objective measure of severity for metopic craniosynostosis. This method will help clinicians easily quantify the severity and perform robust longitudinal assessments of the condition.