AI-Based Automatic Segmentation of Craniomaxillofacial Anatomy From CBCT Scans for Automatic Detection of Pharyngeal Airway Evaluations in OSA patients

Abstract This study aims to generate and also validate an automatic detection algorithm for pharyngeal airway on CBCT data using an AI system which will procure an easy, errorless and fast method. The second aim is to validate the newly developed artificial intelligence system in comparison to commercially available software for 3D CBCT evaluation. A Convolutional Neural Network based machine learning algorithm did the segmentation of the pharyngeal airways in OSA and non-OSA patients. Radiologists used a semi-automatic software to manually determine the airway and their measurements were compared with the AI. OSA patients were classified as minimal, mild, moderate and severe groups and the mean airway volumes were compared. Narrowest points (mm), airway areas (mm2) and airway volumes (cc) of both OSA and non-OSA patients were also compared. There was no statistically significant difference between the manual and Diagnocat measurements in all groups (p>0.05). According to the results of the Diagnocat and manual segmentation, a successful algorithm which can automatically segment the pharyngeal airway from was created which can be used for a swift and precise measurement of pharyngeal airway volume.