A deep learning algorithm proposal to automatic pharyngeal airway detection and segmentation on CBCT images

Abstract

Objectives: This study aims to evaluate an automatic segmentation algorithm for pharyngeal airway in cone-beam computed tomography (CBCT) images using a deep learning artificial intelligence (AI) system. Setting and Sample Population: Archives of the CBCT images were reviewed, and the data of 306 subjects with the pharyngeal airway were included in this retrospective study. Material and Methods: A machine learning algorithm, based on Convolutional Neural Network (CNN), did the segmentation of the pharyngeal airway on serial CBCT images. Semi-automatic software (ITK-SNAP) was used to manually generate the airway, and the results were compared with artificial intelligence. Dice similarity coefficient (DSC) and Intersection over Union (IoU) were used as the accuracy of segmentation in comparing the measurements of human measurements and artificial intelligence algorithms. Results: The human observer found the average volume of the pharyngeal airway to be 18.08 cm3 and artificial intelligence to be 17.32 cm3. For pharyngeal airway segmentation, a dice ratio of 0.919 and a weighted IoU of 0.993 is achieved. Conclusions: In this study, a successful AI algorithm that automatically segments the pharyngeal airway from CBCT images was created. It can be useful in the quick and easy calculation of pharyngeal airway volume from CBCT images for clinical application.