Accuracy of convolutional neural networks-based automatic segmentation of pharyngeal airway sections according to craniofacial skeletal pattern.

INTRODUCTION: This study aimed to evaluate a 3-dimensional (3D) U-Net-based convolutional neural networks model for the fully automatic segmentation of regional pharyngeal volume of interests (VOIs) in cone-beam computed tomography scans to compare the accuracy of the model performance across different skeletal patterns presenting with various pharyngeal dimensions. METHODS: Two-hundred sixteen cone-beam computed tomography scans of adult patients were randomly divided into training (n = 100), validation (n = 16), and test (n = 100) datasets. We trained the 3D U-Net model for fully automatic segmentation of pharyngeal VOIs and their measurements: nasopharyngeal, velopharyngeal, glossopharyngeal, and hypopharyngeal sections as well as total pharyngeal airway space (PAS). The test datasets were subdivided according to the sagittal and vertical skeletal patterns. The segmentation performance was assessed by dice similarity coefficient, volumetric similarity, precision, and recall values, compared with the ground truth created by 1 expert's manual processing using semiautomatic software. RESULTS: The proposed model achieved highly accurate performance, showing a mean dice similarity coefficient of 0.928 ± 0.023, the volumetric similarity of 0.928 ± 0.023, precision of 0.925 ± 0.030, and recall of 0.921 ± 0.029 for total PAS segmentation. The performance showed region-specific differences, revealing lower accuracy in the glossopharyngeal and hypopharyngeal sections than in the upper sections (P <0.001). However, the accuracy of model performance at each pharyngeal VOI showed no significant difference according to sagittal or vertical skeletal patterns. CONCLUSIONS: The 3D-convolutional neural network performance for region-specific PAS analysis is promising to substitute for laborious and time-consuming manual analysis in every skeletal and pharyngeal pattern.

Craniofacial treatment protocol for a pediatric patient with obstructive sleep apnea and skeletal Class III malocclusion: A 13-year follow-up.

This report aimed to describe the long-term effects of craniofacial growth modification treatment on sleep and breathing functions in a 7-year-old girl diagnosed with skeletal Class III malocclusion and sleep-disordered breathing. Based on the flowchart of orthodontic intervention protocol that we proposed for phenotype-based patient selection and skeletal target-based treatment selection for pediatric patients with sleep-disordered breathing, a 2-phase treatment targeting the nasomaxillary complex was performed. Posttreatment 3-dimensional changes in the skeletal structure and upper airway were evaluated in association with functional assessment using a validated pediatric sleep questionnaire and home sleep test. Esthetic improvement and obstructive sleep apnea cure were achieved without skeletal surgery. The 2-year retention records showed stable occlusion and improved facial profile with normal breathing and sleep.

Effect of extraction treatment on upper airway dimensions in patients with bimaxillary skeletal protrusion relative to their vertical skeletal pattern.

OBJECTIVE: To investigate dimensional changes in regional pharyngeal airway spaces after premolar extraction in bimaxillary skeletal protrusion (BSP) patients according to vertical skeletal pattern, and to further identify dentoskeletal risk factors to predict posttreatment pharyngeal changes. METHODS: Fifty-five adults showing BSP treated with microimplant anchorage after four premolar extractions were included in this retrospective study. The subjects were divided into two groups according to the mandibular plane steepness: hyperdivergent (Frankfort horizontal plane to mandibular plane [FH-MP] ≥ 30) and nonhyperdivergent groups (FH-MP < 30). The control group consisted of 20 untreated adults with skeletal Class I normodivergent pattern and favorable profile. Treatment changes in cephalometric variables were evaluated and compared. The association between posttreatment changes in the dentoskeletal and upper airway variables were analyzed using linear regression analysis. RESULTS: The BSP patients showed no significant decrease in the pharyngeal dimensions to the lower level in comparison with controls, except for middle airway space (MAS, p < 0.01). The upper airway variable representing greater decrease in the hyperdivergent group than in the nonhyperdivergent group was the MAS (p < 0.01). Posttreatment changes in FH-MP had negative correlation with changes in MAS (ß = -0.42, p < 0.01) and inferior airway space (ß = -0.52, p < 0.01) as a result of multivariable regression analysis adjusted for sagittal skeletal relationship. CONCLUSIONS: Decreased pharyngeal dimensions after treatment in BSP patients showed no significant difference from the normal range of pharyngeal dimensions. However, the glossopharyngeal airway space may be susceptible to treatment when vertical dimension increased in hyperdivergent BSP patients.