Journal: Diagnostics

Article Title: Application of Artificial Intelligence in Cone-Beam Computed Tomography for Airway Analysis: A Narrative Review

doi: 10.3390/diagnostics14171917

Figure Lengend Snippet: Summary of articles reviewed, highlighting the CBCT machine and technical specifications, number of CBCT data, type of AI application, image processing method and its software and hardware used, and the significant benefits of the AI models.

Article Snippet: Park et al., 2021, South Korea [ ] , PaX-i3D (Vatech Co., Hwaseong-si, South Korea) (105–114 KVP, 5.6–6.5 mA with 160 mm × 160 mm field of view, and 0.3 mm in voxel size) , 315 , 2D CNN Regression-based models , 5 coordinates predicted for airway segmentation in sagittal plane includes posterior palate, vomer, 1st, 2nd, or 3rd cervical vertebrae - Image processing using MATLAB 2020a (MathWorks, Natick, MA, USA) , Own model - Program developed based on MATLAB 2020a (MathWorks, Natick, MA, USA) Network training using NVIDIA Titan RTX GPU with CUDA (version 10.1) , - Good to excellent reliability - Fully automatic segmentation of the airway is possible by training via AI - High correlation between manual data and AI data.

Techniques: Software, Imaging, Comparison, Generated, Diagnostic Assay