Effectiveness Of Cone-Beam Computed Tomography (CBCT)- Generated Cephalograms Using Artificial Intelligence (AI) Cephalometric Analysis

Abstract

Lateral cephalograms and related analysis have become a “gold standard”, since its introduction. However, since conventional cephalometric radiographs display a three-dimensional structure on a 2D plane, inaccuracies may be produced when quantitative evaluation is required. CBCT has minimal image distortion and important parts can be observed without overlapping. It provides a high-resolution 3D image at a relatively low dose and cost but still shows a higher dose than lateral cephalogram. It is especially true for children who are more susceptible to radiation doses and often have difficult diagnoses. If the DICOM data obtained from CBCT are reconstructed, such as the conventional lateral cephalometric radiograph, can be obtained. This study evaluated the applicability of lateral cephalograms generated by CBCT using an artificial intelligence analysis program. Group comprised conventional lateral cephalometric radiographs, group comprised lateral cephalometric radiographs generated from CBCT using OnDemand 3D™, and group comprised lateral cephalometric radiographs generated from CBCT using Invivo 5™. All measurements in the three groups showed non-significant results. Therefore, a CBCT scan and AI programs are an efficient means when performing orthodontic analysis on pediatric or orthodontic patients for orthodontic diagnosis and planning.