Background: This study aims to compare an automated cephalometric analysis based on the latest deep learning method of automatically identifying cephalometric landmarks with a manual tracing method using broadly accepted cephalometric software. Methods: A total of 100 cephalometric X-rays taken using a CS8100SC cephalostat were collected from a private practice. The X-rays were taken in maximum image size (18 × 24 cm lateral image). All cephalometric X-rays were first manually traced using the Dolphin 3D Imaging program version 11.0 and then automatically, using the Artificial Intelligence CS imaging V8 software. The American Board of Orthodontics analysis and the European Board of Orthodontics analysis were used for the cephalometric measurements. This resulted in the identification of 16 cephalometric landmarks, used for 16 angular and 2 linear measurements. Results: All measurements showed great reproducibility with high intra-class reliability (>0.97). The two methods showed great agreement, with an ICC range of 0.70–0.92. Mean values of SNA, SNB, ANB, SN-MP, U1-SN, L1-NB, SNPg, ANPg, SN/ANS-PNS, SN/GoGn, U1/ANS-PNS, L1-APg, U1-NA, and L1-GoGn landmarks had no significant differences between the two methods (p > 0.0027), while the mean values of FMA, L1-MP, ANS-PNS/GoGn, and U1-L1 were statistically significantly different (p < 0.0027). Conclusions: The automatic cephalometric tracing method using CS imaging V8 software is reliable and accurate for all cephalometric measurements.

Background/objectives: The purpose of this study was to compare the differences in tooth movements when implementing the same virtual setup on the following four different software packages: ClinCheck^® Pro, Ortho Analyzer^®, SureSmile^®, and Ortho Insight 3D^®. Materials/Methods: Twenty-five adult patients treated with Invisalign^® at the Case School of Dental Medicine (CWRU)’s department of orthodontics were retrospectively collected. Initial stereolithography (STL) files were obtained and imported into three software packages. The teeth were moved in order to replicate the virtual setup from ClinCheck^® Pro. The final outcomes were exported from each software package. ClinCheck^® Pro STL files were used as the reference while STL files produced by the other software packages were used as the targets. Best fit superimpositions were performed using Geomagic^® Control X. Based on the results, tooth position was adjusted in the three software packages until the virtual setups from ClinCheck^® Pro were replicated. Once confirmed, the tables containing the tooth movements were compared. The number of aligners and number of attachments automatically generated from each of the software packages were also evaluated. Results: Extrusion/intrusion (p ≤ 0.0001) and translation buccal/lingual (p ≤ 0.0004) were significantly different among the software packages. ClinCheck^® Pro and SureSmile^® (p ≤ 0.000), SureSmile^® and Ortho Insight 3D^® (p ≤ 0.014), SureSmile^® and Ortho Analyzer^® (p ≤ 0.009), and Ortho Insight 3D^® and Ortho Analyzer^® (p ≤ 0.000) generated a significantly different number of maxillary aligners. The results varied slightly for mandibular aligners, with only ClinCheck^® Pro and Ortho Insight 3D^® (p ≤ 0.000), SureSmile^® and Ortho Insight 3D^® (p ≤ 0.000), and Ortho Insight 3D^® and Ortho Analyzer^® (p ≤ 0.000) exhibiting a significant difference. ClinCheck^® Pro and SureSmile^® (p ≤ 0.000) differed significantly in the number of attachments produced. Conclusions: There are statistically significant differences in extrusion/intrusion, translation buccal/lingual, the number of aligners, and the number of attachments when implementing the same virtual setup on different software packages. Clinicians may need to consider this when utilizing software programs for digital diagnosis and treatment planning.