Comparison of AudaxCeph®'s fully automated cephalometric tracing technology to a semi-automated approach by human examiners.

OBJECTIVE: To compare the reliability of cephalometric landmark identification by an automated tracing software based on convolutional neural networks to human tracers. MATERIALS AND METHODS: Sixty cephalograms were traced by two board-certified orthodontists and AudaxCeph®'s artificial intelligence software. The following thirteen landmarks were identified in each tracing: Sella, Nasion, A point, B point, Porion, Menton, Pogonion, Orbitale, Gonion, Upper Central Incisor Incisal Edge (U1 Tip), Upper Central Incisor Root Apex (U1 apex), Lower Central Incisor Incisal Edge (L1 Tip), Lower Central Incisor Root Apex (L1 apex). An x-y axis was positioned in the bottom left corner of each cephalogram, and the x- and y-coordinates for the landmarks were exported into Excel. Distributions of landmarks (X, Y, radial distance) were compared using t-tests of equivalence with a 2mm equivalence bound. These compared the AI position to the two orthodontists - and the orthodontists' reliability by comparing equivalence against each other. RESULTS: There was no statistical difference between the orthodontists and AudaxCeph®'s automatic tracing software except for the x- and y-dimension of Porion and the y-dimension of L1 apex. The two orthodontists had good intra-examiner reliability with no statistical difference found when comparing them. CONCLUSION: AudaxCeph®'s automated cephalometric tracing software is a good adjunctive tool to use when diagnosing and treatment planning orthodontic cases.

Do composite resin polishing systems damage enamel?

Finishing and polishing of composite resin restorations may cause damage to the bordering enamel. Although many studies have investigated the effect of polish on restorative materials, few have quantified the effect on bordering enamel. The objective of this study was to compare enamel loss surrounding composite restorations after finishing and polishing sequences. The null hypothesis was that there would be no difference in enamel loss between different finishing and polishing sequences. Class V preparations on the buccal and lingual surfaces of 15 extracted human molars were restored with a composite resin and assigned to 1 of 2 finishing and polishing sequences, so that each tooth underwent both sequences (n = 15 per sequence). In sequence 1, a tungsten carbide finishing bur and aluminum oxide polishing discs were used; in sequence 2, a diamond finishing bur, aluminum oxide-impregnated finishing cup, and diamond-impregnated polishing cup were used. Tooth surfaces were scanned with an optical scanner after preparation, finishing, initial polishing, and final polishing. The finishing and polishing scans were aligned to the preparation scan using Cumulus software. The depth of enamel surface loss was calculated and statistically analyzed (α = 0.05; paired t test). Most enamel loss (mean [SD]) resulted from the finishing step with the tungsten carbide bur (51.8 [21.3] µm) or diamond bur (43.3 [12.6] µm). Each polishing step increased mean enamel loss by only a few microns. There was no statistically significant difference between the 2 finishing and polishing sequences. The majority of enamel damage during finishing and polishing of composite resin restorations resulted from the finishing burs. Little enamel was removed by either of the tested composite resin polishing systems.