3D superimposition of dental casts based on coloured landmark detection using combined computer vision and 3D computer graphics techniques

The aim of this study was to evaluate the validity and reliability of three-dimensional (3D) landmark-based palatal superimposition of digital dental models using the customized software Ortho Mechanics Sequential Analyzer (OMSA) revised by the addition of a computer vision algorithm. The sample consisted of pre- and post-treatment digital maxillary dental models of 20 orthodontic cases. For each case, the pre- and post-treatment digital models were superimposed using colour detection capabilities of a computer vision algorithm added to OMSA. The same set of parameters was measured on the superimposed 3D data by the two software versions for comparison. Agreement in the superimposition outcomes among the two superimposition methods was evaluated with Dahlberg error (DE), intraclass correlation coefficients (ICCs) using two-way ANOVA mixed model for absolute agreement and Bland-Altman agreement limits (LOA). Repeatability was excellent for all variables (all ICCs over 0.99 with the lower 95% confidence limit >= 0.95). The Dahlberg error (DE) ranged from 0.14 mm to 0.36 mm. The absolute error did not exceed 0.5 mm for any variable. The results indicate that OMSA with computer vision algorithms offers a valid and reliable tool for 3D landmark-based digital dental model superimposition using colour detection of three reference points marked along the mid-palatal raphe.