Evaluation of smile aesthetics with artificial intelligence algorithms developed with deep learning method over orthodontic photographs

Aim: The aim of this study is to investigate the success of anatomical point detection using a special artificial intelligence algorithm on facial smile images. Material and Method: The dataset of our study is to create anatomical points marked using a special artificial intelligence algorithm on the records obtained from the facial smile images taken before orthodontic treatment of 1000 patients. Labeling of points on the images was done using CranioCatch labeling software (CranioCatch, Eskişehir, Turkey). The training of the artificial intelligence model was carried out using 300 Epochs with the CNN-based deep learning method applied to PyTorch. Results: In the artificial intelligence model trained in the study, the highest SDR value was found at the Labiale superius point. The lowest SDR value was observed at Menton, Nasion and Pogonion points. The SDR value showed a success rate of over 80%, except for 6 points in the 2 mm interval. Conclusion: Our study is very important for the development of deep learning-based smile analysis systems to be made in the future. It is thought that these systems will play a role as a decision support mechanism by saving time for physicians in their clinical routine. At the same time, it is estimated that during the determination of anatomical points, it will be very helpful in minimizing the differences between observers and inconsistencies that may occur in the evaluations of the observers at different times.