Investigation of the esthetic perception of different canine parameters

Deep learning driven segmentation of maxillary impacted canine on cone beam computed tomography images

The process of creating virtual models of dentomaxillofacial structures through three-dimensional segmentation is a crucial component of most digital dental workflows. This process is typically performed using manual or semi-automated approaches, which can be time-consuming and subject to observer bias. The aim of this study was to train and assess the performance of a convolutional neural network (CNN)-based online cloud platform for automated segmentation of maxillary impacted canine on CBCT image. A total of 100 CBCT images with maxillary canine impactions were randomly allocated into two groups: a training set (n = 50) and a testing set (n = 50). The training set was used to train the CNN model and the testing set was employed to evaluate the model performance. Both tasks were performed on an online cloud-based platform, 'Virtual patient creator' (Relu, Leuven, Belgium). The performance was assessed using voxel- and surface-based comparison between automated and semi-automated ground truth segmentations. In addition, the time required for segmentation was also calculated. The automated tool showed high performance for segmenting impacted canines with a dice similarity coefficient of 0.99 ± 0.02. Moreover, it was 24 times faster than semi-automated approach. The proposed CNN model achieved fast, consistent, and precise segmentation of maxillary impacted canines.

Three-dimensional evaluation of social smile asymmetry in patients with unilateral impacted maxillary canine: a 3D stereophotogrammetry study

OBJECTIVE

This study aimed to evaluate social smile asymmetry in patients with unilateral impacted maxillary canine on 3D stereophotogrammetric images.

MATERIAL AND METHODS

The 3D social smile images of participants with unilateral impacted maxillary canine (n:20) and without impaction as a control group (n:20) were included. The images were recorded with a hand-held 3D stereophotogrammetry device (Fuel3D® Scanify®) and Geomagic Essentials 2 reverse engineering software were used for analyses. After the orientation process of the 3D records, the tissues around the smile area were divided into five morphological regions: cheek, upper lip lateral and medial, and lower lip lateral and medial. The deviation margins in the negative and positive directions for the 95% mesh rate and the total percentages of meshes between - 0.5- and + 0.5-mm deviations were calculated. ICC, paired samples t test, independent samples t test, and the Mann-Whitney U test were used for statistical analyses.

RESULTS

In individuals with impacted canine, the amount of maximum positive deviation in the upper lip medial was 5.64 mm ± 1.46 and maximum negative deviation was - 4.6 mm ± 1.17. In the control group, mean of deviation limits for all parameters was less than 1.19 mm ± 2.62, while in individuals with unilateral impacted maxillary canine, the maximum value was 8.34 mm ± 2.23. The mesh percentage between - 0.5 and 0.5-mm deviations was over 95% in all morphological areas in the control group, while in the impacted canine group, the number of meshes within the specified deviation limits was less than 95%.

CONCLUSION

Individuals with unilateral impacted maxillary canine exhibit greater asymmetry in social smile compared to the control group, with the asymmetry being most prominent near the corners of the mouth and cheeks.

CLINICAL RELEVANCE

Amount of asymmetry was higher in impaction group compared to the control group in social smile. The quantification of a possible smile asymmetry due to the impacted canine is crucial for the diagnosis and treatment planning of orthodontic and/or orthognathic cases for ideal aesthetic results. Hence, smile asymmetry should not be overlooked and should be considered in diagnosis and treatment planning.