Search

Accurately segmenting teeth and identifying the corresponding anatomical landmarks on dental mesh models are essential in computer-aided orthodontic treatment. Manually performing these two tasks is time-consuming, tedious, and, more importantly, highly dependent on orthodontists experiences due to the abnormality and large-scale variance of patients teeth. Some machine learning-based methods have been designed and applied in the orthodontic field to automatically segment dental meshes (e.g., intraoral scans). In contrast, the number of studies on tooth landmark localization is still limited. This paper proposes a two-stage framework based on mesh deep learning (called TS-MDL) for joint tooth labeling and landmark identification on raw intraoral scans. Our TS-MDL first adopts an end-to-end iMeshSegNet method (i.e., a variant of the existing MeshSegNet with both improved accuracy and efficiency) to label each tooth on the downsampled scan. Guided by the segmentation outputs, our TS-MDL further selects each tooths region of interest (ROI) on the original mesh to construct a light-weight variant of the pioneering PointNet (i.e., PointNet-Reg) for regressing the corresponding landmark heatmaps. Our TS-MDL was evaluated on a real-clinical dataset, showing promising segmentation and localization performance. Specifically, iMeshSegNet in the first stage of TS-MDL reached an averaged Dice similarity coefficient (DSC) at 0.964±0.054 , significantly outperforming the original MeshSegNet. In the second stage, PointNet-Reg achieved a mean absolute error (MAE) of 0.597±0.761 mm in distances between the prediction and ground truth for 66 landmarks, which is superior compared with other networks for landmark detection. All these results suggest the potential usage of our TS-MDL in orthodontics.

The objective of this study was to explore the feasibility of current 3D reconstruction in assessing the position of maxillary impacted canines from 2D panoramic X-rays. A dataset was created using pre-treatment CBCT data from a total of 123 patients, comprising 74 patients with impacted canines and 49 patients without impacted canines. From all 74 subjects, we generated a dataset containing paired 2D panoramic X-rays and pseudo-3D images. This pseudo-3D image contained information about the location of the impacted canine in the buccal/lingual, mesial/distal, and apical/coronal positions. These data were utilized to train a deep-learning reconstruction algorithm, a generative AI. The location of the crown of the maxillary impacted canine was determined based on the output of the algorithm. The reconstruction was evaluated using the structure similarity index measure (SSIM) as a metric to indicate the quality of the reconstruction. The prediction of the impacted canine's location was assessed in both the mesiodistal and buccolingual directions. The reconstruction algorithm predicts the position of the impacted canine in the buccal, middle, or lingual position with 41% accuracy, while the mesial and distal positions are predicted with 55% accuracy. The mean SSIM for the output is 0.71, with a range of 0.63 to 0.84. Our study represents the first application of AI reconstruction output for multidisciplinary care involving orthodontists, periodontists, and maxillofacial surgeons in diagnosing and treating maxillary impacted canines. Further development of deep-learning algorithms is necessary to enhance the robustness of dental reconstruction applications. [ABSTRACT FROM AUTHOR]

To identify predictors regarding the type and severity of malocclusion that affect total Invisalign treatment duration based on an intraoral digital scan. The subjects of this retrospective clinical cohort were 116 patients treated with Invisalign. A deep learning method was used for automated tooth segmentation and landmark identification of the initial and final digital models. The changes in the six degrees of freedom (DOF), representing types of malalignment, were measured. Linear regression was performed to find the contributing factors associated with treatment time. In addition, the Peer Assessment Rating (PAR) score and a composite score combining 6 DOF were correlated separately to the treatment time. The number of trays differed between sexes (P =.0015). The absolute maximum torque was marginally associated with the total number of trays (P =.0518), while the rest of the orthodontic tooth movement showed no correlation. The composite score showed a higher correlation with the total number of trays (P =.0045) than did individual tooth movement. Pretreatment upper and lower anterior segment PAR scores were positively associated with the treatment time (P <.001). There is not enough evidence to conclude that certain types of tooth movement affect the total aligner treatment time. A composite score seems to be a better predictor for total treatment time than do individual malalignment factors in aligner treatment. Upper and lower anterior malalignment factors have a significant effect on the treatment duration. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to quantify the 3D asymmetry of the maxilla in patients with unilateral cleft lip and palate (UCP) and investigate the defect factors responsible for the variability of the maxilla on the cleft side using a deep-learning-based CBCT image segmentation protocol.Setting and Sample Population: Cone beam computed tomography (CBCT) images of 60 patients with UCP were acquired. The samples in this study consisted of 39 males and 21 females, with a mean age of 11.52 years (SD = 3.27 years; range of 8-18 years).Materials and Methods: The deep-learning-based protocol was used to segment the maxilla and defect initially, followed by manual refinement. Paired t-tests were performed to characterize the maxillary asymmetry. A multiple linear regression was carried out to investigate the relationship between the defect parameters and those of the cleft side of the maxilla.Results: The cleft side of the maxilla demonstrated a significant decrease in maxillary volume and length as well as alveolar length, anterior width, posterior width, anterior height and posterior height. A significant increase in maxillary anterior width was demonstrated on the cleft side of the maxilla. There was a close relationship between the defect parameters and those of the cleft side of the maxilla.Conclusions: Based on the 3D volumetric segmentations, significant hypoplasia of the maxilla on the cleft side existed in the pyriform aperture and alveolar crest area near the defect. The defect structures appeared to contribute to the variability of the maxilla on the cleft side. [ABSTRACT FROM AUTHOR]

To determine the accuracy of three-dimensional (3D) printed models fabricated from cone-beam computed tomography (CBCT) scans of human mandibular dry skulls in comparison with models derived from intraoral scanner (IOS) data. Six human mandibular dry skulls were scanned by IOS and CBCT. Digital models (DMs) constructed from the IOS and CBCT data were fabricated physically using a 3D printer. The width and thickness of individual teeth and intercanine and molar widths were measured using a digital caliper. The accuracy of the DMs was compared between IOS and CBCT. Paired t-tests were used for intergroup comparisons. All intraclass correlation coefficient values for the three measurements (mesial-distal, buccal-lingual, width) exceeded 0.9. For the mandibular teeth, there were significant discrepancies in model accuracy between the IOS (average discrepancies of 0.18 ± 0.08 mm and 0.16 ± 0.12 mm for width and thickness, respectively) and CBCT (0.28 ± 0.07 mm for width, 0.37 ± 0.2 mm for thickness; P <.01). Intercanine (P =.38) and molar widths (P =.41) showed no significant difference between groups. There was a statistically significant difference in the accuracy of DMs obtained from CBCT and IOS; however, this did not seem to result in any important clinical difference. CBCT could be routinely used as an orthodontic diagnostic tool and for appliance construction. [ABSTRACT FROM AUTHOR]

To compare the normal eruption pattern and angulation in impacted maxillary canines using panoramic radiographs to predict maxillary canine impaction. Patients aged 6 to 15 years were classified into the normal eruption group (n = 229) and the impaction group (n = 191). At least two panoramic radiographs were taken in the normal eruption group during the eruption process of the maxillary canine. The growth pattern of the maxillary canine was analyzed using an XY coordinate system, with the tip of the maxillary lateral incisor as the origin and the tooth's long axis as the Y-axis and measurement of the relative position of the crown tip and angulation of the maxillary canine. The crown tips of normally erupted maxillary canines were intensively distributed along the distal surface of the maxillary lateral incisor, while those of impacted canines were widely distributed. The angulations of the normally erupted canines increased as eruption increased along the lateral incisor and then decreased at the cervical point of the lateral incisor. The angulations of the impacted canines were scattered, with no uniform pattern. While using the normal eruption path of the maxillary canine and the pattern of change in angulation based on the distal surface of the maxillary lateral incisor, early intervention or regular follow-up is needed to prevent maxillary canine impaction. [ABSTRACT FROM AUTHOR]

Objective: To examine the robustness of the published machine learning models in the prediction of extraction vs non‐extraction for a diverse US sample population seen by multiple providers. Setting and Sample Population: Diverse group of 838 patients (208 extraction, 630 non‐extraction) were consecutively enrolled. Materials and Methods: Two sets of input features (117 and 22) including clinical and cephalometric variables were identified based on previous studies. Random forest (RF) and multilayer perception (MLP) models were trained using these feature sets on the sample population and evaluated using measures including accuracy (ACC) and balanced accuracy (BA). A technique to identify incongruent data was used to explore underlying characteristics of the data set and split all samples into 2 groups (G1 and G2) for further model training. Results: Performance of the models (75%‐79% ACC and 72%‐76% BA) on the total sample population was lower than in previous research. Models were retrained and evaluated using G1 and G2 separately, and individual group MLP models yielded improved accuracy for G1 (96% ACC and 94% BA) and G2 (88% ACC and 85% BA). RF feature ranking showed differences between top features for G1 (maxillary crowding, mandibular crowding and L1‐NB) and G2 (age, mandibular crowding and lower lip to E‐plane). Conclusions: An incongruent data pattern exists in a consecutively enrolled patient population. Future work with incongruent data segregation and advanced artificial intelligence algorithms is needed to improve the generalization ability to make it ready to support clinical decision‐making. [ABSTRACT FROM AUTHOR]