This study aimed to test the accuracy of the 3-dimensional (3D) digital dental models generated by the Dental Monitoring (DM) smartphone application in both photograph and video modes over successive DM examinations in comparison with 3D digital dental models generated by the iTero Element intraoral scanner. Methods: Ten typodonts with setups of class I malocclusion and comparable severity of anterior crowding were used in the study. iTero Element scans along with DM examination in photograph and video modes were performed before tooth movement and after each set of 10 Invisalign aligners for each typodont. Stereolithography (STL) files generated from the DM examinations in photograph and video modes were superimposed with the STL files from the iTero scans using GOM Inspect software to determine the accuracy of both photograph and video modes of DM technology. Results: No clinically significant differences, according to the American Board of Orthodontics-determined standards, were found. Mean global deviations for the maxillary arch ranged from 0.00149 to 0.02756 mm in photograph mode and from 0.0148 to 0.0256 mm in video mode. Mean global deviations for the mandibular arch ranged from 0.0164 to 0.0275 mm in photograph mode and from 0.0150 to 0.0264 mm in video mode. Statistically significant differences were found between the 3D models generated by the iTero and the DM application in photograph and video modes over successive DM examinations. Conclusions: 3D digital dental models generated by the DM smartphone application in photograph and video modes are accurate enough to be used for clinical applications.
Introduction
We aim to apply deep learning to achieve fully automated detection and classification of the Cervical Vertebrae Maturation (CVM) stages. We propose an innovative custom-designed deep Convolutional Neural Network (CNN) with a built-in set of novel directional filters that highlight the edges of the Cervical Vertebrae in X-ray images.
Methods
A total of 1018 Cephalometric radiographs were labeled and classified according to the Cervical Vertebrae Maturation (CVM) stages. The images were cropped to extract the cervical vertebrae using an Aggregate Channel Features (ACF) object detector. The resulting images were used to train four different Deep Learning (DL) models: our proposed CNN, MobileNetV2, ResNet101, and Xception, together with a set of tunable directional edge enhancers. When using MobileNetV2, ResNet101 and Xception, data augmentation is adopted to allow adequate network complexity while avoiding overfitting. The performance of our CNN model was compared with that of MobileNetV2, ResNet101 and Xception with and without the use of directional filters. For validation and performance assessment, k-fold cross-validation, ROC curves, and p-values were used.
Results
The proposed innovative model that uses a CNN preceded with a layer of tunable directional filters achieved a validation accuracy of 84.63%84.63% in CVM stage classification into five classes, exceeding the accuracy achieved with the other DL models investigated. MobileNetV2, ResNet101 and Xception used with directional filters attained accuracies of 78.54%, 74.10%, and 80.86%, respectively. The custom-designed CNN method also achieves 75.11% in six-class CVM stage classification. The effectiveness of the directional filters is reflected in the improved performance attained in the results. If the custom-designed CNN is used without the directional filters, the test accuracy decreases to 80.75%. In the Xception model without the directional filters, the testing accuracy drops slightly to 79.42% in the five-class CVM stage classification.
Conclusion
The proposed model of a custom-designed CNN together with the tunable Directional Filters (CNNDF) is observed to provide higher accuracy than the commonly used pre-trained network models that we investigated in the fully automated determination of the CVM stages.
Objective
The extent to which the modelling behaviour of the anterior alveolus limits tooth movement remains unclear. Will the labial and lingual cortical plates model as incisors retract, or will they remain unchanged, therefore limiting the extent of possible tooth movement?
Setting and Sample population.
Pre‐ and post‐treatment lateral cephalometric radiographs of 29 bimaxillary protrusive patients of South Korean descent were examined. Treatment consisted of two premolar extractions in one or both arches with en masse retraction of the incisors using miniscrew anchorage.
Materials and Methods
Pre‐ and post‐treatment measurements of both tooth and cortical plate position were made at various increments along the length of the root and then compared using paired t tests.
Results
Despite the use of miniscrew anchorage, the incisors were retracted by controlled tipping. The labial cortical plates in both arches modelled to follow tooth movement. Following retraction of the incisors in the maxilla, the incisor root approached the lingual cortical plate, which remained unchanged. In the mandible, the lingual cortical plate position was unchanged except at the level closest to the cementoenamel junction.
Conclusions
The maxillary and mandibular lingual cortical plates did not model to follow the incisor movement while the labial cortical plates did. These findings suggest that lingual cortical plates may act as limitations to planned orthodontic tooth movement.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.