Background: Temporary anchorage devices (TADs) are broadly used in orthodontic treatment. TADs must be placed accurately to avoid collision against tooth roots. To place miniscrews with a higher accuracy, a digitally designed surgical guide was proposed in previous studies. However, to our knowledge, there have been no articles that have assessed the minimal required length to achieve good drilling accuracy. The objective of the present study was to evaluate the accuracy of pre-drilling using computer-aided designed surgical guides with different lengths. Methods: A typodont model was scanned, and surgical guides of 3.0, 4.5, and 6.0 mm were designed. Duplicated typodonts and the surgical guides were printed with a 3D printer. Using these models and surgical guides, pre-drillings were performed. Freehand drilling was also conducted for the control. The drilled models were scanned with micro-computed tomography to evaluate the accuracy. Results: The mean errors at the tip of the drill were 0.44 mm, 0.61 mm, 0.41 mm, and 0.24 mm for the freehand drilling, and 3.0, 4.5, and 6.0 mm for the surgical guide, respectively. Conclusion: The results suggested that a longer surgical guide was recommended to achieve good insertion accuracy for a narrow interradicular space, and that 3.0 mm was enough when an error of 1.0 mm was acceptable for the insertion site.

Background: This study aimed to evaluate the effect of external force applied from mini-screws to the aligner during space closure in extraction cases, and to determine the optimal loading conditions to prevent lingual crown tipping of the incisor and mesial tipping of the molar using the finite element (FE) method. Methodology: A three-dimensional FE model of the maxillary dentition with extraction of first premolars was constructed, and three different loading conditions were designed. The aligner was activated for 0.25 mm of incisor retraction without using mini-screws, with application of 0, 100, 200, or 300 cN of distal force through mini-screws placed in the posterior region, or with application of 0, 100, 200, 300, or 400 cN of intrusive force through mini-screws placed in the anterior region, in addition to the application of 300 cN of distal force. Results: As the magnitude of distal force increased, the degree of mesial tipping of the first molar gradually decreased, becoming almost zero with nearly 300 cN of distal force. As the magnitude of intrusive force increased in addition to the application of 300 cN of distal force, the degree of lingual crown tipping of the central incisor gradually decreased, becoming almost zero with nearly 400 cN of intrusive force. Conclusion: Application of 300 cN of distal force to the aligner from mini-screws placed in the posterior region could completely prevent mesial tipping of the molar and anchorage loss during anterior retraction. Application of 400 cN of intrusive force from mini-screws placed in the anterior region could prevent lingual crown tipping of the incisor, thus providing better torque control for the incisors.

Background/Objectives: Accurate prediction of craniofacial growth is essential for establishing orthodontic diagnoses and planning treatment. However, the ultimate extent of jaw growth remains largely judged subjectively based on clinical experience. In this study, we developed a convolutional neural network (CNN) model to predict chronological age from lateral cephalograms and to investigate whether artificial intelligence (AI) can autonomously learn growth-related morphological features. We also reevaluated which anatomical regions are most informative for predicting growth. Methods: We retrospectively analyzed 2116 cephalograms from patients 5–30 years old with malocclusion. After excluding patients with craniofacial syndromes or systemic diseases, 2014 images were used for training and 102 for testing. The mean age of the training dataset was 19.51 years (standard deviation [SD]: 4.71), whereas that of the test dataset was 18.20 years (SD: 7.33). In addition to the entire cephalograms, five regional datasets were generated (mandible, maxilla, cervical vertebrae, frontal region, and cranial base). All images were resized to 256 × 256 pixels and trained with a ResNet50-based CNN. Performance was evaluated using mean absolute error (MAE), Pearson’s correlation coefficient (r), and coefficient of determination (R²). To assess growth-related learning, test data were divided into growth (5–19 years) and post-growth (20–30 years) groups, and age trends were analyzed using a sliding window approach with an 8-year window. Results: The model trained on entire cephalograms achieved high accuracy in the younger group (MAE 1.16 years, r 0.952, R² 0.884), but performance declined markedly in the older group. Among the regional models, accuracy was highest for the mandible, followed by the cervical vertebrae and maxilla. Conclusions: The CNN model predicted chronological age with high accuracy, particularly in patients <20 years old, and may have captured age-associated craniofacial features related to growth. Prediction was most accurate in the mandible and cervical vertebrae—regions clinically used to assess growth. As a proof of concept, this approach may provide a foundation for future studies of craniofacial growth prediction through transfer learning, although further validation is required.