American Journal of Orthodontics and Dentofacial Orthopedics最新文献

Introduction: Machine learning, a common artificial intelligence technology in medical image analysis, enables computers to learn statistical patterns from pairs of data and annotated labels. Supervised learning in machine learning allows the computer to predict how a specific anatomic structure should be segmented in new patients. This study aimed to develop and validate a deep learning algorithm that automatically creates 3-dimensional surface models of human teeth from a cone-beam computed tomography scan.

Methods: A multiresolution dataset, including 216 × 272 × 272, 512 × 512 × 512, and 576 × 768 × 768. Ground truth labels for teeth segmentation were generated. Random partitioning was applied to allocate 140 patients to the training set, 40 to the validation set, and 30 scans for testing and model performance evaluation. Different evaluation metrics were used for assessment.

Results: Our teeth identification model has achieved an accuracy of 87.92% ± 4.43% on the test set. The general (binary) teeth segmentation model achieved a notably higher accuracy, segmenting the teeth with 93.16% ± 1.18%.

Conclusions: The success of our model not only validates the efficacy of using artificial intelligence for dental imaging analysis but also sets a promising foundation for future advancements in automated and precise dental segmentation techniques.

Introduction: Distraction osteogenesis has been the preferred treatment modality for patients with hemifacial microsomia. Although an immediate improvement in facial asymmetry is noted at the completion of the procedure, long-term data regarding postdistraction stability is rare. In this study, a ≥12-year follow-up was conducted on patients who underwent distraction osteogenesis to examine the long-term stability of the surgical procedure. This study aimed to evaluate the cephalometric distraction relapse tendency after ≥12 years.

Methods: Three patients with hemifacial microsomia who underwent distraction osteogenesis were recalled, and their records were taken. Multiple measurements, such as mandibular length, ramus height, maxillary height, occlusal height, and chin position, were made to record the changes in the mandible and maxilla from posteroanterior and 45° lateral oblique cephalograms after ≥12 years.

Results: Mandibular length, ramus height, maxillary height, chin deviation, occlusal cant, and the interantegonial plane angle showed immediate improvements after distraction. After ≥12 years of distraction, the mandibular length, maxillary height, and occlusal height remained relatively stable, but the ramus height and chin deviation were unstable, resulting in an increase in facial asymmetry.

Conclusions: A combination of decreased growth and postsurgical relapse on the affected side contributes to the continuous worsening of facial asymmetry. Dentoalveolar remodeling contributed to even more facial asymmetry into adulthood. Thus, overcorrection was needed to reduce and overcome the degree of long-term facial asymmetry after growth completion.

Introduction: The objective of this study was to evaluate the short-term and long-term skeletal and airway changes associated with the use of headgear and to compare these changes to a group of untreated control subjects.

Methods: The sample included 2 Class II groups: a group treated with cervical headgear and a group of untreated control subjects, with 30 subjects in each group. Lateral cephalograms were taken at 3 time points: pretreatment (T1), posttreatment (T2), and long-term postretention (T3), and a single examiner performed skeletal and airway measurements. Paired samples t test was used to compare T1, T2, and T3 skeletal and airway measurements within the groups, and independent samples t test was used to compare treatment (T2 - T1), posttreatment (T3 - T2), and overall (T3 - T1) skeletal and airway changes in the treatment group compared with the control group.

Results: There was a significant decrease in the SNA (3.1°) and an increase in the SN-PP (1.5°) in the treatment group at T2 (P <0.001), which remained significant at T3 (P <0.05). In addition, there was a significant short-term increase in the mandibular plane angle and a decrease in SNB (P <0.05). Paired t tests showed no significant change in airway width within the treatment group (P >0.05). The independent samples t test showed no significant differences in any of the changes in airway variables between the groups (P >0.05).

Conclusions: The use of headgear did not result in any change in airway width, both short-term and long-term. A decrease in SNA and an increase in SN-PP were found with the use of the headgear, and these changes remained stable for up to 8 years posttreatment.