Background: The purpose was to determine the predictability of tooth movements through clear aligner among premolar extraction patients and to explore the effects of various factors on tooth movements. Methods: A total of 31 extraction patients (10 males and 20 females; age 14–44) receiving clear aligner treatment (Invisalign) were enrolled in this study. The actual post-treatment models and pre-treatment models were superimposed using the palatal area as a reference and registered with virtual post-treatment models. A paired t test was used to compare the differences between actual and designed tooth movements of maxillary first molars, canines, and central incisors. A multivariate linear mixed model was performed to examine the influence of variables on actual tooth movements. Results: Compared to the designed tooth movements, the following undesirable tooth movements occurred: mesial movement (2.2 mm), mesial tipping (5.4°), and intrusion (0.45 mm) of first molars; distal tipping (11.0°), lingual tipping (4.4°), and distal rotation of canines (4.9°); lingual tipping (10.6°) and extrusion (1.5 mm) of incisors. Age, crowding, mini-implant, overbite, and attachments have differential effects on actual tooth movements. Moreover, vertical rectangular attachments on canines are beneficial in achieving more predictable canine and incisor tooth movements over optimized attachments. Lingual tipping and extrusion of incisors were significantly influenced by the interaction effects between incisor power ridge and different canine attachments (p < 0.05). Conclusions: Incisors, canines, and first molars are subject to unwanted tooth movements with clear aligners among premolar extraction patients. Age, crowding, mini-implant, overbite, and attachments influence actual tooth movements. Moreover, vertical rectangular attachments on canines are beneficial in achieving more predictable incisor tooth movements over optimized canine attachments.

Objectives: To analyze the biomechanical system of anterior retraction with clear aligner therapy (CAT) with and without an anterior mini-screw and elastics. Materials and Methods: Models including a maxillary dentition (without first premolars), maxilla, periodontal ligaments (PDLs), attachments, and aligners were constructed and imported to finite element software. Three model groups were created: (1) control (CAT alone), (2) labial elastics (CAT with elastics between the anterior mini-screw and buttons on central incisors), and (3) linguoincisal elastics (CAT with elastics between the anterior mini-screw and precision cuts on the lingual sides of the aligner). Elastic forces (0–300 g, in 50 g increments) were applied. Results: CAT alone caused lingual tipping and extrusion of the incisors. Labial elastics caused palatal root torquing and intrusion and mesial tipping of the central incisors, while linguoincisal elastics produced palatal root torquing and intrusion of both central and lateral incisors. Second premolars were intruded in all three groups, with less intrusion in the linguoincisal elastics group. For the control group, stress was concentrated on both labial and lingual root surfaces, alveolar ridge, and cervical and apical PDLs. Stress was more concentrated in the labial elastics group and less concentrated in the linguoincisal elastics group. Conclusions: CAT produced lingual tipping and extrusion of incisors during anterior retraction. Anterior mini-screws and elastics can achieve incisor intrusion and palatal root torquing. Linguoincisal elastics are superior to labial elastics with a lower likelihood of buccal open bite. Root resorption and alveolar defects may occur in CAT, more likely for labial elastics and less likely for linguoincisal elastics.

Background: Cervical vertebral maturation (CVM) is widely used to evaluate growth potential in the field of orthodontics. This study is aimed to develop an artificial intelligence (AI) system to automatically determine the CVM status and evaluate the AI performance. Methods: A total of 1080 cephalometric radiographs, with the age of patients ranging from 6 to 22 years old, were included in the dataset (980 in training dataset and 100 in testing dataset). Two reference points and thirteen anatomical points were labelled and the cervical vertebral maturation staging (CS) was assessed by human examiners as gold standard. A convolutional neural network (CNN) model was built to train on 980 images and to test on 100 images. Statistical analysis was conducted to detect labelling differences between AI and human examiners, AI performance was also evaluated. Results: The mean labelling error between human examiners was 0.48 ± 0.12 mm. The mean labelling error between AI and human examiners was 0.36 ± 0.09 mm. In general, the agreement between AI results and the gold standard was good, with the intraclass correlation coefficient (ICC) value being up to 98%. Moreover, the accuracy of CVM staging was 71%. In terms of F1 score, CS6 stage (85%) ranked the highest accuracy. Conclusions: In this study, AI showed a good agreement with human examiners, being a useful and reliable tool in assessing the cervical vertebral maturation.