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.

Background: Cleidocranial dysplasia (CCD) is a rare and underdiagnosed congenital disorder in dentistry. The purpose of this study was to illustrate and quantify the maxillofacial bone abnormalities detected on panoramic radiographs from a relatively large retrospective case series and to provide a series of diagnostic references for dentists to indicate the presence of disease and help in making an early and accurate diagnosis. Methods: The dental panoramic radiographs of thirty CCD patients aged 11 to 45 years (18 males and 12 females) were examined retrospectively. The dentition states, including supernumerary teeth and impacted teeth, were recorded. Twelve quantified measurements were adopted to determine the abnormalities of maxillofacial bones, including the degree of the zygomatic arch downward bend, bicondylar breadth, ramal height, mandibular height, mandibular aspect ratio, mandibular body height, condylar height, coronoid height, distance between the coronoid process and the condyle, bigonial width, gonial angle and best-fit gonial circle diameter. The Wilcoxon rank-sum test was used to compare the findings of the CCD patients with those of their matched controls (n = 300). Results: Supernumerary teeth were detected in 27 patients (90.0%), and all 30 patients presented impacted teeth. Compared to the matched controls, the CCD patients had a significantly larger degree of zygomatic arch downward bend (ZAD), a larger diameter of the best-fit gonial circle (BGC), and a shorter distance between the coronoid process and the condyle (DCC) in panoramic radiographs (P < 0.001). According to the reference cutoff values established from the 5th or 95th percentile of the measurements in the control group, ZAD higher than 6.90 mm, DDC less than 22.37 mm and BGC higher than 52.41 mm were significantly associated with the CCD features identified. Other panoramic measurements were not significantly different between the two groups. Conclusions: Panoramic radiographs had great value in the diagnosis of CCD. In this study, we identified some dental and maxillofacial features on panoramic radiographs from a relatively large retrospective case series of CCD. A series of reliable quantitative indicators were provided for dentists that can indicate the presence of disease and improve the diagnostic specificity.

(1) Background: With the increasing aesthetic pursuit of facial features, the clinical use of Botulinum Toxin Type A (BoNT-A) injections for masseter hypertrophy has been on the rise. However, due to variations in masseter muscle structure and differences in clinicians’ injection techniques, blind injections may lack precision, potentially compromising treatment accuracy and increasing the risk of complications. (2) Objectives: The study aims to use ultrasonography to detail the deep inferior tendon (DIT) within the masseter muscle in a young Chinese cohort, refine its classification, analyze muscle belly thickness and variations across groups, and propose a customized ultrasound-guided BoNT-A injection protocol. (3) Methods: Ultrasound imaging was used to observe the bilateral masseter muscles at rest and during clenching. The features of the DIT were classified from these images, and the thickness of the masseter’s distinct bellies associated with the DIT types was measured in both states. (4) Results: The study cohort included 103 participants (27 male, 76 female), with 30 muscles in the normal masseter group and 176 muscles in the hypertrophy group. The DIT was categorized as Type A, B (subtypes B1, B2), and C. The distribution of these types was consistent across normal, hypertrophic, and gender groups, all following the same trend (B > A > C). In hypertrophy, Type B1 showed uniform thickness across masseter bellies, B2 presented with a thinner intermediate belly, and Type C had mainly superficial muscle enlargement. Changes in muscle thickness during clenching were noted but not statistically significant among different bellies. (5) Conclusions: The study evidences individual variation in the DIT, highlighting the importance of precise DIT classification for effective BoNT-A injections. A tailored ultrasound-guided BoNT-A injection strategy based on this classification may enhance safety and efficacy of the therapy.

We aimed to establish the characteristics and potential etiological risk factors of eruption disturbances in mandibular second molars (MM2). We retrospectively enrolled patients with eruption disturbances in MM2. A total of 143 MM2 with eruption disturbances from 112 patients (mean age 17.45 ± 6.35) were included in this study. Panoramic radiographs were employed to determine the risk factor, angulation type, impaction depth, tooth development stage, and associated pathology. The novel classification method of MM2 was based on impaction depth and angulation. Of 143 MM2, 137 and 6 were diagnosed with impaction and retention, respectively. Insufficient space was the most frequent risk factor for eruption disturbances. There were no significant differences between retention and impaction regarding sex, age, or side. The most frequent impaction type was Type I. The most frequent angulation of impacted MM2 was mesioangular. Impacted MM2 with shallower depth were more frequently associated with the presence of first molar undercut. Impaction types did not differ according to age, side, development stage, or distance from the MM1 distal surface to the anterior border of the ramus. Dentigerous cysts were associated with earlier MM2 development stages and greater MM2 depth. In conclusion, MM2 impaction types differed according to the risk factor, angulation type, MM1 undercut, and presence of cysts. Early MM2 development stage and greater MM2 depth were risk factors for MM2 eruption disturbances with cysts.