Accurate detection of cephalometric landmarks is crucial for orthodontic diagnosis and treatment planning. Current landmark detection methods are mainly divided into heatmap-based and regression-based approaches. However, these methods often rely on parallel computation of multiple models to improve accuracy, significantly increasing the complexity of training and deployment. This paper presented a novel regression method that can simultaneously detect all cephalometric landmarks in high-resolution X-ray images. By leveraging the encoder module of Transformer, a dual-encoder model was designed to achieve coarse-to-fine localization of cephalometric landmarks. The entire model consisted of three main components: a feature extraction module, a reference encoder module, and a fine-tuning encoder module, responsible for feature extraction and fusion of X-ray images, coarse localization of cephalometric landmarks, and fine localization of landmarks, respectively. The model was fully end-to-end differentiable and could learn the intercorrelation relationships between cephalometric landmarks. Experimental results showed that the successful detection rate (SDR) of our algorithm was superior to other existing methods. It attained the highest 2 mm SDR of 89.51% on test set 1 of the ISBI2015 dataset and 90.68% on the test set of the ISBI2023 dataset. Meanwhile, it reduces memory consumption and enhances the model's popularity and applicability, providing more reliable technical support for orthodontic diagnosis and treatment plan formulation.
Cephalometry/methods* ; Humans ; Algorithms ; Anatomic Landmarks/diagnostic imaging* ; Image Processing, Computer-Assisted/methods* ; X-Rays

OBJECTIVE: To establish a similarity measurement model for patients with dentofacial deformity based on 3D craniofacial features and to validate the similarity results with quantifying subjective expert scoring. METHODS: In the study, 52 cases of patients with skeletal Class Ⅲ malocclusions who underwent bimaxillary surgery and preoperative orthodontic treatment at Peking University School and Hospital of Stomatology from January 2020 to December 2022, including 26 males and 26 females, were selected and divided into 2 groups by sex. One patient in each group was randomly selected as a reference sample, and the others were set as test samples. Three senior surgeons rated the similarity scores between the test samples and the reference sample. Similarity scores ranged from 1 to 10, where 1 was completely different, and 10 was exactly the same. Scores larger than 7.5 was considered as clinically similar. Preoperative cone beam computed tomography (CBCT) and 3D facial images of the patients were collected. The three-dimensional hard and soft tissue features, including distances, angles and 3D point cloud features were extracted. The similarity measurement model was then established to fit with the experts' similarity scoring by feature selection algorithm and linear regression model. To verify the reliability of the model, 14 new patients were selected and input to similarity measurement model for finding similar cases. The similarity scoring of these similar cases were rated by experts, and used to evaluate the reliability of the model. RESULTS: The similarity metric models indicated that the features of the middle and lower craniofacial features were the main features to influence the craniofacial similarity. The main features that were related to the expert' s similarity scoring included distance of anterior nasal spine-menton (ANS-Me), distance of right upper canion point-Frankfurt horizontal plane (U3RH), distance of left superior point of the condyle-left gonion (CoL-GoL), distance of left gonion-menton (CoL-Me), distance of pogonion-midsagittal plane (Pog-MSP), distance of right alar base-left alar base (AlR-AlL), angle of pronasale-soft tissue pogonion-labrale inferius (Pn-Pog' -Li), distance of trichion-right tragus (Tri-TraR), distance of left exocanthion-left alar base (ExL-AlL), lower 1/3 of skeletal face, middle and lower 2/3 of skeletal face and upper lip region of soft tissue. Fourteen new patients were chosen to evaluate the model. The similar cases selected by the model had an average experts' similarity scoring of 7.627± 0.711, which was not significantly different with 7.5. CONCLUSION The similarity measurement model established by this model could find the similar cases which highly matched experts' subjective similarity scoring. The study could be further used for similar cases retrieval in skeletal Ⅲ malocclusion patients.
Humans ; Male ; Female ; Imaging, Three-Dimensional/methods* ; Cone-Beam Computed Tomography ; Malocclusion, Angle Class III/surgery* ; Orthognathic Surgical Procedures/methods* ; Face/anatomy & histology* ; Cephalometry/methods* ; Adult ; Adolescent ; Dentofacial Deformities/surgery* ; Young Adult

OBJECTIVE: To propose a new protocol for personalized mandibular reconstruction assisted by three-dimensional (3D) retrieval model based on fully connected neural network (FCNN) and a database of mandibles, and to verify clinical feasibility of the protocol. METHODS: A database of mandibles of 300 normal northern Chinese Han people was established. On the basis of cephalometry, the mandible landmarks with good stability were further screened. Mandibular landmarks were selected and geometric features of the mandible were extracted. A 3D retrieval algorithm was developed, which could retrieve the mandible most similar to a given mandible from the database. A FCNN was built to train the algorithm to improve accuracy of the 3D retrieval model. Using Geomagic Control 2014 software, matching accuracy of the 3D retrieval model was based on aforementioned mandible database and algorithm. From December 2019 to March 2021, a total of 5 patients underwent personalized mandibular reconstruction assisted by a 3D retrieval model based on mandible database and FCNN in the Department of Oral and Maxillofacial Surgery, Peking University School and Hospital of Stomatology. The most similar mandible was retrieved from mandible database through 3D retrieval algorithm. It was used to restore the premorbid morphology of defect area and guide mandibular reconstruction. For the 5 patients, mandible was reconstructed with iliac flap. Virtual surgical plan was transformed using individual surgical guides. RESULTS: Through screening, mandibular landmarks with high reproducibility and stability were identified and composed of mandibular landmarker protocols. After training, the average deviation between most similar mandible retrieved from the 300-case mandible database through 3D retrieval model based on FCNN and given mandible was (1.77±0.44) mm. And the root-mean-square deviation between the most similar mandible retrieved from the database and given mandible was (2.58±0.86) mm. The mandibular reconstruction surgery was successful in all the 5 patients. Their facial symmetry and occlusion were restored. All the patients were satisfied with postoperative appearance. The mean deviation between postoperative mandible and preoperative design was (0.98±0.17) mm. The area with a deviation ≤1 mm accounted for 61.34%±14. 13%, ≤2 mm accounted for 83.82%±7.35%, and ≤3 mm accounted for 93.94%± 2.87%. CONCLUSION The personalized mandibular reconstruction assisted by 3D retrieval model based on the 300-case mandible database and FCNN is feasible clinically.
Humans ; Neural Networks, Computer ; Mandibular Reconstruction/methods* ; Mandible/diagnostic imaging* ; Imaging, Three-Dimensional/methods* ; Adult ; Databases, Factual ; Female ; Male ; Algorithms ; Middle Aged ; Cephalometry

OBJECTIVE: To compare the aesthetic effects of anterior maxilla clockwise rotation combined with segmental Le Fort Ⅰ osteotomy and whole maxilla clockwise rotation on improving paranasal concavity in patients with Class Ⅲ maxillofacial deformity. METHODS: A non-randomized controlled trial was designed, and 21 patients diagnosed with skeletal Class Ⅲ maxillofacial deformity were included. In the study, 11 patients in the test group were treated by segmental Le Fort Ⅰ osteotomy combined with anterior maxilla clockwise rotation, and 10 patients in the control group were treated by whole maxilla clockwise rotation. The CBCT and 3D photography of preoperative (T0), 2 weeks postoperative (T1), and 6 months postoperative (T2) were collected respectively, and the three-dimensional cephalometry was carried out. The differences of specific parameters between the two groups were compared by independent sample t-test, including saggital displacement of the cheek mass point (CK) and subalare point (SA), nasolabial angle, occlusal plane angle and labial inclination angle of the upper incisor. RESULTS: There were no significant differences of the parameters on T0 between the two groups. The average sagittal displacement of the upper incisors of the test group was (-0.71±1.67) mm and smaller than that of control group [(2.26±1.68) mm], t=-4.052, P < 0.05. The average angle of the occlusal plane clockwise rotation of the test group was 1.46°±2.38° and smaller than that of the control group (4.31°±1.83°), t=-3.047, P < 0.05. The angle of anterior maxilla clockwise rotation was 11.73°±2.81° during the surgery. The average saggital displacement of the paranasal soft tissue landmarks of the test group from T0 to T2 was larger than that of the control group [CK point, (4.96±1.18) mm vs. (2.01± 1.50) mm, P < 0.05;SA point, (5.19±1.17) mm vs. (2.69±1.45) mm, P < 0.05]. The labial inclination angle of the upper incisor of the test group was 112.15°±5.40° in T2 and significantly smaller than that of the control group (122.38°±8.83°), t=-3.237, P < 0.05. The nasolabial angle of the test group was 106.54°±12.82° in T2 and significantly larger than that of the control group (93.90°±12.46°), t=2.288, P < 0.05. CONCLUSION Compared with whole maxilla clockwise rotation, anterior maxilla clockwise rotation combined with segmental Le Fort Ⅰ osteotomy can increase the saggital displacement of the paranasal soft tissue, correct labial inclination of the upper incisors and the acute naso-labial angle and better improve the paranasal aesthetic defects in patients with Class Ⅲ maxillofacial deformity with less changing on the saggital orientation of the upper incisors and the occlusal plane angle.
Humans ; Maxilla/surgery* ; Female ; Male ; Osteotomy, Le Fort/methods* ; Malocclusion, Angle Class III/surgery* ; Adult ; Cephalometry ; Young Adult ; Rotation ; Adolescent

Protrusive facial deformities, characterized by the forward displacement of the teeth and/or jaws beyond the normal range, affect a considerable portion of the population. The manifestations and morphological mechanisms of protrusive facial deformities are complex and diverse, requiring orthodontists to possess a high level of theoretical knowledge and practical experience in the relevant orthodontic field. To further optimize the correction of protrusive facial deformities, this consensus proposes that the morphological mechanisms and diagnosis of protrusive facial deformities should be analyzed and judged from multiple dimensions and factors to accurately formulate treatment plans. It emphasizes the use of orthodontic strategies, including jaw growth modification, tooth extraction or non-extraction for anterior teeth retraction, and maxillofacial vertical control. These strategies aim to reduce anterior teeth and lip protrusion, increase chin prominence, harmonize nasolabial and chin-lip relationships, and improve the facial profile of patients with protrusive facial deformities. For severe skeletal protrusive facial deformities, orthodontic-orthognathic combined treatment may be suggested. This consensus summarizes the theoretical knowledge and clinical experience of numerous renowned oral experts nationwide, offering reference strategies for the correction of protrusive facial deformities.
Humans ; Orthodontics, Corrective/methods* ; Consensus ; Malocclusion/therapy* ; Patient Care Planning ; Cephalometry

OBJECTIVES: This study aims to compare the effects of two orthodontic treatment modalities for skeletal class Ⅲ malocclusion on specific changes in airway volume, morphology, palatal angle, mandibular rotation, and bone displacement. Results provide scientific evidence for the selection of orthodontic treatment plans and reduce the risk of developing obstructive sleep apnea hypopnea syndrome (OSAHS). METHODS: Thirty-six patients diagnosed with skeletal class Ⅲ malocclusion at the Department of Orthodontics, the Affiliated Stomatological Hospital of Nanjing Medical University from September 2018 to December 2023 were divided into two groups: orthodontic-orthognathic treatment group (18 patients) and camouflage orthodontic treatment group (18 patients). Changes in airway volume, cross-sectional area, palatal angle, mandibular, and tongue positions were observed through pre- and post-operative cone beam computed tomography and 3D cephalometric measurements. RESULTS: In the camouflage orthodontic treatment group, nasopharyngeal volume and oropharyngeal volume statistically increased after treatment (P<0.05). In the orthodontic-orthognathic treatment group, changes in nasopharyngeal volume, nasopharyngeal airway, distance from posterior tongue to pharyngeal wall, palatal angle, mandibular rotation, and hyoid bone displacement were statistically significant after surgery (P<0.05). In the comparison between the two groups after treatment, changes in the distance from posterior tongue to pharyngeal wall, palatal angle, and distance from hyoid bone to sella turcica point were statistically significant (P<0.05). CONCLUSIONS Patients in the orthodontic-orthognathic treatment group showed significantly greater changes in oropharyngeal cross-sectional area, palate angle, and tongue position compared with patients in the camouflage orthodontic treatment group. As individuals susceptible to OSAHS often exhibit mandibular retrusion and decreased minimum airway cross-sectional area, special attention should be paid to airway morphology changes when adopting orthodontic-orthognathic treatment to avoid adverse consequences.
Humans ; Hyoid Bone/diagnostic imaging* ; Malocclusion, Angle Class III/therapy* ; Male ; Female ; Cone-Beam Computed Tomography ; Cephalometry ; Orthodontics, Corrective/methods* ; Adult ; Mandible ; Pharynx/diagnostic imaging* ; Sleep Apnea, Obstructive/etiology* ; Orthognathic Surgical Procedures

OBJECTIVES: The aim of this study was to compare the anterior and posterior occlusal plane characteristics of patients with different temporomandibular joint osseous statuses. METHODS: A total of 306 patients with initial cone beam CT (CBCT) and cephalograms were included. They were divided into three groups on the basis of their temporomandibular joint osseous status: bilateral normal (BN) group, indeterminate for osteoarthrosis (I) group, and osteoarthrosis (OA) group. The anterior and posterior occlusal planes (AOP and POP) of the different groups were compared. Then, the regression equation was established after adjusting for confounding factors, and a correlation analysis between the occlusion planes and other parameters was performed. RESULTS: SNA, SNB, FMA, SN-MP, Ar-Go, and S-Go were correlated with the occlusal planes. Relative to the BN and I groups, the FH-OP of the OA group increased by 1.67° on the average, FH-POP increased by 1.42° on the average, and FH-AOP increased by 2.05° on the average. CONCLUSIONS The occlusal planes were steeper in the patients with temporomandibular osteoarthrosis than in the patients without it, and the mandible rotated downward and backward. The height of the mandibular ramus, the mandibular body length, and the posterior face height were small. In clinical practice, attention should be given to the potential risk of temporomandibular joint osteoarthrosis in such patients. In addition, SNB, FMA, SN-MP, Ar-Go, S-Go, and occlusal planes had moderate correlations.
Humans ; Dental Occlusion ; Cephalometry ; Mandible ; Temporomandibular Joint Disorders/diagnostic imaging* ; Temporomandibular Joint/diagnostic imaging* ; Osteoarthritis/diagnostic imaging* ; Mandibular Condyle

OBJECTIVES: This study aimed to conduct a meta-analysis of the efficacy of mandibular advance clear alig-ners with traditional functional appliances as the control group. METHODS: PubMed, Web of Science, Embase, Cochrane Library, China Biomedical Abstracts Database, China Knowledge Network Database, Wanfang Database, and Weipu Database were used in this study. The two groups of researchers screened the literature and extracted data based on the inclusion and exclusion criteria established by PICOS entries, and used the ROBINS-I scale for quality evaluation. Revman 5.4 and Stata 17.0 software were used for meta-analysis. RESULTS: Nine clinical controlled trials were included in this study with a total sample size of 283 cases. No significant difference was found in SNA, SNB, ANB, Go-Pog, U1-SN, Overjet, and other aspects between the invisible group and the traditional group in the treatment of skeletal class Ⅱ ma-locclusion patients; there was a 0.90° difference in mandibular plane angle between the two groups; the growth of the mandibular ramus (Co-Go) in the traditional group was 1.10 mm more than that in the invisible group; the lip inclination of the lower teeth in the invisible group was better controlled, 1.94° less than that in the control group. CONCLUSIONS The invisible group can better control the lip inclination of the mandibular anterior teeth when guiding the mandible. Furthermore, the mandibular plane angle (MP-SN) can remain unchanged, but the growth of the mandibular ramus is not as good as the traditional group, and auxiliary measures should be taken to improve it in clinical practice.
Humans ; Malocclusion, Angle Class II/therapy* ; Mandibular Advancement ; Orthodontics, Corrective ; Orthodontic Appliances, Functional ; Mandible ; Orthodontic Appliances, Removable ; Cephalometry

Objective: To establish a comprehensive diagnostic classification model of lateral cephalograms based on artificial intelligence (AI) to provide reference for orthodontic diagnosis. Methods: A total of 2 894 lateral cephalograms were collected in Department of Orthodontics, Capital Medical University School of Stomatology from January 2015 to December 2021 to construct a data set, including 1 351 males and 1 543 females with a mean age of (26.4± 7.4) years. Firstly, 2 orthodontists (with 5 and 8 years of orthodontic experience, respectively) performed manual annotation and calculated measurement for primary classification, and then 2 senior orthodontists (with more than 20 years of orthodontic experience) verified the 8 diagnostic classifications including skeletal and dental indices. The data were randomly divided into training, validation, and test sets in the ratio of 7∶2∶1. The open source DenseNet121 was used to construct the model. The performance of the model was evaluated by classification accuracy, precision rate, sensitivity, specificity and area under the curve (AUC). Visualization of model regions of interest through class activation heatmaps. Results: The automatic classification model of lateral cephalograms was successfully established. It took 0.012 s on average to make 8 diagnoses on a lateral cephalogram. The accuracy of 5 classifications was 80%-90%, including sagittal and vertical skeletal facial pattern, mandibular growth, inclination of upper incisors, and protrusion of lower incisors. The acuracy rate of 3 classifications was 70%-80%, including maxillary growth, inclination of lower incisors and protrusion of upper incisors. The average AUC of each classification was ≥0.90. The class activation heat map of successfully classified lateral cephalograms showed that the AI model activation regions were distributed in the relevant structural regions. Conclusions: In this study, an automatic classification model for lateral cephalograms was established based on the DenseNet121 to achieve rapid classification of eight commonly used clinical diagnostic items.
Male ; Female ; Humans ; Young Adult ; Adult ; Artificial Intelligence ; Deep Learning ; Cephalometry ; Maxilla ; Mandible/diagnostic imaging*

OBJECTIVES: To investigate the effect of different soft-tissue morphologies on the treatment of skeletal class Ⅰ malocclusion patients by analyzing measurement data before and after treatment. METHODS: Pre- and post-treatment lateral cephalograms of 55 adult female Angle class Ⅰ patients were collected in the Department of Orthodontics, Hospital of Stomatology, Jilin University from January 2012 to December 2020. Chin soft-tissue morphologies in the lateral cranial radiographs were used to divide the patients into an abnormal chin morphology group (flat and retracted chins, n=27) and a normal chin morphology group (rounded and prominent chins, n=28). Relevant soft- and hard-tissue indexes were selected to study in-group varieties and intergroup differences in the varying chin morphologies before and after treatment. RESULTS: The chin-lip angle, mandibular chin angle, mandibular chin vertex angle, PP-MP, LL-E, UL-E, Po-Pos, and B-B' thickness in the abnormal chin morphology group were significantly higher than those in the normal chin morphology group (P<0.05). Furthermore, m∶BMe and n∶B'Mes in the abnormal chin morphology group were signi-ficantly lower than those in the normal chin morphology group (P<0.05). After treatment, the mandibular chin angle, mandibular chin vertex angle, U1-SN, L1-MP, LL-E, UL-E, SNA, SNB, and B-B' thickness of the abnormal chin morphology group significantly decreased (P<0.05), whereas the nasolabial angle, m∶BMe, n∶B' Mes, and Po-Pos significantly increased (P<0.05). In the normal chin morphology group, the U1-SN, L1-MP, LL-E, UL-E, and B-B' thicknesses decreased significantly (P<0.05), whereas the nasolabial angle significantly increased (P<0.05). Among them, m∶BMe and n∶B' Mes were positively correlated. CONCLUSIONS Chin morphology affects the formulation of treatment plans. Compared with the normal chin morphology group, the abnormal chin morphology group required a larger retraction of incisors. Although the chin of soft-tissue morphology is related to the morphology of bones, the changes in soft tissue chin after treatment cannot be directly predicted according to the bone changes. Soft-tissue chin morphology affects the aesthetic assessment of the soft-tissue lateral profile and the change in soft tissue before and after treatment. The method of predicting the change in soft-tissue chin after treatment should consider the morphology of the soft-tissue chin.
Adult ; Humans ; Female ; Chin ; Lip ; Cephalometry/methods* ; Esthetics, Dental ; Mandible