Background and Aim:As dental anomalies can significantly affect esthetic and function, early detection and diagnosis are crucial for treatment and minimizing potential negative effects. Artificial intelligence (AI) has emerged as a promising tool for the segmentation and detection of dental anomalies in number, morphology, size, position, and structure that may be missed by dentists. This study aimed to investigate the application of various AI models in dental anomaly detection and diagnosis, including supernumerary teeth, tarodontism, impaction, ectopic eruption, and molar-incisor hypomineralization in both dental radiography and photography. Method:A comprehensive literature search was conducted in PubMed/Medline, Scopus, Web of Science, and Google Scholar for studies published from the initiate up to 2023 on AI applications in dental anomaly detection. Inclusion criteria encompassed recent AI models utilizing imaging modalities for identifying dental abnormalities, with full-text availability in English. Studies lacking imaging-based AI applications or methodological clarity were excluded. Results and Conclusion:A total of 20 studies assessed various AI models for detecting dental anomalies in radiographic and photographic imaging. Deep learning models, particularly EfficientDet-D3, nnU-Net, and ResNeXt, demonstrated the highest accuracy for supernumerary teeth, ectopic eruption, and molar-incisor hypomineralization, respectively, with most models achieving accuracy rates above 85%. These findings underscore AI's significant potential for automated dental anomaly detection; however, performance varied across different anomalies and imaging modalities, highlighting the need for further optimization. Given the complexity of simultaneous dental anomalies, future research should focus on developing multi-class AI models capable of detecting multiple conditions concurrently and integrating clinical and radiographic data for improved diagnostic accuracy and treatment planning.

ObjectiveThe aim of this paper is to investigate clear aligner therapy (CAT) practice patterns among Turkish orthodontists and compare them with Iranian specialist orthodontists.MethodsA web-based cross-sectional survey of Turkish specialist orthodontists assessed CAT use, adjuncts, training, case selection by malocclusion and age, monitoring and retention protocols, and perceived advantages/disadvantages. Findings were compared with a previously published survey of 142 Iranian orthodontists.ResultsA total of 178 Turkish orthodontists participated (7.5% response rate; 71 males, 107 females). Most were aged 30–39 years (53.9%), had 11–20 years of experience (42.1%), and worked in private practice (62.9%). CAT use was reported by 96.1% of Turkish orthodontists versus 69.0% of Iranian orthodontists. More Turkish orthodontists initiated >50 new CAT cases annually (33.1% vs. 7.7%), while fewer reported <10 cases/year (18.0% vs. 35.9%). CAT use was significantly higher in Turkey across all age groups (P < 0.001). Preferences were similar for mild crowding, spacing, and anterior cross-bite. Turkish orthodontists more frequently used CAT for complex cases, including mild/moderate open bite and severe crowding (P < 0.05). CAT was preferred more for limited extraction and space-opening cases than orthognathic surgery cases. Iranian orthodontists more commonly used local manufacturers (49.3% vs. 15.7%) and in-office aligner production (19% vs. 9%). Perceptions regarding CAT advantages and limitations were largely similar between groups.ConclusionAmong respondents, CAT was more widely integrated into orthodontic practice in Turkey, with broader self-reported clinical indications and more positive clinician perceptions than in Iran. Iranian orthodontists relied more on locally manufactured and in-office aligners.

This study presents a multi-stage deep learning pipeline for automated Angle’s classification of occlusion using intraoral images in orthodontics. The pipeline integrates three key stages: (1) a binary Occlusion Side Classifier (OSC) to determine whether the input image represents the right or left side of the patient’s dentition, (2) side-specific bounding box detection models (MolarBBoxNet-R or MolarBBoxNet-L) to localize the molar region, and (3) a unified classifier (AngleClassifier-R50) to predict Class I, II, or III occlusal relationships. A dataset of 8909 lateral intraoral occlusion images from three orthodontic centers was used, including patients older than 6 years, ensuring the presence of fully erupted first molars. Images were annotated by two experts, with discrepancies resolved through consensus. The pipeline achieved perfect occlusion side classification (accuracy 1.00) and high molar classification accuracy (97.41

INTRODUCTION:Early identification of vertical skeletal discrepancies is essential for orthodontic diagnosis and treatment planning. Since panoramic radiographs (OPGs) are more routinely obtained than lateral cephalometric radiographs (LCR), this study evaluated whether artificial intelligence could predict vertical skeletal angles on OPGs. METHODS:LCRs and OPGs of 715 patients were retrospectively collected from four imaging centre (2022-2025). LCRs were traced using WebCeph to obtain reference measurements of the Frankfort-mandibular plane angle (FMA), gonial angle, and Sum of Björk. Multiple convolutional neural network (CNN) architectures (EfficientNet-B3, DenseNet121/169, ResNet-50/101, VGG16/19) were trained to predict these parameters from corresponding OPGs. Ensemble averaging was also employed as a non-learned aggregation strategy. Model performance was evaluated using mean absolute error (MAE) and the coefficient of determination (R2). Wilcoxon signed-rank test assessed the differences in predictive performance. Inter-model agreement was quantified using intraclass correlation coefficients (ICC). Gradient-weighted Class Activation Mapping (Grad-CAM) was used for model interpretability. RESULTS:Ensemble averaging achieved the highest predictive accuracy across all angular parameters, with MAE values of 2.53°±0.08 for FMA, 3.16°±0.10 for the gonial angle, and 3.04°±0.09 for the Sum of Björk. High agreement was observed among the CNN architectures for all measurements (P<0.001). Grad-CAM visualizations indicated that predictions primarily relied on the gonial angle region, followed by the condylar area and mandibular ramus. CONCLUSION:Deep learning demonstrates promising potential for estimating vertical angular measurements on OPGs. Although current prediction errors preclude replacement of cephalometric analysis, the incorporation of larger datasets, geometry-aware models, and external validation will help improving predictive accuracy.

Machine learning models for Obstructive Sleep Apnea (OSA) diagnosis have largely inherited some structural limitations: reliance on generic, opportunistically collected feature sets; use of the Apnea-Hypopnea Index (AHI) as the sole ground truth; poor performance in multi-class severity grading; and predictions that offer clinicians no mechanistic insight. This study addresses these gaps by prospectively assembling a multi-domain dataset that, alongside established demographic, anthropometric, and questionnaire-based predictors, incorporates a panel of craniofacial and intraoral metrics specifically designed to capture the structural-anatomical contributors to OSA — integrating these into an interpretable framework for three-class severity classification evaluated against both AHI and the Oxygen Desaturation Index (ODI). In this single-center study, 233 treatment-naïve adults from a tertiary referral cohort (61.8

The soft-tissue facial profile is a cornerstone of orthodontic diagnosis and treatment planning, strongly influencing facial esthetics and patient satisfaction. This study aimed to develop and evaluate a deep learning–based framework for automated classification of facial convexity (convex, normal, concave) from standardized profile photographs, with an emphasis on transparent preprocessing and model interpretability. A dataset of 1200 natural head position (NHP) profile photographs (400 per class) was labeled by three experienced orthodontists using a consensus approach based on the soft-tissue facial convexity angle, operationally defined by the Glabella–Subnasale–Pogonion (G–Sn–Pg) landmarks. Images underwent cropping, background removal using U2-Net, silhouette generation, and contour extraction to emphasize geometric profile features while minimizing photometric and demographic confounding factors. A custom convolutional neural network (Contour-CNN) was trained using L2 regularization, dropout, cosine-annealing learning-rate scheduling, and Bayesian hyperparameter optimization. Model performance was evaluated using accuracy, precision, recall, F1-score, confusion matrix analysis, receiver operating characteristic (ROC) curves, and saliency-based interpretability measures. The proposed model achieved an overall accuracy of 98

This study aimed to develop and evaluate a fully automated, artificial intelligence–driven system for tooth detection and segmentation from complete orthodontic photographic plates, with the goal of improving clinical outcomes and workflow efficiency in dentistry. Manual tooth charting and segmentation are often labor-intensive, prone to human error, and inconsistent across clinicians, potentially compromising diagnosis, treatment planning, and long-term patient records. A dataset of 2000 composite dental images was annotated and divided into training (n = 1600), validation (n = 200), and testing (n = 200) sets. Model performance was further assessed on an independent external validation dataset obtained from a separate dental institution. The proposed multi-stage system consisted of intraoral view identification and maxilla/mandible localization using YOLOv11 (referred to as YOLO-Arch), followed by tooth-level detection with a separate YOLOv11 model (referred to as YOLO-Tooth), and finally pixel-level segmentation using the Segment Anything Model (SAM). Each detected tooth was assigned a class label and confidence score, and segmentation masks were generated in a zero-shot manner without additional training. The system achieved excellent performance, with 99.5

Accurate facial asymmetry assessment is essential in orthodontics, maxillofacial surgery, and plastic surgery. While minor asymmetry is common, severe cases often result from congenital conditions or trauma. Traditional methods struggle to comprehensively quantify asymmetry's extent and direction. This study developed and compared artificial neural networks (ANN) and Siamese neural networks (SNN) to detect facial asymmetry and determine deviation direction (horizontal/vertical). A dataset of 1200 frontal photographs, annotated by three orthodontists, was used. The MediaPipe model facilitated facial landmark detection and midline alignment. Two approaches were employed: (1) extracting features from facial landmarks and using them to train an ANN, and (2) SNN-based comparison of mirrored facial halves. Exploratory data analysis (EDA) was used to quantify facial asymmetry in both vertical and horizontal dimensions. The ANN and SNN performance was evaluated using accuracy, recall, and F1-score. The SNN outperformed ANN, achieving 97% accuracy and strong agreement with expert evaluations (Cohen's Kappa: 0.84 for asymmetry detection, 0.73 for horizontal deviation, and 0.80 for vertical asymmetry). The symmetry group showed 96.14% mean similarity, while the asymmetry group had 83.97%. The SNN's ROC curve yielded an AUC of 0.98, indicating high diagnostic performance. This study demonstrates the potential of AI-driven methods, particularly SNN, for reliable and objective facial asymmetry assessment in clinical settings. Future research should focus on expanding datasets and refining midline alignment to improve accuracy, especially in cases with vertical eye asymmetry.

Objective(s): The interplay between masticatory muscle function and dental arch size holds considerable significance within the discipline of orthodontics. This research endeavored to quantify masseter muscle dimensions via ultrasonography (USG) and subsequently analyze their correlative relationship with dental arch width. Methods: 45 participants were enrolled in this cross sectional study, stratified by gender and age cohorts. Bilateral USG assessments, utilizing a 7.5 MHz linear transducer, were conducted to quantify masseter muscle thickness and anterior-posterior (AP) width during both relaxed and clenched states. Intermolar width was determined through direct measurement with a metal caliper on dental casts of the maxillary and mandibular arches. Independent samples t-tests were employed to analyze mean differences between male and female subjects. The association between masseter muscle dimensions (thickness and width) and intermolar width was evaluated using Spearman's rank correlation coefficient and Pearson's correlation coefficient, as appropriate at p<0.05. Results: The study cohort comprised 20 females and 25 males within the age range of 16 to 30 years. Statistically significant sexual dimorphism was observed, with males demonstrating substantially greater masseter muscle thickness and AP width compared to females in both relaxed and clenched states (p < 0.001). Consistent with expectations, males demonstrated statistically significant greater intermolar widths in both the maxilla and mandible (p < 0.001). Across the entire study population, a statistically significant positive correlation was identified between masseter muscle thickness and intermolar width (p < 0.05). Specifically, individuals exhibiting larger masseter muscle dimensions presented with correspondingly increased intermolar widths in both the maxillary and mandibular arches. However, when these variables were stratified by gender or age group, no statistically significant correlations were observed (p > 0.05). Conclusion:USG is validated as a safe and reproducible technique for the objective measurement of masseter muscle thickness.

Aim: Common mixed dentition space analysis methods, such as Moyers and Tanaka-Johnston, may not be accurate for all populations. Therefore, the current study aimed to assess the applicability of these methods to Iranians and develop customized equations to predict maxillary and mandibular permanent dentition sizes.Methods: In this cross-sectional study, pre-treatment digital study models of 246 Iranian patients (163 females and 83 males) were obtained from the Orthodontics Department at Shahid Beheshti University of Medical Sciences, Tehran, Iran. After taking digital impressions using Shining 3D Scanner®, mesiodistal widths of mandibular and maxillary permanent incisors, canines, and premolars were measured using Maestro 3D Ortho Studio® software. Paired and independent t-tests were used to compare actual dimensions and widths estimated through Moyers and Tanaka-Johnston methods. Spearman’s test was used to identify correlations between the tooth dimensions, which were implemented to develop predictive linear equations. The significance level was set at P<0.05.Results: The dimensions predicted using Moyers and Tanaka-Johnston methods were significantly overestimated compared to actual measurements (P<0.001 for all). The inter-method comparisons also showed significant differences between the sizes yielded from the two methods (P<0.001 for all).Conclusion: The mesiodistal widths of unerupted permanent canines and premolars predicted using Moyers and Tanaka-Johnston methods were not highly accurate among an Iranian population. Therefore, six new linear equations were developed tailored to this specific population. Nevertheless, further validation studies are necessary to verify the equations’ applicability and accuracy.

Orthognathic surgery is often required to address moderate to severe skeletal class II malocclusion, a condition that affects both facial aesthetics and function. Traditional diagnosis relies on cephalometric radiographs and expert evaluation, which can be time-consuming and subject to inter-observer variability. The need for AI-assisted initial screening based exclusively on lateral soft tissue profiles is increasingly recognized, particularly for identifying mandibular retrusion relative to the maxilla. This study aimed to develop and evaluate a deep learning-based model for classifying lateral facial profile photographs into surgical (S) and non-surgical (NS) categories. A dataset of 524 standardized profile images from skeletal class II patients was collected from three dental centers. Each image was independently reviewed by a panel of five experts (three orthodontists and two maxillofacial surgeons), with labels assigned based on majority consensus. To minimize visual bias and enhance model performance, images underwent preprocessing involving facial cropping, background removal via U2-Net segmentation, silhouette contour extraction, and resizing to 128 × 128 pixels. A custom convolutional neural network (ContourNet) was developed and optimized using fivefold cross-validation. The model achieved an overall accuracy of 90

BACKGROUND:Dental age (DA) estimation, crucial for appropriate orthodontic and paediatric treatment planning, traditionally relies on the analysis of developmental stages of teeth. Artificial intelligence (AI) has been increasingly employed for DA estimation through dental radiographs. The current study aimed to systematically review the literature on the application of AI models for radiographic DA estimation among subjects undergoing dental maturation. MATERIAL AND METHODS:The electronic search was conducted through five databases, namely PubMed, Embase, Scopus, Web of Science, and Google Scholar, in July 2024. The search sought studies relying on AI models for DA estimation based on dental radiographs. Data were analysed using STATA software V.14 and heterogeneity was evaluated using I-squared statistics. A random-effects model was employed for meta-analysis. Publication bias was assessed using a funnel plot, Egger's test, Begg's test, and the trim-and-fill method. Heterogeneity was evaluated with a Galbraith plot, and sensitivity analysis tested robustness. RESULTS:Thirteen studies were deemed eligible for qualitative synthesis, seven of which were included in the meta-analysis. The mean absolute error varied from 0.6915 to 12.04, with accuracy between 0.404 and 0.959. Sensitivity ranged from 0.42 to 1.00, specificity ranged from 0.8014 to 0.982, and positive predictive value ranged from 0.43 to 0.90. The pooled accuracy of seven studies equalled 0.85 (95% CI: 0.79-0.91). CONCLUSION:The present findings support the effectiveness of AI models in DA estimation of individuals under 25 years old based on their dental radiographs. However, further studies with larger sample sizes for both test and training datasets are suggested to validate the reliability and clinical applicability of AI in DA estimation.

Background and Aims:Dentofacial orthopedic treatment planning highly depends on the estimation of skeletal growth peak. In most cases, chronological age and biological age differ, some techniques estimate skeletal age by analyzing cervical vertebrae maturation (CVM) staging on lateral cephalograms. In this study, we aimed to review the different applications of AI in orthodontics and specifically discussed the different designs of AI models used for CVM estimation. Methods:Comprehensive searches was conducted across databases including PubMed, Web of Science, Google scholar, Embase, and Scopus using keywords such as orthodontics, cervical vertebra maturation, skeletal age and artificial intelligence. Results:Utilizing AI algorithms in assessing CVM-based skeletal age enhanced the accuracy of diagnosis, reduced analysis time and minimized observer variability. Deep learning techniques, especially convolutional neural networks (CNNs), have demonstrated promising results in identifying CVM stages from lateral cephalometric radiographs. Conclusion:AI algorithms can assist orthodontists in identifying CVM stages on lateral cephalograms. While the accuracy of AI algorithm depends on factors such as data set size, labeling methods, and model design, expert supervision and a solid understanding of CVM principles remain essential. AI should be considered as a supportive tool, not a replacement for clinical judgment.

Aim: This umbrella review examined the impact of orthodontic treatment on temporomandibular joint disorders (TMDs), highlighting key themes, research gaps, and evidence trends.Methods: A comprehensive electronic search was conducted in PubMed, Scopus, Web of Science, and Cochrane databases. Eligible studies included systematic reviews, network meta-analyses, and consensus-based recommendations evaluating orthodontic interventions and TMD. Data extraction included demographics, treatment types, TMD diagnostic methods, and study findings. Quality assessment was performed using the AMSTAR 2 tool.Results: The initial search yielded 6,928 studies, reduced to 4,611 after duplicate removal. Title/abstract screening resulted in 82 articles, with 25 studies ultimately included. Orthodontic treatments, including clear aligners, functional therapy, and orthognathic surgery, showed inconsistent effects on TMD onset or progression. Non-orthodontic interventions, including cognitive behavioral therapy (CBT) with biofeedback, splints, and cervical mobilization, consistently alleviated symptoms. Systemic conditions, such as juvenile idiopathic arthritis, were associated with higher TMD prevalence. Heterogeneity in study design, diagnostic criteria, and follow-up duration limited definitive conclusions.Conclusion: Orthodontic treatment does not consistently influence TMD. Management should prioritize multidisciplinary and non-orthodontic approaches. Standardized, long-term studies are needed to clarify orthodontic-TMD relationships, particularly for contemporary treatments like clear aligners and orthognathic surgery.

White spot lesions (WSLs) can result from bacterial plaque around orthodontic brackets, leading to enamel demineralization. While other preventive strategies rely on patient compliance, incorporating zinc oxide (ZnO) nanoparticles into adhesives offers antimicrobial protection, independent of compliance. This study aimed to develop a ZnO-containing adhesive and evaluated its antibacterial and mechanical properties for clinical application. This in vitro study, conducted at Shahid Beheshti University of Medical Sciences, sampled 30 extracted premolar teeth and randomly assigned them to three groups: (1) control (synthesized adhesive without ZnO), (2) ZnO (1.5

This study aimed to develop a Progressive Growing Generative Adversarial Network with Gradient Penalty (WPGGAN-GP) to generate high-quality facial profile images, addressing the scarcity of diverse training data in orthodontics. A dataset of 50,000 profile images, representing varied ages, genders, and ethnicities, was collected from two centers. The WPGGAN-GP model was trained to generate high-resolution images (1024 × 1024 pixels) using a progressive growing approach. Evaluation included both quantitative and qualitative assessments. The Sliced Wasserstein Distance (SWD) between real and generated images reached 0.026. A Turing test was conducted with 15 observers (orthodontists, surgeons, and laypersons), each assessing 100 images (50 real, 50 generated). Average classification accuracies were 0.58, 0.578, and 0.46 for orthodontists, surgeons, and laypersons, respectively. Aesthetic evaluation involved six key facial angles, with only the naso-frontal angle showing a statistically significant difference (p = 0.032). The intra-class correlation coefficient (ICC) for repeated measurements ranged from 0.952 to 0.968, and inter-rater ICC values exceeded 0.90, indicating excellent measurement consistency. Additionally, signal-to-noise ratio (SNR) analysis revealed no significant difference between real and generated images (p > 0.05), confirming comparable photometric quality. The results suggest that the WPGGAN-GP model effectively generates realistic facial profiles with both anatomical and perceptual fidelity. This approach offers valuable applications in orthodontic education, treatment simulation, and data augmentation, particularly where patient privacy and dataset balance are critical. Future research should explore conditional generation models for specific malocclusion types and further diversify training data to enhance clinical relevance.

Classifying the cervical vertebral maturation (CVM) degree is helpful in determining the peak period of growth and predicting the growth rate and pattern. The current study proposed a multistage framework for automated CVM classification.The dataset consisted of 2325 lateral cephalograms. Two orthodontists independently classified the images into six classes. One object detection (Faster RCNN) and two classification models (ResNet 101) were designed using the Python programming language and PyTorch library. The First classification model classified images into two main groups (i.e., C1-C3 and C4-C6) based on the C4 vertebrae shape. The second one classified each group into its subcategories. Each classification model was trained and tested using a 10-fold cross-validation strategy. The general framework reached an accuracy of 82.96%. The object detection of ROI extraction reached the mAP50 and mAP75 of 100%. The first classifier model had an accuracy of 99.10% on the hold out test set. The classifier of C1-C3 images had higher accuracy than the C4-C6 classification model (86.49% versus 82.80%) The accuracy of this fully automated framework was promising. Considering the gradual changes in cervical vertebrae morphology the use of visualized data by gradient-weighted class activation maps (Grad-CAM) is suggested to improve the model’s performance.