Search Results (272)

Background/Objectives: Automated cephalometric landmark detection using deep learning has the potential to streamline routine orthodontic diagnosis. However, the clinical relevance of artificial intelligence (AI) localisation accuracy depends on how detection errors propagate into derived angular measurements and skeletal classifications. We retrospectively evaluated 14 YOLO-based model configurations and quantified the agreement between AI-derived and expert-derived ANB-based skeletal classifications. Methods: Twelve working YOLO-based models (YOLOv5xu, YOLOv11 nano/small/medium/large variants) were trained on a single-centre dataset of 120 lateral cephalograms and evaluated on an independent test set of 11 cephalograms (stratified across skeletal Classes I, II, III). The four ANB-defining landmarks (Sella, Nasion, A-point, B-point) were the focus of the analysis. Each test cephalogram had been annotated by four orthodontists (44 measurements per image), yielding the expert reference. We assessed the effects of architecture, bounding-box size (40/100/150 px), training dataset scale (235–4255 images) and training epochs on localisation accuracy (mean radial error, MRE; Successful Detection Rate, SDR) and on the downstream ANB-based skeletal classification. Diagnostic concordance was quantified by classification agreement, Cohen’s $\kappa$ with bootstrap 95% confidence intervals (10,000 iterations), an exact one-sided binomial test for discordance, and Wilson exact CIs per class. Results: The best-performing model (Model 2; YOLOv11l, 40 × 40 px bounding box, 1175 training images) achieved an MRE of $3.10\pm 1.00$ mm and a SDR@4 mm of 87.2% for S, N, A, and B. ANB-based skeletal classification demonstrated 96.9% concordance with expert assessments (95% bootstrap CI: 93.8–99.2%; Cohen’s $\kappa$ = 0.946 [95% CI 0.89–0.99]; exact binomial test against a 90% concordance threshold $p=0.003$). Per-class concordance was Class I 95.8% (23/24), Class II 94.9% (56/59), and Class III 100% (47/47). Three of four discordant cases clustered near the Class I/II diagnostic threshold (expert ANB $\approx 4.5°$). Bounding-box size dominated localisation accuracy, with a 3.5-fold increase in MRE from 40 × 40 to 150 × 150 px configurations and SDR@4 mm collapsing from 82.8% to 0%. Conclusions: Within the constraints of a retrospective single-centre design with a small (n = 11) independent test set, YOLO-based AI landmark detection demonstrated promising diagnostic concordance with expert consensus for ANB-based skeletal classification. These findings warrant prospective, multi-centre external validation before clinical deployment and support a confidence-aware workflow in which AI predictions for borderline ANB values undergo mandatory clinician verification. Bounding-box calibration emerged as the single most impactful preprocessing decision. Full article

Background: Congenital tooth agenesis is a common dental anomaly in individuals with orofacial clefts and may be related not only to cleft type but also to skeletal growth characteristics. This study aimed to investigate whether the number of congenitally missing permanent teeth is associated with cleft type, sex, and sagittal and vertical skeletal patterns in non-syndromic cleft patients. Materials and Methods: A retrospective cross-sectional analysis was conducted on 60 patients aged ≥17 years (36 males, 24 females; mean age 19.5 ± 1.8 years) with surgically repaired cleft lip and/or palate, based on clinical records collected over a long-term follow-up period. Sagittal (Class I, II, III) and vertical (normal, deep bite, open bite) skeletal patterns were extracted from available orthodontic records based on routine cephalometric assessment. The number of congenitally missing permanent teeth, excluding third molars, was recorded. Statistical analysis included non-parametric tests and Poisson regression. Results: The distribution of missing teeth deviated significantly from normality according to the Shapiro–Wilk test (p < 0.001). In the Poisson regression model, sex (p = 0.011) and cleft type (p < 0.001) were significantly associated with the number of congenitally missing teeth, whereas sagittal skeletal pattern (p = 0.338) and vertical skeletal pattern (p = 0.281) were not significant predictors. Conclusions: In this retrospective record-based analysis, the number of congenitally missing teeth appeared most consistently associated with cleft type, while sex showed a model-dependent association in the adjusted regression analysis. Full article

Background/Objectives: Upper airway constriction and craniofacial structural variation are recognised risk factors for paediatric sleep-disordered breathing (SDB). Population-specific normative cephalometric reference data are lacking, and are needed to characterise these features in paediatric orthodontic patients, especially in Asian populations. This study examined upper airway structure and lymphoid tissue hypertrophy in a large paediatric orthodontic population. The aims of the study were to investigate upper airway differences across skeletal patterns, age, gender, and ancestry groups, establish pharyngeal airway, skeletal, dental, and soft tissue cephalometric dimensions, and determine adenotonsillar hypertrophy prevalence in a large paediatric orthodontic population in Singapore. Methods: Lateral cephalograms of children aged 7–11 years were obtained from a national dental centre, and a retrospective analysis was performed. Standardised cephalometric measurements were used to assess airway, skeletal, dental, and soft tissue parameters, with comparisons across demographic and skeletal groups. Results: A total of 404 children (203 boys, 201 girls; aged 7.04–10.99 years) were included in the final analysis. Thirteen airway variables differed significantly by gender and age, six by antero-posterior, and four by vertical skeletal pattern. One variable (AH-CV) differed between Chinese and non-Chinese children. A form of lymphoid tissue hypertrophy (Ad/Np ≥ 0.5 and/or Tn/Op ≥ 0.5) was present in 92.3% of subjects, comprising combined adenotonsillar hypertrophy (49.5%), isolated tonsillar hypertrophy (36.6%), and isolated adenoid hypertrophy (6.2%). Conclusions: Cephalometric norms for upper airway, skeletal, dental, and soft tissue structures in a 7–11-year-old orthodontic population in Singapore were reported. Adenotonsillar hypertrophy was present in nearly half of the subjects, while isolated tonsillar hypertrophy affected about one-third. Patients who were younger, male, Chinese, Class I, Class II, and had increased mandibular plane angles displayed cephalometric features associated with anatomical risk indicators for SDB. These population-specific cephalometric reference data provide a benchmark for contextualising upper airway and craniofacial measurements in paediatric orthodontic patients, supporting the potential utility of cephalometric assessment to identify children who may benefit from referral for comprehensive SDB evaluation. Full article

Background/Objective: This study evaluated the diagnostic performance of vertical growth patterns and mandibular morphology, alongside the anteroposterior dysplasia indicator (APDI), for classifying skeletal malocclusions in a Saudi adult population using cephalometric analysis. Materials and Methods: This retrospective cross-sectional discriminatory performance study analyzed 162 archived lateral cephalometric radiographs of Saudi adults aged 18–44 years. The assessed variables included Frankfort-mandibular plane angle (FMA), gonial angle, ANB angle, and APDI. Statistical analysis involved descriptive statistics, ANOVA with post hoc testing, Pearson correlation, logistic regression, and receiver operating characteristic (ROC) curve analysis. Results: Significant differences among skeletal classes were observed for all evaluated variables (p < 0.05). APDI showed the largest effect size and the highest diagnostic performance, particularly for Class III malocclusion, with excellent discriminatory ability reflected by area under the curve (AUC) values, high sensitivity, and acceptable specificity at optimal cutoff points. FMA showed moderate discriminatory performance, with higher specificity but limited sensitivity, while the gonial angle exhibited comparatively weaker diagnostic performance. In logistic regression analysis, APDI was the only significant independent associated variable of Class II malocclusion. Conclusions: Within the ANB-based classification framework used in this study, APDI showed the highest discriminatory performance for skeletal malocclusion classification, supporting its role as a primary sagittal indicator. FMA contributed adjunctive information on vertical skeletal pattern, while the gonial angle showed limited diagnostic value. Combined assessment of sagittal and vertical parameters may improve cephalometric diagnosis. Full article

Background: This study aimed to compare the measurement agreement and intramethod reliability of four cephalometric analysis workflows: manual tracing, semi-automated digital analysis (Dolphin), fully automated AI-based analysis (WebCeph), and expert-adjusted AI analysis (WebCeph+). Methods: In this retrospective method-comparison study, 67 lateral cephalometric radiographs were initially included. After the exclusion of radiographs containing extreme values, 54 radiographs (35 females, 19 males; mean age: 15.0 ± 2.13 years) were analyzed. Twenty-one skeletal, dental, and soft-tissue parameters (13 angular, 8 linear) were evaluated across the four methods. Intramethod repeatability was assessed via the intraclass correlation coefficient (ICC). Intermethod comparisons were analyzed using ANOVA and post hoc pairwise tests. Pragmatic clinical relevance thresholds were predefined as ±2 degrees for angular measurements and ±2 mm for linear measurements. Results: All methods demonstrated high intramethod reliability, with ICC values exceeding 0.90 in 20 out of 21 parameters. Manual and Dolphin methods yielded statistically comparable results (p > 0.05). In contrast, WebCeph differed significantly from manual and/or Dolphin in seven parameters, including SNA, IMPA, Go-Gn length, Pog to N-perpendicular, Wits appraisal, nasolabial angle, and mentolabial angle (p < 0.05). Several discrepancies exceeded the predefined pragmatic thresholds (±2 degrees and ±2 mm), highlighting their potential clinical relevance. After expert adjustment (WebCeph+), statistically significant inter-workflow differences were no longer observed; however, residual individual-level variability remained for selected parameters. Conclusions: Fully automated WebCeph analysis showed limited agreement with manual and semi-automated methods for several clinically relevant measurements. Expert adjustment reduced systematic mean discrepancies and improved agreement with clinician-dependent workflows; however, residual individual-level variability remained for selected parameters. AI-driven cephalometric analysis should therefore be considered a supportive tool requiring specialist verification rather than an unsupervised replacement for conventional methods. Full article

Background and Objectives: Maintenance of condylar position during bilateral sagittal split ramus osteotomy (BSSRO) is important for preserving temporomandibular joint biomechanics and skeletal stability. During surgery, loss of muscle tone under general anesthesia may alter the condyle–fossa relationship, making accurate repositioning of the proximal segment challenging. Although manual positioning remains the most commonly used intraoperative approach, evidence regarding its ability to preserve the preoperative condyle–fossa relationship remains limited. This study evaluated changes in the condyle–fossa relationship following BSSRO performed with manual proximal segment positioning. Materials and Methods: This single-center retrospective study included lateral cephalometric radiographs of 14 patients (8 females, 6 males; aged 19–29 years) with skeletal Class III malocclusion treated with combined orthodontic treatment and BSSRO. Radiographs were obtained preoperatively (T0), immediately postoperatively (T1), and at the final follow-up examination (T2). Condylar position was assessed using a Cartesian coordinate system, joint space measurements, and the Condyle Position Index (CPI). Statistical analyses were performed using the Friedman and Wilcoxon signed-rank tests (p < 0.05). Results: Significant differences were observed in CPI and anterior joint space measurements across the observation periods. Interval analysis demonstrated increased CPI values and decreased anterior joint space measurements between T1 and T2, whereas no significant immediate postoperative changes were observed. Intra-observer reliability was excellent, with intraclass correlation coefficients exceeding 0.90 for all variables. Conclusions: Manual positioning of the proximal segment during BSSRO may provide acceptable immediate postoperative condyle–fossa stability but may not completely maintain the preoperative condyle–fossa relationship over time. Although no significant immediate postoperative changes were observed, significant changes in the condyle–fossa relationship were identified at the final follow-up examination. These findings support the need for further prospective studies incorporating clinical temporomandibular joint assessment and three-dimensional imaging. Full article

This systematic review aimed to evaluate the available evidence on methods used to predict mandibular autorotation after maxillary repositioning in orthognathic surgery. A systematic search of PubMed/MEDLINE, Cochrane Library, Scopus, Google Scholar, and EMBASE covering the period from 1970 to 2026 was performed to identify studies reporting on prediction methods for mandibular autorotation after maxillary repositioning. Data on study design, sample size, surgical setting, prediction method, and prediction error were extracted. Because of substantial heterogeneity and incomplete reporting, quantitative synthesis was considered exploratory. Risk of bias was assessed using the ROBINS-I tool. A total of six studies met the inclusion criteria. The available evidence showed marked heterogeneity in study design, outcome definitions, anatomical landmarks, and reporting format. Earlier studies mainly used 2D cephalometric or geometric methods, whereas more recent investigations relied on 3D virtual planning and simulation-based workflows. In the exploratory subgroup meta-analysis, 3D approaches were associated with a lower pooled mean prediction error (0.57 mm, 95% CI: 0.05–1.08) than 2D methods (2.13 mm, 95% CI: 0.65–4.92), although the subgroup difference was not statistically significant (p = 0.2772). Leave-one-out sensitivity analysis showed that the direction of effect consistently favoured 3D methods. Overall, the available evidence suggests that 3D approaches may show lower mandibular autorotation prediction errors than 2D methods; however, this finding should be interpreted cautiously because of the small number of studies, substantial methodological heterogeneity, and the exploratory nature of the quantitative synthesis. Full article

Background/Objectives: Cephalometric analysis is essential in orthodontics and for studying conditions such as obstructive sleep apnea syndrome (OSAS). However, manually identifying anatomical landmarks and segmenting the pharyngeal airway on lateral cephalograms can be time-consuming and prone to errors. This study evaluates the CEPH_2D system, an AI-based tool designed to automate cephalometric landmark detection and pharyngeal airway segmentation from 2D lateral cephalometric radiographs. Methods: The system was evaluated on 35 anonymized lateral cephalograms obtained from patients aged 6–65 years, including mixed and permanent dentition cases. Two experienced clinicians generated and reviewed the ground truth annotations for cephalometric landmark localization and pharyngeal airway segmentation. System performance was assessed using mean radial error (MRE), successful detection rate (SDR), mean average precision (mAP), Dice similarity coefficient (DSC), precision, recall, and inference time. Results were compared with manual methods and existing automated tools. Results: The system reached a mean radial error (MRE) of 0.740 ± 0.793 mm for the key point detection task and a mean Dice Score (mDSC) of 0.935 ± 0.040 with an average processing time of 2.557 ± 0.504 s. Conclusions: CEPH_2D appears to be a promising adjunctive tool for automatic cephalometric landmark detection and pharyngeal airway segmentation on lateral cephalograms, although clinician verification remains advisable before clinical interpretation or treatment planning, particularly for landmarks showing higher detection errors. Full article

Accurate anatomical landmark detection is important for orthodontic analysis, surgical planning, and morphometric measurement, but fully supervised methods usually require large expert-annotated datasets. This work studies a one-shot setting, where only a single annotated template image is used for training. We propose a foundation-model-based landmark detection framework using a frozen DINO Vision Transformer (ViT) backbone. The proposed framework integrates three complementary components: a Multi-Layer Multi-Facet (MLMF) module that adaptively fuses key and value features from multiple ViT layers through global source-wise reweighting; a Mamba-Based Long-Range Context Aggregation (MLCA) module that injects global anatomical context into fused patch descriptors with linear complexity; and a Topology-Constrained Graph Refinement (TCGR) module that refines the predicted landmark configuration using anatomical graph constraints. Experiments on the Cephalometric dataset and the Hand X-ray dataset demonstrate that the proposed method achieves strong performance. Overall, the results show that jointly exploiting multi-source foundation-model representations, efficient long-range context aggregation, and topology-aware refinement improves annotation-efficient anatomical landmark detection. Full article

Interceptive orthodontics plays a key role in the early management of dento-skeletal discrepancies in growing patients, particularly transverse maxillary deficiency. This retrospective clinical study evaluated the dento-skeletal effects of a digitally manufactured, patient-specific Transversal Sagittal Maxillary Expander (TSME). A sample of 45 pediatric patients (mean age 8.5 years) with transverse and sagittal maxillary deficiency was analyzed. All subjects were treated using a customized titanium TSME designed through a multimodal digital workflow combining intraoral scanning, CBCT imaging, and three-dimensional facial acquisition for diagnostic planning and appliance customization. Quantitative treatment outcome assessment was based on standardized lateral cephalometric analysis between pre-treatment (T0) and post-treatment (T1). Statistically significant changes were observed in sagittal and vertical skeletal parameters, including SNA, SNB, ANB, SN–ANS-PNS, SN–GoGn, N–Me, and APDI. The integration of digital technologies and titanium additive manufacturing may support improved appliance customization and workflow standardization. Within the limitations of this retrospective study, digitally manufactured TSME represents a promising approach for patient-specific appliance customization in interceptive orthodontics. Full article

Prefabricated myofunctional appliances (PMAs) are designed to improve airway function by advancing the mandible, enhancing tongue posture, and reducing airway resistance, thereby facilitating nasal breathing in children with sleep-disordered breathing (SDB). This retrospective study evaluated the effects of PMAs on airway dimensions in children with skeletal Class II division 1 malocclusion. Patients were selected from a departmental database (2017–2019). The treatment group included children with Class II division 1 malocclusion, an incisor overjet of ≥6 mm, cervical vertebral maturation (CVM) stage III or earlier, and documented myofunctional dysfunction (e.g., adenoid hypertrophy, allergic rhinitis, or mouth breathing), with complete pretreatment and one-year follow-up lateral cephalometric radiographs. Patients with prior orthodontic intervention or poor compliance were excluded. A matched observation group consisted of untreated patients undergoing growth monitoring. Airway dimensions of the nasopharynx, oropharynx, and hypopharynx were measured using cephalometric radiographs, along with McNamara Airway Analysis. The total nasal symptom score (TNSS) was used as a self-report measure. A total of 34 patients (mean age 9.4 years) were included in the PMA group and 29 patients (mean age 9.6 years) in the observation group. Compared with controls, the PMA group demonstrated significant increases in nasopharyngeal (p = 0.044) and oropharyngeal (p = 0.039) airway areas, while changes in the hypopharyngeal area were not significant (p = 0.121). McNamara Airway Analysis also showed a significant improvement in upper pharyngeal airway dimensions (p = 0.018). TNSS revealed significant changes following PMA therapy (p < 0.001). These findings indicate that PMA therapy is associated with enlargement of the nasopharyngeal and oropharyngeal airway in children with skeletal Class II division 1 malocclusion, suggesting functional airway adaptation beyond simple mandibular advancement. Full article

Background/Objectives: Artificial intelligence has accelerated cephalometric analysis by enabling rapid and standardized measurements. However, whether these automated outputs can be considered clinically interchangeable with expert manual tracing remains unresolved, particularly for routinely used analyses such as Steiner. Methods: A comparative experimental study was conducted on 100 lateral cephalometric radiographs analysed using two parallel approaches: expert manual tracing and fully automated analysis with the WebCeph platform. Seven Steiner variables (SNA, SNB, ANB, 1–NA, 1–NB, interincisal angle, and FMA) were evaluated. Paired t-tests were used to assess differences between methods, while agreement was evaluated using intraclass correlation coefficients and Bland–Altman analysis. Particularly low agreement was observed for clinically relevant parameters such as ANB and FMA. Results: Six of the seven variables showed statistically significant differences between methods. Automated measurements systematically tended to overestimate both skeletal and dental parameters. Agreement was inconsistent and frequently poor, with ICC values ranging from 0.01 to 0.60 for clinically relevant variables such as ANB and FMA. Importantly, small or non-significant mean differences did not translate into acceptable agreement. Bland–Altman analysis confirmed the presence of systematic bias and wide limits of agreement, especially for dental measurements. Conclusions: Despite its speed and automation, WebCeph does not achieve clinically acceptable agreement with expert manual tracing across several key cephalometric variables. The observed discrepancies—particularly in parameters critical for sagittal and vertical diagnosis—may compromise clinical interpretation and treatment planning. These findings support the use of AI-based cephalometric analysis as an adjunctive tool rather than a substitute for clinician-guided evaluation. Full article

Background/Objectives: Modern artificial intelligence methods are increasingly used in medical and dental image analysis to support diagnosis and treatment planning. In orthodontics, automatic detection of cephalometric landmarks from X-ray images remains a challenging and clinically relevant task. Methods: This study proposes a multi-model approach for cephalometric landmark detection based on the ALD algorithm and three derived models trained with extended image augmentation techniques. The applied augmentations, including contrast and negative transformations, improved the detection of specific anatomical landmarks. The final detection strategy integrates outputs from all four models, selecting the most accurate prediction for each landmark based on historical performance results. Results: The proposed method was evaluated on real datasets. It achieved a mean radial error (MRE) of 2.12 mm compared to 2.26 mm for the baseline model, and a successful detection rate (SDR) of 72.22% within a 2.5 mm threshold compared to 68.87% for the baseline model. Conclusions: The results demonstrate that the ensemble-based approach improves landmark detection accuracy and has the potential to support clinical orthodontic workflows. Full article

Objectives: The present study aimed to evaluate the sexual dimorphism of skeletal and dental anomalies in Romanian orthodontic patients and to describe several important cephalometric measurements in patients with dental malocclusions. Materials and Methods: A total of 450 orthodontic records of patients older than 8 years were evaluated. On lateral cephalometric radiographs, the following cephalometric angles were digitally determined: SNA, SNB, ANB, FMA, IMPA, Max1-FH, SN-Go-Gn, N-A-Pog, Ar-Go-Me, and interincisal angle. The sagittal skeletal and dental malocclusions were diagnosed by two calibrated investigators. Results: The sample comprised 58% females, with a mean age of 20.07 (±8.63) years. The prevalence of dental malocclusions within the Romanian orthodontic sample taken into study was: 50.7% class I, 26.7% class II division 1, 13.3% class III, 4.7% class II, and class II division 2. The prevalence of skeletal anomalies within the Romanian orthodontic patient sample was: 43.3% class I, 28.7% class II due to retrognathic mandible, 17.3% class II due to prognathic maxilla, 8.7% class III due to prognathic mandible, and 2% class III due to retrognathic maxilla. Female patients presented more frequently with Class I or Class II division 2 malocclusion, whereas male patients more frequently exhibited Class III malocclusion. Female patients exhibited skeletal Class II more frequently due to retrognathic mandible, while skeletal Class III, due to prognathic mandible, was more common in male patients. Male patients were more frequently normodivergent, while female patients were more frequently hyperdivergent. Female patients exhibited retroclined upper incisors more frequently, whereas male patients exhibited proclined upper incisors more frequently. Most of the patients with class II division 1 malocclusion were females and exhibited the following cephalometric characteristics: a class II skeletal anomaly due to retrognathic mandible, normal SNA angle, decreased SNB angle, increased ANB angle, proclined upper incisors, proclined lower incisors, decreased interincisal angle, normal vertical growth pattern, closed mandibular angle, and convex facial profile. Most of the patients with class II division 2 malocclusion were females and exhibited the following cephalometric characteristics: a class II skeletal anomaly due to retrognathic mandible, normal SNA angle, decreased SNB angle, increased ANB angle, retroclined upper incisors, proclined lower incisors, increased interincisal angle, hypodivergent vertical growth pattern with a short face tendency, closed mandibular angle, and convex facial profile. Most of the patients with class III malocclusion were males and exhibited the following cephalometric characteristics: both class I and III skeletal anomaly due to prognathic mandible, normal SNA angle, increased SNB angle, decreased ANB angle, proclined upper incisors, normally inclined lower incisors, increased interincisal angle, hypodivergent, normal vertical growth pattern, and a short face tendency, normal mandibular angle, and balanced facial profile. Conclusions: The observed cephalometric differences between Class I, II and III malocclusions provide clinically relevant markers in vertical, sagittal, and dental dimensions that may provide descriptive reference data for similar orthodontic clinical samples. Full article

Background/Objectives: Artificial intelligence (AI) has gained growing interest in the field of orthognathic surgery due to its potential to improve diagnostic accuracy, surgical planning, and treatment outcomes. This scoping review maps literature from 2017 to May 2025 to identify AI applications in orthognathic surgery, assess their clinical relevance, and discuss the associated ethical, legal, and technical limitations. Methods: This scoping review further examines the stages of the orthognathic surgical workflow at which AI applications have been prospectively validated, the artificial intelligence methodologies applied to virtual surgical planning and outcome prediction, and the main methodological, ethical, and legal factors that may constrain broader clinical adoption. Results: A total of 62 studies were included, covering AI use in cephalometric analysis, virtual surgical planning (VSP), outcome prediction, and intraoperative support. While AI demonstrates remarkable potential in orthognathic planning, current approaches are often limited by heterogeneous methodologies and retrospective validation. Conclusions: Future studies should prioritize prospective, multicentre designs integrating AI-assisted decision-making directly into the clinical workflow, with emphasis on model interpretability, patient-specific accuracy, and ethical transparency. These questions extend beyond mapping applications by emphasizing clinical validation, methodological rigor, and ethical accountability—dimensions insufficiently explored in prior reviews. Full article