Orthodontics & Craniofacial Research最新文献

{"title":"Functional Unit-Based Analysis Unveils the Skeletal Mandibular Effects of Class II Elastics Therapy in Adolescents","authors":"Ehab A. Abdulghani,&nbsp;Li Mei,&nbsp;Abeer A. Al-Sosowa,&nbsp;Shijia Li,&nbsp;Majedh Abdo Ali Al-Somairi,&nbsp;Maged S. Alhammadi,&nbsp;Jianru Yi,&nbsp;Yu Li","doi":"10.1111/ocr.70127","DOIUrl":"10.1111/ocr.70127","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>This study sought to thoroughly assess the skeletal impacts of Class II elastics therapy on the developing mandible, highlighting three-dimensional changes in its functional units.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Treatment records of 140 CBCT scans from 70 adolescent patients were retrospectively collected and assigned to one of two groups: the Class II elastics group (<i>n</i> = 35), in which class II elastics were performed on the stainless steel archwires for more than 12 months, and the control group (<i>n</i> = 35). Pre- and post-treatment cone beam computed tomography (CBCT) images were used to assess changes related to the skeletal facial pattern, functional units, and transverse parameters. An independent <i>t</i>-test was used to compare between the two groups.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>In the Class II elastics group, the mandibular body unit length (IAF-MF) increased by 3.09 ± 3.16 mm from pre- to post-treatment, significantly larger than that in the control group (1.37 ± 3.14 mm). No other mandibular functional unit or transverse parameters demonstrated significant differences between the two groups.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Based on the single-center sample included in this study, the adolescent group receiving prolonged Class II elastics may have exhibited a greater increase in mandibular body unit length compared to the group with minimal elastic use. However, these findings cannot be generalized without further validation.</p>\u0000 </section>\u0000 </div>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":"29 5","pages":"848-855"},"PeriodicalIF":2.7,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147777800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning-Based Model for Predicting Short- and Long-Term Growth in Untreated Class III Malocclusion","authors":"Maria Denisa Statie,&nbsp;Michele Nieri,&nbsp;Valentina Rutili,&nbsp;Lorenzo Buffoni,&nbsp;Lorenzo Chicchi,&nbsp;Pietro Auconi,&nbsp;Veronica Giuntini,&nbsp;James A. McNamara,&nbsp;Lorenzo Franchi","doi":"10.1111/ocr.70142","DOIUrl":"10.1111/ocr.70142","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Objective</h3>\u0000 \u0000 <p>To develop a Machine Learning-based model to predict growth of Caucasian subjects with untreated Class III malocclusion in the short- and long-term.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Materials and Methods</h3>\u0000 \u0000 <p>A longitudinal sample of 144 Caucasian subjects with untreated Class III malocclusion was selected (80% training data; 20% test data). Cephalograms of the subjects of the test group were divided into short- and long-term observations. Sixteen cephalometric landmarks were digitised in an X-Y Cartesian coordinate system. The trained model was a Graph Neural Network. A one-sample <i>t</i>-test and the Euclidean distances between predicted and observed values were calculated.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>In the short-term prediction, 16 subjects were examined. On the X-Y axis, the following cephalometric points were statistically significant: SX, PgY, BY, PNSY, NY and SY. Mean Euclidean distance between predicted and actual values revealed high values for the mandibular points Go (2.6 mm), Me (1.9 mm), Gn (1.9 mm), Pg (2.0 mm), and B (2.0 mm). In the long-term prediction, 13 subjects were examined. On the X-Y axis, the following cephalometric points were statistically significant: MeX, GnX, PgX, BX, BY and PtY. Mean Euclidean distance between predicted and actual values revealed high values for the mandibular points Go (3.1 mm), Me (4.3 mm), Gn (4.1 mm), Pg (4.5 mm), and B Point (4.1 mm).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>The ML-based prediction model was accurate for the majority of the landmarks. Cephalometric mandibular landmarks (Go, Me, Gn, Pg, and B Points) showed the highest mean Euclidean distances between predicted and observed values, indicating lower prediction accuracy.</p>\u0000 </section>\u0000 </div>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":"29 5","pages":"954-962"},"PeriodicalIF":2.7,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/ocr.70142","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147964344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparing Facial Attractiveness and Professional Acceptance Between Real and AI-Generated Orthodontic Treatment Outcome Images","authors":"Gil Guilherme Gasparello,&nbsp;Otso Tirkkonen,&nbsp;Sergio Luiz Mota-Júnior,&nbsp;Felipe Calgaro Martins,&nbsp;Marco Antonio Dias da Silva,&nbsp;Orlando Motohiro Tanaka","doi":"10.1111/ocr.70144","DOIUrl":"10.1111/ocr.70144","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Facial attractiveness influences social and professional perceptions, including competence and employability. With the increasing use of artificial intelligence (AI) to generate photorealistic faces, it is important to understand how these images compare to real orthodontic treatment outcomes.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Objective</h3>\u0000 \u0000 <p>To compare perceptions of real versus AI-generated orthodontic treatment results in terms of attractiveness, employability, and distinguishability.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A cross-sectional online survey included 288 Brazilian adults.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Participants</h3>\u0000 \u0000 <p>Dentists (<i>n</i> = 76), dental students (<i>n</i> = 63), and laypeople (<i>n</i> = 149). Each evaluated three sets of images (pre-treatment, post-treatment, and AI-generated post-treatment) for three patients. Participants rated facial attractiveness (VAS 0–100), assessed employability, and identified whether the image was AI-generated.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>AI-generated images were rated significantly more attractive than real post-treatment ones (mean VAS: AI = 68.8; Real = 54.4; <i>p</i> &lt; 0.001). Dentists, students, and laypeople all rated AI images higher. Employability was also greater for AI images (50.4%) than real ones (39.1%) (<i>p</i> = 0.007). Misclassification was common, with dental students achieving the highest accuracy (66.8%).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>Participants showed limited ability to accurately distinguish between real and AI-generated images. AI-generated images were perceived as more attractive and had a greater positive impact on employability judgements compared to real post-treatment images.</p>\u0000 </section>\u0000 </div>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":"29 5","pages":"963-971"},"PeriodicalIF":2.7,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/ocr.70144","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147964264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association Between Facial Profile Attractiveness and Full-Face Attractiveness in Individuals With Convex Facial Profiles","authors":"Simos Psomiadis,&nbsp;Nikolaos Gkantidis,&nbsp;Ioannis Iatrou,&nbsp;Iosif Sifakakis","doi":"10.1111/ocr.70145","DOIUrl":"10.1111/ocr.70145","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Objectives</h3>\u0000 \u0000 <p>Facial attractiveness significantly influences social and personal outcomes, and therefore, interventions in orthodontics and maxillofacial surgery often aim at enhancing facial appearance. This study investigated the relationship between facial profile attractiveness and overall (frontal and profile) facial attractiveness to determine whether assessments relying solely on profile views sufficiently capture comprehensive facial evaluation.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Materials and Methods</h3>\u0000 \u0000 <p>The sample consisted of 36 Class II Division 1 individuals with convex profiles, balanced in sex distribution. Ratings were provided by orthodontists, surgeons, patients, and laypersons. Facial attractiveness was evaluated using a validated visual analogue scale, comparing profile-only images with images showing the frontal and profile facial views simultaneously.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>A moderate to strong positive correlation between profile and overall facial attractiveness was demonstrated across all rater groups (Pearson's <i>r</i> = 0.62–0.84). Surgeons tended to rate profiles less favourably than the overall face, while laypeople rated profiles higher. Median absolute differences between profile and overall attractiveness ratings reached 8.3/100, with deviations occasionally reaching clinically significant levels in individual cases. The variation in ratings suggests that factors beyond profile attractiveness influence overall facial attractiveness. Scatter plot analyses revealed stronger correlations among specialists compared to non-specialists.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>These findings highlight the limitations of relying solely on profile assessments for treatment planning and outcome evaluation in patients with convex profiles. Comprehensive evaluation of multiple facial aspects, ideally including 3D analysis, is recommended to better address patients' aesthetic concerns and social functionality.</p>\u0000 </section>\u0000 </div>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":"29 5","pages":"937-944"},"PeriodicalIF":2.7,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/ocr.70145","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147942407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative Evaluation of Modified Vacuum-Formed Aligners Versus Conventional Micro-Implant Anchorage in Molar Intrusion for Pre-Restorative Orthodontics","authors":"Tiancong Wang,&nbsp;Yuan Zhang,&nbsp;Jun Ji,&nbsp;Xiang Yan","doi":"10.1111/ocr.70115","DOIUrl":"10.1111/ocr.70115","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Objective</h3>\u0000 \u0000 <p>This study aimed to compare the efficacy of modified vacuum-formed aligners (clear aligners with three-dimensional digital design) versus conventional micro-implant anchorage in molar intrusion for pre-restorative orthodontic treatment.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A total of 91 patients requiring pre-restorative orthodontic treatment were enrolled from Nanjing Stomatological Hospital, Affiliated Hospital of Medical School, Institute of Stomatology, Nanjing University between January 2022 and December 2025. All participants exhibited overeruption of antagonist molars due to long-term absence of mandibular first or second molars, resulting in insufficient space for implant restoration and occlusal plane disturbance, thus requiring molar intrusion prior to prosthetic rehabilitation. Patients were divided into two groups: the aligner group (<i>n</i> = 44, treated with digitally designed clear aligners) and the anchorage group (<i>n</i> = 47, treated with traditional micro-implant anchorage).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The anchorage group achieved significantly greater buccal and palatal intrusion than the aligner group (<i>p</i> &lt; 0.05). Postoperative VAS scores at 24 h and 3 days in the aligner group were lower than those in the anchorage group (<i>p</i> &lt; 0.05). Both groups showed comparable intrusion of buccal, palatal, mesial, and distal cusps (<i>p</i> &gt; 0.05). The aligner group had a shorter treatment duration (<i>p</i> &lt; 0.05). The complication rate in the aligner group was significantly lower than that in the anchorage group (<i>p</i> &lt; 0.05).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>Modified vacuum-formed aligners provided better patient comfort, shorter treatment duration, and fewer complications, whereas micro-implant anchorage demonstrated superior efficiency in molar intrusion. Both techniques achieved satisfactory three-dimensional control, and clinical selection should be based on individual patient needs.</p>\u0000 </section>\u0000 </div>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":"29 5","pages":"840-847"},"PeriodicalIF":2.7,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147486743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Success Rate and Factors Affecting Stability of Buccal Shelf Miniscrew Implants in Orthodontic Patients: A Systematic Review and Meta-Analysis.","authors":"Navleen Kaur Bhatia, Uday Hemant Barhate, Ritu Duggal, Prabhat Kumar Chaudhari, Vilas D Samrit, Rajiv Balachandran, Shivam Pandey","doi":"10.1111/ocr.70175","DOIUrl":"https://doi.org/10.1111/ocr.70175","url":null,"abstract":"<p><p>The primary role of buccal-shelf miniscrew implants (BS-MSI) in orthodontic treatment is to provide extra-alveolar anchorage that alleviates severe crowding and allows for distalization of the entire mandibular arch and may obviate the need for orthognathic surgery, particularly in patients with skeletal malocclusion. The stability of these screws is crucial to their successful function throughout orthodontic treatment. Therefore, this systematic review aimed to assess the success rate and various factors affecting the stability of BS-MSI. The databases were searched electronically using PubMed/MEDLINE, EMBASE, Scopus, and the Cochrane databases on 7th February 2025 and re-searched on 22nd February 2026. The reference list and additional bibliographic databases, including clinical trial registries and Google Scholar, were also searched. This review includes clinical trials published in English, comprising prospective randomised controlled trials (RCTs), non-randomised trials (NRCTs), and retrospective cohort studies (RCs) that described the success rate of BS-MSI for orthodontic anchorage in human subjects. Success rates and associated risk factors for BS-MSI were determined utilising a random-effects model. The determinants influencing stability were categorised into patient, mechanics, and implant-related aspects, and subsequently underwent subgroup analysis and meta-regression. The evaluation of study quality was performed using the Cochrane risk-of-bias tools for randomised trials (RoB 2.0) and non-randomised trials (ROBINS-I). This meta-analysis included nine studies: three RCTs, two NRCTs, and four RCs. A total of 2366 BS-MSI were aggregated in a random-effects model, revealing an overall success rate of 93% (95% CI 0.81-1.00; prediction interval = 0.39-1). In a sensitivity analysis, experiments using more than 100 screws exhibited a 91% success rate, comparable to those with fewer than 100 screws. A meta-regression study indicated an inverse relationship between age and success rate. A considerable heterogeneity was observed across all subgroups. Three assessments indicated a low-, two indicated a moderate-, and four indicated a high-risk of bias. BS-MSI demonstrated a high success rate and therefore can provide a reliable source of orthodontic anchorage. However, given the low certainty and high heterogeneity in the existing evidence, the results should be interpreted with caution. Although numerous factors appear to influence BS-MSI stability, most require further investigation due to inadequate data and data quality. Furthermore, future studies are necessary to corroborate the findings of this meta-analysis and investigate other critical factors, such as location, dental cleanliness, gender, insertion torque, and operator experience, which could not be evaluated due to insufficient data. Trial Registration: PROSPERO registration: CRD420250653597.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148875724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical Outcomes Associated With Integrated Orthodontic Management of Tipped Teeth: A Retrospective Cohort Analysis of Functional Recovery, Occlusal Stability, Complications, and Retreatment.","authors":"Lei He, Rujuan Gong","doi":"10.1111/ocr.70177","DOIUrl":"https://doi.org/10.1111/ocr.70177","url":null,"abstract":"<p><strong>Background: </strong>Tipped teeth are frequently managed by orthodontic uprighting, retention, and subsequent tooth-preserving or restorative care, but real-world pathways are heterogeneous. Evidence comparing coordinated treatment pathways with less standardised management remains limited, and observational comparisons require careful interpretation.</p><p><strong>Methods: </strong>We retrospectively analysed 204 adult patients with at least one tipped tooth requiring clinical management at a single tertiary dental centre from January 2021 to January 2025. The integrated pathway group received orthodontic uprighting followed by standardised retention and coordinated preservation or restorative care (n = 127). The non-standard management group included patients treated by direct restorative treatment without orthodontic uprighting (n = 45) and patients treated orthodontically without standardised retention or coordinated restorative follow-up (n = 32). Patients were classified according to the treatment pathway selected at the initial treatment decision and index intervention stage. Outcomes were assessed at the patient level and included satisfactory functional recovery, occlusal stability, complications, retreatment, and an exploratory composite of overall treatment success. Baseline balance was summarised using standardised mean differences in addition to p values. Multivariable logistic regression was used only as an exploratory adjustment for prespecified pretreatment covariates; causal language was avoided.</p><p><strong>Results: </strong>Of 242 potentially eligible patients, 38 were excluded, leaving 204 patients for analysis. Satisfactory functional recovery was recorded more often in the integrated pathway group than in the non-standard management group (89.8% [114/127] vs. 75.3% [58/77], p = 0.006). Occlusal stability was also more frequent (86.6% [110/127] vs. 70.1% [54/77], p = 0.004). Complications occurred in 13.4% (17/127) and 27.3% (21/77), respectively (p = 0.011), and retreatment was required in 8.7% (11/127) and 18.2% (14/77), respectively (p = 0.028). Exploratory adjusted estimates suggested higher odds of the composite adverse outcome with severe initial inclination and direct restoration without uprighting; however, the low events-per-variable ratio limited model stability and precluded confirmatory interpretation.</p><p><strong>Conclusion: </strong>In this retrospective cohort, integrated orthodontic-retention-restorative management was associated with more favourable functional and clinical outcomes than heterogeneous non-standard management. Because treatment selection was not randomised and some outcome definitions relied on routine clinical records, the findings should be interpreted as hypothesis-generating rather than causal.</p>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148866331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of a Facial Dysmorphology Analysis Algorithm (Face2Gene) in Identifying Treacher Collins Syndrome Amongst Diverse Population","authors":"Jie Han Timothy Sng,&nbsp;Jonas Jun Jie Hue,&nbsp;Josep Rubio-Palau","doi":"10.1111/ocr.70113","DOIUrl":"10.1111/ocr.70113","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Treacher Collins Syndrome (TCS) is an uncommon congenital disease of the craniofacial complex. While there are ‘classic’ facial manifestations of TCS, they present with a wide range of variability. Face2Gene (F2G) is a deep-learning algorithm that can provide differential diagnoses of syndromes via analysis of 2-dimensional facial images. This may aid early recognition of TCS, thus improving early multidisciplinary management. Our primary aim is to evaluate and compare the performance of F2G in TCS patients of various races. The secondary aim will be to correlate the pathognomonic facial features of these TCS patients with the diagnostic stratification by F2G.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Publicly available images of TCS patients of White (<i>n</i> = 81), Chinese (<i>n</i> = 23), and Indian (<i>n</i> = 23) race were sourced for and screened prior to inclusion for documentation of facial dysmorphological features and F2G evaluation. The diagnostic sensitivity of F2G and computed gestalt score of TCS for each image were then derived. Statistical analysis for correlation between clinical features and F2G-derived gestalt scores for the TCS patients was performed.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>A total of 127 images of TCS patients were analysed by F2G. A high diagnostic accuracy of 93.7% was obtained. However, F2G was less confident when diagnosing Asians with TCS than White individuals (<i>p</i> &lt; 0.05). Malar hypoplasia was less prevalent in Indian TCS patients (<i>p</i> &lt; 0.001). However, multidimensionality reduction showed no significant differences across the racial groups. Certain facial features were associated with higher model certainty in TCS diagnosis.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>F2G is a useful diagnostic adjunct for TCS. Nonetheless, further training on non-White datasets may help improve model certainty in diagnosis.</p>\u0000 </section>\u0000 </div>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":"29 4","pages":"680-687"},"PeriodicalIF":2.7,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/ocr.70113","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147434732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the Artificial Intelligence Driven Monitoring System Notifications: Clear Aligner and Oral Hygiene Perspectives","authors":"Analia Tahir,&nbsp;Budi Kusnoto,&nbsp;Phimon Atsawasuwan,&nbsp;Grace Viana,&nbsp;Veerasathpurush Allareddy,&nbsp;Tolga F. Tozum,&nbsp;Mohammed H. Elnagar","doi":"10.1111/ocr.70120","DOIUrl":"10.1111/ocr.70120","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Introduction</h3>\u0000 \u0000 <p>The widespread use of smartphones presents a remarkable opportunity for real-time management of orthodontic treatment. The development of orthodontic smartphone applications, such as Dental Monitoring (DM), epitomises the use of Artificial Intelligence Driven Remote Monitoring (AIDRM) for sophisticated image analysis. The primary aim of this study is to evaluate the validity of DM's AI image analysis notification software in detecting unfavorable clinical conditions regarding clear aligner and oral hygiene concerns.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Twenty-three patients undergoing clear aligner treatment with the implementation of DM were recruited for this study. To assess the validity of DM's AI image analysis software in detecting unfavourable clinical conditions, all notifications were compared to the ‘gold standard’ orthodontist visual exam of uploaded DM scans. A range of 533–1425 observations were assessed for identifying generalised and localised detection of clinical conditions regarding clear aligner and oral hygiene parameters. Then, the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Dental Monitoring AI image analysis software demonstrated a higher accuracy for generalised detection of clear aligner and oral hygiene parameters, while a lower accuracy was demonstrated for localised detection of stated parameters.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Dental monitoring is a viable option for clinical use in remotely monitoring clear aligner and oral hygiene parameters during clear aligner orthodontic treatment. However, the clinician should remain aware that the AI notification software has trouble identifying specific areas of clinical issues, and therefore, the monitoring is not fully automated and must be closely followed by the overseeing orthodontist.</p>\u0000 </section>\u0000 </div>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":"29 4","pages":"728-736"},"PeriodicalIF":2.7,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147609475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sector Classification of Unerupted Maxillary Canines: A Deep Learning-Based Automated Framework Using Panoramic Radiographs","authors":"Marzio Galdi,&nbsp;Davide Cannatà,&nbsp;Flavia Celentano,&nbsp;Luigia Rizzo,&nbsp;Domenico Rossi,&nbsp;Tecla Bocchino,&nbsp;Genoveffa Tortora,&nbsp;Stefano Martina","doi":"10.1111/ocr.70106","DOIUrl":"10.1111/ocr.70106","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Objectives</h3>\u0000 \u0000 <p>To develop a deep learning-based framework to automate sector classification of unerupted maxillary canines (UMCs), assessing its accuracy and reliability compared to human ones.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Material and Methods</h3>\u0000 \u0000 <p>One thousand five hundred twenty-eight UMCs from digital panoramic radiographs (PRs) were selected using data from the Dental Department, “San Giovanni di Dio e Ruggi d'Aragona” Hospital, Salerno. After a training session with an expert in sector classification, six dental practitioners allocated UMCs of a 20% random sample of the original set (T0) in 3 different sectors according to Kim's sector classification system. The assessment was repeated after 4 weeks (T1). The accuracy and reliability of the human in determining the position of the canines were defined based on the level of agreement between the trainer and the examiners and the intra-examiner agreement, respectively, both assessed through Cohen's K. The same radiographs were tested on different artificial intelligence (AI) models, pre-trained on the extended dataset. The best-performing model was identified based on its sensitivity and precision, and the model accuracy and repeatability were determined.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Regarding UMC allocation according to different sectors, the agreement between examiners and trainer was 0.78 (95% confidence interval = 0.77–0.80). The overall intra-examiner agreement was 0.85 (95% confidence interval = 0.83–0.87). DenseNet121 proved to be the best-performing model in allocating UMCs in the three different sectors, with an overall accuracy and repeatability of 76.8% and 95.3%, respectively.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>The developed framework provides an automated approach in sector classification of UMCs, whose accuracy is comparable to that of humans, but the reliability is greater.</p>\u0000 </section>\u0000 </div>","PeriodicalId":19652,"journal":{"name":"Orthodontics & Craniofacial Research","volume":"29 4","pages":"631-639"},"PeriodicalIF":2.7,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/ocr.70106","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147344625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}