Australian dental journal最新文献

{"title":"Artificial Intelligence in Paediatric Dentistry: A Scoping Review.","authors":"Rata Rokhshad, Antonin Tichy, Jung-Wei Chen, Sadaf Taheri, Salar Motamedi, Falk Schwendicke","doi":"10.1111/adj.70076","DOIUrl":"https://doi.org/10.1111/adj.70076","url":null,"abstract":"<p><p>This review scoped artificial intelligence (AI) in paediatric dentistry to summarize current applications and limitations. A comprehensive literature search was completed across PubMed, Google Scholar, Scopus, Embase, IEEE Xplore, and medRxiv/aArXiv. The preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) checklist was used for reporting the present study. Studies concerning paediatric dentistry and utilizing AI, machine learning (ML) or large language models (LLMs) were included. Two independent reviewers screened and three extracted data on AI methodologies, performance metrics, and clinical applications. Fifty-nine studies were included. Computer vision studies (n = 32) most often used panoramic radiographs (n = 14), mainly for tooth detection, numbering and segmentation (n = 10) and caries detection (n = 9). Non-imaging ML studies (n = 18) primarily used clinical variables and questionnaire data (n = 8) or salivary/biological samples (n = 10). Accuracy ranged from 50% to 100%, with sensitivity reaching 100% in biomarker-based studies. LLM accuracy varied widely (33%-96%). Computer vision and non-imaging ML show promise for paediatric dentistry, particularly in the detection of dental structures and diseases, as well as risk stratification. Variable LLM performance underscores the need for standardized evaluation before clinical integration. CLINICAL RELEVANCE: AI-based tools may support paediatric dentists by improving tooth detection, dental structure assessment, caries detection, disease prediction and risk stratification. Computer vision and non-imaging machine learning approaches appear to have potential, but their clinical value depends on robust external validation, transparent reporting and integration into paediatric dental workflows. Given their variable performance, AI tools should be used only as adjunctive tools or a second reviewer.</p>","PeriodicalId":8593,"journal":{"name":"Australian dental journal","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149227016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 Screening for Osteonecrosis of the Jaw in Panoramic Radiographs.","authors":"Valéria Nagyová, Dominik Blaňár, Jan Kybic, Antonín Tichý","doi":"10.1111/adj.70071","DOIUrl":"https://doi.org/10.1111/adj.70071","url":null,"abstract":"<p><strong>Background: </strong>Osteonecrosis of the jaw (ONJ) is a serious condition associated mainly with antiresorptive therapy and maxillofacial radiotherapy. As detection of its radiographic findings may facilitate patient referral, this study aimed to develop convolutional neural networks (CNNs) for ONJ screening in panoramic radiographs (OPGs).</p><p><strong>Methods: </strong>A dataset of 888 ONJ-positive OPGs and 888 ONJ-negative controls was assembled and annotated using bounding boxes. The dataset was split at patient level 70-10-20 for training, validation, and testing. Multiple CNNs (ResNet18, ResNet34, MobileNetV2, EfficientNet-B0) were trained on cropped image regions and evaluated using standard performance metrics. Performance on full OPGs (without cropping) was tested, and subgroup analysis was performed. Regions contributing to model predictions were visualised using Gradient-weighted Class Activation Mapping (Grad-CAM).</p><p><strong>Results: </strong>EfficientNet-B0 performed best, with per-crop accuracy, sensitivity, specificity, precision, and F1-score of 92.24%, 89.80%, 94.69%, 94.42% and 82.05%, respectively. At 0.9 probability threshold, per-image accuracy, sensitivity, specificity, precision, and F1-score equalled 76.65%. Grad-CAM highlighted clinically relevant regions; however, differentiation from other changes in bone density was suboptimal.</p><p><strong>Conclusions: </strong>Despite promising results at crop level, model performance in full OPG analysis is currently insufficient for clinical application. Further optimisation of localisation strategies and external validation are needed for reliable clinical application.</p>","PeriodicalId":8593,"journal":{"name":"Australian dental journal","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149222977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Diagnosis to Decision-Making: AI-Driven Triage of Oral Mucosal Lesions Detected on Intraoral Photographs.","authors":"Julia Schwärzler, Ekaterina Tolstaya, Antonin Tichy, Tami Yap, Michael McCullough, Yoana Malenova, David Steybe, Sven Otto, Sebastian Paris, Falk Schwendicke","doi":"10.1111/adj.70079","DOIUrl":"https://doi.org/10.1111/adj.70079","url":null,"abstract":"<p><strong>Background: </strong>Managing oral mucosal lesions in general dental practice is challenging, as visually similar conditions may require very different treatments. We developed an AI-based triage system connecting intraoral image analysis with guideline-based treatment recommendations, tested it externally, and compared its performance with clinicians' recommendations.</p><p><strong>Methods: </strong>YOLOv8 and YOLOv11 were trained on 4079 intraoral photographs to classify 11 oral mucosal lesion types. These were mapped into five treatment tiers defined by urgency and management aim: T1 specialist referral for malignant and high-risk lesions, T2 interdisciplinary referral for specialist-led non-cancer management, T3 risk-adapted surveillance, T4 dental treatment with reassessment, and T5 no treatment. Model performance was compared with two general dentists and four specialists on an internal test set. YOLOv11 was additionally tested on an external dataset.</p><p><strong>Results: </strong>YOLOv11 outperformed YOLOv8 in macro-averaged precision, recall, and F1 score, achieving 0.72, 0.74, and 0.73 respectively. However, 25% of T1 high-risk cases were under-triaged. YOLOv11 significantly outperformed all clinicians, whose F1 scores ranged from 0.33 to 0.69. External performance decreased markedly (F1 score: 0.58), consistent with domain shift.</p><p><strong>Conclusion: </strong>Guideline-oriented AI triage is feasible but requires multicentre training for improved generalizability, as well as safety-focused optimization, and prospective user evaluation before clinical use.</p>","PeriodicalId":8593,"journal":{"name":"Australian dental journal","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149191012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Navigating the Regulatory Landscape of Artificial Intelligence in Australian Clinical Dentistry.","authors":"Rishi Ramani, Arosha Weerakoon, Tami Yap, Bree Jones","doi":"10.1111/adj.70078","DOIUrl":"https://doi.org/10.1111/adj.70078","url":null,"abstract":"<p><p>Artificial intelligence (AI) is rapidly transforming clinical dentistry, with an increasing number of AI-powered diagnostic and treatment planning tools entering the Australian healthcare market. As clinicians adopt AI-based dental software, it is becoming increasingly important to understand the regulatory frameworks that govern them. This narrative review explores the regulatory approval pathways and governance of AI tools used in Australian dental and healthcare settings to inform and educate practitioners. Australia regulates AI-based dental software primarily through the Therapeutic Goods Administration, which classifies eligible products as software as a medical device under a risk-based, technology-agnostic framework established by the Therapeutic Goods Act 1989. AI tools that function as clinical decision-support systems are subject to mandatory conformity assessment and registration on the Australian Register of Therapeutic Goods (ARTG) prior to lawful supply. Although the Australian framework aligns with the International Medical Device Regulators Forum principles, the approval process is comparatively less transparent than that required in jurisdictions such as the United States and the European Union, and questions remain regarding the consistency of post-market oversight. This review also highlights emerging regulatory challenges associated with adaptive AI systems. Software could initially receive approval as a low-risk device that evolves to provide specific clinical advice beyond its approval scope. These updates to functionality risk bypassing established oversight pathways that rely on self-reported intended use. Furthermore, currently available AI tools lack comprehensive public-facing transparent evidence for regulatory compliance that is complicated by ambiguous and inconsistent terminology and adaptive AI system classification. Regardless of regulatory approval, clinicians remain professionally accountable for the use of AI tools in clinical decision-making and for ensuring that patient care meets accepted standards of practice.</p>","PeriodicalId":8593,"journal":{"name":"Australian dental journal","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149191004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond Explainability: Governing Black-Box Artificial Intelligence in Dentistry.","authors":"Amirul Faiz Luai, Aznul Qalid Md Sabri","doi":"10.1111/adj.70077","DOIUrl":"https://doi.org/10.1111/adj.70077","url":null,"abstract":"","PeriodicalId":8593,"journal":{"name":"Australian dental journal","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149164834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perception of Special Needs Dentistry Amongst Allied Dental Professionals in Australia.","authors":"Jessica Francis, Gelsomina Lucia Borromeo","doi":"10.1111/adj.70075","DOIUrl":"https://doi.org/10.1111/adj.70075","url":null,"abstract":"<p><strong>Objective: </strong>In Australia, Dental Therapists (DTs), Dental Hygienists (DHs) and Oral Health Therapists (OHTs) encounter Special Needs (SN) patients in their clinical practice. This study investigates their perception, training, working experience and referral patterns within Special Needs Dentistry (SND).</p><p><strong>Materials and methods: </strong>Paper-based questionnaire was distributed to a systematically selected sample of 1000 registered DHs, DTs and OHTs who were members of professional bodies in Australia. Respondents were included irrespective of age, gender, length of working experience and country of graduation. Data analysis consisted of Chi-squared regression analysis (p < 0.05) using IBM SPSS Windows Version 29.0 (Melbourne, Victoria, Australia).</p><p><strong>Results: </strong>A response rate of 49.8% (215 DTs, 107 DHs and 163 OHTs) was obtained. A significantly larger proportion of OHTs (59.5%) was aware of SND as a specialty compared to DHs (45%) and DTs (41.9%) (p < 0.05) and hence OHTs referred to SND specialists more often than other groups. In addition, 73.6% of OHTs, 63.6% of DHs and 40% of DTs had both didactic and clinical training in SND (p < 0.05). All the categories stated lack of training and continuing professional development (CPD) in SND as the main reasons for not treating SN patients. They therefore expressed interest in attending related CPD training (OHTs: 90.2%, DHs: 88.8% and DTs: 88.3%).</p><p><strong>Conclusions: </strong>OHTs demonstrated greater awareness, training, working experience and referral in SND than DHs and DTs; however, training gaps across all groups highlight the need for strengthened undergraduate education and accessible CPD in SND.</p><p><strong>Clinical relevance: </strong>Understanding the perception of allied dental professionals regarding SND is crucial for improving access to and the quality of care for patients with special needs. Prior research has highlighted gaps in training and confidence levels amongst general practitioners; however, little is known about the perspectives of allied professionals. This study provides valuable insights into their awareness, perceived roles and educational needs, emphasizing the importance of inclusive team-based care.</p>","PeriodicalId":8593,"journal":{"name":"Australian dental journal","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149126452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Micro-Computed Tomography Evaluation of the Marginal and Internal Fit of Ceramic-Filled Resin Crowns Fabricated by Subtractive and Additive Manufacturing.","authors":"Egem Yuvanç, Funda Akaltan, Mert Ocak, Kaan Orhan","doi":"10.1111/adj.70073","DOIUrl":"https://doi.org/10.1111/adj.70073","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this in vitro study was to compare the marginal and internal fit of ceramic-filled resin crowns fabricated using subtractive manufacturing (SM) and additive manufacturing (AM) techniques and to evaluate the effect of stereolithography (SLA) and digital light processing (DLP) technologies on restoration adaptation.</p><p><strong>Materials and methods: </strong>Thirty-three ceramic-filled resin crowns were fabricated for a standardized mandibular first molar preparation and assigned to 3 groups (n = 11): SM, SLA-based AM, and DLP-based AM. Crowns were designed using a standardized digital workflow with a 50-μm cement space and cemented with a radiopaque dual-cure resin cement. Marginal and internal gaps were assessed by micro-computed tomography using linear measurements from coronal and sagittal sections at 18 predefined locations. Non-parametric statistical analyses were performed (α = 0.05), and correlations between marginal and internal gap values were evaluated.</p><p><strong>Results: </strong>Significant differences were identified among manufacturing techniques at selected marginal and internal locations (p = 0.005 to p = 0.047). DLP-fabricated crowns exhibited lower gap values, particularly in the marginal and axial regions. Region-based analysis revealed significant differences between SLA and DLP in the marginal region (p = 0.048) and between DLP and SM in the internal region (p = 0.031). All techniques produced gap values within clinically acceptable limits, and a positive correlation was observed between marginal and internal gaps.</p><p><strong>Conclusions: </strong>The manufacturing technique significantly affected the marginal and internal fit of ceramic-filled resin crowns. Although all techniques produced clinically acceptable results, DLP-based additive manufacturing demonstrated superior overall adaptation. DLP-based additive manufacturing may be considered a predictable alternative to subtractive manufacturing for definitive crown fabrication.</p>","PeriodicalId":8593,"journal":{"name":"Australian dental journal","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149073497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Medication Related Osteonecrosis of the Jaw: Knowledge, Attitudes and Practice Patterns Among Australian Dental Practitioners.","authors":"Ying Shi Chang, Christopher Friel, Gary Low, Albert Yaacoub, Stephen Clive Cox","doi":"10.1111/adj.70074","DOIUrl":"https://doi.org/10.1111/adj.70074","url":null,"abstract":"<p><strong>Background: </strong>Medication related osteonecrosis of the jaw (MRONJ) is a debilitating condition associated with antiresorptive and antiangiogenic therapies. As the use of these medications continues to increase, dental practitioners play a critical role in prevention and management of at-risk patients. This survey evaluated the awareness, knowledge and practice patterns of Australian dental practitioners regarding MRONJ.</p><p><strong>Materials and methods: </strong>A cross-sectional online survey of registered Australian dental practitioners was conducted. The 26-item questionnaire assessed knowledge of MRONJ diagnosis, clinical features, risk factors and practice patterns. Responses were analysed descriptively.</p><p><strong>Results: </strong>A total of 343 dental practitioners participated. Overall MRONJ awareness was high, with 88.6% correctly identifying the principal diagnostic criteria. Knowledge of antiresorptive medications was strong, but familiarity with antiangiogenic agents was limited, with 25% unable to identify any associated medication. Only 62.4% were comfortable assessing MRONJ risk before extraction and just 37.9% comfort in performing extractions in at-risk patients. Public practitioners reported greater MRONJ-related education and clinical confidence than private practitioners.</p><p><strong>Conclusion: </strong>Australian dental practitioners demonstrated strong awareness of MRONJ. However, confidence in providing invasive treatment for at-risk patients remained limited, particularly among private dental practitioners. These findings highlight the need for targeted education and clinical support as the use of MRONJ associated medications continues to increase.</p><p><strong>Clinical relevance: </strong>Although overall awareness of MRONJ is high among Australian dental practitioners, ongoing knowledge and confidence gaps may contribute to variation in clinical practice. Addressing these gaps through continuing professional education, evidence-based guidance, and structured risk assessment may enhance patient safety and optimise the prevention and management of MRONJ.</p>","PeriodicalId":8593,"journal":{"name":"Australian dental journal","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149068867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial Intelligence in Intraoral Scanning: A Narrative Review.","authors":"Camila Tirapelli, Bree Jones, Caio Uehara Martins, Bruna Neves de Freitas, Alessandra Alaniz Macedo, Ruben Pauwels","doi":"10.1111/adj.70068","DOIUrl":"https://doi.org/10.1111/adj.70068","url":null,"abstract":"<p><p>Intraoral scanning (IOS) enables the acquisition of three-dimensional surface models of dental and oral structures, supporting diagnosis, treatment planning and digital workflows. However, many processing steps remain operator-dependent and time-consuming. The integration of artificial intelligence (AI) with intraoral scanning (IOS) represents a rapidly evolving area in digital dentistry, aiming to automate or facilitate tasks such as tooth segmentation, landmark detection, registration and quality control. This narrative review aims to summarise technical principles, current applications, challenges, and opportunities associated with AI applied to IOS data. A narrative approach was adopted to identify and describe recent studies involving AI applications using IOS datasets. Current evidence demonstrates that automated tooth segmentation is the most developed application, with emerging uses in orthodontics, prosthodontics, surgery, and diagnostics. Despite promising performance, challenges persist, including limited dataset availability, variability across scanning systems, annotation complexity, computational demands, and reduced generalisability. Future research should prioritise standardised datasets, external validation, and clinically meaningful outcomes to support safe and effective implementation.</p>","PeriodicalId":8593,"journal":{"name":"Australian dental journal","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149007805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Influence of Span Length on Long-Term Complications of Tooth-Supported Fixed Dental Prostheses.","authors":"Ali Alenezi, Reem Altail, Riham Tork","doi":"10.1111/adj.70072","DOIUrl":"https://doi.org/10.1111/adj.70072","url":null,"abstract":"<p><strong>Aim: </strong>This retrospective study evaluated the long-term clinical performance and complication rates of tooth-supported fixed dental prostheses (FDPs) of different span lengths and assessed the influence of design, span length, material type and location on complication rate.</p><p><strong>Methods: </strong>A total of 199 FDPs placed in 199 patients (mean age: 50.3 ± 12.9 years) were examined clinically and radiographically at a mean follow-up of 9.0 ± 6.3 years. Biological complications (secondary caries, loss of tooth vitality) and technical complications (loss of retention, framework or veneer fracture) were recorded. Biological and technical complications were summarized descriptively. Kaplan-Meier, life-table and univariate and multivariable Cox proportional hazards analyses were performed.</p><p><strong>Results: </strong>The mean observation period was 9.0 ± 6.3 years. At least one complication was detected in 170 FDPs (85.4%); biological complications were detected in 133 (66.8%) and technical complications in 40 (20.1%). Crude total complication frequencies differed by design (p = 0.002), whereas span length was not associated with complication frequency. In the adjusted Cox model, metal-ceramic restorations had a lower hazard of complication detection than full-ceramic restorations (hazard ratio [HR] = 0.400; 95% confidence interval [CI], 0.253 to 0.634; p < 0.001). Cantilever FDPs also showed a lower adjusted hazard than conventional FDPs (HR = 0.578; 95% CI, 0.337 to 0.989; p = 0.046); other adjusted associations were not statistically significant.</p><p><strong>Conclusions: </strong>Biological complications were more frequent than technical complications in this follow-up cohort. The findings support structured long-term maintenance, but comparisons by design and material should be interpreted cautiously because complication onset was approximated by the follow-up examination, historical resolved complications were not systematically captured, and several subgroups were small.</p>","PeriodicalId":8593,"journal":{"name":"Australian dental journal","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148975543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}