Removing plastic carrier obturators during root canal retreatment is challenging and often takes a long time. The aim of this laboratory investigation is to compare a recently described indirect, two-stage technique for removing plastic carriers from curved canals and evaluate its efficiency, safety and efficacy in comparison to a conventional direct technique. Thirty-six extracted mandibular premolars were chosen and root filled with plastic carrier obturators and endodontic cement. The teeth were allocated randomly into two different retreatment techniques: Group 0 (Direct technique), where the plastic carriers were removed together with the gutta-percha using rotary NiTi files; Group 1 (Indirect technique), where the carriers were removed first using an ultrasonic tip and Hedström files, with the surrounding gutta-percha being removed subsequently with rotary NiTi endodontic files. The duration of retreatment procedures, number of fractured instruments and plastic carriers, ledge formation, apical transportation and root canal perforations were recorded for each technique, as well as the amount of remaining root filling material. The Student’s t-test and Fisher’s exact tests were used to determine significant differences among groups for each variable. Removal of root fillings was significantly more rapid in Group 1 (p < 0.05). Fracture of the carrier, ledge creation and apical deviation, occurred significantly less often in Group 1 (p < 0.05), although the intergroup comparisons of the other variables revealed no significance differences (p > 0.05). Root canal perforations did not occur in either group. In this laboratory study on extracted teeth, the indirect technique of removing plastic carriers before the gutta-percha was more rapid and associated with fewer intra-operative complications in terms of fracture of the carrier, ledge formation and apical transportation.

AIM:To develop a comprehensive classification system for unrepaired iatrogenic tooth perforations to improve diagnosis, treatment planning, communication, and standardisation in clinical practice and research. METHODOLOGY:A structured multi-phase consensus methodology was employed to develop a comprehensive classification of unrepaired iatrogenic tooth perforations. A steering committee consisting of international experts developed an initial draft classification comprising various domains, categories, codes, their descriptions, and explanatory notes. An online Delphi process involving a global community of academic and clinical endodontic specialists, general dental practitioners, and postgraduate students was conducted to evaluate the clarity of the text and whether each category should be included. A discussion on the feedback from the Delphi process and a general debate of the classification was held subsequently by a group of international experts during an online meeting. The steering committee then revised the classification based on the feedback. RESULTS:A total of 26 international experts participated in the online Delphi process, which was completed in a single round as over 70% of members assigned a score between 7 and 9 for each domain, thus fulfilling the study design set out a priori. The subsequent online meeting was attended by 15 experts plus the steering committee. The classification consists of an alphanumeric coding system designed to allow consistent clinical characterisation of iatrogenic perforations and enhance communication between stakeholders. It consists of seven domains: endodontic status at the time of perforation, degree of infection, treatment stage at which perforation occurred, size of perforation, level of perforation, root surface of perforation, and pathosis in the periradicular tissues adjacent to the perforation. CONCLUSIONS:A comprehensive classification system for iatrogenic tooth perforations was developed using a structured consensus process involving international experts. The classification integrates biological, procedural, and anatomical factors into a unified and comprehensive framework that has the potential to enhance clinical decision-making, communication, and standardisation in research and clinical practice. The classification enables standardised data collection to explore relationships between perforation characteristics, treatment strategies, and clinical outcomes. This will facilitate future research aimed at developing evidence-based treatment algorithms and prognostic models.

Objectives To describe the potential of digital twin (DT) technology to enhance personalised root canal treatment within endodontics, drawing upon its established applications in various healthcare sectors. Discussion DT models are gaining traction as transformative tools for enabling individualised decision-making across different medical disciplines. These models leverage multimodal patient data to simulate physiological and clinical outcomes. In endodontics, DTs could facilitate the simulation of intricate parameters, such as root canal morphology, access cavity preparation, microbial biofilm dynamics, disinfection protocols, clinical techniques for root canal preparation and filling, and the long-term behaviour of restorations. The application of DTs will empower clinicians to formulate more tailored treatment plans and improve prognostic predictions. Beyond their clinical applications, DTs can enrich research settings, linking laboratory research with tailored patient care. While deploying DTs in endodontics remains largely aspirational at this stage, it has the potential to shift the paradigm from standardised approaches to personalised treatments. Key challenges to address include data standardisation, interoperability among systems, ethical regulations, and the need for specialised clinician training. This article suggests actionable strategies for the translational development of DTs in endodontics, inspired by successful frameworks in other medical domains. Conclusion DT models can reshape the vision in endodontics, facilitating real-time, patient-specific simulation and clinical decision-making. Moreover, DT technology presents a cohesive framework that could enhance precision in endodontic practice while also expediting the translation of research findings into clinical applications. This advancement may lead to the development of personalised and predictive approaches to root canal treatment, significantly improving patient outcomes.

AIM:To establish a novel comprehensive three-dimensional coding system for the classification of teeth with dens invaginatus (DI) using cone beam computed tomography (CBCT) imaging. METHODOLOGY:An initial draft classification of teeth with DI was developed by the project directors and steering group based on the interpretation of CBCT images. A group of 26 global experts then provided their perspectives on the classification via a consensus-building online Delphi process. Following the achievement of consensus, six endodontists independently examined CBCT images of teeth with DI to evaluate the reliability of the draft classification. Inter-rater reliability was employed to ascertain the agreement among the six assessors and intra-rater reliability was assessed following the re-evaluation of the identical CBCT images 3 weeks later. The steering group then revised and finalized the classification. RESULTS:The online Delphi process was completed in a single round with a 100% response rate. The inter-rater reliability score of 0.89 and the intra-rater reliability score of 0.88 revealed "almost perfect" agreement among and within the evaluators. The final CARES classification of teeth with DI includes five domains: Communication (C), cross-sectional Anatomy (A), Root formation (R), vertical Extent (E), and Supplementary features (S). CONCLUSION:The three-dimensional CARES classification system provides stakeholders with a consistent and unambiguous method of categorizing teeth with DI. The system has the potential to enhance the precision of diagnosis and clinical decision-making during the management of DI and ensures clinicians can communicate more accurately with patients and other healthcare professionals.

Background:This study aimed to evaluate treatment decision-making processes when assessing periapical radiographs of teeth with post-treatment apical periodontitis (AP) among dental students (DS), general dental practitioners (GDP), and endodontists (E) within Chile, and to identify demographic and tooth-related factors associated with extraction decisions. Material and Methods:A cross-sectional study was conducted between 2023 and 2024, involving 431 participants who assessed standardised periapical radiographs depicting clinical scenarios and selected one treatment option: root canal retreatment, apical surgery/intentional replantation, or extraction. A nested mixed logistic regression model and simple logistic regression analyses were performed to evaluate associations between treatment choices and clinician- or tooth-related variables (p &lt; .05). Results:Demographic factors significantly associated with extraction decisions included professional group, age, and workplace. GDP and DS were significantly more likely to recommend extraction (p &lt; 0.001 for both), particularly among GDPs aged 36-45 years (p = 0.003) and those working in the public sector. All tooth-related variables significantly influenced decisions. Teeth with indirect restorations were associated with higher extraction rates, especially among GDP (p &lt; 0.001). Inadequate root canal fillings significantly increased extraction decisions by GDPs (p &lt; 0.001). GDPs also had a strong tendency to extract teeth with medium (p &lt; 0.001) and large apical lesions (p = 0.001). Conclusions:Significant differences were observed across professional groups, with E demonstrating a greater tendency toward tooth preservation. Improving clinical decision-making in undergraduate and continuing dental education may help reduce unnecessary extractions and support evidence-based health planning in underserved areas with limited access to specialist care.

Background Overviews of systematic reviews, or umbrella reviews, synthesize evidence across related research questions and inform clinical practice, policy, and research prioritization. A core component of overviews is the methodological appraisal of included systematic reviews, which guides interpretation, weighting of evidence, and confidence in conclusions. Although structured tools such as A Measurement Tool to Assess Systematic Reviews 2 (AMSTAR 2) and the Risk of Bias in Systematic Reviews (ROBIS) are commonly applied, these assessments remain interpretive, requiring judgment about reporting adequacy, methodological decisions, and the distinction between conduct and reporting limitations. Evidence shows substantial variability in ratings across research teams, even when using standardized instruments, and systematic review authorship or professional allegiance can influence appraisals, potentially affecting conclusions and comparability across overviews. Discussion To address these challenges, this commentary proposes a participatory validation framework in which overview authors conduct independent methodological appraisals and subsequently invite authors of included systematic reviews to comment on and reassess these judgments. Responses are compared with the original assessments, and areas of agreement and disagreement are transparently documented without requiring consensus. The framework is intended to enhance transparency and interpretability by making concordance and discordance visible rather than to establish a single definitive rating or resolve all disagreement. The framework is feasible within existing workflows, with minimal disruption beyond sharing assessments and documenting responses. Ethical considerations, such as potential self-serving bias, are mitigated through independent initial appraisal, anonymous reassessment, and transparent reporting. While adoption may be limited by selective participation and administrative burden, the framework represents a pragmatic, exploratory strategy to improve transparency, credibility, and interpretability of methodological appraisal in overviews, providing richer, more informative guidance for authors, guideline developers, policymakers, and the broader evidence synthesis community.

AIM:To outline the biological and electrochemical principles supporting impedance-guided localisation of pulp chambers and canal orifices in calcified root canal systems, and to present an accessory concept relating to impedance patterns at the coronal dentine-gutta-percha interface, potentially serving as a surrogate marker of fluid leakage associated with deficient non-conductive root fillings. SUMMARY:Calcific metamorphosis produces structural alterations that complicate localisation of pulp chambers and canal orifices. Adjunctive modalities such as CBCT, guided endodontics, microscopic magnification and ultrasonic troughing provide geometric information but lack real-time biological feedback. Electrical impedance behaviour differs significantly between sclerotic dentine and residual conductive pathways and offers a biological cue during access. The impedance-guided localisation concept applies these principles through a structured, conservative workflow. In addition, impedance patterns observed at coronal dentine-gutta-percha interfaces will, in theory, reflect electrochemical variations associated with potential fluid leakage and the reduced effectiveness of existing non-conductive root fillings to provide a fluid-tight seal. CONCLUSION:Impedance-guided localisation may provide a biologically grounded adjunct to visual and geometric strategies for locating pulp chambers and canal orifices when managing calcified root canal systems during root canal treatment. The interface-related impedance concept serves as an optional scientific extension, derived from established electrochemical principles, that may offer insight into potential fluid leakage or reduced sealing effectiveness associated with non-conductive root canal fillings. CLINICAL SIGNIFICANCE:Impedance-guided pulp chamber and canal orifice localisation provides real-time biological feedback that reduces the risk of iatrogenic perforations and enhances conservative dentine management, particularly for inexperienced clinicians with potential relevance for preclinical training and early clinical education. The accessory interface-related impedance concept may offer surrogate insight into potential leakage or reduced sealing effectiveness of root fillings.

The management of iatrogenic perforations in the permanent dentition is challenging. Early detection and timely repair of iatrogenic tooth perforations are crucial for achieving a favourable prognosis. This article brings together information on the factors that affect the success of perforation repair and categorises them into three domains: Perforation-related, patient-related, and clinician-related. By analysing the existing literature, the review offers a holistic perspective on how these factors impact the prognosis of perforation repair, providing useful guidance for clinical decision-making and risk evaluation. In highlighting the current limitations within the evidence base, the review also suggests avenues for future research aimed at enhancing the predictability and success rates of iatrogenic perforation repair in contemporary endodontic treatment.

Objectives An inherent `black box` nature of artificial intelligence (AI) remains a significant barrier to clinical adoption. Explainable artificial intelligence (XAI) has emerged as an approach to enhance transparency and interpretability. This narrative review evaluates the evolving role of XAI, with particular emphasis on its current applications, prospective utility in endodontics, and inherent challenges. Data and Sources A search was conducted across databases, including PubMed and Scopus, covering literature up to April 2026. The retrieved studies were subsequently synthesised narratively. Study selection Studies on the discourse surrounding XAI were reviewed, including the technical foundations of XAI, applications of XAI in dentistry and endodontics, the benefits and challenges of XAI in endodontics, and research gaps and future directions in XAI for endodontics. Conclusion The investigation of XAI in endodontics remains relatively limited. The literature review highlights the necessity of XAI systems that are methodologically rigorous, clinically relevant, and ethically sound, with their development supported by well-designed prospective studies. XAI development should be advanced as a transformative framework that strengthens the speciality’s evidence base and enables interpretable, equitable, and precisely tailored treatment strategies. XAI has the potential to support more transparent, personalised, and reliable endodontic care. Clinical Significance By enhancing the transparency of AI systems, XAI have the potential to improve clinical decision-making in endodontics and contribute to the delivery of high-quality, patient-centred care.

OBJECTIVES:To validate DT-RAG, a curated retrieval-augmented generation system for dental traumatology decision support, against eight commercial large language models. METHODS:A knowledge base of 250 curated text units ("chunks") from five authoritative sources (IADT 2020, ESE 2021, Krastl 2021, AAE 2013, Cochrane) was built and deployed with Gemini 2.5 Flash as base model. In Study 1, 99 binary clinical questions were submitted in three runs to DT-RAG and eight LLMs; modal accuracy was compared by McNemar exact tests with Holm correction. In Study 2, seven blinded specialists scored DT-RAG against three frontier LLMs on ten clinical scenarios using a 92-point rubric; differences were estimated by linear mixed-effects regression. RESULTS:DT-RAG achieved 96.0% modal accuracy (95% CI 90.1-98.4), significantly exceeding every commercial LLM (best comparator GPT-5.5 87.9%; paired difference +8.1 pp, 95% CI +2.9 to +14.9; p_Holm = 0.013). The curated knowledge base elevated the base model from 49.5% to 98.0% valid rationale rate, eliminating confabulations in this evaluation (0 vs 21). In Study 2, DT-RAG achieved the highest mean score (82.1/92; 89.3%), significantly exceeding Claude Opus 4.5 (72.6; paired difference +9.6 points, exact Wilcoxon p = 0.016), Gemini 2.5 Pro (60.3) and GPT-4.1 (50.4); all seven evaluators ranked DT-RAG first (Kendall's W = 0.97). CONCLUSIONS:DT-RAG, a curated retrieval-augmented configuration, outperformed frontier-tier general-purpose LLMs on this dental traumatology benchmark, with no confabulated rationales observed among the responses assessed. This approach may be applicable to other well-defined clinical domains with authoritative guidelines. CLINICAL SIGNIFICANCE:Curated retrieval augmentation produced accurate, source-traceable and reproducible responses in dental traumatology under benchmark and simulated-scenario conditions, making every error auditable against its source. Clinical safety requires prospective evaluation.

Autonomous artificial intelligence (AI), such as Medical Intelligence for Reasoning and Action and Articulate Medical Intelligence Explorer, represents an evolution in healthcare AI, extending its capabilities beyond task-specific decision support towards longitudinal clinical reasoning and patient management. Although these systems have been developed in medicine, they raise important questions regarding the future of oral healthcare. This perspective proposes agentic dentistry as a conceptual framework for considering how autonomous AI could eventually influence dental practice. We discuss the potential opportunities of agentic AI to enhance clinical decision-making, care coordination, continuity of care, and personalised treatment, while critically examining the scientific, ethical, educational, regulatory, and professional challenges associated with its translation into dentistry. Finally, we propose a research and policy agenda to support the responsible development of autonomous AI in oral healthcare. By initiating this discussion before widespread clinical adoption, dentistry can proactively shape the future integration of agentic AI.

This case report describes the conservative management of an incompletely erupted, subgingivally positioned mandibular right second molar with extensive caries and periapical pathosis in close anatomical relationship to the IAN canal. Complete extraction was initially considered as a provisional treatment option; however, CBCT revealed partial encirclement of the IAN canal by the roots, leading to a conservative treatment plan comprising root canal treatment followed by coronectomy. The initial treatment involved the extraction of tooth 48, followed by root canal treatment and tooth restoration of tooth 47; the patient declined coronectomy. At the 1-year follow-up, the patient was asymptomatic and periapical radiographs and CBCT scans indicated substantial periapical healing and preservation of the IAN. This case illustrates the role of CBCT-guided conservative endodontic management of impacted teeth as a viable alternative to extraction in high-risk anatomical situations.

Introduction and Aim: High-quality artificial intelligence (AI) models in endodontics require access to diverse, well-annotated datasets. This review introduces federated learning (FL) as a privacy-preserving framework for collaborative AI in endodontics. Methods: In this narrative review, a comprehensive literature search was conducted across databases, encompassing studies published up to April 2026. The search strategy was intentionally broad to facilitate a thorough exploration of the evolution of the relevant concepts. However, to ensure consistency in comprehension and analysis, the review was limited to publications in English. Studies describing the fundamentals and applications of FL were reviewed and comparatively analysed. The narrative review served as the framework for outlining implementation pathways, challenges, and research priorities for its application to diagnostic and decision-support tasks. Results: Traditional centralised training methods face legal and ethical challenges due to data protection regulations. FL allows institutions to retain local patient data while contributing model updates to a central server or decentralised network, thus providing a viable alternative. The article explores FL principles, privacy and security mechanisms, architectures, technical challenges, and adversarial risks. Regulatory and ethical considerations hinge on a mix of advanced technical measures and robust organisational practices. A proposed roadmap for implementing FL includes pilot studies, standardised data processes, clinical validation, and regulatory engagement. FL promises to enhance AI development in endodontics while safeguarding patient privacy, with potential benefits in diagnostics and personalised care. Conclusion: FL could advance AI integration in endodontics, prioritising the protection of patient privacy. This initiative holds the potential to improve diagnostic processes and facilitate personalised treatment approaches. Clinical Relevance: FL enables the development of multicentre AI models without sharing patient data. By leveraging diverse clinical datasets, this approach may improve the accuracy and generalisability of AI systems for endodontic diagnosis, treatment planning, and outcome prediction while preserving patient privacy.

This case report describes the extraction of 3 mandibular posterior teeth (teeth #19, 20 and 21) with extensive invasive external cervical resorption (ECR) followed by guided double auto-transplantation of immature mandibular third molars (teeth #17 and 32). A 17-year-old male with a history of orthodontic treatment reported with intermittent pain in the mandibular left posterior region. Clinical and radiographic examination revealed extensive tooth tissue loss in teeth #19, 20 and 21 that was diagnosed as class 3 ECR (Patel 3Dp for teeth #20 and 21, 3Bp for tooth #19). Guided double auto-transplantation of the immature molar tooth #17 was performed to replace premolar teeth 20 and 21, and tooth #32 to replace tooth #19. At the 6-month follow-up the donor tooth #32 had symptoms of pulpitis and was managed with a full pulpotomy using tricalcium silicate cement. Both teeth were followed-up for 36 months when they were asymptomatic, had no associated periodontal defects, had positive pulp sensibility tests as well as radiographic evidence of substantial periapical bony healing. The roots of tooth #17 had only a limited increase in length, with apical hard tissue barrier deposition, whereas tooth #32 (after pulpotomy) had continued root development. The 36 months follow-up of this case highlights the success of an interdisciplinary approach when integrating three-dimensional guides for double auto-transplantation of immature molars to successfully replace multiple teeth with extensive invasive ECR.