Federated Learning in Endodontics: A Framework for Privacy-Preserving Multicentre Artificial Intelligence

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.

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.

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.

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.

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.