Artificial Intelligence in Endodontics: A State-of-the-Art Comprehensive Review
Year: 2026
Type: article
Abstract: Artificial intelligence (AI) is reshaping endodontic practice through advances in diagnostic imaging, treatment planning, prognostic assessment, and clinical decision support. Machine learning and deep learning algorithms, particularly convolutional neural networks, have demonstrated promising capabilities in analyzing periapical radiographs and cone-beam computed tomography (CBCT) datasets for detecting periapical lesions, identifying vertical root fractures, and characterizing root canal morphology. Emerging applications include AI-assisted guided endodontics, dynamic navigation, outcome prediction, and digital education. This state-of-the-art review synthesizes evidence from PubMed/MEDLINE, Scopus, Web of Science, and Google Scholar to critically examine the diagnostic, therapeutic, prognostic, educational, and ethical dimensions of AI in endodontics. Emerging technologies, including explainable AI, radiomics, and integrated digital workflows, are discussed alongside challenges related to dataset heterogeneity, algorithmic transparency, external validation, data privacy, and medico-legal accountability. Current evidence indicates that AI may enhance diagnostic consistency, procedural precision, and individualized treatment planning. However, methodological heterogeneity, limited external validation, and a predominance of retrospective and laboratory-based studies constrain its clinical generalizability. Future translation into routine practice will require robust multicenter validation, standardized reporting, interpretable algorithms, and responsible clinician-supervised implementation. AI should therefore be regarded as an adjunct to, rather than a replacement for, clinical expertise in evidence-based, patient-centered endodontic care.
Institution: Hi-Tech Medical College & Hospital
Language: English
Subfield: Oral Surgery
Field: Dentistry
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W7228923610
