Background: Artificial intelligence (AI) is increasingly being integrated into dental implantology, particularly in treatment planning, a critical phase for implant success. Traditionally dependent on clinician expertise, planning can now be supported by AI-assisted systems that aim to improve diagnostic accuracy, precision, and efficiency. Objective: To synthesise recent evidence on the use of AI in dental implant planning, particularly its ability to analyse cone beam computed tomography (CBCT) imaging to identify edentulous regions and assess bone dimensions compared with conventional planning methods. Methods: A systematic search was conducted across PubMed, Scopus, Google Scholar, and the Cochrane Library, with additional manual searches from October 2024 to July 2025. Eligibility was defined using the Population, Intervention, Comparison, Outcome (PICO) framework, focusing on adults undergoing implant procedures planned using AI-assisted CBCT imaging and deep learning (DL) models, particularly U-Net architectures, for CBCT segmentation. Results: Ten studies were included, AI systems demonstrated high accuracy (92–99.7%) in detecting teeth and edentulous regions, with precision and recall frequently exceeding 90%. AI-assisted planning also showed improved efficiency, and, in one study, higher implant success rates compared with traditional planning (92% vs. 78%). However, variability in study design, inconsistent reporting, and limited ethical oversight were noted. Conclusions: AI, particularly DL models applied to CBCT imaging, shows strong potential to enhance diagnostic precision and efficiency in dental implant planning. Nevertheless, the field requires standardised evaluation metrics, larger datasets, and well-designed clinical trials before widespread clinical implementation.
Zaman et al. (Thu,) studied this question.