Applications for the YOLO deep learning framework in dentistry: A narrative review

Abstract

Purpose: This narrative review aims to provide dental professionals and researchers with a comprehensive overview of YOLO applications in dentistry.

Study Selection: A narrative review approach was used in this study. Literature relevant to YOLO models in dentistry was identified and organized thematically into dental domains such as dental caries detection, tooth numbering, dental biomaterials and restorative evaluation, prosthodontics and implant planning and treatment, dental education, salivary biomarker analysis, and oral cancer detection.

Results: YOLO-based models consistently achieved high precision and efficiency across diverse applications. Notable successes include reliable caries detection, automated restoration evaluation, support for prosthodontic and implant planning through cone-beam computed tomography analysis, and enhanced educational platforms that provide real-time feedback to students. Emerging studies have further demonstrated YOLO’s role in point-of-care diagnostics through salivary biomarker analysis and the early detection of potentially malignant oral disorders and cancer. Despite these advances, challenges persist, particularly regarding small datasets, variability in imaging protocols, and limited external validation.

Conclusions: YOLO algorithms are a transformative tool in dentistry that enable rapid, accurate, and reproducible image interpretation. Although further validation and standardization are required, YOLO has a strong potential to enhance diagnostics, prosthodontic treatment planning, education, patient-oriented care, and advance dentistry towards greater precision and efficiency.