The use of deep learning technologies in dental practice has been steadily increasing in recent years, accompanied by significant progress in related research. This study provides a comprehensive review of deep learning-based image processing techniques within the field of dentistry, with a particular focus on the performance of models applied in dental segmentation and classification tasks. The analysis reveals that architectures such as U-Net, Mask R-CNN, and YOLO have demonstrated high accuracy in detecting teeth, diseases, and lesions in dental radiographs. By systematically examining studies conducted between 2020 and 2025, this review highlights the potential of deep learning methods to enhance clinical diagnosis and treatment processes, emphasizing the growing importance of automated dental image analysis. The discussion section offers a detailed evaluation of the frequent use and success of U-Net, Mask R-CNN, and YOLO architectures, concluding that deep learning-based approaches can be effectively integrated into clinical workflows. These technologies play a critical role in the early diagnosis of dental pathologies and the development of personalized treatment plans.
Şener et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: