Hung Man, Yevseyevich Daniel, Khazana Milan, Schwartz Connor, Lipsky Martin S
College of Dental Medicine, Roseman University of Health Sciences, South Jordan, UT 84095, USA.
Division of Public Health, University of Utah, Salt Lake City, UT 84108, USA.
Dent J (Basel). 2025 Aug 12;13(8):366. doi: 10.3390/dj13080366.
Dental caries remains a public health concern, and early detection prevents its progression and complications. Panoramic radiographs are essential diagnostic tools, yet the interpretation of panoramic X-rays varies among practitioners. Artificial intelligence (AI) presents a promising approach to enhance diagnostic accuracy in detecting dental caries. This scoping review examines the current literature on the use of AI programs to analyze panoramic radiographs for the diagnosis of dental caries. This scoping review searched PubMed, Scopus, Web of Science, and Dentistry and Oral Sciences Source, adhering to PRISMA guidelines. The review included peer-reviewed, original research published in English that investigated the use of AI to diagnose dental caries. Data were extracted on the AI model characteristics, advantages, disadvantages, and diagnostic performance. Seven studies met the inclusion criteria. The Deep Learning Model achieved the highest performance (specificity 0.9487, accuracy 0.9789, F1 score 0.9245), followed by Diagnocat and Tooth Type Enhanced Transformer. Models such as CranioCatch and CariSeg showed moderate performance, while the Dental Caries Detection Network demonstrated the lowest. Benefits included improved diagnostic support and workflow efficiency, while limitations involved dataset biases, interpretability challenges, and computational demands. Applying AI technologies to panoramic X-rays demonstrates the potential for enhancing caries diagnosis, with some models achieving near-expert performance. However, future research must address the generalizability, transparency, and integration of AI models into clinical practice. Future research should focus on diverse training datasets, explainable AI development, clinical validation, and incorporating AI training into dental education and training.
龋齿仍然是一个公共卫生问题，早期检测可预防其进展和并发症。全景X线片是重要的诊断工具，但全景X线片的解读在从业者之间存在差异。人工智能（AI）为提高龋齿检测的诊断准确性提供了一种有前景的方法。本范围综述考察了关于使用AI程序分析全景X线片以诊断龋齿的当前文献。本范围综述按照PRISMA指南检索了PubMed、Scopus、科学网和牙科学与口腔科学资源库。该综述纳入了以英文发表的、经同行评审的原创研究，这些研究调查了使用AI诊断龋齿的情况。提取了关于AI模型特征、优点、缺点和诊断性能的数据。七项研究符合纳入标准。深度学习模型表现最佳（特异性0.9487，准确性0.9789，F1分数0.9245），其次是Diagnocat和牙齿类型增强变压器。CranioCatch和CariSeg等模型表现中等，而龋齿检测网络表现最差。优点包括改善诊断支持和工作流程效率，而局限性包括数据集偏差、可解释性挑战和计算需求。将AI技术应用于全景X线片显示了增强龋齿诊断的潜力，一些模型达到了近乎专家的表现。然而，未来的研究必须解决AI模型的通用性、透明度以及将其整合到临床实践中的问题。未来的研究应关注多样化的训练数据集、可解释AI的开发、临床验证以及将AI培训纳入牙科教育和培训。
