In recent years, the application of artificial intelligence technology in the field of orthodontics has gradually increased, and deep learning, as a hot direction, has also been rapidly applied in the detection, evaluation, diagnosis, prediction and effect evaluation. At present, deep learning research has the advantages of high efficiency and accuracy, but it also has limitations such as weak interpretability and insufficient data volume. This paper reviewed the proposal and development of deep learning, the application in orthodontic diagnosis and treatment, as well as the limitations and countermeasures of the popularization, and prospect of the future research.
近年口腔正畸领域人工智能技术的应用研究逐渐增加，深度学习作为其中的热门方向，也迅速被应用于正畸诊疗的检测、评估、诊断、预测以及疗效评价等多个环节。目前，深度学习研究在表现出高效、准确优势的同时，也存在可解释性不强、数据量不足等限制。本文从深度学习的提出与发展、正畸诊疗中的应用以及推广的限制与对策三方面进行综述，并进行展望。.