Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (20): 13-34.DOI: 10.3778/j.issn.1002-8331.2210-0327

• Research Hotspots and Reviews • Previous Articles     Next Articles

Review of Image Segmentation Methods for Dental X-Ray Radiographs

HAN Zhiyuan, JIANG Xijun, WANG Chen, LIU Ruijun   

  1. 1.School of Computer Science and Engineering, Beijing Technology and Business University, Beijing 100048, China
    2.Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing 100048, China
    3.Department of Pediatric Dentistry, Peking University School and Hospital of Stomatology, Beijing 100081, China
  • Online:2023-10-15 Published:2023-10-15



  1. 1.北京工商大学 计算机学院,北京 100048
    2.食品安全大数据技术北京市重点实验室,北京 100048
    3.北京大学口腔医院 儿童口腔科,北京 100081

Abstract: In recent years, with the continuous improvement of national medical standards and the increasing popularity of medical imaging equipment in primary hospitals, medical imaging data has become an important basis for doctors to make pathological diagnoses, and the use of computer technology to process dental medical images has also attracted the interest of researchers. The design of algorithms for the automatic segmentation of regions of interest in dental images has important clinical applications for assisting dentists in diagnosis and improving the efficiency of film reading, and has important research implications for alleviating the intensity of manual segmentation work. Through a review of dental radiograph segmentation methods in the last decade, dental image segmentation methods are classified into methods based on manual features and methods based on deep learning. First, the current status of research on these two categories of methods is reviewed and described. Then, the datasets used and common evaluation metrics of some studies are summarized, and the experimental results of each type of method on the relevant datasets are compared. Finally, the current problems in the field of dental image segmentation and possible directions for future research are analyzed.

Key words: deep learning, dental image segmentation, assisted diagnosis, manual feature

摘要: 近年来,随着国民医疗水平的不断提高,医疗影像设备在基层医院的不断普及,医学影像数据已经成为医生做出病理诊断的重要依据,利用计算机技术处理口腔医学影像也引起了研究人员的兴趣。设计相关算法自动分割牙齿图像中的感兴趣区域,对于辅助口腔医生诊断,提升阅片效率,都有着重要的临床应用价值,同时对缓解手工分割工作强度也有重要研究意义。通过对近十年牙齿X线片分割方法进行回顾,将牙齿图像分割方法分为基于手工特征的方法和基于深度学习的方法。对这两大类方法的研究现状进行了梳理和阐述;总结了部分研究的使用数据集和常用的评价指标,并比较了各类方法在相关数据集上的实验结果;分析了牙齿图像分割领域目前存在的问题和未来可研究的方向。

关键词: 深度学习, 牙齿图像分割, 辅助诊断, 手工特征