上海口腔医学 ›› 2024, Vol. 33 ›› Issue (4): 339-344.doi: 10.19439/j.sjos.2024.04.002

• 论著 • 上一篇    下一篇

基于深度学习牙体分割算法的准确性研究

张博钧1, 崔智铭2, 柳稚旭1, 陈思悦1, 顾恺隽1, 李思彤1, 吴艳棋1, 沈定刚2, 朱敏1   

  1. 1.上海交通大学医学院附属第九人民医院 口腔颅颌面科,上海交通大学口腔医学院,国家口腔医学中心, 国家口腔疾病临床医学研究中心,上海市口腔医学重点实验室,上海市口腔医学研究所,上海 200011;
    2.上海科技大学 生物医学工程学院,上海 201210
  • 收稿日期:2023-10-16 修回日期:2023-12-05 出版日期:2024-08-25 发布日期:2024-09-03
  • 通讯作者: 朱敏,E-mail:zminnie@126.com
  • 作者简介:张博钧(1997-),男,硕士,E-mail:1411576398@qq.com
  • 基金资助:
    国家自然科学基金(82001027); 科技部-科技基础资源调查专项课题(2018FY101001); 中国牙病防治基金会(A2021-145); 上海交通大学医学院附属第九人民医院临床研究助推计划(JYLJ202017)

Accuracy of tooth segmentation algorithm based on deep learning

ZHANG Bo-jun1, CUI Zhi-ming2, LIU Zhi-xu1, CHEN Si-yue1, GU Kai-jun1, LI Si-tong1, WU Yan-qi1, SHEN Ding-gang2, ZHU Min1   

  1. 1. Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,Shanghai Jiao Tong University School of Medicine; College of Stomatology, Shanghai Jiao Tong University; National Center for Stomatology; National Clinical Research Center for Oral Diseases; Shanghai Key Laboratory of Stomatology; Shanghai Research Institute of Stomatology. Shanghai 200011;
    2. School of Biomedical Engineering, Shanghai Tech University. Shanghai 201210, China
  • Received:2023-10-16 Revised:2023-12-05 Online:2024-08-25 Published:2024-09-03

摘要: 目的:应用建立的全自动AI牙体分割算法,从CBCT影像中实现牙体的快速自动化分割,以口内扫描真实离体牙获得的三维数据作为金标准,验证算法的准确性。方法:从上海交通大学医学院附属第九人民医院收集30套CBCT数据及相应的59颗离体牙,通过建立的算法,分割出CBCT中的牙体三维数据。将离体牙处理后扫描获得的数字化信息作为金标准。为了比较算法分割结果以及扫描结果之间的差异,选取骰子系数(Dice)、灵敏度(sensitivity,Sen)以及平均表面距离(average symmetric surface distance,ASSD)评价算法的分割准确性。选用组内相关系数(ICC)评价AI系统获得单个牙与数字化离体牙的长度、面积和体积差异。由于存在不同体素大小的CBCT,使用ANOVA单因素方差分析不同体素组间的差异,同时通过SNK法对其进行两两比较。采用SPSS 25.0软件包对数据进行统计学分析。结果:算法分割结果与离体牙扫描结果对比后,得到平均Dice值为(94.7±1.88)%,平均Sen为(95.8±2.02)%,平均ASSD为(0.49±0.12) mm。比较数字化离体牙与AI系统获得的单个牙的长度、面积和体积的组内相关系数ICC值,分别为0.734、0.719和0.885,AI系统分割出的单个牙与数字化模型在评价长度、面积和体积时有着较好的一致性,但分割结果在具体数值上与真实情况仍有差异。CBCT体素越小,即分辨率越高,分割结果表现更好。结论:本研究建立的CBCT牙体分割算法能够准确实现各分辨率下CBCT中全牙列的牙体分割。CBCT分辨率提高,能让算法结果更准确。相比目前的分割算法,本研究的算法性能更好。但与实际情况相比,仍有一定差异,需对算法继续改进及验证。

关键词: 人工智能, CBCT, 牙体分割, 准确性

Abstract: PURPOSE: The established automatic AI tooth segmentation algorithm was used to achieve rapid and automatic tooth segmentation from CBCT images. The three-dimensional data obtained by oral scanning of real isolated teeth were used as the gold standard to verify the accuracy of the algorithm. METHODS: Thirty sets of CBCT data and corresponding 59 isolated teeth were collected from Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine. The three-dimensional tooth data in CBCT images were segmented by the algorithm. The digital information obtained by scanning the extracted teeth after processing was used as the gold standard. In order to compare the difference between the segmentation results and the scanning results of the algorithm. The Dice coefficient(Dice), sensitivity (Sen) and average symmetric surface distance (ASSD) were selected to evaluate the segmentation accuracy of the algorithm. The intra-class correlation coefficient(ICC) was used to evaluate the differences in length, area, and volume between the single tooth obtained by the AI system and the digital isolated tooth. Due to the existence of CBCT with different resolution, ANOVA was used to analyze the differences between groups with different resolution, and SNK method was used to compare them between two groups. SPSS 25.0 software package was used to analyze the data. RESULTS: After comparing the segmentation results with the in vitro dental scanning results, the average Dice value was (94.7±1.88)%, the average Sen was (95.8±2.02)%, and the average ASSD was (0.49±0.12) mm. By comparing the length, area and volume of a single tooth obtained by the digital isolated tooth and the AI system, the ICC values of the intra-group correlation coefficients were 0.734, 0.719 and 0.885, respectively. The single tooth divided by the AI system has a good consistency with the digital model in evaluating the length, area and volume, but the segmentation results were still different from the real situation in terms of specific values. The smaller the voxel of CBCT, the higher the resolution, the better the segmentation results. CONCLUSIONS: The CBCT tooth segmentation algorithm established in this study can accurately achieve the tooth segmentation of the whole dentition in CBCT at all resolutions. The improvement of CBCT resolution ratio can make the algorithm more accurate. Compared with the current segmentation algorithms, our algorithm has better performance. Compared with the real situation, there are still some differences, and the algorithm needs to be further improved and verified.

Key words: Artificial intelligence, Cone-beam CT, Tooth Segmentation, Accuracy

中图分类号: