基于深度学习牙体分割算法的准确性研究

doi:10.19439/j.sjos.2024.04.002

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

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.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. 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/Abstract

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:

R781.05

张博钧, 崔智铭, 柳稚旭, 陈思悦, 顾恺隽, 李思彤, 吴艳棋, 沈定刚, 朱敏. 基于深度学习牙体分割算法的准确性研究[J]. 上海口腔医学, 2024, 33(4): 339-344.

ZHANG Bo-jun, CUI Zhi-ming, LIU Zhi-xu, CHEN Si-yue, GU Kai-jun, LI Si-tong, WU Yan-qi, SHEN Ding-gang, ZHU Min. Accuracy of tooth segmentation algorithm based on deep learning[J]. Shanghai Journal of Stomatology, 2024, 33(4): 339-344.

参考文献

[1] 巩汉顺, 徐伟, 徐寿平, 等. 不同扫描条件下CBCT影像质量及其HU值长期稳定性分析[J].中国医疗器械杂志, 2016, 40(2): 86-89, 94.
[2] Chung M, Lee M, Hong J, et al.Pose-aware instance segmentation framework from cone beam CT images for tooth segmentation[J]. Comput Biol Med, 2020, 120: 103720.
[3] Cui Z, Li C, Wang W.ToothNet: automatic tooth instance segmentation and identification from cone beam CT images[C]. Proc IEEE/CVF Conf Comput Vis Pattern Recognit(CVPR), 2019: 6361-6370.
[4] 赵一姣, 王斯维, 刘怡, 等. 基于影像学牙周膜解剖特征快速提取活体牙三维牙根形态的方法[J]. 北京大学学报(医学版), 2017, 49(1): 54-59.
[5] Lee RJ, Pi S, Park J, et al.Accuracy and reliability of the expected root position setup methodology to evaluate root position during orthodontic treatment[J]. Am J Orthod Dentofacial Orthop, 2018, 154(4): 583-595.
[6] Gao H, Chae O.Individual tooth segmentation from CT images using level set method with shape and intensity prior[J]. Pattern Recognit, 2010, 43(7): 2406-2417.
[7] Gan Y, Xia Z, Xiong J, et al.Tooth and alveolar bone segmentation from dental computed tomography images[J]. IEEE J Biomed Health Inform, 2017, 22(1): 196-204.
[8] Evain T, Ripoche X, Atif J, et al.Semi-automatic teeth segmentation in cone-beam computed tomography by graph-cut with statistical shape priors[C]. 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), 2017: 1197-1200.
[9] Jang TJ, Kim KC, Cho HC, et al.A fully automated method for 3D individual tooth identification and segmentation in dental CBCT[J]. IEEE Trans Pattern Anal Mach Intell, 2022, 44(10): 6562-6568.
[10] Chen Y, Du H, Yun Z, et al.Automatic segmentation of individual tooth in dental CBCT images from tooth surface map by a multi-task FCN[J]. IEEE Access, 2020, 8: 97296-97309.
[11] Wu X, Chen H, Huang Y, et al.Center-sensitive and boundary-aware tooth instance segmentation and classification from cone-beam CT[C]. 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), 2020: 939-942.
[12] Yang Y, Xie R, Jia W, et al.Accurate and automatic tooth image segmentation model with deep convolutional neural networks and level set method[J]. Neurocomputing, 2021, 419: 108-125.
[13] Cui Z, Zhang B, Lian C, et al.Hierarchical morphology-guided tooth instance segmentation from CBCT images[C]. Information Processing in Medical Imaging: 27th International Conference, 2021: 150-162.
[14] Cui Z, Fang Y, Mei L, et al.A fully automatic AI system for tooth and alveolar bone segmentation from cone-beam CT images[J]. Nat Commun, 2022, 13(1): 2096.
[15] Róth I, Czigola A, Fehér D, et al.Digital intraoral scanner devices: a validation study based on common evaluation criteria[J]. BMC Oral Health, 2022, 22(1): 140-156.
[16] Chiu A, Chen YW, Hayashi J, et al.Accuracy of CAD/CAM digital impressions with different intraoral scanner parameters[J]. Sensors(Basel), 2020, 20(4): 1157-1166.
[17] Christopoulou I, Kaklamanos EG, Makrygiannakis MA, et al.Intraoral scanners in orthodontics: a critical review[J]. Int J Environ Res Public Health, 2022, 19(3): 1407-1418.
[18] Kihara H, Hatakeyama W, Komine F, et al.Accuracy and practicality of intraoral scanner in dentistry: a literature review[J]. J Prosthodont Res, 2020, 64(2): 109-113.
[19] Tomita Y, Uechi J, Konno M, et al.Accuracy of digital models generated by conventional impression/plaster-model methods and intraoral scanning[J]. Dent Mater J, 2018, 37(4): 628-633.
[20] Gavounelis NA, Gogola CC, Halazonetis DJ.The effect of scanning strategy on intraoral scanner's accuracy[J]. Dent J, 2022, 10(7): 123-133.
[21] 林翔, 傅裕杰, 任根强, 等. U-Net神经网络分割锥形束CT影像中下颌磨牙牙体与牙髓腔及其准确性验证[J]. 上海口腔医学, 2022, 31(5): 454-459.
[22] Abramson Z, Susarla SM, Lawler M, et al.Three-dimensional computed tomographic airway analysis of patients with obstructive sleep apnea treated by maxillomandibular advancement[J]. J Oral Maxillofac Surg, 2011, 69(3): 677-686.
[23] Honey OB, Scarfe WC, Hilgers MJ, et al.Accuracy of cone-beam computed tomography imaging of the temporomandibular joint: comparisons with panoramic radiology and linear tomography[J]. Am J Orthod Dentofacial Orthop, 2007, 132(4): 429-438.
[24] Schubert M, Proff P, Kirschneck C.Improved eruption path quantification and treatment time prognosis in alignment of impacted maxillary canines using CBCT imaging[J]. Eur J Orthod, 2018, 40(6): 597-607.
[25] 程涛. 口腔正畸治疗中牙根吸收的研究进展[J]. 临床口腔医学杂志, 2016, 32(1) : 59-61.
[26] Pei Y, Ai X, Zha H, et al.3D exemplar-based random walks for tooth segmentation from cone-beam computed tomography images[J]. Med Phys, 2016, 43(9): 5040-5050.
[27] Lahoud P, EzEldeen M, Beznik T, et al. Artificial intelligence for fast and accurate 3-dimensional tooth segmentation on cone-beam computed tomography[J]. J Endod, 2021, 47(5): 827-835.
[28] Ayidh Alqahtani K, Jacobs R, Smolders A, et al.Deep convolutional neural network-based automated segmentation and classification of teeth with orthodontic brackets on cone-beam computed-tomographic images: a validation study[J]. Eur J Orthod, 2023, 45(2): 169-174.

基于深度学习牙体分割算法的准确性研究

Accuracy of tooth segmentation algorithm based on deep learning

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	于子航, 段亦格, 崔宇彤, 田玉楼. 不同矢状骨面型均角患者宽度特征分析[J]. 上海口腔医学, 2024, 33(3): 312-317.
[2]	李爽, 肖容容, 王明锋. 偏颌患者平面横向倾斜度与颞下颌关节间隙的相关性分析[J]. 上海口腔医学, 2024, 33(3): 318-323.
[3]	夏婷婷, 汪涌. 重度牙周炎后牙位点保存术中联合应用浓缩生长因子的疗效评价[J]. 上海口腔医学, 2023, 32(6): 650-655.
[4]	赵君, 吴晓波, 刘娜, 郝新河. 基于CBCT及三维重建技术对下颌阻生第三磨牙舌侧骨板厚度及形态的研究[J]. 上海口腔医学, 2023, 32(6): 661-667.
[5]	冯二玫, 杨剑珍, 张彦霞. TF和S3预备磨牙重度弯曲根管的效果评价[J]. 上海口腔医学, 2020, 29(2): 146-149.