国际口腔医学杂志 ›› 2023, Vol. 50 ›› Issue (4): 491-498.doi: 10.7518/gjkq.2023069

• 综述 • 上一篇    

机器学习在口腔种植学中的应用研究进展

朱可石(),廖安琪,余优成()   

  1. 复旦大学附属中山医院口腔科 上海 200032
  • 收稿日期:2023-01-12 修回日期:2023-04-11 出版日期:2023-07-01 发布日期:2023-06-21
  • 通讯作者: 余优成
  • 作者简介:朱可石,硕士,Email:1329747692@qq.com
  • 基金资助:
    国家自然科学基金(82170990);上海市科技委员会重大临床研究子项目(SHDC2020CR2042B);上海市科技委员会多中心临床研究(19411950103)

Research progress on the application of machine learning in dental implantology

Zhu Keshi(),Liao Anqi,Yu Youcheng.()   

  1. Dept. of Stomatology, Zhongshan Hospital Affiliated to Fudan University, Shanghai 200032, China
  • Received:2023-01-12 Revised:2023-04-11 Online:2023-07-01 Published:2023-06-21
  • Contact: Youcheng. Yu
  • Supported by:
    National Natural Science Foundation of China(82170990);Major Clinical Research Subproject of Shanghai Municipal Science and Technology Commission(SHDC2020CR2042B);Multicenter Clinical Study of Shanghai Municipal Science and Technology Commission(19411950103)

摘要:

近年来,人工智能技术的发展正在逐渐改变传统的医疗行业,机器学习是实现人工智能的主流方法。在口腔种植领域,机器学习技术可以辅助医生的诊疗过程,包括影像学资料智能识别、种植方案优化、自动化机器人等方面,是未来口腔种植学的发展趋势。本文就机器学习在口腔种植领域的研究进展做一总结,并对口腔种植的数字化、智能化未来进行展望。

关键词: 机器学习, 人工智能, 口腔种植

Abstract:

In recent years, artificial intelligence has been gradually changing the traditional medical industry, and machine learning is the main approach to realize it. In aspect of dental implantation, it can assist doctors in their daily diagnosis and treatment, including intelligent recognition of imaging data, implant scheme optimization, automatic robot and so on. It is the future of dental implantation. This paper summarizes the research progress of machine learning in dental implantation and looks forward to its intellectualization in the future.

Key words: machine learning, artificial intelligence, dental implant

中图分类号: 

  • R 782

表 1

不同CNN模型智能识别/分类口腔种植系统的内容及比较"

文献CNN模型影像学资料模型评价指标结果结论
[9]SqueezeNet;GoogLeNet;Res-Net-18;MobileNet-v2;ResNet-50801张来源于根尖X线片的单种植体图片准确率、平均精度(average precision,AP)、召回率、F1评分5种模型的测试AP均超过90%;MobileNet-v2和Squee-zeNet的准确率分别约达96%和97%使用参数不到400万的小型网络和少量的图像,CNN也能达较高的精度
[10]CNN(Keras&Tensorflow)1 800张根尖X线片准确率、敏感性、特异性、阳性/阴性预测值(positive predictive value,PPV/ negative predictive value,NPV)、受试者操作特征(receiver operating characteristic,ROC)曲线训练数据组、测试数据组和验证数据的系统准确率分别为99.78%、99.36%和85.29%CNN识别较少种植系统(3个)时可以达到很高的准确率
[11]微调版You Only Look Once(YOLO) v3-1 282张曲面体层片真阳性率(true positive,TP)、AP、平均AP、平均交并比识别每个种植体系统的TP和AP分别为0.50~0.82和0.51~0.85图片质量和样本数量影响了模型对同品牌不同种植系统的识别准确率
[12]CNN-transfer-Inception v31 206张来源于根尖X线片的种植体图片准确率、敏感性、特异性、PPV、NPV、ROC曲线和ROC曲线下面积(area under curve,AUC)诊断准确率93.8%;敏感性为93.5%;特异性为94.2%;PPV为92%深度CNN模型在从X线片识别牙种植体方面有良好的表现。但影像资料数据库规模太小
[13]

基础CNN;VGG16-transfer;微调版VGG16 VGG19-transfer;

微调版VGG19

8 859张来源于曲面体层片的种植体图像准确率、精密度、召回率、ROC、F1评分微调版VGG16和微调版VGG19的准确率分别达0.94和0.93对深度CNN模型的特定卷积块进行微调,深度CNN可以更专门地用于特定分类任务
[14]多任务CNN:ResNet18、34、50、101和1529 767张来源于曲面体层片的种植体图像准确率、AP、召回率、特异性、F1评分、ROC曲线、AUC

多任务模式下,CNN识别准确率均超98%;

多任务模式下,CNN模型的各评价指标都显著高于单任务模式

多任务模式下的迭代学习显著提高了CNN模型的准确性
[15]自动化深层CNN(automate deep CNN, ADCNN):Neuro-T version 2.0.17 146张曲面体层片、4 384张根尖X线片ROC曲线、AUC、Youden指数、敏感性、特异性ADCNN的AUC、Youden指数、敏感性和特异性值分别为0.95、0.81、0.96和0.85ADCNN的表现显著优于大多数参与对照实验的口腔医生
1 Das K, Behera RN. A survey on machine learning: concept, algorithms and applications[J]. Int J Innov Res Comput Commun Eng, 2017, 5: 1301-1309.
2 吴志娜, 胡敏, 宫洵, 等. 机器学习在口腔正畸诊疗中的应用进展[J]. 中华口腔医学杂志, 2021, 101(12): 1277-1281.
Wu ZN, Hu M, Gong X, et al. Application of machine learning in orthodontics[J]. Chin J Stomatol, 2021, 101(12): 1277-1281.
3 汪潇潇, 程兴群. 人工智能在口腔医学领域的应用进展[J]. 实用口腔医学杂志, 2021, 37(5): 710-715.
Wang XX, Cheng XQ. Progress in the application of artificial intelligence in the field of stomatology[J]. J Pract Stomatol, 2021, 37(5): 710-715.
4 刘蓬然, 霍彤彤, 陆林, 等. 人工智能在医学中的应用现状与展望[J]. 中华医学杂志, 2021, 101(44): 3677-3683.
Liu PR, Huo TT, Lu L, et al. The application status and prospects of artificial intelligence in medicine[J]. Natl Med J China, 2021, 101(44): 3677-3683.
5 Revilla-León M, Gómez-Polo M, Vyas S, et al. Artificial intelligence applications in implant dentistry: a systematic review[J]. J Prosthet Dent, 2023, 129(2): 293-300.
6 Putra RH, Doi C, Yoda N, et al. Current applications and development of artificial intelligence for digital dental radiography[J]. Dentomaxillofac Radiol, 2022, 51(1): 20210197.
7 Jokstad A, Braegger U, Brunski JB, et al. Quality of dental implants[J]. Int Dent J, 2003, 53(6 ): 409-443.
8 Esposito M, Ardebili Y, Worthington HV. Interventions for replacing missing teeth: different types of dental implants[J]. Cochrane Database Syst Rev, 2014(7): CD003815.
9 Kim JE, Nam NE, Shim JS, et al. Transfer learning via deep neural networks for implant fixture system classification using periapical radiographs[J]. J Clin Med, 2020, 9(4): 1117.
10 da Mata Santos R, Prado H, Neto I, et al. Automated identification of dental implants using artificial intelligence[J]. Int J Oral Maxillofac Implants, 2021, 36(5): 918-923.
11 Takahashi T, Nozaki K, Gonda T, et al. Identification of dental implants using deep learning-pilot study[J]. Int J Implant Dent, 2020, 6(1): 53.
12 Saïd MH, le Roux MK, Catherine JH, et al. Deve-lopment of an artificial intelligence model to identify a dental implant from a radiograph[J]. Int J Oral Maxillofac Implants, 2020, 36(6): 1077-1082.
13 Sukegawa S, Yoshii K, Hara T, et al. Deep neural networks for dental implant system classification[J]. Biomolecules, 2020, 10(7): 984.
14 Sukegawa S, Yoshii K, Hara T, et al. Multi-task deep learning model for classification of dental implant brand and treatment stage using dental pano-ramic radiograph images[J]. Biomolecules, 2021, 11(6): 815.
15 Lee JH, Kim YT, Lee JB, et al. A performance comparison between automated deep learning and dental professionals in classification of dental implant systems from dental imaging: a multi-center study[J]. Diagnostics (Basel), 2020, 10(11): 910.
16 Lee DW, Kim SY, Jeong SN, et al. Artificial intelligence in fractured dental implant detection and classification: evaluation using dataset from two dental hospitals[J]. Diagnostics (Basel), 2021, 11(2): 233.
17 Cha JY, Yoon HI, Yeo IS, et al. Peri-implant bone loss measurement using a region-based convolutio-nal neural network on dental periapical radiographs[J]. J Clin Med, 2021, 10(5): 1009.
18 Liu M, Wang SM, Chen H, et al. A pilot study of a deep learning approach to detect marginal bone loss around implants[J]. BMC Oral Health, 2022, 22(1): 11.
19 Dalago HR, Schuldt Filho G, Rodrigues MA, et al. Risk indicators for periimplantitis. A cross-sectional study with 916 implants[J]. Clin Oral Implan Res, 2017, 28(2): 144-150.
20 El Hage M, Nurdin N, Abi Najm S, et al. Osteotome sinus floor elevation without grafting: a 10-year study of cone beam computerized tomography vs periapical radiography[J]. Int J Periodontics Restora-tive Dent, 2019, 39(3): e89-e97.
21 Kwak GH, Kwak EJ, Song JM, et al. Automatic mandibular canal detection using a deep convolutional neural network[J]. Sci Rep, 2020, 10(1): 5711.
22 Ariji Y, Yanashita Y, Kutsuna S, et al. Automatic detection and classification of radiolucent lesions in the mandible on panoramic radiographs using a deep learning object detection technique[J]. Oral Surg Oral Med Oral Pathol Oral Radiol, 2019, 128(4): 424-430.
23 Orhan K, Bayrakdar IS, Ezhov M, et al. Evaluation of artificial intelligence for detecting periapical pathosis on cone-beam computed tomography scans[J]. Int Endod J, 2020, 53(5): 680-689.
24 Kurt Bayrakdar S, Orhan K, Bayrakdar IS, et al. A deep learning approach for dental implant planning in cone-beam computed tomography images[J]. BMC Med Imaging, 2021, 21(1): 86.
25 Lin Y, Shi M, Xiang D, et al. Construction of an end-to-end regression neural network for the determination of a quantitative index sagittal root inclination[J]. J Periodontol, 2022, 93(12): 1951-1960.
26 Albrektsson T, Zarb G, Worthington P, et al. The long-term efficacy of currently used dental implants: a review and proposed criteria of success[J]. Int J Oral Maxillofac Implants, 1986, 1(1): 11-25.
27 Zhang HG, Shan J, Zhang P, et al. Trabeculae microstructure parameters serve as effective predictors for marginal bone loss of dental implant in the mandible[J]. Sci Rep, 2020, 10(1): 18437.
28 Ha SR, Park HS, Kim EH, et al. A pilot study using machine learning methods about factors influencing prognosis of dental implants[J]. J Adv Prosthodont, 2018, 10(6): 395-400.
29 Liu CH, Lin CJ, Hu YH, et al. Predicting the failure of dental implants using supervised learning techniques[J]. Appl Sci, 2018, 8(5): 698.
30 Papantonopoulos G, Gogos C, Housos E, et al. Prediction of individual implant bone levels and the exis-tence of implant “phenotypes”[J]. Clin Oral Implants Res, 2017, 28(7): 823-832.
31 Khoshkhounejad M, Hashemi Nasab MS, Aminsobhani M, et al. Challenging diagnosis of severe bila-teral cervicofacial subcutaneous emphysema follo-wing root perforation in a maxillary lateral incisor: a case report[J]. Iran Endod J, 2019, 14(3): 220-224.
32 International Surgical Outcomes Study (ISOS) group. Prospective observational cohort study on gra-ding the severity of postoperative complications in global surgery research[J]. Br J Surg, 2019, 106(2): e73-e80.
33 Oliveira ALI, Baldisserotto C, Baldisserotto J. A comparative study on machine learning techniques for prediction of success of dental implants[M]//Lecture notes in computer science. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005: 939-948.
34 Mahri M, Shen N, Berrizbeitia F, et al. Osseointegration pharmacology: a systematic mapping using artificial intelligence[J]. Acta Biomater, 2021, 119: 284-302
35 王岚, 秦思琪, 陈思宇, 等. 三维有限元分析法在口腔种植学中的应用进展[J]. 现代医药卫生, 2022, 38(6): 995-999.
Wang L, Qin SQ, Chen SY, et al. Progress in the application of three-dimensional finite element analysis in dental implant science[J]. J Mod Med Heal, 2022, 38(6): 995-999.
36 Zaw K, Liu GR, Deng B, et al. Rapid identification of elastic modulus of the interface tissue on dental implants surfaces using reduced-basis method and a neural network[J]. J Biomech, 2009, 42(5): 634-641.
37 Roy S, Dey S, Khutia N, et al. Design of patient specific dental implant using FE analysis and computational intelligence techniques[J]. Appl Soft Comput, 2018, 65: 272-279.
38 Li HY, Shi ML, Liu XM, et al. Uncertainty optimization of dental implant based on finite element method, global sensitivity analysis and support vector regression[J]. Proc Inst Mech Eng H, 2019, 233(2): 232-243.
39 Javaid M, Haleem A. Current status and applications of additive manufacturing in dentistry: a literature-based review[J]. J Oral Biol Craniofac Res, 2019, 9(3): 179-185.
40 Türker H, Aksoy B, Özsoy K. Fabrication of Customized dental guide by stereolithography method and evaluation of dimensional accuracy with artificial neural networks[J]. J Mech Behav Biomed Mater, 2022, 126: 105071.
41 Bekeny JR, Ozer E. Transoral robotic surgery frontiers[J]. World J Otorhinolaryngol Head Neck Surg, 2016, 2(2): 130-135.
42 柯怡芳, 张耀鹏, 王勇, 等. 机器人在口腔修复领域的研发及应用现状[J]. 中华口腔医学杂志, 2021(9): 939-944.
Ke YF, Zhang YP, Wang Y, et al. Application and outlook of robotics in prosthetic dentistry[J]. Chin J Stomatol, 2021(9): 939-944.
43 Brief J, Hasβfeld S, Boesecke R, et al. Robot assis-ted dental implantology[J]. Int Poster J Dent Oral Med, 2002, 4(1): 109.
44 Kim G, Seo H, Im S, et al. A study on simulator of human‑robot cooperative manipulator for dental implant surgery[C/OL]//2009 IEEE International Symposium on Industrial Electronics, 2009: 2159‑2164[2021‑07‑14].
45 Sun XY, McKenzie FD, Bawab S, et al. Automated dental implantation using image-guided robotics: registration results[J]. Int J Comput Assist Radiol Surg, 2011, 6(5): 627-634.
46 Syed AA, Mahmood Soomro A, Nighat Khizar A, et al. Tele-robotic assisted dental implant surgery with virtual force feedback[J]. TELKOMNIKA Indonesian J Electr Eng, 2014, 12(1): 450-458.
47 Bolding SL, Reebye UN. Accuracy of haptic robotic guidance of dental implant surgery for completely edentulous arches[J]. J Prosthet Dent, 2022, 128(4): 639-647.
48 白石柱, 赵铱民. 口腔种植机器人的相关研究[C]//第十一次全国口腔修复学学术会议论文汇编, 2017: 147-148.
Bai SZ, Zhao YM. Research on dental implant robots[C]//Compilation of papers from the 11th national conference on prosthodontics, 2017: 147-148.
49 吴秦. 口腔种植机器人空间映射装置的研发及其应用研究[D]. 西安: 第四军医大学, 2016.
Wu Q. Research and application of spatial mapping device for dental implant robot[D]. Xi’an: The Fourth Military Medical University, 2016.
50 白石柱, 任楠, 冯志宏, 等. 自主式口腔种植机器人手术系统动物体内种植精度的研究[J]. 中华口腔医学杂志, 2021, 56(2): 170-174.
Bai SZ, Ren N, Feng ZH, et al. Animal experiment on the accuracy of the autonomous dental implant robotic system[J]. Chin J Stomatol, 2021, 56(2): 170-174.
51 曹正纲. 基于图像引导的颧种植手术机器人系统的研究[D]. 上海: 上海交通大学, 2019.
Cao ZG. Research on image-guided zygomatic implant surgery robot system[D]. Shanghai: Shanghai Jiao Tong University, 2019.
52 Shaheen E, Leite A, Alqahtani KA, et al. A novel deep learning system for multi-class tooth segmentation and classification on cone beam computed tomography. A validation study[J]. J Dent, 2021, 115: 103865.
53 Wang H, Minnema J, Batenburg KJ, et al. Multiclass CBCT image segmentation for orthodontics with deep learning[J]. J Dent Res, 2021, 100(9): 943-949.
54 Hao J, Liao W, Zhang YL, et al. Toward clinically applicable 3-dimensional tooth segmentation via deep learning[J]. J Dent Res, 2022, 101(3): 304-311.
55 Raith S, Vogel EP, Anees N, et al. Artificial Neural Networks as a powerful numerical tool to classify specific features of a tooth based on 3D scan data[J]. Comput Biol Med, 2017, 80: 65-76.
56 Joda T, Gallucci GO, Wismeijer D, et al. Augmented and virtual reality in dental medicine: a systema-tic review[J]. Comput Biol Med, 2019, 108: 93-100.
57 Chen YN, Lee JKY, Kwong G, et al. Morphology and fracture behavior of lithium disilicate dental crowns designed by human and knowledge-based AI[J]. J Mech Behav Biomed Mater, 2022, 131: 105256.
58 Chen QX, Wu J, Li SS, et al. An ontology-driven, case-based clinical decision support model for removable partial denture design[J]. Sci Rep, 2016, 6: 27855.
[1] 韩冲,何东宁,余飞燕,吴东潮. 口腔种植术后疼痛机制及治疗的研究进展[J]. 国际口腔医学杂志, 2024, 51(1): 99-106.
[2] 林慧平,徐婷,林军. 人工智能在口腔癌和口腔潜在恶性疾病诊断中的研究进展[J]. 国际口腔医学杂志, 2023, 50(2): 138-145.
[3] 唐粤亭,代佳琪,董雯萱,王虎,郭际香,游梦. 基于机器学习的牙龄评测研究进展[J]. 国际口腔医学杂志, 2023, 50(2): 146-151.
[4] 满毅, 黄定明. 美学区种植骨增量与邻牙慢性根尖周病的联合治疗策略(下):临床诊治流程及实践病例[J]. 国际口腔医学杂志, 2022, 49(6): 621-632.
[5] 满毅, 黄定明. 美学区种植骨增量与邻牙慢性根尖周病的联合治疗策略(上):应用基础及适应证[J]. 国际口腔医学杂志, 2022, 49(5): 497-505.
[6] 罗恩. 人工智能正颌外科的探索与临床初步应用[J]. 国际口腔医学杂志, 2022, 49(2): 125-131.
[7] 田而慷,向倩蓉,赵欣然,彭佳涵,舒睿. 口腔诊疗中人工智能的运用[J]. 国际口腔医学杂志, 2021, 48(4): 475-484.
[8] 刘梦齐,盖阔,蒋丽. 抗菌性口腔种植材料的研究进展[J]. 国际口腔医学杂志, 2018, 45(5): 516-521.
[9] 陈青娅, 黄茜, 王黎. 口腔种植患者牙科焦虑的调查分析[J]. 国际口腔医学杂志, 2018, 45(1): 14-19.
[10] 万双全, 邓飞龙. 上皮下结缔组织瓣在种植软组织缺陷中的应用[J]. 国际口腔医学杂志, 2018, 45(1): 68-73.
[11] 王晓娜 赵静辉 储顺礼 周延民. 骨替代材料在口腔种植领域中的成骨效果[J]. 国际口腔医学杂志, 2016, 43(1): 113-.
[12] 雷文龙1 施斌1,2. 血小板衍生生长因子-BB在口腔种植领域中的作用[J]. 国际口腔医学杂志, 2014, 41(2): 199-203.
[13] 杨世茂1综述 王明国2审校. 富血小板纤维蛋白的研究进展[J]. 国际口腔医学杂志, 2012, 39(3): 373-375.
[14] 郭大伟1,2综述 梁星1 陈悦1审校. 发达国家口腔种植学的教育现状[J]. 国际口腔医学杂志, 2011, 38(3): 326-328.
[15] 张勇综述 李昀生审校. 应用牙槽窝保存技术减少拔牙后骨吸收的研究进展[J]. 国际口腔医学杂志, 2011, 38(3): 288-291.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 张京剧. 青年期至中年期颅面复合体变化的头影测量研究[J]. 国际口腔医学杂志, 1999, 26(06): .
[2] 刘玲. 镍铬合金中铍对可铸造性和陶瓷金属结合力的影响[J]. 国际口腔医学杂志, 1999, 26(06): .
[3] 王昆润. 在种植体上制作固定义齿以后下颌骨密度的动态变化[J]. 国际口腔医学杂志, 1999, 26(06): .
[4] 王昆润. 修补颌骨缺损的新型生物学相容材料[J]. 国际口腔医学杂志, 1999, 26(06): .
[5] 陆加梅. 不可复性关节盘移位患者术前张口度与关节镜术后疗效的相关性[J]. 国际口腔医学杂志, 1999, 26(06): .
[6] 王昆润. 重型颌面部炎症死亡和康复病例的实验室检查指标比较[J]. 国际口腔医学杂志, 1999, 26(06): .
[7] 王昆润. 二甲亚砜和双氯芬酸并用治疗根尖周炎[J]. 国际口腔医学杂志, 1999, 26(06): .
[8] 汤庆奋,王学侠. 17β-雌二醇对人类阴道和口腔颊粘膜的渗透性[J]. 国际口腔医学杂志, 1999, 26(06): .
[9] 王昆润. 咀嚼口香糖对牙周组织微循环的影响[J]. 国际口腔医学杂志, 1999, 26(06): .
[10] 宋红. 青少年牙周炎外周血分叶核粒细胞的趋化功能[J]. 国际口腔医学杂志, 1999, 26(06): .