Application of artificial intelligence in digital and intelligent manufacturing of prosthodontics

doi:10.12439/kqhm.1005-4979.2025.05.002

Abstract

Abstract:

In recent years, the rapid advancement of artificial intelligence (AI) technology has brought about transformative technological advancements in the field of dental defect restoration. AI has significantly enhanced the accuracy and efficiency of personalized restoration, driving the transition of dental rehabilitation from traditional methods toward digital and intelligent solutions. However, certain technical challenges remain that limit its effective translation into clinical practice. This review summarizes the current applications and unresolved issues of AI in the field of dental prosthodontics, aiming to provide insights for clinical reference.

Key words: artificial intelligence, deep learning, prosthodontics

摘要：

近年来，人工智能（artificial intelligence，AI）技术的快速发展为口腔修复的智能制造带来了技术性的变革。AI技术显著提升了个性化修复的准确率和效能，驱动着口腔修复由传统医疗模式向数智化转型，但目前其应用仍面临一些技术瓶颈，制约着临床转化的应用效能。本文就AI技术在口腔修复领域中的应用进展及存在的问题进行综述，以期为临床提供参考。

关键词: 人工智能, 深度学习, 口腔修复

WANG Yue, WU Junhua. Application of artificial intelligence in digital and intelligent manufacturing of prosthodontics[J]. 《Journal of Oral and Maxillofacial Surgery》, 2025, 35(5): 343-350.

王悦, 吴珺华. 人工智能在口腔修复数智制造中的应用[J]. 《口腔颌面外科杂志》, 2025, 35(5): 343-350.

/ / Recommend / Download Citations

URL: https://journal06.magtech.org.cn/Jweb_joms/EN/10.12439/kqhm.1005-4979.2025.05.002

https://journal06.magtech.org.cn/Jweb_joms/EN/Y2025/V35/I5/343

Figures/Tables 1

References 73

[1]	Miyazaki T, Hotta Y. CAD/CAM systems available for the fabrication of crown and bridge restorations[J]. Aust Dent J, 2011, 56(Suppl 1): 97-106.
[2]	Blatz MB, Conejo J. The current state of chairside digital dentistry and materials[J]. Dent Clin North Am, 2019, 63(2): 175-197. doi: S0011-8532(18)30091-0 pmid: 30825985
[3]	Lee SJ, Poon J, Jindarojanakul A, et al. Artificial intelligence in dentistry: Exploring emerging applications and future prospects[J]. J Dent, 2025, 155: 105648.
[4]	Meghil MM, Rajpurohit P, Awad ME, et al. Artificial intelligence in dentistry[J]. Dent Rev, 2022, 2(1): 100009.
[5]	Steels L, Lopez de Mantaras R. The Barcelona declaration for the proper development and usage of artificial intelligence in Europe[J]. AI Commun, 2018, 31(6): 485-494.
[6]	Glick A, Clayton M, Angelov N, et al. Impact of explainable artificial intelligence assistance on clinical decision-making of novice dental clinicians[J]. JAMIA Open, 2022, 5(2): ooac031.
[7]	Park WJ, Park JB. History and application of artificial neural networks in dentistry[J]. Eur J Dent, 2018, 12(4): 594-601. doi: 10.4103/ejd.ejd_325_18 pmid: 30369809
[8]	Lee JH, Jeong SN. Efficacy of deep convolutional neural network algorithm for the identification and classification of dental implant systems, using panoramic and periapical radiographs: A pilot study[J]. Medicine, 2020, 99(26): e20787.
[9]	Kong HJ, Kim YL. Application of artificial intelligence in dental crown prosthesis: A scoping review[J]. BMC Oral Health, 2024, 24(1): 937.
[10]	Sadowsky SJ. An overview of treatment considerations for esthetic restorations: A review of the literature[J]. J Prosthet Dent, 2006, 96(6): 433-442. doi: 10.1016/j.prosdent.2006.09.018 pmid: 17174661
[11]	Tabatabaian F, Beyabanaki E, Alirezaei P, et al. Visual and digital tooth shade selection methods, related effective factors and conditions, and their accuracy and precision: A literature review[J]. J Esthet Restor Dent, 2021, 33(8): 1084-1104. doi: 10.1111/jerd.12816 pmid: 34498789
[12]	Geier J, Hudák M. Changing the Chevreul illusion by a background luminance ramp: Lateral inhibition fails at its traditional stronghold—a psychophysical refutation[J]. PLoS One, 2011, 6(10): e26062.
[13]	王胤霖, 张馨月, 李明星, 等. 前牙瓷贴面美学修复体比色的影响因素[J]. 口腔医学, 2024, 44(3): 203-208.
[14]	Dagg H, O'Connell B, Claffey N, et al. The influence of some different factors on the accuracy of shade selection[J]. J Oral Rehabil, 2004, 31(9): 900-904. doi: 10.1111/j.1365-2842.2004.01310.x pmid: 15369473
[15]	Wei JQ, Peng MD, Li Q, et al. Evaluation of a novel computer color matching system based on the improved back-propagation neural network model[J]. J Prosthodont, 2018, 27(8): 775-783. doi: 10.1111/jopr.12561 pmid: 27860023
[16]	Kim M, Kim B, Park B, et al. A digital shade-matching device for dental color determination using the support vector machine algorithm[J]. Sensors, 2018, 18(9): 3051.
[17]	Yang JW, Hao ZZ, Xu JN, et al. Fusion machine learning model predicts CAD-CAM ceramic colors and the corresponding minimal thicknesses over various clinical backgrounds[J]. Dent Mater, 2024, 40(2): 285-296. doi: 10.1016/j.dental.2023.11.013 pmid: 37996303
[18]	Shetty S, Gali S, Augustine D, et al. Artificial intelligence systems in dental shade-matching: A systematic review[J]. J Prosthodont, 2024, 33(6): 519-532.
[19]	Lee S, Kim JE. Evaluating the precision of automatic segmentation of teeth, gingiva and facial landmarks for 2D digital smile design using real-time instance segmentation network[J]. J Clin Med, 2022, 11(3): 852.
[20]	Li MX, Xu XY, Punithakumar K, et al. Automated integration of facial and intra-oral images of anterior teeth[J]. Comput Biol Med, 2020, 122: 103794.
[21]	Lee S, Jin G, Park JH, et al. Evaluation metric of smile classification by peri-oral tissue segmentation for the automation of digital smile design[J]. J Dent, 2024, 145: 104871.
[22]	Khaled Ali GA, Abdelbadei KA, Essam M, et al. Smile. AI: A deep learning system for digital smile design[C]// 2023 Eleventh International Conference on Intelligent Computing and Information Systems (ICICIS). November 21-23, 2023, Cairo, Egypt: IEEE, 2023: 568-573.
[23]	Coachman C, Calamita MA, Sesma N. Dynamic documentation of the smile and the 2D/3D digital smile design process[J]. Int J Periodontics Restorative Dent, 2017, 37(2): 183-193. doi: 10.11607/prd.2911 pmid: 28196157
[24]	Blatz MB, Chiche G, Bahat O, et al. Evolution of aesthetic dentistry[J]. J Dent Res, 2019, 98(12): 1294-1304. doi: 10.1177/0022034519875450 pmid: 31633462
[25]	Cheung K, Cheung W, Liu YS, et al. Establishment of a 3D esthetic analysis workflow on 3D virtual patient and preliminary evaluation[J]. BMC Oral Health, 2024, 24(1): 328. doi: 10.1186/s12903-024-04085-0 pmid: 38475773
[26]	Mourgues T, González-Olmo MJ, Huanca Ghislanzoni L, et al. Artificial intelligence in aesthetic dentistry: Is treatment with aligners clinically realistic[J]. J Clin Med, 2024, 13(20): 6074.
[27]	Mehl A, Blanz V. New procedure for fully automatic occlusal surface reconstruction by means of a biogeneric tooth model[J]. Int J Comput Dent, 2005, 8(1): 13-25. pmid: 15892521
[28]	Bohner LOL, Neto PT, Ahmed AS, et al. CEREC chairside system to register and design the occlusion in restorative dentistry: A systematic literature review[J]. J Esthet Restor Dent, 2016, 28(4): 208-220. doi: 10.1111/jerd.12226 pmid: 27312653
[29]	徐昕恺, 陈虎, 王相, 等. 口腔数智仿生诊疗技术研究应用进展[J]. 中国实用口腔科杂志, 2024, 17(4): 406-413.
[30]	Broll A, Goldhacker M, Hahnel S, et al. Generative deep learning approaches for the design of dental restorations: A narrative review[J]. J Dent, 2024, 145: 104988.
[31]	Bobeică O, Iorga D. Artificial neural networks development in prosthodontics—a systematic mapping review[J]. J Dent, 2024, 151: 105385.
[32]	Çakmak G, Cho JH, Choi J, et al. Can deep learning-designed anterior tooth-borne crown fulfill morphologic, aesthetic, and functional criteria in clinical practice[J]. J Dent, 2024, 150: 105368.
[33]	Jahangiri L, Wahlers C, Hittelman E, et al. Assessment of sensitivity and specificity of clinical evaluation of cast restoration marginal accuracy compared to stereomicroscopy[J]. J Prosthet Dent, 2005, 93(2): 138-142. doi: 10.1016/j.prosdent.2004.11.007 pmid: 15674223
[34]	Papadiochou S, Pissiotis AL. Marginal adaptation and CAD-CAM technology: A systematic review of restorative material and fabrication techniques[J]. J Prosthet Dent, 2018, 119(4): 545-551. doi: S0022-3913(17)30488-2 pmid: 28967399
[35]	Mai HN, Han JS, Kim HS, et al. Reliability of automatic finish line detection for tooth preparation in dental computer-aided software[J]. J Prosthodont Res, 2023, 67(1): 138-143.
[36]	Zhang B, Dai N, Tian SK, et al. The extraction method of tooth preparation margin line based on S-Octree CNN[J]. Int J Numer Method Biomed Eng, 2019, 35(10): e3241.
[37]	张贝, 戴宁, 田素坤, 等. 结合稀疏八叉树卷积神经网络的牙齿预备体颈缘线提取方法[J]. 计算机辅助设计与图形学学报, 2019, 31(12): 2129-2135.
[38]	Choi J, Ahn J, Park JM. Deep learning-based automated detection of the dental crown finish line: An accuracy study[J]. J Prosthet Dent, 2024, 132(6): 1286.e1-1286.e9.
[39]	Ferraris F. Posterior indirect adhesive restorations (PIAR): Preparation designs and adhesthetics clinical protocol[J]. Int J Esthet Dent, 2017, 12(4): 482-502. pmid: 28983533
[40]	Tian SK, Wang MH, Yuan FL, et al. Efficient computer-aided design of dental inlay restoration: A deep adversarial framework[J]. IEEE Trans Med Imag, 2021, 40(9): 2415-2427.
[41]	Farook TH, Ahmed S, Jamayet NB, et al. Computer-aided design and 3-dimensional artificial/convolutional neural network for digital partial dental crown synthesis and validation[J]. Sci Rep, 2023, 13: 1561. doi: 10.1038/s41598-023-28442-1 pmid: 36709380
[42]	Hwang JJ, Azernikov S, Efros AA, et al. Learning beyond human expertise with generative models for dental restorations[J/OL]. arXiv, 2018: 1804.00064[2024-04-23]. https://arxiv.org/abs/1804.00064.
[43]	Yuan FL, Dai N, Tian SK, et al. Personalized design technique for the dental occlusal surface based on conditional generative adversarial networks[J]. Int J Numer Meth Biomed Eng, 2020, 36(5): e3321.
[44]	Tian SK, Huang RK, Li ZY, et al. A dual discriminator adversarial learning approach for dental occlusal surface reconstruction[J]. J Healthc Eng, 2022, 2022(1): 1933617.
[45]	Tian SK, Wang MH, Dai N, et al. DCPR-GAN: Dental crown prosthesis restoration using two-stage generative adversarial networks[J]. IEEE J Biomed Health Inform, 2022, 26(1): 151-160.
[46]	Isola P, Zhu JY, Zhou TH, et al. Image-to-image translation with conditional adversarial networks[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA: IEEE, 2017: 5967-5976.
[47]	Wu JJ, Zhang CK, Xue TF, et al. Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling[C]// 30th Conference on Neural Information Processing Systems (NIPS 2016). Barcelona, Spain: Curran Associates Inc., 2016: 82-90.
[48]	Chau RCW, Hsung RT, McGrath C, et al. Accuracy of artificial intelligence-designed single-molar dental prostheses: A feasibility study[J]. J Prosthet Dent, 2024, 131(6): 1111-1117.
[49]	Ding H, Cui ZM, Maghami E, et al. Morphology and mechanical performance of dental crown designed by 3D-DCGAN[J]. Dent Mater, 2023, 39(3): 320-332.
[50]	中华口腔医学会口腔修复学专业委员会. 椅旁计算机辅助设计与辅助制作全瓷修复技术指南[J]. 中华口腔医学杂志, 2022, 57(10): 992-996.
[51]	Feng Y, Tao BX, Fan JC, et al. 3D reconstruction for maxillary anterior tooth crown based on shape and pose estimation networks[J]. Int J Comput Assist Radiol Surg, 2023, 18(8): 1405-1416. doi: 10.1007/s11548-023-02841-1 pmid: 36754949
[52]	Chen D, Yu MQ, Li QJ, et al. Precise tooth design using deep learning-based templates[J]. J Dent, 2024, 144: 104971.
[53]	Liu CM, Lin WC, Lee SY. Evaluation of the efficiency, trueness, and clinical application of novel artificial intelligence design for dental crown prostheses[J]. Dent Mater, 2024, 40(1): 19-27.
[54]	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.
[55]	Cho JH, Yi Y, Choi J, et al. Time efficiency, occlusal morphology, and internal fit of anatomic contour crowns designed by dental software powered by generative adversarial network: A comparative study[J]. J Dent, 2023, 138: 104739.
[56]	Cho JH, Çakmak G, Yi Y, et al. Tooth morphology, internal fit, occlusion and proximal contacts of dental crowns designed by deep learning-based dental software: A comparative study[J]. J Dent, 2024, 141: 104830.
[57]	Macrì M, D'Albis V, D'Albis G, et al. The role and applications of artificial intelligence in dental implant planning: A systematic review[J]. Bioengineering, 2024, 11(8): 778.
[58]	Samaranayake L, Tuygunov N, Schwendicke F, et al. The transformative role of artificial intelligence in dentistry: A comprehensive overview. Part 1: Fundamentals of AI, and its contemporary applications in dentistry[J]. Int Dent J, 2025, 75(2): 383-396.
[59]	Elgarba BM, Fontenele RC, Tarce M, et al. Artificial intelligence serving pre-surgical digital implant planning: A scoping review[J]. J Dent, 2024, 143: 104862.
[60]	Mangano FG, Admakin O, Lerner H, et al. Artificial intelligence and augmented reality for guided implant surgery planning: A proof of concept[J]. J Dent, 2023, 133: 104485.
[61]	Zhang CN, Fan LF, Zhang SS, et al. Deep learning based dental implant failure prediction from periapical and panoramic films[J]. Quant Imaging Med Surg, 2023, 13(2): 935-945.
[62]	Oh S, Kim YJ, Kim J, et al. Deep learning-based prediction of osseointegration for dental implant using plain radiography[J]. BMC Oral Health, 2023, 23(1): 208. doi: 10.1186/s12903-023-02921-3 pmid: 37031221
[63]	Huang NN, Liu P, Yan YL, et al. Predicting the risk of dental implant loss using deep learning[J]. J Clin Periodontol, 2022, 49(9): 872-883.
[64]	Gui HJ, Yang HW, Zhang SL, et al. Mirroring tool: The simplest computer-aided simulation technology[J]. J Craniofacial Surg, 2015, 26(7): 2115-2119.
[65]	Yao BC, He Y, Jie BM, et al. Reconstruction of bilateral post-traumatic midfacial defects assisted by three-dimensional craniomaxillofacial data in normal Chinese people-a preliminary study[J]. J Oral Maxillofac Surg, 2019, 77(11): 2302.e1-2302.e13.
[66]	Raith S, Wolff S, Steiner T, et al. Planning of mandibular reconstructions based on statistical shape models[J]. Int J Comput Assist Radiol Surg, 2017, 12(1): 99-112. doi: 10.1007/s11548-016-1451-y pmid: 27393280
[67]	熊宇韬, 徐蕾, 曾维, 等. 基于深度学习的上颌骨缺损虚拟重建与临床验证[J]. 中华口腔医学杂志, 2022, 57(10): 1029-1035.
[68]	Xiong YT, Zeng W, Xu L, et al. Virtual reconstruction of midfacial bone defect based on generative adversarial network[J]. Head Face Med, 2022, 18(1): 19.
[69]	Zhong CL, Xiong YT, Tang W, et al. A stage-wise residual attention generation adversarial network for mandibular defect repairing and reconstruction[J]. Int J Neural Syst, 2024, 34(7): 2450033.
[70]	Jain P, Kathuria H, Dubey N. Advances in 3D bioprinting of tissues/organs for regenerative medicine and in-vitro models[J]. Biomaterials, 2022, 287: 121639.
[71]	Prendergast ME, Burdick JA. Recent advances in enabling technologies in 3D printing for precision medicine[J]. Adv Mater, 2020, 32(13): e1902516.
[72]	Zhang ZR, Zhou XH, Fang YC, et al. AI-driven 3D bioprinting for regenerative medicine: From bench to bedside[J]. Bioact Mater, 2025, 45: 201-230. doi: 10.1016/j.bioactmat.2024.11.021 pmid: 39651398
[73]	An J, Chua CK, Mironov V. Application of machine learning in 3D bioprinting: Focus on development of big data and digital twin[J]. Int J Bioprint, 2021, 7(1): 342.

指标	目标	功能	目的
一般指标
均方根误差（root mean square error，RMSE）	↓	测量预测图像和真实图像中对应像素值之间的平均差异	利用RMSE实现准确的像素级重建
结构相似度指数（structural similarity index，SSIM）	↑	评价图像之间的结构信息、亮度和对比度的相似性	反映人类对图像质量的感知，用于压缩或失真评估
多维结构相似度指数（multi-scale SSIM，MS-SSIM）	↑	将结构相似性指数SSIM扩展到多个尺度，捕捉图像质量的细微变化	评价不同分辨率或尺度下的图像处理效果
峰值信噪比（peak signal-to noise ratio，PSNR）	↑	通过比较峰值信号值与噪声水平来衡量图像质量	广泛应用于有损图像的压缩，提供重建保真度的直观度量
特征相似性指数（feature similarity index，FSIM）	↑	为感知相关的图像相似性融入结构信息，客观评价两幅图像视觉质量相似度	专注于图像关键特征（如边缘、纹理、结构信息）的保真度，强调人眼感知特性
F分数（F-score）	↑	结合查准率和查全率来量化目标检测的准确性	综合评估计算机视觉算法的性能
交并比（intersection over union，IoU）	↑	用2个物体各自的边界框来度量2个物体的重叠程度	评估计算机视觉任务中的定位和分割精度
平均绝对误差（mean absolute error，MAE）	↓	测量生成数据与真实值之间的平均绝对偏差	对生成数据的整体精度进行评估
三维指标
倒角距离（chamfer distance，CD）	↓	用于衡量2个点集之间的平均距离，通过计算每个点到对方点集的最近距离，并取平均值，反映2个点集的总体匹配程度	对重建三维结构的空间对齐度和精度进行评估
推土距离（earth mover's distance，EMD）	↓	通过考虑最小转换代价来量化2片点云之间的不相似度	从几何结构和空间分布的角度，科学地评估点云之间的差异程度
豪斯多夫距离（Hausdorff distance，HD）	↓	用于衡量2个点集之间相距最远的一对点的距离，反映2个集合之间的最大分离程度	在医学影像和形状匹配方面提供相异性、相关性的综合度量

指标	目标	功能	目的
一般指标
均方根误差（root mean square error，RMSE）	↓	测量预测图像和真实图像中对应像素值之间的平均差异	利用RMSE实现准确的像素级重建
结构相似度指数（structural similarity index，SSIM）	↑	评价图像之间的结构信息、亮度和对比度的相似性	反映人类对图像质量的感知，用于压缩或失真评估
多维结构相似度指数（multi-scale SSIM，MS-SSIM）	↑	将结构相似性指数SSIM扩展到多个尺度，捕捉图像质量的细微变化	评价不同分辨率或尺度下的图像处理效果
峰值信噪比（peak signal-to noise ratio，PSNR）	↑	通过比较峰值信号值与噪声水平来衡量图像质量	广泛应用于有损图像的压缩，提供重建保真度的直观度量
特征相似性指数（feature similarity index，FSIM）	↑	为感知相关的图像相似性融入结构信息，客观评价两幅图像视觉质量相似度	专注于图像关键特征（如边缘、纹理、结构信息）的保真度，强调人眼感知特性
F分数（F-score）	↑	结合查准率和查全率来量化目标检测的准确性	综合评估计算机视觉算法的性能
交并比（intersection over union，IoU）	↑	用2个物体各自的边界框来度量2个物体的重叠程度	评估计算机视觉任务中的定位和分割精度
平均绝对误差（mean absolute error，MAE）	↓	测量生成数据与真实值之间的平均绝对偏差	对生成数据的整体精度进行评估
三维指标
倒角距离（chamfer distance，CD）	↓	用于衡量2个点集之间的平均距离，通过计算每个点到对方点集的最近距离，并取平均值，反映2个点集的总体匹配程度	对重建三维结构的空间对齐度和精度进行评估
推土距离（earth mover's distance，EMD）	↓	通过考虑最小转换代价来量化2片点云之间的不相似度	从几何结构和空间分布的角度，科学地评估点云之间的差异程度
豪斯多夫距离（Hausdorff distance，HD）	↓	用于衡量2个点集之间相距最远的一对点的距离，反映2个集合之间的最大分离程度	在医学影像和形状匹配方面提供相异性、相关性的综合度量

Please choose a citation manager

Content to export