多模态数据融合技术在口腔正畸领域的应用及研究进展

doi:10.7518/gjkq.2025103

摘要/Abstract

摘要：

随着数字化技术的发展，多模态数据融合技术在口腔正畸领域的应用越来越广泛。多模态数据融合技术通过将患者临床数据、影像学数据、口腔扫描数据、三维颜面扫描数据、生物力学数据、电子面弓数据等整合，以提高口腔正畸诊断的准确性和临床治疗的有效性。本文旨在探讨多模态数据融合技术在口腔正畸科研及临床中的应用现状、潜在价值及在口腔正畸领域的挑战和未来发展方向。

关键词: 多模态数据融合, 口腔正畸, 精确诊断, 个性化治疗

Abstract:

With the advancement of digital technology, multimodal data fusion has been widely applied in orthodontics. This technology integrates patient clinical data, imaging data, oral scanning data, 3D facial scan data, biomechanical data, and electronic facial arch data to improve the accuracy of orthodontic diagnosis and the effectiveness of clinical treatment. This study aims to explore the current application status, potential value, challenges, and future development directions of multimodal data fusion in orthodontic research and clinical practice.

Key words: multimodal data fusion, orthodontics, accurate diagnosis, personalized treatment

中图分类号:

R783.5

张俭,白雪,何小倩,葛振林. 多模态数据融合技术在口腔正畸领域的应用及研究进展[J]. 国际口腔医学杂志, 2025, 52(6): 764-770.

Jian Zhang,Xue Bai,Xiaoqian He,Zhenlin Ge. Application and research progress of multimodal data fusion in orthodontics[J]. Int J Stomatol, 2025, 52(6): 764-770.

图/表 2

表 1

表 2

参考文献 55

[1]	Revilla-León M, Kois DE, Zeitler JM, et al. An overview of the digital occlusion technologies: intraoral scanners, jaw tracking systems, and computeri-zed occlusal analysis devices[J]. J Esthet Restor Dent, 2023, 35(5): 735-744.
[2]	Yuan Y, Liu Q, Yang S, et al. Four-dimensional superimposition techniques to compose dental dyna-mic virtual patients: a systematic review[J]. J Funct Biomater, 2023, 14(1): 33.
[3]	Li Q, Bi MN, Yang KW, et al. The creation of a virtual dental patient with dynamic occlusion and its application in esthetic dentistry[J]. J Prosthet Dent, 2021, 126(1): 14-18.
[4]	Azam MA, Khan KB, Salahuddin S, et al. A review on multimodal medical image fusion: compendious analysis of medical modalities, multimodal databa-ses, fusion techniques and quality metrics[J]. Comput Biol Med, 2022, 144: 105253.
[5]	Zhou T, Cheng QR, Lu HL, et al. Deep learning methods for medical image fusion: a review[J]. Comput Biol Med, 2023, 160: 106959.
[6]	Zadeh A, Liang PP, Poria S, et al. Multi-attention recurrent network for human communication comprehension[J]. Proc AAAI Conf Artif Intell, 2018, 2018: 5642-5649.
[7]	Cai HS, Qu ZD, Li Z, et al. Feature-level fusion approaches based on multimodal EEG data for depression recognition[J]. Inf Fusion, 2020, 59: 127-138.
[8]	Wang W, Jia M. A facial expression recognition network based on attention double branch enhanced fusion[J]. PeerJ Comput Sci, 2024, 10: e2266.
[9]	Modak SKS, Jha VK. A novel multimodal biometric authentication framework using rule-based ANFIS based on hybrid level fusion[J]. Wirel Pers Commun, 2023, 128(1): 187-207.
[10]	Karim S, Tong G, Li JY, et al. Current advances and future perspectives of image fusion: a comprehensive review[J]. Inf Fusion, 2023, 90: 185-217.
[11]	Wang SP, He X, Jian ZQ, et al. Advances and prospects of multi-modal ophthalmic artificial intelligence based on deep learning: a review[J]. Eye Vis, 2024, 11(1): 38.
[12]	Dar MN, Akram MU, Yuvaraj R, et al. EEG-based emotion charting for Parkinson’s disease patients using Convolutional Recurrent Neural Networks and cross dataset learning[J]. Comput Biol Med, 2022, 144: 105327.
[13]	Bardak B, Tan M. Improving clinical outcome predictions using convolution over medical entities with multimodal learning[J]. Artif Intell Med, 2021, 117: 102112.
[14]	Conejo J, Dayo AF, Syed AZ, et al. The digital clone: intraoral scanning, face scans and cone beam computed tomography integration for diagnosis and treatment planning[J]. Dent Clin North Am, 2021, 65(3): 529-553.
[15]	Park JH, Lee GH, Moon DN, et al. Creation of digital virtual patient by integrating CBCT, intraoral scan, 3D facial scan: an approach to methodology for integration accuracy[J]. J Craniofac Surg, 2022, 33(4): e396-e398.
[16]	Kau CH. Creation of the virtual patient for the study of facial morphology[J]. Facial Plast Surg Clin North Am, 2011, 19(4): 615-622.
[17]	Mangano C, Luongo F, Migliario M, et al. Combi-ning intraoral scans, cone beam computed tomography and face scans: the virtual patient[J]. J Craniofac Surg, 2018, 29(8): 2241-2246.
[18]	Lepidi L, Kim BC, Giberti L, et al. The 4D virtual patient: a proof of concept in digital dentistry[J]. J Prosthet Dent, 2024: S0022-S3913(24)00194-X.
[19]	Adel SM, Vaid NR, El-Harouni N, et al. TIP, TORQUE & ROTATIONS: how accurately do digital superimposition softwarepackages quantify tooth movement[J]. Prog Orthod, 2022, 23(1): 8.
[20]	Rahman F, Celebi AA, Louis PJ, et al. A comprehensive treatment approach for idiopathic condylar resorption and anterior open bite with 3D virtual surgical planning and self-ligated customized lingual appliance[J]. Am J Orthod Dentofacial Orthop, 2019, 155(4): 560-571.
[21]	Zhang XJ, He L, Guo HM, et al. Integrated three-dimensional digital assessment of accuracy of anterior tooth movement using clear aligners[J]. Korean J Orthod, 2015, 45(6): 275-281.
[22]	Jreige CS, Kimura RN, Segundo ÂRTC, et al. Esthetic treatment planning with digital animation of the smile dynamics: a technique to create a 4-dimensional virtual patient[J]. J Prosthet Dent, 2022, 128(2): 130-138.
[23]	Li YH, El Habib Daho M, Conze PH, et al. A review of deep learning-based information fusion te-chniques for multimodal medical image classification[J]. Comput Biol Med, 2024, 177: 108635.
[24]	Zheng JZ, Xiao JY, Wang YW, et al. CIRF: coupled image reconstruction and fusion strategy for deep learning based multi-modal image fusion[J]. Sensors, 2024, 24(11): 3545.
[25]	赵阳, 李俊诚, 成博栋, 等. 深度学习在口腔医学影像中的应用与挑战[J]. 中国图象图形学报, 2024, 29(3): 586-607.
	Zhao Y, Li JC, Cheng BD, et al. Applications and challenges of deep learning in dental imaging[J]. J Image Graph, 2024, 29(3): 586-607.
[26]	Wongkhuenkaew R, Auephanwiriyakul S, Chaiworawitkul M, et al. Grey wolf optimizer with behavior considerations and dimensional learning in three-dimensional tooth model reconstruction[J]. Bioengineering, 2024, 11(3): 254.
[27]	Dhopte A, Bagde H. Smart smile: revolutionizing dentistry with artificial intelligence[J]. Cureus, 2023, 15(6): e41227.
[28]	Katta M, Petrescu SM, Dragomir LP, et al. Using the finite element method to determine the odontoperiodontal stress for a patient with angle class Ⅱ division 1 malocclusion[J]. Diagnostics, 2023, 13(9): 1567.
[29]	Ciklacandir S, Gokce Kara G, Isler Y. A biomechanical investigation of miniscrews placed on a mandible for temporary anchorage; a patient-specific finite element analysis[J]. Comput Methods Biomech Biomed Engin, 2024: 1-10.
[30]	Kılıç B, İbrahim AH, Aksoy S, et al. A family-centered orthodontic screening approach using a machine learning-based mobile application[J]. J Dent Sci, 2024, 19(1): 186-195.
[31]	夏泽洋. 精准口腔正畸诊疗机器人[J]. 科技纵览, 2018(2): 54-55.
	Xia ZY. Precision orthodontic treatment robot[J]. IEEE Spectr, 2018(2): 54-55.
[32]	Weissheimer A, Pham J, Tong HS, et al. Esthetic outcomes in orthodontics through digital customization with a lingual appliance system[J]. J Esthet Restor Dent, 2024, 36(9): 1267-1280.
[33]	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.
[34]	de Leotard A, Le Norcy E. Comparison of dental movements in digital setups created by orthodontists and “3shape design service^®” engineers: a cross-sectional study[J]. Int Orthod, 2024, 22(4): 100919.
[35]	唐敏, 郭宏铭, 白玉兴, 等. 三维整合牙颌模型在个性化舌侧托槽计算机辅助设计中的应用[J]. 中华口腔医学杂志, 2012, 47(8): 501-504.
	Tang M, Guo HM, Bai YX, et al. Application of integrated digital maxillodental model in computer aided design of individualized lingual brackets[J]. Chin J Stomatol, 2012, 47(8): 501-504.
[36]	Hansa I, Semaan SJ, Vaid NR, et al. Remote monitoring and “Tele-orthodontics”: concept, scope and applications[J]. Semin Orthod, 2018, 24(4): 470-481.
[37]	Yoon K, Jeong HM, Kim JW, et al. AI-based dental caries and tooth number detection in intraoral photos: model development and performance evaluation[J]. J Dent, 2024, 141: 104821.
[38]	Duy HB, Hue TT, Son TM, et al. A dental intraoral image dataset of gingivitis for image captioning[J]. Data Brief, 2024, 57: 110960.
[39]	Snider V, Homsi K, Kusnoto B, et al. Clinical eva-luation of Artificial Intelligence Driven Remote Monitoring technology for assessment of patient oral hygiene during orthodontic treatment[J]. Am J Orthod Dentofacial Orthop, 2024, 165(5): 586-592.
[40]	Du J, Li W, Lu K, et al. An overview of multi-modal medical image fusion[J]. Neurocomputing, 2016, 215: 3-20.
[41]	Hermessi H, Mourali O, Zagrouba E. Multimodal medical image fusion review: theoretical back- ground and recent advances[J]. Signal Process, 2021, 183: 108036.
[42]	沈颉飞. 口腔修复诊疗中构建虚拟患者的机遇与挑战[J]. 华西口腔医学杂志, 2024, 42(1): 1-11.
	Shen JF. The chance and challenge of creating vir-tual patients in prosthodontics[J]. West China J Stomatol, 2024, 42(1): 1-11.
[43]	Badesha AS, Frood R, Bailey MA, et al. A scoping review of machine-learning derived radiomic analysis of CT and PET imaging to investigate atherosc-lerotic cardiovascular disease[J]. Tomography, 2024, 10(9): 1455-1487.
[44]	Liu TG, Bai QZ, Torigian DA, et al. VSmTrans: a hybrid paradigm integrating self-attention and convolution for 3D medical image segmentation[J]. Med Image Anal, 2024, 98: 103295.
[45]	Li Y, Zhao J, Lü Z, et al. Medical image fusion method by deep learning[J]. Int J Cogn Comput Eng, 2021, 2: 21-29.
[46]	Jiang YS, Yang K, Shang CX, et al. A fast adaptive spatio-temporal fusion method to enhanced Fit-FC[J]. PLoS One, 2024, 19(7): e0301077.
[47]	Yuan S, Chen RY, Zang L, et al. Development of a software system for surgical robots based on multimodal image fusion: study protocol[J]. Front Surg, 2024, 11: 1389244.
[48]	Shin H, Ryu K, Kim JY, et al. Application of privacy protection technology to healthcare big data[J]. Digit Health, 2024, 10: 20552076241282242.
[49]	He ZM, Wei JC, Chen CT, et al. Gradient-based optimization for quantum architecture search[J]. Neural Netw, 2024, 179: 106508.
[50]	Castro C, Leiva V, Garrido D, et al. Blockchain in clinical trials: bibliometric and network studies of applications, challenges, and future prospects based on data analytics[J]. Comput Methods Programs Biomed, 2024, 255: 108321.
[51]	刘鎵仪, 周彦恒. 人工智能在正畸诊疗及疗效预测中的应用进展[J]. 口腔医学研究, 2023, 39(10): 862-865.
	Liu JY, Zhou YH. Application progress of artificial intelligence in orthodontic diagnosis, treatment, and soft tissue prediction[J]. J Oral Sci Res, 2023, 39(10): 862-865.
[52]	Homsi K, Snider V, Kusnoto B, et al. In-vivo evaluation of Artificial Intelligence Driven Remote Monitoring technology for tracking tooth movement and reconstruction of 3-dimensional digital models du-ring orthodontic treatment[J]. Am J Orthod Dentofacial Orthop, 2023, 164(5): 690-699.
[53]	唐建明. 精准医学开拓个体化医疗领域“蓝海市场”的进程[J]. 中国医药导刊, 2024, 26(5): 425-431.
	Tang JM. Precision medicine sailing into “A Blue Sea” of individualized health care[J]. Chin J Med Guide, 2024, 26(5): 425-431.
[54]	Huang GM, Li YY, Jameel S, et al. From explaina-ble to interpretable deep learning for natural language processing in healthcare: how far from reality[J]. Comput Struct Biotechnol J, 2024, 24: 362-373.
[55]	何剑虎, 王德健, 赵志锐, 等. 大语言模型在医疗领域的前沿研究与创新应用[J]. 医学信息学杂志, 2024, 45(9): 10-18.
	He JH, Wang DJ, Zhao ZR, et al. The frontier research and innovative applications of large language models in the medical field[J]. J Med Inform, 2024, 45(9): 10-18.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

方法名称	适用范围	优点	缺点	实现难度
特征级融合（早期融合）	图像、文本、音频等多种模态数据的融合	可以捕捉不同模态间的低级关联信息	可能面临过拟合风险，在跨视图动态建模方面可能表现不佳	中等
决策级融合（后期融合）	多用于分类、决策任务，如医疗诊断、安防系统	能更好地对特定视图的动态进行建模	在探索动态交互和低级模态互动方面存在不足	较低
混合级融合	根据不同的应用场景和数据特点灵活应用	适应不同模态的数据，提升结果的质量、准确性和鲁棒性，灵活性高	实现较为复杂，需要设计合理的融合机制	较高

主要技术挑战	应对策略
数据获取与处理的复杂性	数据标准化、数据预处理、专业设备和技术
数据融合算法复杂程度高	算法优化、计算资源增强、可解释性提升
数据安全与隐私保护问题	数据加密、隐私保护技术、法规和政策