Similar articles

Abstract: artificial intelligence (AI) has been utilized in soft-tissue analysis and prediction in orthodontic treatment planning, although its reliability has not been systematically assessed. This scoping review was conducted to outline the development of AI in terms of predicting soft-tissue changes after orthodontic treatment, as well as to comprehensively evaluate its prediction accuracy. Six electronic databases (PubMed, EBSCOhost, Web of Science, Embase, Cochrane Library, and Scopus) were searched up to March 14, 2023. Clinical studies investigating the performance of AI-based systems in predicting post-orthodontic soft-tissue alterations were included. The Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) and Joanna Briggs Institute (JBI) appraisal checklist for diagnostic test accuracy studies were applied to assess risk of bias, while the Grading of Recommendation, Assessment, Development, and Evaluation (GRADE) assessment was conducted to evaluate the certainty of outcomes. After screening 2500 studies, four non-randomized clinical trials were finally included for full-text evaluation. We found a low level of evidence indicating an estimated high overall accuracy of AI-generated prediction, whereas the lower lip and chin seemed to be the least predictable regions. Furthermore, the facial morphology simulated by AI via the fusion of multimodality images was considered to be reasonably true. Since all of the included studies that were not randomized clinical trials (non-RCTs) showed a moderate to high risk of bias, more well-designed clinical trials with sufficient sample size are needed in future work.

人工智能预测正畸面部变化的研究进展和准确度：概况性系统综述

[1]AbiodunOI, JantanA, OmolaraAE, et al., 2019. Comprehensive review of artificial neural network applications to pattern recognition. IEEE Access, 7:158820-158846.

[2]BralA, OlateS, ZarorC, et al., 2020. A prospective study of soft- and hard-tissue changes after mandibular advancement surgery: midline changes in the chin area. Am J Orthod Dentofacial Orthop, 157(5):662-667.

[3]CampbellJM, KlugarM, DingS, et al., 2020. Chapter 9: Diagnostic test accuracy systematic reviews. In: Aromataris E, Munn Z (Eds.), JBI Manual for Evidence Synthesis. JBI, p.309-359.

[4]ChenS, LouHD, GuoL, et al., 2012. 3-D finite element modelling of facial soft tissue and preliminary application in orthodontics. Comput Methods Biomech Biomed Engin, 15(3):255-261.

[5]GrafCC, DritsasK, GhamriM, et al., 2022. Reliability of cephalometric superimposition for the assessment of craniofacial changes: a systematic review. Eur J Orthod, 44(5):477-490.

[6]HoldawayRA, 1983. A soft-tissue cephalometric analysis and its use in orthodontic treatment planning. Part I. Am J Orthod, 84(1):1-28.

[7]HowardJ, 2019. Artificial intelligence: implications for the future of work. Am J Ind Med, 62(11):917-926.

[8]JavidAM, DasS, SkoglundM, et al., 2021. A ReLU dense layer to improve the performance of neural networks. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, p.2810-2814.

[9]KaratasOH, ToyE, 2014. Three-dimensional imaging techniques: a literature review. Eur J Dent, 8(1):132-140.

[10]KasaiK, 1998. Soft tissue adaptability to hard tissues in facial profiles. Am J Orthod Dentofacial Orthop, 113(6):‍674-684.

[11]KassemHE, MarzoukES, 2018. Prediction of changes due to mandibular autorotation following miniplate-anchored intrusion of maxillary posterior teeth in open bite cases. Prog Orthod, 19:13.

[12]KhanagarSB, Al-EhaidebA, VishwanathaiahS, et al., 2021. Scope and performance of artificial intelligence technology in orthodontic diagnosis, treatment planning, and clinical decision-making ‍– a systematic review. J Dent Sci, 16(1):482-492.

[13]LeonardiR, GiordanoD, MaioranaF, 2009. An evaluation of cellular neural networks for the automatic identification of cephalometric landmarks on digital images. J Biomed Biotechnol, 2009:717102.

[14]LimYN, YangBE, ByunSH, et al., 2022. Three-dimensional digital image analysis of skeletal and soft tissue points A and B after orthodontic treatment with premolar extraction in bimaxillary protrusive patients. Biology (Basel), 11(3):381.

[15]LiuCX, KongDH, WangSF, et al., 2021. Deep3D reconstruction: methods, data, and challenges. Front Inform Technol Electron Eng, 22(5):652-672.

[16]LuxCJ, StellzigA, VolzD, et al., 1998. A neural network approach to the analysis and classification of human craniofacial growth. Growth Dev Aging, 62(3):95-106.

[17]MoonJH, KimMG, HwangHW, et al., 2022. Evaluation of an individualized facial growth prediction model based on the multivariate partial least squares method. Angle Orthod, 92(6):705-713.

[18]MörchCM, AtsuS, CaiW, et al., 2021. Artificial intelligence and ethics in dentistry: a scoping review. J Dent Res, 100(13):1452-1460.

[19]MoyersRE, BooksteinFL, 1979. The inappropriateness of conventional cephalometrics. Am J Orthod, 75(6):‍599-617.

[20]NandaSB, KalhaAS, JenaAK, et al., 2015. Artificial neural network (ANN) modeling and analysis for the prediction of change in the lip curvature following extraction and non-extraction orthodontic treatment. J Dent Specialities, 3(2):130-139.

[21]PageMJ, McKenzieJE, BossuytPM, et al., 2021. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ, 372:n71.

[22]PanYH, 2021. Miniaturized five fundamental issues about vis

[23]ual knowledge. Front Inform Technol Electron Eng, 22(5):615-618.

[24]PanYH, 2022. On visual understanding. Front Inform Technol Electron Eng, 23(9):1287-1289.

[25]ParkJH, KimYJ, KimJ, et al., 2021. Use of artificial intelligence to predict outcomes of nonextraction treatment of Class II malocclusions. Semin Orthod, 27(2):87-95.

[26]ParkYS, ChoiJH, KimY, et al., 2022. Deep learning-based prediction of the 3D postorthodontic facial changes. J Dent Res, 101(11):1372-1379.

[27]RickettsRM, 1960. Cephalometric synthesis: an exercise in stating objectives and planning treatment with tracings of the head roentgenogram. Am J Orthod, 46(9):647-673.

[28]RongoR, BucciR, AdaimoR, et al., 2020. Two-dimensional versus three-dimensional Frӓnkel Manoeuvre: a reproducibility study. Eur J Orthod, 42(2):157-162.

[29]RyanR, HillS, 2016. How to GRADE the quality of the evidence. Cochrane Consumers and Communication Group. http://cccrg.cochrane.org/author-resources

[30]SampleLB, SadowskyPL, BradleyE, 1998. An evaluation of two VTO methods. Angle Orthod, 68(5):401-408. https://doi.‍org/10.‍1043/0003-3219(1998)068<0401:AEOTVM>2.3.CO;2

[31]ScarfeWC, AzevedoB, ToghyaniS, et al., 2017. Cone Beam Computed Tomographic imaging in orthodontics. Aust Dent J, 62(Suppl 1):33-50.

[32]SchwendickeF, GollaT, DreherM, et al., 2019. Convolutional neural networks for dental image diagnostics: a scoping review. J Dent, 91:103226.

[33]ShenDG, WuGR, SukHI, 2017. Deep learning in medical image analysis. Annu Rev Biomed Eng, 19:221-248.

[34]SoheilifarS, SoheilifarS, AfrasiabiZ, et al., 2022. Prediction accuracy of Dolphin software for soft-tissue profile in Class I patients undergoing fixed orthodontic treatment. J World Fed Orthod, 11(1):29-35.

[35]StratemannSA, HuangJC, MakiK, et al., 2008. Comparison of cone beam computed tomography imaging with physical measures. Dentomaxillofac Radiol, 37(2):80-93.

[36]SubramanianAK, ChenY, AlmalkiA, et al., 2022. Cephalometric analysis in orthodontics using artificial intelligence ‍– ‍a comprehensive review. Biomed Res Int, 2022:1880113.

[37]TanikawaC, YamashiroT, 2021. Development of novel artificial intelligence systems to predict facial morphology after orthognathic surgery and orthodontic treatment in Japanese patients. Sci Rep, 11:15853.

[38]ter HorstR, van WeertH, LoonenT, et al., 2021. Three-dimensional virtual planning in mandibular advancement surgery: soft tissue prediction based on deep learning. J Cranio-Maxillofac Surg, 49(9):775-782.

[39]Toepel-SieversC, Fischer-BrandiesH, 1999. Validity of the computer-assisted cephalometric growth prognosis VTO (Visual treatment objective) according to ricketts. J Orofac Orthop, 60(3):185-194.

[40]TongX, 2022. Three-dimensional shape space learning for vis

[41]ual concept construction: challenges and research progress. Front Inform Technol Electron Eng, 23(9):‍1290-1297.

[42]VazJM, BalajiS, 2021. Convolutional neural networks (CNNs): concepts and applications in pharmacogenomics. Mol Divers, 25(3):1569-1584.

[43]WenYF, WongHM, McGrathCP, 2019. Developmental shape changes in facial morphology: geometric morphometric analyses based on a prospective, population-based, Chinese cohort in Hong Kong. PLoS ONE, 14(6):e0218542.

[44]WhitingPF, RutjesAWS, WestwoodME, et al., 2011. QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Ann Intern Med, 155(8):529-536.

[45]ZhangX, MeiL, YanXY, et al., 2019. Accuracy of computer-aided prediction in soft tissue changes after orthodontic treatment. Am J Orthod Dentofacial Orthop, 156(6):‍823-831.

[46]ZhangXB, HuY, ChenW, et al., 2021. 3D brain glioma segmentation in MRI through integrating multiple densely connected 2D convolutional neural networks. J Zhejiang Univ-Sci B (Biomed & Biotechnol), 22(6):462-475.