{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T22:15:26Z","timestamp":1782512126435,"version":"3.54.5"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T00:00:00Z","timestamp":1713225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005626","name":"Universit\u00e4t Regensburg","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005626","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Background and objective<\/jats:title><jats:p>Due to the high prevalence of dental caries, fixed dental restorations are regularly required to restore compromised teeth or replace missing teeth while retaining function and aesthetic appearance. The fabrication of dental restorations, however, remains challenging due to the complexity of the human masticatory system as well as the unique morphology of each individual dentition. Adaptation and reworking are frequently required during the insertion of fixed dental prostheses (FDPs), which increase cost and treatment time. This article proposes a data-driven approach for the partial reconstruction of occlusal surfaces based on a data set that comprises 92 3D mesh files of full dental crown restorations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A Generative Adversarial Network (GAN) is considered for the given task in view of its ability to represent extensive data sets in an unsupervised manner with a wide variety of applications. Having demonstrated good capabilities in terms of image quality and training stability, StyleGAN-2 has been chosen as the main network for generating the occlusal surfaces. A 2D projection method is proposed in order to generate 2D representations of the provided 3D tooth data set for integration with the StyleGAN architecture. The reconstruction capabilities of the trained network are demonstrated by means of 4 common inlay types using a Bayesian Image Reconstruction method. This involves pre-processing the data in order to extract the necessary information of the tooth preparations required for the used method as well as the modification of the initial reconstruction loss.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The reconstruction process yields satisfactory visual and quantitative results for all preparations with a root mean square error (RMSE) ranging from 0.02 mm to 0.18 mm. When compared against a clinical procedure for CAD inlay fabrication, the group of dentists preferred the GAN-based restorations for 3 of the total 4 inlay geometries.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>This article shows the effectiveness of the StyleGAN architecture with a downstream optimization process for the reconstruction of 4 different inlay geometries. The independence of the reconstruction process and the initial training of the GAN enables the application of the method for arbitrary inlay geometries without time-consuming retraining of the GAN.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2024.1339193","type":"journal-article","created":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T04:41:04Z","timestamp":1713242464000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["A data-driven approach for the partial reconstruction of individual human molar teeth using generative deep learning"],"prefix":"10.3389","volume":"7","author":[{"given":"Alexander","family":"Broll","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Rosentritt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Schlegl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"Goldhacker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,4,16]]},"reference":[{"key":"B1","first-page":"293","article-title":"A statistical method for robust 3D surface reconstruction from sparse data","volume-title":"IEEE 2nd International Symposium on 3D Data Processing, Visualization and Transmission (3DPVT)","author":"Blanz","year":"2004"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.prosdent.2022.12.004","article-title":"Accuracy of artificial intelligence-designed single-molar dental prostheses: a feasibility study","author":"Chau","year":"2023","journal-title":"J. Prosthet. Dent"},{"key":"B3","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.dental.2023.02.001","article-title":"Morphology and mechanical performance of dental crown designed by 3D-DCGAN","volume":"39","author":"Ding","year":"2023","journal-title":"Dental Mater"},{"key":"B4","doi-asserted-by":"publisher","first-page":"102224","DOI":"10.1016\/j.bspc.2020.102224","article-title":"High-resolution dermoscopy image synthesis with conditional generative adversarial networks","volume":"64","author":"Ding","year":"2021","journal-title":"Biomed. Sig. Proc. Control"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1405","DOI":"10.1007\/s11548-023-02841-1","article-title":"3D reconstruction for maxillary anterior tooth crown based on shape and pose estimation networks","volume":"18","author":"Feng","year":"2023","journal-title":"Int. J. Comput. Assist. Radiol. Surg"},{"key":"B6","first-page":"27","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B7","article-title":"Learning beyond human expertise with generative models for dental restorations","author":"Hwang","year":"2018","journal-title":"arXiv preprint arXiv:1804.00064"},{"key":"B8","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.632","article-title":"Image-to-image translation with conditional adversarial networks","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Isola","year":"2017"},{"key":"B9","first-page":"24","article-title":"Regression plane en 3D","author":"Jacquelin","year":"2011","journal-title":"Regres. Traject"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1016\/S0140-6736(18)32279-7","article-title":"Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990\u20132017: a systematic analysis for the Global Burden of Disease Study 2017","volume":"392","author":"James","year":"2018","journal-title":"Lancet"},{"key":"B11","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.compbiomed.2015.11.001","article-title":"Robust tooth surface reconstruction by iterative deformation","volume":"68","author":"Jiang","year":"2016","journal-title":"Comput. Biol. Med"},{"key":"B12","article-title":"Progressive growing of gans for improved quality, stability, and variation","author":"Karras","year":"2017","journal-title":"arXiv preprint arXiv:1710.10196"},{"key":"B13","first-page":"12104","article-title":"Training generative adversarial networks with limited data","author":"Karras","year":"","journal-title":"34th International Conference on Neural Information Processing Systems (NIPS)"},{"key":"B14","first-page":"8110","article-title":"Analyzing and improving the image quality of StyleGAN","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Karras","year":""},{"key":"B15","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"B16","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1002\/ajpa.21086","article-title":"Technical note: occlusal fingerprint analysis: quantification of tooth wear pattern","volume":"139","author":"Kullmer","year":"2009","journal-title":"Am. J. Phys. Anthropol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1109\/TMI.2020.3041452","article-title":"LCANet: learnable connected attention network for human identification using dental images","volume":"40","author":"Lai","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B18","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.bspc.2017.07.005","article-title":"Dental diagnosis from X-Ray images: an expert system based on fuzzy computing","volume":"39","author":"Le Son","year":"2018","journal-title":"Biomed. Signal Proc. Control"},{"key":"B19","first-page":"39","article-title":"AI-based dental prostheses fabrication using generative adversarial networks","volume":"40","author":"Lee","year":"2021","journal-title":"Quant. Bio-Sci"},{"key":"B20","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/JBHI.2021.3085770","article-title":"Unsupervised domain adaptation based image synthesis and feature alignment for joint optic disc and cup segmentation","volume":"26","author":"Lei","year":"2022","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B21","article-title":"Bayesian image reconstruction using deep generative models","author":"Marinescu","year":"2020","journal-title":"arXiv preprint arXiv:2012.04567"},{"key":"B22","volume-title":"An Introduction to Morse Theory, volume 208 of Iwanami Series in Modern Mathematics","author":"Matsumoto","year":"2002"},{"key":"B23","doi-asserted-by":"publisher","first-page":"101782","DOI":"10.1016\/j.bspc.2019.101782","article-title":"An image augmentation approach using two-stage generative adversarial network for nuclei image segmentation","volume":"57","author":"Pandey","year":"2020","journal-title":"Biomed. Sig. Proc. Control"},{"key":"B24","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1007\/s00784-013-1029-9","article-title":"Influence of cusp inclination and curvature on the in vitro failure and fracture resistance of veneered zirconia crowns","volume":"18","author":"Preis","year":"2014","journal-title":"Clin. Oral Invest"},{"key":"B25","doi-asserted-by":"publisher","first-page":"102939","DOI":"10.1016\/j.bspc.2021.102939","article-title":"Gender classification on digital dental x-ray images using deep convolutional neural network","volume":"69","author":"Rajee","year":"2021","journal-title":"Biomed. Sig. Proc. Control"},{"key":"B26","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1111\/jerd.13044","article-title":"An overview of the digital occlusion technologies: Intraoral scanners, jaw tracking systems, and computerized occlusal analysis devices","volume":"35","author":"Revilla-Le\u00f3n","year":"2023","journal-title":"J. Esthet. Restor. Dent"},{"key":"B27","doi-asserted-by":"publisher","first-page":"104364","DOI":"10.1016\/j.jdent.2022.104364","article-title":"Impact of the occlusal contact pattern and occlusal adjustment on the wear and stability of crowns","volume":"128","author":"Schnitzhofer","year":"2023","journal-title":"J. Dent"},{"key":"B28","first-page":"3838","article-title":"SCARP: 3D shape completion in ARbitrary poses for improved grasping","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Sen","year":"2023"},{"key":"B29","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1145\/1057432.1057456","article-title":"Laplacian surface editing","author":"Sorkine","year":"2004","journal-title":"Symposium on geometry processing (SGP)"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/1933617","article-title":"A dual discriminator adversarial learning approach for dental occlusal surface reconstruction","volume":"2022","author":"Tian","year":"","journal-title":"J. Healthc. Eng"},{"key":"B31","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/JBHI.2021.3119394","article-title":"DCPR-GAN: dental crown prosthesis restoration using two-stage generative adversarial networks","volume":"26","author":"Tian","year":"","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B32","doi-asserted-by":"publisher","first-page":"103954","DOI":"10.1016\/j.bspc.2022.103954","article-title":"Efficient tooth gingival margin line reconstruction via adversarial learning","volume":"78","author":"Tian","year":"","journal-title":"Biomed. Sign. Proc. Control"},{"key":"B33","doi-asserted-by":"publisher","first-page":"2415","DOI":"10.1109\/TMI.2021.3077334","article-title":"Efficient computer-aided design of dental inlay restoration: a deep adversarial framework","volume":"40","author":"Tian","year":"2021","journal-title":"IEEE Trans. Med. Imag"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","article-title":"Dynamic graph CNN for learning on point clouds","volume":"38","author":"Wang","year":"2018","journal-title":"ACM Trans. Graph"},{"key":"B35","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1109\/JBHI.2017.2660527","article-title":"Model-based orthodontic assessments for dental panoramic radiographs","volume":"22","author":"Wu","year":"2018","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B36","first-page":"82","article-title":"Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling","author":"Wu","year":"2016","journal-title":"30th International Conference on Neural Information Processing Systems (NIPS)"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1109\/TMI.2018.2827462","article-title":"Low-dose CT image denoising using a generative adversarial network with wasserstein distance and perceptual loss","volume":"37","author":"Yang","year":"2018","journal-title":"IEEE Trans. Med. Imag"},{"key":"B38","doi-asserted-by":"publisher","first-page":"14114","DOI":"10.1109\/TPAMI.2023.3309253","article-title":"AdaPoinTr: diverse point cloud completion with adaptive geometry-aware transformers","volume":"45","author":"Yu","year":"2023","journal-title":"IEEE Trans. Pattern Analy. Mach. Intell"},{"key":"B39","doi-asserted-by":"publisher","first-page":"e3321","DOI":"10.1002\/cnm.3321","article-title":"Personalized design technique for the dental occlusal surface based on conditional generative adversarial networks","volume":"36","author":"Yuan","year":"2020","journal-title":"Int. J. Numer. Methods Biomed. Eng"},{"key":"B40","first-page":"10021","article-title":"LION: latent point diffusion models for 3D shape generation","volume":"35","author":"Zeng","year":"2022","journal-title":"Adv. Neural Inf. Proc. Syst"},{"key":"B41","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.cad.2010.11.003","article-title":"A novel 3D morphing approach for tooth occlusal surface reconstruction","volume":"43","author":"Zheng","year":"2011","journal-title":"Comput. Aided Des"},{"key":"B42","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/978-3-031-05981-0_13","article-title":"ToothCR: a two-stage completion and reconstruction approach on 3D dental model","volume-title":"26th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)","author":"Zhu","year":"2022"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1339193\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T04:41:14Z","timestamp":1713242474000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1339193\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,16]]},"references-count":42,"alternative-id":["10.3389\/frai.2024.1339193"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1339193","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,16]]},"article-number":"1339193"}}