INFLUENCE OF ARTIFICIALLY GENERATED INTRAORAL SCAN DEFECTS ON THE QUALITY OF AUTOMATED TOOTH SEGMENTATION IN PATIENTS WITH ANTERIOR DENTAL CROWDING
DOI:
https://doi.org/10.35220/2523-420X/2026.3.11Keywords:
intraoral scanner, digital impression, tooth segmentation, artificial intelligence, dental crowding, scan defects, orthodontics, digital modelAbstract
To evaluate the influence of the localization of artificially generated digitalsurface defects within intraoral scans on the quality of automated segmentation of digital models in patients with anterior dental crowding. Research methods. Eighteen anonymized mandibular intraoral scans obtained from patients with anterior dental crowding were included. Four digital investigation conditions were generated for each original scan: intact scan data (no graphical defects present); localized vestibular-surface defect; proximal-surface defect not involving the visual intertooth demarcation line; proximal-surface defect extending across the visual demarcation line between adjacent teeth. Artificial defects were generated in the Medit Design software environment by local deletion of polygonal mesh fragments. Automated segmentation was performed using Medit Ortho Simulation. Results. Automated segmentation defects were registered in 4 of 18 intact scans (22,22%), 5 of 18 scans with vestibular defects (27,78%), 8 of 18 scans with proximal defects not crossing the inter-tooth visual boundary (44,44%), and 15 of 18 scans in which the defect extended across the visual inter-tooth demarcation line (83,33%). The most characteristic errors in the latter condition were displacement or loss of part of the segmentation boundary, partial fusion of adjacent tooth segments, fragmentation of an individual tooth segment, and incorrect automated labeling. The frequency of segmentation defects differed significantly across the four conditions (Cochran Q=24.67; p < 0,001). Conclusions. The localization of a digital-surface defect relative to the boundary between adjacent teeth appears to be more important for automated segmentation quality than the mere presence of localized data loss itself. Vestibular defects had a limited effect, whereas defects extending across the inter-tooth visual boundary substantially increased the risk of critical segmentation errors
References
Christopoulou, I., Kaklamanos, E.G., Makrygiannakis, M.A., Bitsanis, I., Perlea, P., & Tsolakis, A.I. (2022). Intraoral scanners in orthodontics: a critical review. International Journal of Environmental Research and Public Health, 19(3), 1407. https://doi.org/10.3390/ijerph19031407
Alassiry, A.M. (2023). Clinical aspects of digital three-dimensional intraoral scanning in orthodontics–A systematic review. The Saudi Dental Journal, 35(5), 437-442. https://doi.org/10.1016/j.sdentj.2023.04.004
Eggmann, F., & Blatz, M.B. (2024). Recent advances in intraoral scanners. Journal of Dental Research, 103(13), 1349-1357. https://doi.org/10.1177/00220345241271937
Revilla-León, M., Aragoneses, R., Arroyo Valverde, E.M., Gómez-Polo, M., & Kois, J.C. (2025). Classification of scanning errors of digital scans recorded by using intraoral scanners. Journal of Esthetic and Restorative Dentistry, 37(6), 1363-1371. https://doi.org/10.1111/jerd.13419
Vasilescu, V.G., Ciocan, L.T., Imre, M., & Pituru, S.M. (2026). Clinical identification and classification of scanning errors in intraoral digital scans. Journal of Dentistry, 167, 106365. https://doi.org/10.1016/j.jdent.2026.106365
Yacout, Y.M., Eid, F.Y., Tageldin, M.A., & Kassem, H.E. (2024). Evaluation of the accuracy of automated tooth segmentation of intraoral scans using artificial intelligence-based software packages. American Journal of Orthodontics and Dentofacial Orthopedics, 166(3), 282-291.e1. https://doi.org/10.1016/j.ajodo.2024.05.015
Wu, T.H., Lian, C., Lee, S., Pastewait, M., Piers, C., Liu, J., Wang, F., Wang, L., Chiu, C. Y., Wang, W., Jackson, C., Chao, W. L., Shen, D., & Ko, C. C. (2022). Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans. IEEE Transactions on Medical Imaging, 41(11), 3158-3166. https://doi.org/10.1109/TMI.2022.3180343
Wang, X., Alqahtani, K. A., Van den Bogaert, T., Shujaat, S., Jacobs, R., & Shaheen, E. (2024). Convolutional neural network for automated tooth segmentation on intraoral scans. BMC Oral Health, 24(1), 804. https://doi.org/10.1186/s12903-024-04582-2
Krenmayr, L., von Schwerin, R., Schaudt, D., Riedel, P., & Hafner, A. (2024). DilatedToothSegNet: Tooth Segmentation Network on 3D Dental Meshes Through Increasing Receptive Vision. Journal of Imaging Informatics in Medicine, 37(4), 1846-1862. https://doi.org/10.1007/s10278-024-01061-6
Li, J., Cheng, B., Niu, N., Gao, G., Ying, S., Shi, J.,& Zeng, T. (2024). A fine-grained orthodontics segmentation model for 3D intraoral scan data. Computers in Biology and Medicine, 168, 107821. https://doi.org/10.1016/j.compbiomed.2023.107821
Del Cacho-Salvador, G., Burgos-Artizzu, X.P.,García-Arranz, J., González-Martín, Ó., Oteo-Morilla, C., Gallas-Torreira, M., Cernadas, E., & Piedra-Cascón, W. (2026). Performance assessment of five artificial intelligence-based algorithms for automated tooth segmentation and labeling on intraoral scans. Journal of Prosthodontics, Advance online publication, 1046-1057. https://doi.org/10.1111/jopr.70117
Anh, J.W., Park, J.M., Chun, Y.S., Kim, M., & Kim, M. (2016). A comparison of the precision of three-dimensional images acquired by 2 digital intraoral scanners: effects of tooth irregularity and scanning direction. The Korean Journal of Orthodontics, 46(1), 3-12. https://doi.org/10.4041/kjod.2016.46.1.3
Lin, W.Q., Pan, C.Y., Chen, P.H., Liu, C.., Hung, C.C., & Lan, T.H. (2024). Trueness of intraoral scanning for different tooth-size arch-length deficiencies.Journal of Dental Sciences, 19(1), 397-403. https://doi.org/10.1016/j.jds.2023.08.006
Elhussain, E., Figueras-Álvarez, O., Roig-Cayon, M., Ortega-Martínez, J., & Vidal-Ponsoda, C. (2025). Impact of dental crowding on the trueness and precision of intraoral scanners: Comparison across different devices and techniques. American Journal of Orthodontics and Dentofacial Orthopedics, 168(6), 670–681. https://doi.org/10.1016/j.ajodo.2025.08.004
Navarro, P., Alemán, I., Sandoval, C., Matamala, C., & Corsini, G. (2020). Statistical Testing Methods for Data Analysis in Dental Morphology. International Journal of Morphology, 38(5), 1317.
de Freitas, B.N., Capel, C.P., Vieira, M.A., Barbin, G.F., Cardoso, L., & Tirapelli, C. (2024). Do intraoral scanning technologies affect the trueness of dental arches with crowding, diastema, and edentulous spaces? A clinical perspective. Journal of Dentistry, 149, 105285.https://doi.org/10.1016/j.jdent.2024.105285
Revilla-Leon, M., Quesada-Olmo, N., Gomez-Polo, M., Sicilia, E., Farjas-Abadia, M., & Kois, J.C. (2021). Influence of rescanning mesh holes on the accuracy of an intraoral scanner: An in vivo study. Journal of Dentistry, 115, 103851. https://doi.org/10.1016/j.jdent.2021.103851
Revilla-León, M., Sicilia, E., Agustín-Panadero, R., Gómez-Polo, M., & Kois, J. C. (2023). Clinical evaluation of the effects of cutting off, overlapping, and rescanning procedures on intraoral scanning accuracy. The Journal of Prosthetic Dentistry, 130(5), 746-754. https://doi.org/10.1016/j.prosdent.2021.10.017
Guo, J., Lu, Y., Li, R., Zhou, K., Ge, R., Zhao, D., Xia, S., & Wang, Y. (2024). Influence of repeated cutoff and rescanning on the trueness of the intraoral digital scans. Journal of Dentistry, 150, 105153. https://doi.org/10.1016/j.jdent.2024.105153
Gomez-Polo, M., Piedra-Cascon, W., Methani, M.M., Quesada-Olmo, N., Farjas-Abadia, M., & Revilla-León, M. (2021). Influence of rescanning mesh holes and stitching procedures on the complete-arch scanning accuracy of an intraoral scanner: An in vitro study. Journal of dentistry, 110, 103690. https://doi.org/10.1016/j.jdent.2021.103690
Faur, A.B., Rotar, R.N., Adam, D., & Jivănescu, A. (2023). Rescanning of digital impressions’ mesh holes: In vivo and in vitro accuracy evaluation of three different scanning protocols. Applied Sciences, 13(5), 2867. https://doi.org/10.3390/app13052867
Li, H.A., Wang, C., Yang, K., & Peng, L. (2026). 3D dental model hole filling based on adaptive threshold region segmentation. Computer Aided Geometric Design, 102602. https://doi.org/10.1016/j.cagd.2026.102602
Hongan, L.I., Kun, Y.A.N.G., Long, P.E.N.G., & Qingfang, L.I.U. (2026). 3D tooth semi-closed hole-filling algorithm based on the moving least-squares method. Virtual Reality & Intelligent Hardware, 8(3), 365-382. https://doi.org/10.1016/j.vrih.2026.04.002
