Convolutional neural network for automated tooth segmentation on intraoral scans.
Artificial intelligence
Dentistry
Dentition
Machine learning
Neural networks, Computer
Optical imaging
Journal
BMC oral health
ISSN: 1472-6831
Titre abrégé: BMC Oral Health
Pays: England
ID NLM: 101088684
Informations de publication
Date de publication:
16 Jul 2024
16 Jul 2024
Historique:
received:
28
09
2023
accepted:
05
07
2024
medline:
17
7
2024
pubmed:
17
7
2024
entrez:
16
7
2024
Statut:
epublish
Résumé
Tooth segmentation on intraoral scanned (IOS) data is a prerequisite for clinical applications in digital workflows. Current state-of-the-art methods lack the robustness to handle variability in dental conditions. This study aims to propose and evaluate the performance of a convolutional neural network (CNN) model for automatic tooth segmentation on IOS images. A dataset of 761 IOS images (380 upper jaws, 381 lower jaws) was acquired using an intraoral scanner. The inclusion criteria included a full set of permanent teeth, teeth with orthodontic brackets, and partially edentulous dentition. A multi-step 3D U-Net pipeline was designed for automated tooth segmentation on IOS images. The model's performance was assessed in terms of time and accuracy. Additionally, the model was deployed on an online cloud-based platform, where a separate subsample of 18 IOS images was used to test the clinical applicability of the model by comparing three modes of segmentation: automated artificial intelligence-driven (A-AI), refined (R-AI), and semi-automatic (SA) segmentation. The average time for automated segmentation was 31.7 ± 8.1 s per jaw. The CNN model achieved an Intersection over Union (IoU) score of 91%, with the full set of teeth achieving the highest performance and the partially edentulous group scoring the lowest. In terms of clinical applicability, SA took an average of 860.4 s per case, whereas R-AI showed a 2.6-fold decrease in time (328.5 s). Furthermore, R-AI offered higher performance and reliability compared to SA, regardless of the dentition group. The 3D U-Net pipeline was accurate, efficient, and consistent for automatic tooth segmentation on IOS images. The online cloud-based platform could serve as a viable alternative for IOS segmentation.
Sections du résumé
BACKGROUND
BACKGROUND
Tooth segmentation on intraoral scanned (IOS) data is a prerequisite for clinical applications in digital workflows. Current state-of-the-art methods lack the robustness to handle variability in dental conditions. This study aims to propose and evaluate the performance of a convolutional neural network (CNN) model for automatic tooth segmentation on IOS images.
METHODS
METHODS
A dataset of 761 IOS images (380 upper jaws, 381 lower jaws) was acquired using an intraoral scanner. The inclusion criteria included a full set of permanent teeth, teeth with orthodontic brackets, and partially edentulous dentition. A multi-step 3D U-Net pipeline was designed for automated tooth segmentation on IOS images. The model's performance was assessed in terms of time and accuracy. Additionally, the model was deployed on an online cloud-based platform, where a separate subsample of 18 IOS images was used to test the clinical applicability of the model by comparing three modes of segmentation: automated artificial intelligence-driven (A-AI), refined (R-AI), and semi-automatic (SA) segmentation.
RESULTS
RESULTS
The average time for automated segmentation was 31.7 ± 8.1 s per jaw. The CNN model achieved an Intersection over Union (IoU) score of 91%, with the full set of teeth achieving the highest performance and the partially edentulous group scoring the lowest. In terms of clinical applicability, SA took an average of 860.4 s per case, whereas R-AI showed a 2.6-fold decrease in time (328.5 s). Furthermore, R-AI offered higher performance and reliability compared to SA, regardless of the dentition group.
CONCLUSIONS
CONCLUSIONS
The 3D U-Net pipeline was accurate, efficient, and consistent for automatic tooth segmentation on IOS images. The online cloud-based platform could serve as a viable alternative for IOS segmentation.
Identifiants
pubmed: 39014389
doi: 10.1186/s12903-024-04582-2
pii: 10.1186/s12903-024-04582-2
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
804Informations de copyright
© 2024. The Author(s).
Références
Erten O, Yılmaz BN. Three-dimensional imaging in orthodontics. Turkish J Orthod. 2018;31(3):86–94.
doi: 10.5152/TurkJOrthod.2018.17041
Mangano F, Gandolfi A, Luongo G, Logozzo S. Intraoral scanners in dentistry: a review of the current literature. BMC Oral Health. 2017;17(1):1–11.
doi: 10.1186/s12903-017-0442-x
Kondo T, Ong SH, Foong KWC. Tooth segmentation of dental study models using range images. IEEE Trans Med Imaging. 2004;23(3):350–62.
doi: 10.1109/TMI.2004.824235
pubmed: 15027528
Tian S, Dai N, Zhang B, Yuan F, Yu Q, Cheng X. Automatic classification and segmentation of teeth on 3D dental model using hierarchical deep learning networks. IEEE Access. 2019;7:84817–28.
doi: 10.1109/ACCESS.2019.2924262
Hao J, Liao W, Zhang YL, Peng J, Zhao Z, Chen Z, et al. Toward clinically applicable 3-dimensional tooth segmentation via deep learning. J Dent Res. 2021;101:304–11.
doi: 10.1177/00220345211040459
pubmed: 34719980
Baan F, de Waard O, Bruggink R, Xi T, Ongkosuwito EM, Maal TJJ. Virtual setup in orthodontics: planning and evaluation. Clin Oral Investig. 2020;24(7):2385–93.
doi: 10.1007/s00784-019-03097-3
pubmed: 31720852
Kumar Y, Janardan R, Larson B, Moon J. Improved segmentation of teeth in dental models. Comput Aided Des Appl. 2011;8(2):211–24.
doi: 10.3722/cadaps.2011.211-224
Zou Bji, Liu S, jian, Liao S, hui, Ding X, Liang Y. Interactive tooth partition of dental mesh base on tooth-target harmonic field. Comput Biol Med. 2015;56:132–44.
doi: 10.1016/j.compbiomed.2014.10.013
pubmed: 25464355
Li Z, Wang H. Interactive tooth separation from dental model using segmentation field. PLoS ONE. 2016;11(8):1–16.
doi: 10.1371/journal.pone.0161159
Tandon D, Rajawat J. Present and future of artificial intelligence in dentistry. J Oral Biol Craniofac Res. 2020;10(4):391–6.
doi: 10.1016/j.jobcr.2020.07.015
pubmed: 32775180
pmcid: 7394756
Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60–88.
doi: 10.1016/j.media.2017.07.005
pubmed: 28778026
Khanagar SB, Al-ehaideb A, Maganur PC, Vishwanathaiah S, Patil S, Baeshen HA, et al. Developments, application, and performance of artificial intelligence in dentistry – a systematic review. J Dent Sci. 2020;16:508–22.
doi: 10.1016/j.jds.2020.06.019
pubmed: 33384840
pmcid: 7770297
Leonardi R, Lo Giudice A, Farronato M, Ronsivalle V, Allegrini S, Musumeci G, et al. Fully automatic segmentation of sinonasal cavity and pharyngeal airway based on convolutional neural networks. Am J Orthod Dentofac Orthop. 2021;159(6):824–e8351.
doi: 10.1016/j.ajodo.2020.05.017
Lo Giudice A, Ronsivalle V, Spampinato C, Leonardi R. Fully automatic segmentation of the mandible based on convolutional neural networks (CNNs). Orthod Craniofac Res. 2021;24(S2):100–7.
doi: 10.1111/ocr.12536
pubmed: 34553817
Hung K, Yeung AWK, Tanaka R, Bornstein MM. Current applications, opportunities, and limitations of AI for 3D imaging in dental research and practice. Int J Environ Res Public Health. 2020;17(12):1–18.
doi: 10.3390/ijerph17124424
Zanjani FG, Pourtaherian A, Zinger S, Moin DA, Claessen F, Cherici T, et al. Mask-MCNet: tooth instance segmentation in 3D point clouds of intra-oral scans. Neurocomputing. 2021;453:286–98.
doi: 10.1016/j.neucom.2020.06.145
He X, Wang H, Hu H, et al. Unsupervised pre-training improves tooth segmentation in 3-Dimensional intraoral mesh scans. Proc Mach Learn Res. 2022;172:1–15.
Lian C, Wang L, Wu TH, Wang F, Yap PT, Ko CC, et al. Deep multi-scale mesh feature learning for automated labeling of raw dental surfaces from 3D intraoral scanners. IEEE Trans Med Imaging. 2020;39(7):2440–50.
doi: 10.1109/TMI.2020.2971730
pubmed: 32031933
Wu TH, Lian C, Lee S, Pastewait M, Piers C, Liu J, et al. Two-stage mesh deep learning for automated tooth segmentation and landmark localization on 3D intraoral scans. IEEE Trans Med Imaging. 2022;41(11):3158–66.
doi: 10.1109/TMI.2022.3180343
pubmed: 35666796
pmcid: 10547011
Schwendicke F, Singh T, Lee JH, Gaudin R, Chaurasia A, Wiegand T, et al. Artificial intelligence in dental research: Checklist for authors, reviewers, readers. J Dent. 2021;107:103610.
doi: 10.1016/j.jdent.2021.103610
pubmed: 33631303
Çiçek Ö, Abdulkadir A, Lienkamp S, Brox T, Olaf Ronneberger O. 3D U-Net: learning dense volumetric segmentation from sparse annotation. Med Image Comput Comput Interv. 2016;424–32.
Verhelst PJ, Smolders A, Beznik T, Meewis J, Vandemeulebroucke A, Shaheen E, et al. Layered deep learning for automatic mandibular segmentation in cone-beam computed tomography. J Dent. 2021;114:103786.
doi: 10.1016/j.jdent.2021.103786
pubmed: 34425172
Matheson GJ. We need to talk about reliability: making better use of test-retest studies for study design and interpretation. PeerJ. 2019;2019(5):1–25.
Cui Z, Li C, Chen N, Wei G, Chen R, Zhou Y, et al. TSegNet: an efficient and accurate tooth segmentation network on 3D dental model. Med Image Anal. 2021;69:101949.
doi: 10.1016/j.media.2020.101949
pubmed: 33387908
Zhang L, Zhao Y, Meng D, Cui Z, Gao C, Gao X et al. TSGCNet: Discriminative geometric feature learning with two-stream GraphConvolutional network for 3D dental model segmentation. ArXiv: 2012. 1369v1. Posted 26 Dec 2020. http://arxiv.org/abs/2012.13697 . Accessed 24 June 2024.
Shaheen E, Leite A, Alqahtani KA, Smolders A, Van Gerven A, Willems H, et al. A novel deep learning system for multi-class tooth segmentation and classification on cone beam computed tomography. A validation study: deep learning for teeth segmentation and classification. J Dent. 2021;115:103865.
doi: 10.1016/j.jdent.2021.103865
pubmed: 34710545
Shujaat S, Jazil O, Willems H, Van Gerven A, Shaheen E, Politis C, et al. Automatic segmentation of the pharyngeal airway space with convolutional neural network. J Dent. 2021;111:103705.
doi: 10.1016/j.jdent.2021.103705
pubmed: 34077802
Elgarba BM, Van Aelst S, Swaity A, Morgan N, Shujaat S, Jacobs R. Deep learning-based segmentation of dental implants on cone-beam computed tomography images: a validation study. J Dent. 2023;137:104639.
doi: 10.1016/j.jdent.2023.104639
pubmed: 37517787
Carrillo-Perez F, Pecho OE, Morales JC, Paravina RD, Della Bona A, Ghinea R, et al. Applications of artificial intelligence in dentistry: a comprehensive review. J Esthet Restor Dent. 2022;34(1):259–80.
doi: 10.1111/jerd.12844
pubmed: 34842324
Thurzo A, Jančovičová V, Hain M, Thurzo M, Novák B, Kosnáčová H et al. Human remains identification using Micro-CT, chemometric and AI methods in forensic experimental reconstruction of dental patterns after concentrated sulphuric acid significant impact. Molecules. 2022;27(13).
Vodanovi M, Milo D, Gali I, Brki H. Artificial intelligence in forensic medicine and forensic dentistry. J Forensic Odontostomatol. 2023;41(2):30–41.
Simonyan K, Vedaldi A, Zisserman A. Deep inside convolutional networks: visualising image classification models and saliency maps. ArXiv: 1312. 6034v2 [Prinprint]. Posted 19 Apr 2014. http://arxiv.org/abs/1312.6034 . Accessed 24 June, 2024.
Reyes M, Meier R, Pereira S, Silva CA, Dahlweid FM, von Tengg-Kobligk H et al. On the interpretability of artificial intelligence in radiology: challenges and opportunities. Radiol Artif Intell. 2020;2(3).
Hasany SN, Mériaudeau F, Petitjean C. MiSuRe is all you need to explain your image segmentation. ArXiv: 2406.1217v2 [Prinprint]. Posted 19 June 2024. http://arxiv.org/abs/2406.12173 . Accessed 24 June, 2024.