GFACNet: 3D dental segmentation from intraoral scans integrating geometric features and anatomical constraints

Gaofeng Zheng; Xiaodong Cui; Aibo Song; Mingrui Lin; Gaofeng Zheng; Xiaodong Cui; Aibo Song; Mingrui Lin

doi:10.3934/era.2025342

Electronic Research Archive

2025, Volume 33, Issue 12: 7736-7762. doi: 10.3934/era.2025342

Previous Article Next Article

Research article

GFACNet: 3D dental segmentation from intraoral scans integrating geometric features and anatomical constraints

School of Computer Science and Engineering, Southeast University, Nanjing, China

Received: 26 October 2025 Revised: 28 November 2025 Accepted: 09 December 2025 Published: 23 December 2025

Dental segmentation is a critical step in computer-aided orthodontic treatment planning, but accurate segmentation still faces numerous challenges due to complex tooth morphology, ambiguous gingival boundaries, and clinical issues such as malformed teeth, crowding, and malocclusion. This paper proposes GFACNet, a network that integrates geometric features and anatomical constraints for 3D dental segmentation from intraoral scan data. Our method comprises three key innovations: 1) a morphology-aware graph construction (MAGC) mechanism that adaptively constructs graph structures based on dental geometric characteristics, 2) a multi scale transformer (MST) feature integration module that processes features at different scales while capturing both local and global context, and 3) a hierarchical anatomical constraint loss (HACL) that incorporates multi level anatomical features to guide anatomically consistent segmentation. Experiments on real intraoral scanning datasets demonstrate that GFACNet significantly outperforms existing methods in handling complex dental morphologies, particularly in cases of malformed and missing teeth. Additionally, our method requires reduced computational resources while providing a more practical solution for clinical applications.
- 3D dental segmentation,
- intraoral scanning,
- geometric features,
- tooth segmentation
Citation: Gaofeng Zheng, Xiaodong Cui, Aibo Song, Mingrui Lin. GFACNet: 3D dental segmentation from intraoral scans integrating geometric features and anatomical constraints[J]. Electronic Research Archive, 2025, 33(12): 7736-7762. doi: 10.3934/era.2025342

Related Papers:

Abstract

Dental segmentation is a critical step in computer-aided orthodontic treatment planning, but accurate segmentation still faces numerous challenges due to complex tooth morphology, ambiguous gingival boundaries, and clinical issues such as malformed teeth, crowding, and malocclusion. This paper proposes GFACNet, a network that integrates geometric features and anatomical constraints for 3D dental segmentation from intraoral scan data. Our method comprises three key innovations: 1) a morphology-aware graph construction (MAGC) mechanism that adaptively constructs graph structures based on dental geometric characteristics, 2) a multi scale transformer (MST) feature integration module that processes features at different scales while capturing both local and global context, and 3) a hierarchical anatomical constraint loss (HACL) that incorporates multi level anatomical features to guide anatomically consistent segmentation. Experiments on real intraoral scanning datasets demonstrate that GFACNet significantly outperforms existing methods in handling complex dental morphologies, particularly in cases of malformed and missing teeth. Additionally, our method requires reduced computational resources while providing a more practical solution for clinical applications.

References

[1]	V. Majanga, S. Viriri, A survey of dental caries segmentation and detection techniques, Sci. World J., 2022 (2022), 8415705. https://doi.org/10.1155/2022/8415705 doi: 10.1155/2022/8415705
[2]	Z. Cui, C. Li, N. Chen, G. Wei, R. Chen, Y. Zhou, et al., TSegNet: An efficient and accurate tooth segmentation network on 3D dental model, Med. Image Anal., 69 (2020), 101949. https://doi.org/10.1016/j.media.2020.101949 doi: 10.1016/j.media.2020.101949
[3]	S. Hou, T. Zhou, Y. Liu, P. Dang, H. Lu, H. Shi, Teeth U-Net: A segmentation model of dental panoramic X-ray images for context semantics and contrast enhancement, Comput. Biol. Med., 152 (2023), 106296. https://doi.org/10.1016/j.compbiomed.2022.106296 doi: 10.1016/j.compbiomed.2022.106296
[4]	T. J. Jang, K. C. Kim, H. C. Cho, J. K. Seo, A fully automated method for 3D individual tooth identification and segmentation in dental CBCT, IEEE Trans. Pattern Anal. Mach. Intell., 44 (2021), 6562–6568. https://doi.org/10.1109/TPAMI.2021.3086072 doi: 10.1109/TPAMI.2021.3086072
[5]	T. J. Jang, H. S. Yun, C. M. Hyun, J. Kim, S. Lee, J. K. Seo, Fully automatic integration of dental CBCT images and full-arch intraoral impressions with stitching error correction via individual tooth segmentation and identification, Med. Image Anal., 93 (2024), 103096. https://doi.org/10.1016/j.media.2024.103096 doi: 10.1016/j.media.2024.103096
[6]	S. Kondo, W. Morita, H. Ohshima, The biological significance of tooth identification based on developmental and evolutional viewpoints, J. Oral Biosci., 64 (2022), 287–302. https://doi.org/10.1016/j.job.2022.05.004 doi: 10.1016/j.job.2022.05.004
[7]	S. Zhuang, G. Wei, Z. Cui, Y. Zhou, Robust hybrid learning for automatic teeth segmentation and labeling on 3D dental models, IEEE Trans. Multimedia, 27 (2025), 792–803. https://doi.org/10.1109/TMM.2023.3289760 doi: 10.1109/TMM.2023.3289760
[8]	T. Ari, H. Sağlam, H. Öksüzoğlu, O. Kazan, İ. Ş. Bayrakdar, S. B. Duman, et al., Automatic feature segmentation in dental periapical radiographs, Diagnostics, 12 (2022), 3081. https://doi.org/10.3390/diagnostics12123081 doi: 10.3390/diagnostics12123081
[9]	B. M. Elgarba, S. Van Aelst, A. Swaity, N. Morgan, S. Shujaat, R. Jacobs, Deep learning-based segmentation of dental implants on cone-beam computed tomography images: A validation study, J. Dent., 137 (2023), 104639. https://doi.org/10.1016/j.jdent.2023.104639 doi: 10.1016/j.jdent.2023.104639
[10]	B. Y. Tekin, C. Ozcan, A. Pekince, Y. Yasa, An enhanced tooth segmentation and numbering according to FDI notation in bitewing radiographs, Comput. Biol. Med., 146 (2022), 105547. https://doi.org/10.1016/j.compbiomed.2022.105547 doi: 10.1016/j.compbiomed.2022.105547
[11]	T. Wu, C. Lian, S. Lee, M. Pastewait, C. Piers, J. Liu, et al., Two-stage mesh deep learning for automated tooth segmentation and landmark localization on 3D intraoral scans, IEEE Trans. Med. Imaging, 41 (2022), 3158–3166. https://doi.org/10.1109/TMI.2022.3180343 doi: 10.1109/TMI.2022.3180343
[12]	Z. Li, T. Liu, J. Wang, C. Zhang, X. Jia, Multi-scale bidirectional enhancement network for 3D dental model segmentation, in 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), (2022), 1–5. https://doi.org/10.1109/ISBI52829.2022.9761556
[13]	C. R. Qi, H. Su, K. Mo, L. J. Guibas, Pointnet: Deep learning on point sets for 3D classification and segmentation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2017), 652–660.
[14]	C. R. Qi, L. Yi, H. Su, L. J. Guibas, Pointnet++: Deep hierarchical feature learning on point sets in a metric space, in Advances in Neural Information Processing Systems, 30 (2017).
[15]	C. Lian, L. Wang, T. Wu, F. Wang, P. Yap, C. Ko, et al., Deep multi-scale mesh feature learning for automated labeling of raw dental surfaces from 3D intraoral scanners, IEEE Trans. Med. Imaging, 39 (2020), 2440–2450. https://doi.org/10.1109/TMI.2020.2971730 doi: 10.1109/TMI.2020.2971730
[16]	R. Xie, Y. Yang, Z. Chen, WITS: Weakly-supervised individual tooth segmentation model trained on box-level labels, Pattern Recognit., 133 (2023), 108974. https://doi.org/10.1016/j.patcog.2022.108974 doi: 10.1016/j.patcog.2022.108974
[17]	A. Haghanifar, M. M. Majdabadi, S. Haghanifar, Y. Choi, S. Ko, PaXNet: Tooth segmentation and dental caries detection in panoramic X-ray using ensemble transfer learning and capsule classifier, Multimed. Tools Appl., 82 (2023), 27659–27679. https://doi.org/10.1007/s11042-023-14435-9 doi: 10.1007/s11042-023-14435-9
[18]	Y. Li, R. Bu, M. Sun, W. Wu, X. Di, B. Chen, Pointcnn: Convolution on x-transformed points, in Advances in Neural Information Processing Systems, 31 (2018).
[19]	Y. Wang, Y. Sun, Z. Liu, S. E. Sarma, M. M. Bronstein, J. M. Solomon, Dynamic graph CNN for learning on point clouds, ACM Trans. Graph., 38 (2019), 1–12. https://doi.org/10.1145/3326362 doi: 10.1145/3326362
[20]	H. Zhao, L. Jiang, J. Jia, P. H. S. Torr, V. Koltun, Point transformer, in Proceedings of the IEEE/CVF International Conference on Computer Vision, (2021), 16259–16268.
[21]	M. Guo, J. Cai, Z. Liu, T. Mu, R. R. Martin, S. Hu, PCT: Point cloud transformer, Comput. Vis. Media, 7 (2021), 187–199. https://doi.org/10.1007/s41095-021-0229-5 doi: 10.1007/s41095-021-0229-5
[22]	X. Ma, C. Qin, H. You, H. Ran, Y. Fu, Rethinking network design and local geometry in point cloud: A simple residual MLP framework, preprint, arXiv: 2202.07123.
[23]	G. Qian, Y. Li, H. Peng, J. Mai, H. Hammoud, M. Elhoseiny, et al., Pointnext: Revisiting pointnet++ with improved training and scaling strategies, Advances in Neural Information Processing Systems, 35 (2022), 23192–23204.
[24]	Y. Ma, Z. Li, Computer aided orthodontics treatment by virtual segmentation and adjustment, in 2010 International Conference on Image Analysis and Signal Processing, (2010), 336–339. https://doi.org/10.1109/IASP.2010.5476100
[25]	Y. Kumar, R. Janardan, B. Larson, J. Moon, Improved segmentation of teeth in dental models, Comput. Aided Des. Appl., 8 (2011), 211–224. https://doi.org/10.3722/cadaps.2011.211-224 doi: 10.3722/cadaps.2011.211-224
[26]	N. Wongwaen, C. Sinthanayothin, Computerized algorithm for 3D teeth segmentation, Proc. Int. Conf. Electron. Inf. Eng., 1 (2010), 277–280. https://doi.org/10.1109/ICEIE.2010.5559877 doi: 10.1109/ICEIE.2010.5559877
[27]	B. Graham, M. Engelcke, L. Van Der Maaten, 3D semantic segmentation with submanifold sparse convolutional networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2018), 9224–9232.
[28]	J. Zhang, C. Li, Q. Song, L. Gao, Y. Lai, Automatic 3D tooth segmentation using convolutional neural networks in harmonic parameter space, Graph. Models, 109 (2020), 101071. https://doi.org/10.1016/j.gmod.2020.101071 doi: 10.1016/j.gmod.2020.101071
[29]	Z. Lin, Z. He, X. Wang, B. Zhang, C. Liu, W. Su, et al., DBGANet: Dual-branch geometric attention network for accurate 3D tooth segmentation, IEEE Trans. Circuits Syst. Video Technol., 34 (2024), 4285–4298. https://doi.org/10.1109/TCSVT.2023.3331589 doi: 10.1109/TCSVT.2023.3331589
[30]	A. Rekik, A. Ben-Hamadou, O. Smaoui, F. Bouzguenda, S. Pujades, E. Boyer, TSegLab: Multi-stage 3D dental scan segmentation and labeling, Comput. Biol. Med., 185 (2025), 109535. https://doi.org/10.1016/j.compbiomed.2024.109535 doi: 10.1016/j.compbiomed.2024.109535
[31]	P. Li, C. Gao, F. Liu, D. Meng, Y. Yan, THISNet: Tooth instance segmentation on 3D dental models via highlighting tooth regions, IEEE Trans. Circuits Syst. Video Technol., 34 (2023), 5229–5241. https://doi.org/10.1109/TCSVT.2023.3341805 doi: 10.1109/TCSVT.2023.3341805
[32]	B. Zou, S. Wang, H. Liu, G. Sun, Y. Wang, F. Zuo, et al., Teeth-SEG: An efficient instance segmentation framework for orthodontic treatment based on multi-scale aggregation and anthropic prior knowledge, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2024), 11601–11610.
[33]	X. Chen, H. Tao, H. Zhou, P. Zhou, Y. Deng, Hierarchical and progressive learning with key point sensitive loss for sonar image classification, Multimedia Syst., 30 (2024), 380. https://doi.org/10.1007/s00530-024-01590-8 doi: 10.1007/s00530-024-01590-8
[34]	Y. Apedo, H. Tao, A weakly supervised pavement crack segmentation based on adversarial learning and transformers, Multimedia Syst., 31 (2025), 380. https://doi.org/10.1007/s00530-025-01850-1 doi: 10.1007/s00530-025-01850-1
[35]	F. Naz, M. A. Anwar, M. Qasim, S. S. Bavabeedu, S. U. Khateeb, A. A. Khalil, et al., Clinical evaluation of composite restorations using the Fédération Dentaire Internationale (FDI) criteria: A retrospective cross-sectional study at University Dental Hospital, The University of Lahore, Pakistan, Cureus, 17 (2025), e83582. https://doi.org/10.7759/cureus.83582 doi: 10.7759/cureus.83582
[36]	S. Liu, J. Chi, C. Wu, F. Xu, X. Yu, SGT-Net: A transformer-based stratified graph convolutional network for 3D point cloud semantic segmentation, Comput. Mater. Continua, 79 (2024). https://doi.org/10.32604/cmc.2024.049450 doi: 10.32604/cmc.2024.049450
[37]	L. Qiu, C. Ye, P. Chen, Y. Liu, X. Han, S. Cui, Darch: Dental arch prior-assisted 3D tooth instance segmentation with weak annotations, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2022), 20752–20761.
[38]	Y. Zhao, Y. Liu, Y. Tan, L. Zhang, T. Huang, C. Gao, 3D dental model segmentation with graph attentional convolution network, Pattern Recognit. Lett., 152 (2021), 79–85. https://doi.org/10.1016/j.patrec.2021.09.005 doi: 10.1016/j.patrec.2021.09.005
[39]	M. Fey, J. E. Lenssen, F. Weichert, H. Müller, SplineCNN: Fast geometric deep learning with continuous B-spline kernels, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2018), 869–877.
[40]	Y. Kumar, R. Janardan, B. Larson, J. Moon, Improved segmentation of teeth in dental models, Comput. Aided Des. Appl., 8 (2011), 211–224. https://doi.org/10.3722/cadaps.2011.211-224 doi: 10.3722/cadaps.2011.211-224

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)