3D Dental model segmentation with graph attentional convolution network

Zhao, Yue; Zhang, Lingming; Yang, Chongshi; Tan, Yingyun; Liu, Yang; Li, Pengcheng; Huang, Tianhao; Gao, Chenqiang

doi:10.1016/j.patrec.2021.09.005

“…Although IOSs are becoming ubiquitous in clinical dental practice, there are only few contributions on teeth segmentation/labeling available in the literature, e.g., [1,2,3,4,5,6], and, most importantly, no publicly available benchmark. A fundamental challenge in IOS data analysis is the ability to accurately segment and identify teeth.…”

Section: Background and Summarymentioning

confidence: 99%

Teeth3DS: a benchmark for teeth segmentation and labeling from intra-oral 3D scans

Ben-Hamadou¹,

Smaoui²,

Chaabouni-Chouayakh³

et al. 2022

Preprint

View full text Add to dashboard Cite

Teeth segmentation and labeling are critical components of Computer-Aided Dentistry (CAD) systems. Indeed, before any orthodontic or prosthetic treatment planning, a CAD system needs to first accurately segment and label each instance of teeth visible in the 3D dental scan, this is to avoid time-consuming manual adjustments by the dentist. Nevertheless, developing such an automated and accurate dental segmentation and labeling tool is very challenging, especially given the lack of publicly available datasets or benchmarks. This article introduces the first public benchmark, named Teeth3DS, which has been created in the frame of the 3DTeethSeg 2022 MICCAI challenge to boost the research field and inspire the 3D vision research community to work on intra-oral 3D scans analysis such as teeth identification, segmentation, labeling, 3D modeling and 3D reconstruction. Teeth3DS is made of 1800 intra-oral scans (23999 annotated teeth) collected from 900 patients covering the upper and lower jaws separately, acquired and validated by orthodontists/dental surgeons with more than 5 years of professional experience.

show abstract

“…Multiple Deep Learning based methods have been proposed for automatic tooth segmentation from the 3D intraoral scans in the recent years. We note that a majority of these methods [1][2][3][4][5][6][7][8][9] are fully supervised with the exception of a few which are weakly supervised or semi-supervised. 10 Lian et.…”

Section: Introductionmentioning

confidence: 99%

“…Due to this factor, a majority of the 3D teeth segmentation algorithms developed or analyzed so far are based on private datasets [1], [2], [3], [4]. There are Deep Learning methods that have been proposed for tooth segmentation from 3D intraoral scans [5], [6], [7], [8], [9] Some of these algorithms have achieved excellent accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…The main objective of this work is to investigate and compare the results. It is with this thought that we investigate the robustness of the existing state-of-the-art 3D tooth segmentation methods like -MeshSegNet [5], TSGCNet [8], MBESegNet [7], GAC [6] and some of the latest generic point cloud segmentation methods such as PointNet [11], PointNet++ [12], DGCNN [13], BAAFNet [14], PointMLP [15] and PCT [16]. The choice of adding generic point cloud segmentation methods is due to an observation that we made -a majority of the tooth segmentation algorithms compared the tooth segmentation performance of their methods alongside the generic point cloud segmentation methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic tooth segmentation from 3D dental model using deep learning: a quantitative analysis of what can be learnt from a single 3D dental model

Jana

¹

,

Subhash²,

Metaxas³

2023

18th International Symposium on Medical Information Processing and Analysis

View full text Add to dashboard Cite

3D tooth segmentation is an important task for digital orthodontics. Several Deep Learning methods have been proposed for automatic tooth segmentation from 3D dental models or intraoral scans. These methods require annotated 3D intraoral scans. Manually annotating 3D intraoral scans is a laborious task. One approach is to devise self-supervision methods to reduce the manual labeling effort. Compared to other types of point cloud data like scene point cloud or shape point cloud data, 3D tooth point cloud data has a very regular structure and a strong shape prior. We look at how much representative information can be learnt from a single 3D intraoral scan. We evaluate this quantitatively with the help of ten different methods of which six are generic point cloud segmentation methods whereas the other four are tooth segmentation specific methods. Surprisingly, we find that with a single 3D intraoral scan training, the Dice score can be as high as 0.86 whereas the full training set gives Dice score of 0.94. We conclude that the segmentation methods can learn a great deal of information from a single 3D tooth point cloud scan under suitable conditions e.g. data augmentation. We are the first to quantitatively evaluate and demonstrate the representation learning capability of Deep Learning methods from a single 3D intraoral scan. This can enable building self-supervision methods for tooth segmentation under extreme data limitation scenario by leveraging the available data to the fullest possible extent.

show abstract

“…Multiple Deep Learning based methods have been proposed for automatic tooth segmentation from the 3D intraoral scans in the recent years. We note that a majority of these methods [1][2][3][4][5][6][7][8][9] are fully supervised with the exception of a few which are weakly supervised or semi-supervised. 10 Lian et.…”

Section: Introductionmentioning

confidence: 99%

Automatic Tooth Segmentation from 3D Dental Model using Deep Learning: A Quantitative Analysis of what can be learnt from a Single 3D Dental Model

Jana¹,

Subhash²,

Metaxas³

2022

Preprint

View full text Add to dashboard Cite

3D tooth segmentation is an important task for digital orthodontics. Several Deep Learning methods have been proposed for automatic tooth segmentation from 3D dental models or intraoral scans. These methods require annotated 3D intraoral scans. Manually annotating 3D intraoral scans is a laborious task. One approach is to devise self-supervision methods to reduce the manual labeling effort. Compared to other types of point cloud data like scene point cloud or shape point cloud data, 3D tooth point cloud data has a very regular structure and a strong shape prior. We look at how much representative information can be learnt from a single 3D intraoral scan. We evaluate this quantitatively with the help of ten different methods of which six are generic point cloud segmentation methods whereas the other four are tooth segmentation specific methods. Surprisingly, we find that with a single 3D intraoral scan training, the Dice score can be as high as 0.86 whereas the full training set gives Dice score of 0.94. We conclude that the segmentation methods can learn a great deal of information from a single 3D tooth point cloud scan under suitable conditions e.g. data augmentation. We are the first to quantitatively evaluate and demonstrate the representation learning capability of Deep Learning methods from a single 3D intraoral scan. This can enable building self-supervision methods for tooth segmentation under extreme data limitation scenario by leveraging the available data to the fullest possible extent.

show abstract

3D Dental model segmentation with graph attentional convolution network

Cited by 14 publications

References 17 publications

Teeth3DS: a benchmark for teeth segmentation and labeling from intra-oral 3D scans

Teeth3DS: a benchmark for teeth segmentation and labeling from intra-oral 3D scans

Automatic tooth segmentation from 3D dental model using deep learning: a quantitative analysis of what can be learnt from a single 3D dental model

Automatic Tooth Segmentation from 3D Dental Model using Deep Learning: A Quantitative Analysis of what can be learnt from a Single 3D Dental Model

Contact Info

Product

Resources

About