浏览全部资源
扫码关注微信
收稿：2019-11-21，
修回：2020-2-11，
录用：2020-2-18，
纸质出版：2020-07-16
移动端阅览
目的
2
选取牙齿种子点是计算机正畸中常用牙齿分割方法的关键步骤。目前业内大部分牙齿正畸软件都采用需要交互标记的分割方法，通过人机交互在3维牙颌模型上选取每一颗牙齿的种子点，效率较低。针对这一问题，提出基于特征导向的图卷积网络（feature-steered graph convolutional network，FeaStNet）牙齿种子点自动选取方法。
方法
2
通过分析每个牙齿类型的种子点位置和最终分割效果，设立统一的规则，建立了牙颌模型的种子点数据集；利用特征导向的图卷积构建了新的多尺度网络结构，用于识别3维牙颌模型上的特征信息，为了更好地拟合牙齿特征，加深网络模型的深度；再通过训练调整参数和多尺度网络结构，寻找特定的种子点，使用均值平方差损失函数对模型进行评估，以提高预测模型的精确度；把网络寻找出的特征点作为基础点，在牙颌模型上找出与基础点距离最近的点作为种子点，如果种子点位置准确，则根据种子点将牙齿与牙龈分割开。对于种子点位置不准确的结果，通过人工操作修正种子点位置，再进行分割。
结果
2
实验在自建的数据集中测试，其中种子点全部准确的牙颌占88%，其余情况下只需要调整部分不准确种子点的位置。该方法简单快速，与现有方法相比，需要较少的人工干预，提高了工作效率。
结论
2
提出的种子点自动选取方法，能够自动选取牙齿种子点，解决牙齿分割中需要进行交互标记的问题，基本实现了牙齿分割的自动化，适用于各类畸形牙患者模型的牙齿分割。
Objective
2
With the rapid development of 3D digital imaging technology
increasing applications of computer-aided diagnosis and treatment in oral restoration have gradually become the development trend in this field. A key step in orthodontics is to separate the teeth on the digital 3D dental model. The selection of tooth seed points is crucial in the tooth segmentation method commonly used in computer orthodontics. Most orthodontic software in the industry adopts a segmentation method that requires interactive marking
and the seed point of each tooth is selected on the 3D dental model by human-computer interaction. The efficiency is low. To solve this problem
an automatic selection method for tooth seed points based on feature-steered graph convolutional network (FeaStNet) is proposed.
Method
2
The seed point position and final segmentation effect of each tooth type are analyzed
and a unified rule is established. A seed point dataset of a dental model is built. A new multiscale graph convolution architecture is constructed using feature-steered graph convolutions to identify the feature information on the 3D dental model. The depth of the network model is deepened to fit the characteristics of the teeth. Training is conducted to adjust parameters
and a multiscale network structure is used to find specific seed points. The prediction model is evaluated using the mean squared difference loss function to improve the accuracy. The feature points identified through the network are regarded as the basic points to find the point closest to the base point on the dental model and set it as the seed point. If the seed point position is accurate
then the teeth are separated from the gums in accordance with the seed point. For the result of inaccurate seed point position
the position of the seed point is corrected by manual operation first and then segmentation is performed. The dental model is simplified to improve the training speed. The simplified model is used to establish an experimental dataset and specify the position of the seed points of different types of teeth.The 3D dental model is divided into the following information for preservation: the 3D coordinate values of all vertices in the dental model
the adjacency relationship of the vertices in the dental model
and the 3D coordinate values of the tooth seed points.The mean squared difference loss function is used to perform an imbalance check. The loss value decreases rapidly at the beginning of training
converges promptly
and tends to be stable after an oscillation period.
Result
2
The experiment is conducted on a self-built dataset
in which the exact point of the seed point is 88%. In other cases
only the position of a partially inaccurate seed point needs to be adjusted. The base point of the deviation of the teeth is roughly divided into two cases. One is that the seed point of the incisor deviates
and the other is that the molar is not on the tooth surface. After the basic point is acquired
the point closest to the base point on the dental model is determined as a seed point and applied to the orthodontic software to separate the teeth from the gums.The method is simple and fast and has less manual intervention than existing methods. Thus
its work efficiency improved. After the method is applied to the orthodontic software and the hardware platform
the entire segmentation time is accelerated to approximately 7 s. In the path-planning method
the time taken for segmentation is approximately 20 s. The comparison proves that the current method has obvious advantages in speed.
Conclusion
2
The proposed seed-point automatic selection method solves the problem of tooth segmentation requiring interactive marking and automates dental division. It is applicable to all types of dental deformity in patients with tooth model division.The automatic selection of seed points can also be used as a reference for other segmentation methods. In the segmentation of teeth
in addition to the characteristics of seed points
other tooth feature points are important. Future research is suggested to learn additional tooth features
further improve the speed of tooth segmentation
and help doctors improve work efficiency.
Charles R, Su H, Mo K C and Guibas L.2017.PointNet: deep learning on point sets for 3D classification and segmentation//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, Hi: IEEE: 77-85[ DOI: 10.1109/CVPR.2017.16 http://dx.doi.org/10.1109/CVPR.2017.16 ]
Defferrard M, Bresson X and Vandergheynst P.2016. Convolutional neural networks on graphs with fast localized spectral filtering[EB/OL].[2017-02-05] . https://arxiv.org/pdf/1606.09375.pdf https://arxiv.org/pdf/1606.09375.pdf
Garland M and Heckbert P. 1997. Surface simplification using quadric error metrics//Proceedings of the 24th Annual Conference on Computer Graphics and Interactive Techniques. New York: ACM Press: 209-216[ DOI: 10.1145/258734.258849 http://dx.doi.org/10.1145/258734.258849 ]
Grzegorzek M, Trierscheid M, Papoutsis D and Paulus D. 2010. A multi-stage approach for 3D teeth segmentation from dentition surfaces//Proceedings of the 4th International Conference on Image and Signal Processing. Trois-Rivières, QC, Canada: Springer: 521-530[ DOI: 10.1007/978-3-642-13681-8_61 http://dx.doi.org/10.1007/978-3-642-13681-8_61 ]
Hao G D, Cheng X S, Dai N andYu Q. 2008. The morphology-based interactive segmentation of dental models. Manufacturing Information Engineering of China, 37(1):36-39
郝国栋, 程筱胜, 戴宁, 俞青. 2008.基于形态学的牙齿模型交互分割.中国制造业信息化, 37(1):36-39
Henaff M, Bruna J and LeCun Y. 2015. Deep convolutional networks on graph-structured data[EB/OL].[2018-05-10] . https://arxiv.org/pdf/1506.05163.pdf https://arxiv.org/pdf/1506.05163.pdf
Kipf T N and Welling M. 2016. Semi-supervised classification with graph convolutional networks[EB/OL].[2017-02-22] . https://arxiv.org/pdf/1609.02907.pdf https://arxiv.org/pdf/1609.02907.pdf
Klokov R and Lempitsky V. 2017. Escape from cells: deep Kd-networks for the recognition of 3D point cloud models//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE: 863-872[ DOI: 10.1109/ICCV.2017.99 http://dx.doi.org/10.1109/ICCV.2017.99 ]
Kondo T, Ong S H and Foong K W C. 2004. Tooth segmentation of dental study models using range images. IEEE Transactions on Medical Imaging, 23(3):350-362[DOI:10.1109/TMI.2004.824235]
Kronfeld T, Brunner D and Brunnett G. 2010. Snake-based segmentation of teeth from virtual dental casts. Computer-Aided Design and Applications, 7(2):221-233[DOI:10.3722/cadaps.2010.221-233]
Kumar Y, Janardan R and Larson B. 2013. Automatic virtual alignment of dental arches in orthodontics. Computer-Aided Design and Applications, 10(3):371-398[DOI:10.3722/cadaps.2013.371-398]
Lindstrom P. 2000. Out-of-core simplification of large polygonal models//Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques. New York: ACM Press: 259-262[ DOI: 10.1145/344779.344912 http://dx.doi.org/10.1145/344779.344912 ]
Masci J, Boscaini D, Bronstein M and Vandergheynst P. 2015. Geodesic convolutional neural networks on Riemannian manifolds//Proceedings of 2015 IEEE International Conference on Computer Vision Workshop. Santiago, Chile: IEEE: 832-840[ DOI: 10.1109/ICCVW.2015.112 http://dx.doi.org/10.1109/ICCVW.2015.112 ]
Ronneberger O, Fischer P and Brox T. 2015. U-Net: Convolutional networks for biomedical image segmentation//Proceedings of the 18th Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015. Munich, Germany: Springer: 234-241[ DOI: 10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28 ]
Sarraf S, DeSouza D D, Anderson J and Tofighi G. 2016. DeepAD: Alzheimer's disease classification via deep convolutional neural networks using MRI and fMRI[EB/OL].[2016-08-21] . https://www.biorxiv.org/content/10.1101/070441v4 https://www.biorxiv.org/content/10.1101/070441v4 [ DOI: 10.1101/070441 http://dx.doi.org/10.1101/070441 ].
Schroeder W J, Zarge J A and Lorensen W E. 1997. Decimation of triangle meshes. ACM SIGGRAPH Computer Graphics, 26(2):65-70[DOI:10.1145/133994.134010]
Suk H I and Shen D G. 2013. Deep learning-based feature representation for AD/MCI classification//Proceedings of the 18th Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013. Nagoya, Japan: Springer: 583-590[ DOI: 10.1007/978-3-642-40763-5_72 http://dx.doi.org/10.1007/978-3-642-40763-5_72 ]
Verma N, Boyer E and Verbeek J. 2018. FeaStNet: feature-steered graph convolutions for 3D shape analysis//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE: 2598-2606[ DOI: 10.1109/CVPR.2018.00275 http://dx.doi.org/10.1109/CVPR.2018.00275 ]
Wongwaen N and Sinthanayothin C. 2010. Computerized algorithm for 3D teeth segmentation//Proceedings of 2010 International Conference on Electronics and Information Engineering. Kyoto, Japan: IEEE: V1-277-280[ DOI: 10.1109/ICEIE.2010.5559877 http://dx.doi.org/10.1109/ICEIE.2010.5559877 ]
Wu K, Chen L, Li J and Zhou Y H. 2014. Tooth segmentation on dental meshes using morphologic skeleton. Computers and Graphics, 38:199-211[DOI:10.1016/j.cag.2013.10.028]
Wu T and Zhang L B. 2016. Three dimention tooth reconstruction using level set active contour model. Journal of Image and Graphics, 21(8):1078-1087
吴婷, 张礼兵. 2016.水平集活动轮廓模型的3维牙齿重建.中国图象图形学报, 21(8):1078-1087)[DOI:10.11834/jig.20160812]
Wu T and Zhang L B. 2018. Tooth segmentation on 3D dental meshes based on path planning. Journal of Image and Graphics, 23(1):84-94
吴婷, 张礼兵. 2018. 3维牙颌模型牙齿分割的路径规划方法.中国图象图形学报, 23(1):84-94)[DOI:10.11834/jig.170337]
Yuan T R, Liao W H, Dai N, Cheng X S and Yu Q. 2010. Single-tooth modeling for 3D dental model. International Journal of Biomedical Imaging, 22(4):703-710[DOI:10.1155/2010/535329]
相关作者
相关机构
京公网安备11010802024621
