基于条件生成对抗网络的缺失牙体功能性咬合面形态设计方法

doi:10.3969/j.issn.1004-132X.2021.03.011

摘要/Abstract

摘要： 针对牙齿修复体设计中未考虑牙齿磨耗形态分布以及标准牙难以表达天然牙形态多样性的问题，提出基于颌位空间约束以及牙齿磨耗面引导的缺失牙体功能性咬合面形态设计方法。利用启发式搜索算法半自动提取牙齿磨耗面，并采用自适应视距的正交投影法计算出牙冠及其磨耗面在正视方向上的深度图像。通过对缺失牙齿功能性咬合面特征分级表达，采用基于颌位空间约束的生成网络获得牙齿咬合面的整体形貌，然后以磨耗面为约束条件，合成具有天然牙冠细节特征的功能性咬合面。最后，利用网格重建算法及蒙皮方法设计出满足正常咀嚼功能的全冠修复体。实验结果表明，通过该方法设计出的全冠修复体具有足够的天然牙解剖形态特征以及较高的临床适用性。

关键词: 功能性咬合面, 条件生成对抗网络, 全冠修复, 牙齿磨耗面

Abstract: In view of the problems that the distribution of tooth wear facets was not taken into account in the dental restoration and that the standard crown was difficult to express the diversity of natural tooth morphology, an automatic design method was proposed for the missing tooth functional occlusal surface morphology based on occlusion spatial constraint and tooth wear facet guidance. The wear facets of the crown were semi-automatically extracted by using the heuristic search algorithm, and an adaptive visual distance orthogonal projection method was used to calculate the depth image of the crown and its wear facets in the front view direction. By grading the expression of the functional occlusal surfaces of the missing teeth, a generation network was used to obtain the overall structure of the tooth occlusal surfaces based on the occlusion spatial constraint, and then the functional occlusal surfaces with real crown details were synthesized by using the wear facets as constraints. Finally, the mesh reconstruction algorithm and the skinning method were used to design full crown restoration that satisfied the normal chewing function. Experimental results demonstrate that the full crown restorations designed by the proposed method have sufficient natural tooth anatomical features and higher clinical applicability.

Key words: functional occlusal surface, conditional generative adversarial network(CGAN), full crown restoration, tooth wear facet

中图分类号:

TP391.41

田素坤1；戴宁1；袁福来1；孙玉春2；俞青3；程筱胜1. 基于条件生成对抗网络的缺失牙体功能性咬合面形态设计方法[J]. 中国机械工程, DOI: 10.3969/j.issn.1004-132X.2021.03.011.

TIAN Sukun1；DAI Ning1；YUAN Fulai1；SUN Yuchun2；YU Qing3；CHENG Xiaosheng1. Functional Occlusal Surface Morphology Design Method for Missing Teeth Based on CGAN[J]. China Mechanical Engineering, DOI: 10.3969/j.issn.1004-132X.2021.03.011.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.cmemo.org.cn/CN/10.3969/j.issn.1004-132X.2021.03.011

http://www.cmemo.org.cn/CN/Y2021/V32/I03/331

参考文献

［1］VOS T, ABAJOBIR A A, ABATE K H, et al. Global, Regional, and National Incidence, Prevalence, and Years Lived with Disability for 328 Diseases and Injuries for 195 Countries, 1990—2016：a Systematic Analysis for the Global Burden of Disease Study 2016［J］. The Lancet, 2017, 390(10100)：1211-1259.
［2］SPIJKER A V, KREULEN C M, BRONKHORST E M, et al. Occlusal Wear and Occlusal Condition in a Convenience Sample of Young Adults［J］. Journal of Dentistry, 2015, 43(1)：72-77.
［3］FIORENZA L, BENAZZI S, KULLMER O. Para- masticatory Wear Facets and Their Functional Significance in Hunter-Gatherer Maxillary Molars［J］. Journal of Archaeological Science, 2011, 38(9)：2182-2189.
［4］郑淑贤, 李佳, 孙庆丰. 基于特征映射的义齿表面三维变形设计方法［J］. 机械工程学报, 2011, 47(3):129-134.
ZHENG Shuxian, LI Jia, SUN Qingfeng. 3D Deformation Design Method for Prosthetic Dental Surface Based on Feature Mapping［J］. Journal of Mechanical Engineering, 2011, 47(3)：129-134.
［5］DANIELCZAK R, STOBER T, BOMICKE W, et al. Treatment with a CAD-CAM-fabricated, Double-crown-retained, Removable Partial Denture：a Clinical Report［J］. Journal of Prosthetic Dentistry, 2019, 121(2)：220-224.
［6］WARRETH A, DOODY K, ALMOHSEN M, et al. Fundamentals of Occlusion and Restorative Dentistry. Part Ⅱ：Occlusal Contacts, Interferences and Occlusal Considerations in Implant Patients［J］. Journal of the Irish Dental Association, 2015, 61(5)：252-259.
［7］SANNINO G, GERMANO F, ARCURI L, et al. CEREC CAD/CAM Chairside System［J］. Oral & Implantology, 2015, 7(3):57-70.
［8］BUKHARI S A, REDDY K A, REDDY M R, et al. Evaluation of Virtual Models (3Shape Ortho System) in Assessing Accuracy and Duration of Model Analyses Based on the Severity of Crowding［J］. The Saudi Journal for Dental Research, 2017, 8(1)：11-18.
［9］范然, 金小刚. 模版特征线匹配的牙齿形状修复［J］. 计算机辅助设计与图形学学报, 2014, 26(2):280-286.
FAN Ran, JIN Xiaogang. Tooth Shape Restoration with Template Feature Line Matching［J］. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(2)：280-286.
［10］STEINBRECHER T, GERTH M. Dental Inlay and Onlay Construction by Iterative Laplacian Surface Editing［J］. Computer Graphics Forum, 2008, 27(5)：1441-1447.
［11］JIANG X T, DAI N, CHENG X S, et al. Robust Tooth Surface Reconstruction by Iterative Deformation［J］. Computers in Biology and Medicine, 2016，68：90-100.
［12］张长东, 刘婷婷, 廖文和, 等. 基于颌位空间约束的缺损牙体曲面统计重建算法［J］. 机械工程学报, 2016, 52(1)：165-174.
ZHANG Changdong, LIU Tingting, LIAO Wenhe, et al. Statistical Reconstruction Algorithm for Restoring Broken Tooth Surface Based on Occlusion Spatial Constraint［J］. Journal of Mechanical Engineering, 2016, 52(1)：165-174.
［13］ZHANG C D, LIU T T, LIAO W H, et al. Computer-aided Design of Dental Inlay Restoration Based on Dual-factor Constrained Deformation［J］. Advances in Engineering Software, 2017，114：71-84.
［14］TIAN S K, DAI N, CHANG X S, et al. Relative Trajectory-driven Virtual Dynamic Occlusal Adjustment for Dental Restorations［J］. Medical & Biological Engineering & Computing, 2019, 57(1)：59-70.
［15］HWANG J, JUNG Y, CHO B, et al. An Overview of Deep Learning in the Field of Dentistry［J］. Imaging Science in Dentistry, 2019, 49(1)：1-7.
［16］NAYLOR P, LAE M, REYAL F, et al. Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map［J］. IEEE Transactions on Medical Imaging, 2019, 38(2)：448-459.
［17］LEE J H, KIM D, JEONG S N, et al. Diagnosis and Prediction of Periodontally Compromised Teeth Using a Deep Learning-based Convolutional Neural Network Algorithm［J］. Journal of Periodontal & Implant Science, 2018, 48(2)：114-123.
［18］MIKI Y, MURAMATSU C, HAYASHI T, et al. Classification of Teeth in Cone-beam CT Using Deep Convolutional Neural Network［J］. Computers in Biology and Medicine, 2017，80：24-29.
［19］XU X J, LIU C, ZHENG Y Y. 3D Tooth Segmentation and Labeling Using Deep Convolutional Neural Networks［J］. IEEE Transactions on Visualization and Computer Graphics, 2019, 25(7)：2336-2348.
［20］TIAN S K, DAI N, ZHANG B, et al. Automatic Classification and Segmentation of Teeth on 3D Dental Model Using Hierarchical Deep Learning Networks ［J］.IEEE Access, 2019, 7(1)：84817-84828.
［21］袁福来, 戴宁, 田素坤, 等. 采用条件生成式对抗网络的缺损牙全冠修复技术［J］. 计算机辅助设计与图形学学报, 2019, 31(12):2113-2120.
YUAN Fulai, DAI Ning, TIAN Sukun, et al. A Full Crown Restoration Approach for Defect Teeth Based on CGAN［J］. Journal of Computer-Aided Design & Computer Graphics, 2019, 31(12):2113-2120.
［22］ISOLA P, ZHU J Y, ZHOU T H, et al. Image-to-image Translation with Conditional Adversarial Networks［C］ ∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos, 2017：1125-1134.
［23］PARK J, BAASANTSEREN G, KIM N, et al. View Image Generation in Perspective and Orthographic Projection Geometry Based on Integral Imaging［J］. Optics Express, 2008, 16(12)：8800-8813.
［24］GOODFELLOW I, POUGET A J, MIRZA M, et al. Generative Adversarial Nets［C］∥Proceedings of the IEEE Conference on Neural Information Processing Systems. Cambridge, 2014：2672-2680.
［25］WOODWARD C D. Skinning Techniques for Interactive B-spline Surface Interpolation ［J］. Computer-Aided Design, 1988, 20(8)：441-451.
［26］YUAN F L, DAI N, TIAN S K, et al. Personalized Design Technique for the Dental Occlusal Surface Based on Conditional Generative Adversarial Networks［J］. International Journal for Numerical Methods in Biomedical Engineering, 2020, 36(5)：e3321.
［27］SONG Y L, LI J, YIN L, et al. The Feature-based Posterior Crown Design in a Dental CAD/CAM System［J］. The International Journal of Advanced Manufacturing Technology, 2007, 31(11)：1058-1065.

[1]	孙家乐, 罗晨, 周怡君, 王伟, 张刚. 复杂视觉测量系统的标定参数优化及精度评估[J]. 中国机械工程, 2023, 34(14): 1741-1748,1755.
[2]	崔海华, 徐振龙, 杨亚鹏, 孟亚云, 王宝俊. 一种基于深度学习图像超分的环形靶标稳定检测方法[J]. 中国机械工程, 2021, 32(23): 2861-2867.
[3]	易怀安, 赵欣佳, 唐乐, 陈永伦. 基于彩色图像奇异值熵指标的磨削表面粗糙度视觉测量方法[J]. 中国机械工程, 2021, 32(13): 1577-1583.
[4]	郭保苏；庄集超；章钦；吴凤和. 基于多分量卷积神经网络的多晶硅晶片颜色差异检测[J]. 中国机械工程, 2021, 32(03): 297-304.
[5]	王冠1；张骞2；寇琳媛1；刘志文3；李世康3. 基于混合元胞自动机算法的连续体结构非线性拓扑优化[J]. 中国机械工程, 2020, 31(18): 2161-2173.
[6]	崔长彩;王克贤;黄国钦;黄辉. 单层钎焊金刚石砂轮表面磨粒全场快速测量[J]. 中国机械工程, 2019, 30(14): 1639-1645.
[7]	王兴东1;杨雅伦1;孔建益1;施毅2. 基于区域优化的等厚对接焊缝图像二值化方法[J]. 中国机械工程, 2019, 30(14): 1756-1763.
[8]	王其东1.2;魏振亚1;王乃汉1;陈无畏1;谢有浩3. 基于投影统计与双曲线拟合的车道识别算法[J]. 中国机械工程, 2019, 30(04): 393-399.
[9]	龚立雄1;程双胜2;刘永3. 基于菱形搜索块匹配技术的微机电系统微运动测量研究[J]. 中国机械工程, 2017, 28(22): 2747-2752.
[10]	王玉亮, 刘飞, 沈建新, 刘贤喜. 基于单目视觉的视网膜三维重建技术研究[J]. 中国机械工程, 2016, 27(18): 2477-2481.
[11]	徐侃, 李文龙, 王建庄, 周莉萍, 尹周平, . 一种基于Delaunay三角剖分的特征点坐标对应方法[J]. 中国机械工程, 2016, 27(01): 7-13.
[12]	王玉亮1, 沈建新1, 廖文和1, 张运海2. 基于CUDA的眼底图像快速自动配准与拼接[J]. 中国机械工程, 2013, 24(13): 1749-1754.
[13]	杨庆华1, 陈亮1, 荀一1, 陈文彪2. 基于机器视觉的PCB裸板缺陷自动检测方法[J]. 中国机械工程, 2012, 23(22): 2661-2666.
[14]	丛家慧, 颜云辉. 视觉注意机制在带钢表面缺陷检测中的应用 [J]. 中国机械工程, 2011, 22(10): 1189-1192,1221.
[15]	魏玉兰, 颜云辉, 李兵, 张尧, 李骏. 邻域灰度与空间特征相结合的互信息配准方法研究 [J]. 中国机械工程, 2011, 22(4): 439-443.