中国组织工程研究 ›› 2024, Vol. 28 ›› Issue (2): 252-257.doi: 10.12307/2023.951

• 口腔组织构建 oral tissue construction • 上一篇    下一篇

计算机辅助设计三维牙颌分割及应用场景

崔家礼1,黄敏慧1,刘东林2,贾瑞明1,李  涵1   

  1. 1北方工业大学信息学院,北京市  100144;2北京大学医学部基础医学院,北京市  100191
  • 收稿日期:2022-10-27 接受日期:2023-01-04 出版日期:2024-01-18 发布日期:2023-06-30
  • 通讯作者: 贾瑞明,博士,副研究员,北方工业大学信息学院,北京市 100144
  • 作者简介:崔家礼,男,1975年生,山东省滕州市人,汉族,2006年中科院自动化研究所毕业,博士,副教授,主要从事数字化口腔临床正畸研究、生物医学图像处理的研究。
  • 基金资助:
    北京市教委科研计划项目(KM202110009001),项目参与人:崔家礼,贾瑞明,黄敏慧;北航杭州创新研究院钱江实验室开放基金(2020-Y3-A-014),项目负责人:崔家礼

Computer aided design of 3D dental segmentation and its application scenarios

Cui Jiali1, Huang Minhui1, Liu Donglin2, Jia Ruiming1, Li Han1   

  1. 1School of Information, North China University of Technology, Beijing 100144, China; 2School of Basic Medicine, Peking University Health Science Center, Beijing 100191, China
  • Received:2022-10-27 Accepted:2023-01-04 Online:2024-01-18 Published:2023-06-30
  • Contact: Jia Ruiming, PhD, Associate researcher, School of Information, North China University of Technology, Beijing 100144, China
  • About author:Cui Jiali, PhD, Associate professor, School of Information, North China University of Technology, Beijing 100144, China
  • Supported by:
    Research Program of Beijing Municipal Education Commission, No. KM202110009001 (to CJL, JRM, HMH [project participants]); Qianjiang Laboratory Open Fund of Hangzhou Innovation Institute of Beihang University, No. 2020-Y3-A-014 (to CJL)

摘要:


文题释义:

计算机辅助设计:是指通过半自动或全自动手段简化现有的人工操作,目前多通过神经网络等人工智能方式,达到成本资源降低的辅助目的。
三维牙颌分割:是通过计算牙齿的三维区域,将牙颌中的牙齿与牙龈分隔开。它主要应用于虚拟正畸系统,如牙齿间隙调整、牙齿的移动等功能。


背景:传统的三维牙颌模型分割方法通常利用预定义的空间几何特征如曲率、法向量等作为牙齿分割的参考信息。

目的:提出一种适用于复杂三维牙颌分割的算法并深度挖掘分割结果与应用场景之间的关联性。
方法:建立基于结构特征和空间特征双流提取的三维牙颌分割算法,利用分流的模块化设计避免特征混淆。其中,结构特征流上的注意力机制用于捕获牙齿分割所需的细粒度语义信息,空间特征流上的Tran-Net用于保证模型对复杂牙颌分割的鲁棒性。该算法在包含健康牙颌和缺牙、错牙、牙列拥挤等复杂牙颌的临床数据集上验证有效性和可靠性,通过总体精度、均交并比、方向切割差异等评价指标衡量模型的分割性能。

结果与结论:该算法在临床数据集上的总体分割精度为97.08%,分割效果从定性和定量的角度均优于其他竞争方法。验证了此次设计的结构特征流,通过构建注意力聚合机制从坐标和法向信息中可提取更精细齿形局部细节,设计的空间特征流通过构建变换网络(Tran-Net)可保证模型对缺牙、错牙、牙列拥挤等复杂牙颌的鲁棒性。因此,该牙齿分割算法对于临床医生实操参考具有较强的可靠性。

https://orcid.org/0000-0003-1611-6043(崔家礼)

中国组织工程研究杂志出版内容重点:组织构建;骨细胞;软骨细胞;细胞培养;成纤维细胞;血管内皮细胞;骨质疏松;组织工程

关键词: 口腔疾病预防, 牙齿矫正, 神经网络, 三维牙颌分割, 可靠性

Abstract: BACKGROUND: Traditional 3D dental segmentation methods usually utilize predefined spatial geometric features, such as curvature and normal vectors, as the reference information for tooth segmentation.
OBJECTIVE: To propose an algorithm for complex 3D dental segmentation and deeply explore the correlation between segmentation results and application scenarios. 
METHODS: A 3D dental segmentation algorithm based on dual stream extraction of structural features and spatial features was established, and the modular design of split flow was used to avoid feature confusion. Among them, the attention mechanism on the structural feature flow was used to capture the fine-grained semantic information required for tooth segmentation, and the Tran Net based on the spatial feature flow was used to ensure the robustness of the model to complex tooth and jaw segmentation. This algorithm verified its effectiveness and reliability based on clinical datasets including healthy dental jaws and complex dental jaws such as missing teeth, malocclusion and dentition crowding. The segmentation performance of the model was measured in terms of overall accuracy, mean intersection over union, and directional cut discrepancy. 
RESULTS AND CONCLUSION: The overall segmentation accuracy of this algorithm in the clinical data set is 97.08%, and the segmentation effect is superior to that of other competitive methods from the qualitative and quantitative perspectives. It is verified that the structural feature flow designed in this paper can extract more precise local details of tooth shape from coordinate and normal information by constructing an attention aggregation mechanism, and the spatial feature flow designed in this paper can ensure the robustness of the model to complex teeth such as missing teeth, dislocated teeth, and crowded dentition by constructing a transformation network (Tran Net). Therefore, this tooth segmentation algorithm is highly reliable for clinicians' practical reference.

Key words: oral disease prevention, orthodontics, neural network, 3D dental segmentation, reliability

中图分类号: