Robust Teeth Detection in 3D Dental Scans by Automated Multi-view Landmarking

被引:0
|
作者
Kubik, Tibor [1 ]
Spanel, Michal [1 ,2 ]
机构
[1] Brno Univ Technol, Fac Informat Technol, Dept Comp Graph & Multimedia, Brno, Czech Republic
[2] TESCAN 3DIM, Brno, Czech Republic
来源
PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES (BIOIMAGING), VOL 2 | 2021年
关键词
Landmark Detection in 3D; Polygonal Meshes; Multi-view Deep Neural Networks; RANSAC; U-Net; Heatmap Regression; Teeth Detection; Dental Scans;
D O I
10.5220/0010770700003123
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Landmark detection is frequently an intermediate step in medical data analysis. More and more often, these data are represented in the form of 3D models. An example is a 3D intraoral scan of dentition used in orthodontics, where landmarking is notably challenging due to malocclusion, teeth shift, and frequent teeth missing. What's more, in terms of 3D data, the DNN processing comes with high memory and computational time requirements, which do not meet the needs of clinical applications. We present a robust method for tooth landmark detection based on a multi-view approach, which transforms the task into a 2D domain, where the suggested network detects landmarks by heatmap regression from several viewpoints. Additionally, we propose a post-processing based on Multi-view Confidence and Maximum Heatmap Activation Confidence, which can robustly determine whether a tooth is missing or not. Experiments have shown that the combination of Attention U-Net, 100 viewpoints, and RANSAC consensus method is able to detect landmarks with an error of 0.75 +/- 0.96 mm In addition to the promising accuracy. our method is robust to missing teeth, as it can correctly detect the presence of teeth in 97.68% cases.
引用
收藏
页码:24 / 34
页数:11
相关论文
共 50 条
  • [41] Multi-view 3D display using waveguides
    Lee, Byoungho
    Lee, Chang-Kun
    INTERNATIONAL CONFERENCE ON OPTICAL AND PHOTONIC ENGINEERING (ICOPEN 2015), 2015, 9524
  • [42] A COMPACT 3D REPRESENTATION FOR MULTI-VIEW VIDEO
    Salvador, Jordi
    Casas, Josep R.
    INTERNATIONAL CONFERENCE ON 3D IMAGING 2011 (IC3D 2011), 2011,
  • [43] A method of multi-view intraoral 3D measurement
    Zhao, Huijie
    Wang, Zhen
    Jiang, Hongzhi
    Xu, Yang
    Lv, Peijun
    Sun, Yunchun
    INTERNATIONAL CONFERENCE ON PHOTONICS AND OPTICAL ENGINEERING (ICPOE 2014), 2015, 9449
  • [44] Multi-view 3D shape style transformation
    Xiuping Liu
    Hua Huang
    Weiming Wang
    Jun Zhou
    The Visual Computer, 2022, 38 : 669 - 684
  • [45] Multi-View and 3D Deformable Part Models
    Pepik, Bojan
    Stark, Michael
    Gehler, Peter
    Schiele, Bernt
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (11) : 2232 - 2245
  • [46] Efficient Caching for Multi-View 3D Videos
    Lee, Ji-Tang
    Yang, De-Nian
    Liao, Wanjiun
    2016 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2016,
  • [47] Registration of arbitrary multi-view 3D acquisitions
    Chane, Camille Simon
    Schuetze, Rainer
    Boochs, Frank
    Marzani, Franck S.
    COMPUTERS IN INDUSTRY, 2013, 64 (09) : 1082 - 1089
  • [48] Multi-view PointNet for 3D Scene Understanding
    Jaritz, Maximilian
    Gu, Jiayuan
    Su, Hao
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 3995 - 4003
  • [49] 3D Reconstruction with Multi-view Texture Mapping
    Ye, Xiaodan
    Wang, Lianghao
    Li, Dongxiao
    Zhang, Ming
    NEURAL INFORMATION PROCESSING (ICONIP 2017), PT III, 2017, 10636 : 198 - 207
  • [50] Multi-view 3D shape style transformation
    Liu, Xiuping
    Huang, Hua
    Wang, Weiming
    Zhou, Jun
    VISUAL COMPUTER, 2022, 38 (02): : 669 - 684