Automatic analysis of lateral cephalograms based on high-resolution net

被引:7
|
作者
Chang, Qiao [1 ]
Wang, Zihao [2 ]
Wang, Fan [1 ]
Dou, Jiaheng [3 ]
Zhang, Yong [3 ]
Bai, Yuxing [1 ]
机构
[1] Capital Med Univ, Beijing Stomatol Hosp, Dept Orthodont, TianTan Xili 4, Beijing 100050, Peoples R China
[2] Hong Kong Univ Sci & Technol, Dept Comp & Engn, Hong Kong, Peoples R China
[3] Inst Tsinghua Univ, Beijing, Peoples R China
关键词
X-RAY IMAGES; CEPHALOMETRIC ANALYSIS; IDENTIFICATION; LANDMARKS;
D O I
10.1016/j.ajodo.2022.02.020
中图分类号
R78 [口腔科学];
学科分类号
1003 ;
摘要
Introduction: Cephalometric analysis is essential in orthodontic treatment, and it is progressing toward auto-matic cephalometric analysis. This study aimed to establish a cephalometric landmark detection model on the basis of a high-resolution net and improve the accuracy with high resolution. Methods: A total of 2000 lateral cephalograms were collected to construct a dataset, and the number of target landmarks was 51. A high-resolution network model was applied to the landmark detection task. Four models were trained by adjusting different input resolutions to choose the most suitable resolution. A test set consisting of 300 lateral cephalograms was used for evaluation. The model was evaluated from the error size and distribution of each landmark. Results: After 200 epochs of training, a landmark detection model was established. Under different resolutions of the input image, the mean model radial error decreased initially and then increased. At 680 3 920 pixels resolution, the minimum error and the highest detection success rate were obtained. The mean radial error was 1.08 6 0.87 mm. The detection success rates of 2.0 mm, 2.5 mm, 3.0 mm, and 4.0 mm were 89.00%, 94.00%, 96.33%, and 98.67%, respectively. The mean radial errors of 22 landmarks were <1 mm, and the errors of other landmarks were <2 mm except for the pterion. The error distribution of landmarks followed a certain pattern. Conclusions: An automatic landmark detection model based on a high-resolution net was established to recognize 51 landmarks. The model showed high detection accuracy, which provides a basis for further measurement application. (Am J Orthod Dentofacial Orthop 2023;163:501-8)
引用
收藏
页码:501 / 508.e4
页数:12
相关论文
共 50 条
  • [1] Automatic Analysis of Lateral Cephalograms Based on Multiresolution Decision Tree Regression Voting
    Wang, Shumeng
    Li, Huiqi
    Li, Jiazhi
    Zhang, Yanjun
    Zou, Bingshuang
    JOURNAL OF HEALTHCARE ENGINEERING, 2018, 2018
  • [2] AUTOMATIC ANALYSIS OF HIGH-RESOLUTION GAMMA SPECTRA
    GROSSWENDT, B
    NUCLEAR INSTRUMENTS & METHODS, 1971, 93 (03): : 461 - +
  • [3] Fully Automatic System for Accurate Localisation and Analysis of Cephalometric Landmarks in Lateral Cephalograms
    Lindner, Claudia
    Wang, Ching-Wei
    Huang, Cheng-Ta
    Li, Chung-Hsing
    Chang, Sheng-Wei
    Cootes, Tim F.
    SCIENTIFIC REPORTS, 2016, 6
  • [4] CERNUC - A PROGRAM FOR AUTOMATIC HIGH-RESOLUTION RADIOELEMENTAL ANALYSIS
    ROCA, V
    TERRASI, F
    MORO, R
    SORRENTINO, G
    NUCLEAR INSTRUMENTS & METHODS, 1981, 180 (2-3): : 535 - 540
  • [5] Fully Automatic System for Accurate Localisation and Analysis of Cephalometric Landmarks in Lateral Cephalograms
    Claudia Lindner
    Ching-Wei Wang
    Cheng-Ta Huang
    Chung-Hsing Li
    Sheng-Wei Chang
    Tim F. Cootes
    Scientific Reports, 6
  • [6] Automatic Analysis of High-resolution G Bands of Triticum Monococcum Chromosomes Based on the MBNN
    Cai, Nian
    Pan, Qing
    Hu, Kuanghu
    Xiong, Haitao
    ICNC 2008: FOURTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 5, PROCEEDINGS, 2008, : 457 - +
  • [7] High-Resolution SAR Change Detection Based on ROI and SPP Net
    Li, Lingling
    Yang, Zhengyan
    Jiao, Licheng
    Liu, Fang
    Liu, Xu
    IEEE ACCESS, 2019, 7 : 177009 - 177022
  • [8] AUTOMATIC QUANTITATIVE-ANALYSIS BY HIGH-RESOLUTION NMR-SPECTROSCOPY
    SLONIM, IY
    KLYUCHNIKOV, VN
    JOURNAL OF ANALYTICAL CHEMISTRY OF THE USSR, 1981, 36 (08): : 1132 - 1143
  • [9] Automatic velocity analysis using high-resolution hyperbolic Radon transform
    Chen, Yangkang
    GEOPHYSICS, 2018, 83 (04) : A53 - A57
  • [10] Automatic velocity analysis using high-resolution hyperbolic Radon transform
    Chen Y.
    Geophysics, 2018, 83 (04): : A53 - A57