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 32 条
[31]   Deep learning with convolutional neural network in radiology [J].
Yasaka, Koichiro ;
Akai, Hiroyuki ;
Kunimatsu, Akira ;
Kiryu, Shigeru ;
Abe, Osamu .
JAPANESE JOURNAL OF RADIOLOGY, 2018, 36 (04) :257-272
[32]   Automated 2-D cephalometric analysis on X-ray images by a model-based approach [J].
Yue, Weining ;
Yin, Dali ;
Li, Chengjun ;
Wang, Guoping ;
Xu, Tianmin .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2006, 53 (08) :1615-1623