A cephalometric landmark detection method using dual-encoder on X-ray image.
10.7507/1001-5515.202411034
- Author:
Chao DAI
1
;
Chaolin HUANG
2
;
Minpeng XU
1
;
Yang WANG
3
Author Information
1. Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300354, P. R. China.
2. School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Nanchang 341099, P. R. China.
3. School of Mechanical Engineering, Anhui University of Technology, Maanshan, Anhui 243002, P. R. China.
- Publication Type:Journal Article
- Keywords:
Cephalometric landmark;
Dual-encoder;
High-resolution;
Transformer
- MeSH:
Cephalometry/methods*;
Humans;
Algorithms;
Anatomic Landmarks/diagnostic imaging*;
Image Processing, Computer-Assisted/methods*;
X-Rays
- From:
Journal of Biomedical Engineering
2025;42(5):883-891
- CountryChina
- Language:Chinese
-
Abstract:
Accurate detection of cephalometric landmarks is crucial for orthodontic diagnosis and treatment planning. Current landmark detection methods are mainly divided into heatmap-based and regression-based approaches. However, these methods often rely on parallel computation of multiple models to improve accuracy, significantly increasing the complexity of training and deployment. This paper presented a novel regression method that can simultaneously detect all cephalometric landmarks in high-resolution X-ray images. By leveraging the encoder module of Transformer, a dual-encoder model was designed to achieve coarse-to-fine localization of cephalometric landmarks. The entire model consisted of three main components: a feature extraction module, a reference encoder module, and a fine-tuning encoder module, responsible for feature extraction and fusion of X-ray images, coarse localization of cephalometric landmarks, and fine localization of landmarks, respectively. The model was fully end-to-end differentiable and could learn the intercorrelation relationships between cephalometric landmarks. Experimental results showed that the successful detection rate (SDR) of our algorithm was superior to other existing methods. It attained the highest 2 mm SDR of 89.51% on test set 1 of the ISBI2015 dataset and 90.68% on the test set of the ISBI2023 dataset. Meanwhile, it reduces memory consumption and enhances the model's popularity and applicability, providing more reliable technical support for orthodontic diagnosis and treatment plan formulation.
