CeLR: A Transformer-Based Regression Network for Accurate Cephalometric Landmark Detection in High-Resolution X-Ray Imaging
IEEE Transactions on Medical Imaging · 2026-05 · 45 (5) · 2283-2294
DOI: 10.1109/tmi.2026.3652170 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2026-05. Verfasst von Jiakai Zhou und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Cephalometry, Anatomic Landmarks, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Reliable localization of cephalometric landmarks is essential for automated orthodontic analysis. Existing approaches are limited by high computational cost or complex multi-stage pipelines, hindering end-to-end optimization. In this work, we propose an end-to-end Transformer-based Cephalometric Landmark Regression network (CeLR) for high-resolution X-ray images. First, a feature extractor captures both low-level anatomical details and high-level semantic information. Then, a reference encoder models global dependencies and generates coarse landmark estimates. Next, a finetune decoder employs cross-attention mechanisms to refine these predictions. Additionally, a denoising module is introduced to enhance the robustness of the model. Experiments on multiple public cephalometric datasets demonstrate that CeLR achieves state-of-the-art performance. Specifically, on the ISBI 2015 Challenge Test1 dataset, CeLR achieves an Mean Radial Error (MRE) of 0.98 mm and a 2 mm Success Detection Rate (SDR) of 89.82%. Moreover, it maintains a computational cost of only 91.3 GFLOPs, demonstrating a satisfactory balance between accuracy and efficiency. These results highlight the effectiveness and clinical potential of the proposed method. Code is available at: https://github.com/huang229/D-CeLR.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhou, J., Wang, Y., Huang, C., Dai, C., & Tan, C. (2026). CeLR: A Transformer-Based Regression Network for Accurate Cephalometric Landmark Detection in High-Resolution X-Ray Imaging. IEEE Transactions on Medical Imaging, 45(5), 2283-2294. https://doi.org/10.1109/tmi.2026.3652170
Vancouver
Zhou J, Wang Y, Huang C, Dai C, Tan C. CeLR: A Transformer-Based Regression Network for Accurate Cephalometric Landmark Detection in High-Resolution X-Ray Imaging. IEEE Transactions on Medical Imaging. 2026;45(5):2283-2294. doi:10.1109/tmi.2026.3652170
BibTeX
@article{Zhou2026,
author = {Zhou, Jiakai and Wang, Yang and Huang, Chaolin and Dai, Chao and Tan, Chunyu},
title = {CeLR: A Transformer-Based Regression Network for Accurate Cephalometric Landmark Detection in High-Resolution X-Ray Imaging},
journal = {IEEE Transactions on Medical Imaging},
year = {2026},
volume = {45},
number = {5},
pages = {2283--2294},
doi = {10.1109/tmi.2026.3652170}
}
EUVIMED