Learning-based multi-material CBCT image reconstruction with ultra-slow kV switching
Journal of X-Ray Science and Technology · 2025
DOI: 10.1177/08953996251331790 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology, 2025. Verfasst von Chenchen Ma und 10 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Communication Engineering, Dalian University of Technology, Dalian, Liaoning, China. Hauptthemen laut MEDLINE: Cone-Beam Computed Tomography, Image Processing, Computer-Assisted, Deep Learning. Die Arbeit nennt 34 Literaturangaben. Gefördert von: Basic and Applied Basic Research Foundation of Guangdong Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
Objective The purpose of this study is to perform multiple ( ≥ 3 ) material decomposition with deep learning method for spectral cone-beam CT (CBCT) imaging based on ultra-slow kV switching. Approach In this work, a novel deep neural network called SkV-Net is developed to reconstruct multiple material density images from the ultra-sparse spectral CBCT projections acquired using the ultra-slow kV switching technique. In particular, the SkV-Net has a backbone structure of U-Net, and a multi-head axial attention module is adopted to enlarge the perceptual field. It takes the CT images reconstructed from each kV as input, and output the basis material images automatically based on their energy-dependent attenuation characteristics. Numerical simulations and experimental studies are carried out to evaluate the performance of this new approach. Main Results It is demonstrated that the SkV-Net is able to generate four different material density images, i.e., fat, muscle, bone and iodine, from five spans of kV switched spectral projections. Physical experiments show that the decomposition errors of iodine and CaCl 2 are less than 6 % , indicating high precision of this novel approach in distinguishing materials. Significance SkV-Net provides a promising multi-material decomposition approach for spectral CBCT imaging systems implemented with the ultra-slow kV switching scheme.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information and Communication Engineering, Dalian University of Technology, Dalian, Liaoning, China.
- Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province, College of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen, Guangdong, China.
- Research Center for Advanced Detection Materials and Medical Imaging Devices, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China.
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China.
- State Key Laboratory of Biomedical Imaging Science and System.
- National Innovation Center for Advanced Medical Devices, Shenzhen, Guangdong, China.
ORCID-Profile: Han Cui, Yongshuai Ge
Förderung
- Basic and Applied Basic Research Foundation of Guangdong Province
- National Natural Science Foundation of China
Zitieren
APA
Ma, C., Zhu, J., Zhang, X., Cui, H., Tan, Y., Guo, J., Zheng, H., Liang, D., Su, T., Sun, Y., & Ge, Y. (2025). Learning-based multi-material CBCT image reconstruction with ultra-slow kV switching. Journal of X-Ray Science and Technology. https://doi.org/10.1177/08953996251331790
Vancouver
Ma C, Zhu J, Zhang X, Cui H, Tan Y, Guo J, et al. Learning-based multi-material CBCT image reconstruction with ultra-slow kV switching. Journal of X-Ray Science and Technology. 2025. doi:10.1177/08953996251331790
BibTeX
@article{Ma2025,
author = {Ma, Chenchen and Zhu, Jiongtao and Zhang, Xin and Cui, Han and Tan, Yuhang and Guo, Jinchuan and Zheng, Hairong and Liang, Dong and Su, Ting and Sun, Yi and Ge, Yongshuai},
title = {Learning-based multi-material CBCT image reconstruction with ultra-slow kV switching},
journal = {Journal of X-Ray Science and Technology},
year = {2025},
doi = {10.1177/08953996251331790}
}
EUVIMED