Hybrid deep learning reconstruction for fast four‐dimensional cone beam computed tomography in small animal imaging
Medical Physics · 2025
DOI: 10.1002/mp.70092 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, 2025. Verfasst von Yiqun Han und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering and Applied Physics, University of Science and Technology of China, Hefei, Anhui, China. Hauptthemen laut MEDLINE: Deep Learning, Cone-Beam Computed Tomography, Image Processing, Computer-Assisted, Four-Dimensional Computed Tomography. Die Arbeit nennt 39 Literaturangaben. Gefördert von: Ministry of Science and Technology of China Key Research and Development Projects, Fundamental Research Funds for the Central Universities, Hefei Comprehensive National Science Center.
Abstract (Originalsprache)
Background
Conventional four‐dimensional cone beam computed tomography (4D‐CBCT) usually requires long scan time and high radiation dose. Fast and low‐dose 4D‐CBCT is preferred but its quality is compromised by the reduced number of projections used for reconstruction.
Purpose
This study is aimed to develop a hybrid deep learning reconstruction method for fast 4D‐CBCT (HDR‐4D) which can improve image quality while reducing imaging dose and scanning time.
Methods
The HDR‐4D was initiated with the FDK reconstruction of each phase, followed by deep learning MKB (DL‐MKB) method to preliminarily remove the streak artifacts in 4D‐CBCT images. Then motion compensation (MoCo) was applied to fuse DL‐MKB images of all phases. Finally, data fidelity was enforced under the framework of prior image constrained compressed sensing (PICCS) with the MoCo outputs as the prior information. An adaptive bone weighting strategy was introduced into the PICCS procedure to mitigate the bone‐induced streak artifacts. A neural network SARnet was developed to remove the streak artifacts in the HDR‐4D workflow. In‐vivo animal imaging was conducted to validate the proposed method. Root mean square error (RMSE) and structure similarity index measure (SSIM) were calculated for quantitative evaluation.
Results
The proposed method could reduce the 4D‐CBCT scan time to 45 s. The reconstructed images exhibit no discernible streak artifacts. Compared to direct deep learning prediction, the proposed method demonstrated significantly enhanced performance in preserving detailed anatomical structures. The average RMSE was 2.87 and SSIM was 0.982 for 4D‐CBCT images reconstructed with the HDR‐4D method, outperforming the direct deep learning prediction (RMSE: 3.96, SSIM: 0.966).
Conclusions
The proposed HDR‐4D can generate high quality 4D‐CBCT images while significantly reducing the scan dose and time, and demonstrates strong potential for small animal imaging applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Engineering and Applied Physics, University of Science and Technology of China, Hefei, Anhui, China.
- Research and Development Department, Raycision Medical Technology Co. Ltd., Hefei, Anhui, China.
- Department of Radiation Oncology, the First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China.
- Hefei Ion Medical Center, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China.
Förderung
- Ministry of Science and Technology of China Key Research and Development Projects
- Fundamental Research Funds for the Central Universities
- Hefei Comprehensive National Science Center
Zitieren
APA
Han, Y., Yuan, Z., Huang, Y., Liu, H., & Yang, Y. (2025). Hybrid deep learning reconstruction for fast four‐dimensional cone beam computed tomography in small animal imaging. Medical Physics. https://doi.org/10.1002/mp.70092
Vancouver
Han Y, Yuan Z, Huang Y, Liu H, Yang Y. Hybrid deep learning reconstruction for fast four‐dimensional cone beam computed tomography in small animal imaging. Medical Physics. 2025. doi:10.1002/mp.70092
BibTeX
@article{Han2025,
author = {Han, Yiqun and Yuan, Zengtai and Huang, Yunwen and Liu, Hui and Yang, Yidong},
title = {Hybrid deep learning reconstruction for fast four‐dimensional cone beam computed tomography in small animal imaging},
journal = {Medical Physics},
year = {2025},
doi = {10.1002/mp.70092}
}
EUVIMED