Synthetic CT Generation from MRI Using Generative Adversarial Networks for MR-Only Brain Radiotherapy Planning
Technology in Cancer Research & Treatment · 2025-06 · 24
DOI: 10.1177/15330338251400833 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technology in Cancer Research & Treatment, 2025-12. Verfasst von Chengjian Xiao und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Ganzhou Cancer Hospital, Ganzhou, People's Republic of China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Brain Neoplasms, Radiotherapy Planning, Computer-Assisted, Tomography, X-Ray Computed. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Introduction
Rapid magnetic resonance imaging (MRI) plays an increasingly important role in radiotherapy. It improves the accuracy of delineation of target volumes and organs at risk (OARs), but generating accurate synthetic CT(sCT) from MRI remains challenging, and the lack of electron density information limits its further clinical application. Therefore, the purpose of this study was to develop and evaluate a CBAMPix2Pix model for MRI to CT synthesis.
Methods
We adapted the CBAMPix2Pix architecture, incorporating convolutional block attention module(CBAM), to synthesize CT images from 17260 MRI slices of 86 patients with metastatic brain cancer. The model analyzes local features to enhance image authenticity and is designed to map T1-weighted Contrast-enhanced (T1wc) to sCT. To address the data imbalance between normal tissue and bone, we introduce structural similarity loss(SSIM) to enhance local features of learning images, thereby better reducing differences in Hounsfield Unit(HU).
Results
We evaluate the performance of the model through quantitative and qualitative evaluations. Our proposed model achieves higher peak signal-to-noise ratio (PSNR) of 27.5 ± 3.3 dB, normalized mean absolute error (NMAE) of 0.019 ± 0.023, and structural similarity index (SSIM) of 0.857 ± 0.059 for sCT images in MR simulation sequences, and the average mean absolute error(MAE) was 74.48 ± 22.88 HU in body and 185.89 ± 21.59 HU in bone. The P -values of the Wilcoxon signed-rank test for the CBAMPix2Pix model compared with the other two models in PSNR, SSIM, MAE, and NMAE were all less than 0.05 in the test cohorts.
Conclusion
We have developed a novel CBAMPix2Pix model that can effectively generate realistic sCT images comparable to real images, potentially improving the accuracy of MRI-based treatment planning.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiation Oncology, Ganzhou Cancer Hospital, Ganzhou, People's Republic of China.
- School of Public Health, Wenzhou Medical University, Wenzhou, People's Republic of China.
- Department of Comprehensive Intervention Room, The Second Affiliated Hospital of Nanchang University, Nanchang, People's Republic of China.
- Department of Pathology, Ganzhou Cancer Hospital, Ganzhou, People's Republic of China.
ORCID-Profile: Chengjian Xiao
Zitieren
APA
Xiao, C., Cen, C., Huang, Q., Xie, F., Liu, L., Lin, W., & Xiao, Y. (2025). Synthetic CT Generation from MRI Using Generative Adversarial Networks for MR-Only Brain Radiotherapy Planning. Technology in Cancer Research & Treatment, 24. https://doi.org/10.1177/15330338251400833
Vancouver
Xiao C, Cen C, Huang Q, Xie F, Liu L, Lin W, et al. Synthetic CT Generation from MRI Using Generative Adversarial Networks for MR-Only Brain Radiotherapy Planning. Technology in Cancer Research & Treatment. 2025;24. doi:10.1177/15330338251400833
BibTeX
@article{Xiao2025,
author = {Xiao, Chengjian and Cen, Chaozhe and Huang, Qun and Xie, Fangping and Liu, Lipeng and Lin, Weixiang and Xiao, Ying},
title = {Synthetic CT Generation from MRI Using Generative Adversarial Networks for MR-Only Brain Radiotherapy Planning},
journal = {Technology in Cancer Research & Treatment},
year = {2025},
volume = {24},
doi = {10.1177/15330338251400833}
}
EUVIMED