Synthetic CT generation for pelvic cases based on deep learning in multi-center datasets
Radiation Oncology · 09.07.2024 · 19 (1)
DOI: 10.1186/s13014-024-02467-w ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Radiation Oncology, online erschienen am 09.07.2024. Verfasst von Xianan Li und 10 weiteren Autor:innen. Beteiligte Einrichtung: Peking University People's Hospital, Beijing, China. Hauptthemen laut MEDLINE: Deep Learning, Tomography, X-Ray Computed, Magnetic Resonance Imaging, Radiotherapy Planning, Computer-Assisted. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Industry and Information Technology of the People's Republic of China, Ministry of Industry and Information Technology of the People’s Republic of China.
Abstract (Originalsprache)
Background and purpose To investigate the feasibility of synthesizing computed tomography (CT) images from magnetic resonance (MR) images in multi-center datasets using generative adversarial networks (GANs) for rectal cancer MR-only radiotherapy. Materials and methods Conventional T2-weighted MR and CT images were acquired from 90 rectal cancer patients at Peking University People’s Hospital and 19 patients in public datasets. This study proposed a new model combining contrastive learning loss and consistency regularization loss to enhance the generalization of model for multi-center pelvic MRI-to-CT synthesis. The CT-to-sCT image similarity was evaluated by computing the mean absolute error (MAE), peak signal-to-noise ratio (SNRpeak), structural similarity index (SSIM) and Generalization Performance (GP). The dosimetric accuracy of synthetic CT was verified against CT-based dose distributions for the photon plan. Relative dose differences in the planning target volume and organs at risk were computed.
Results
Our model presented excellent generalization with a GP of 0.911 on unseen datasets and outperformed the plain CycleGAN, where MAE decreased from 47.129 to 42.344, SNRpeak improved from 25.167 to 26.979, SSIM increased from 0.978 to 0.992. The dosimetric analysis demonstrated that most of the relative differences in dose and volume histogram (DVH) indicators between synthetic CT and real CT were less than 1%.
Conclusion
The proposed model can generate accurate synthetic CT in multi-center datasets from T2w-MR images. Most dosimetric differences were within clinically acceptable criteria for photon radiotherapy, demonstrating the feasibility of an MRI-only workflow for patients with rectal cancer.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Peking University People's Hospital, Beijing, China.
- Shenzhen United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China. lecheng.jia@cri-united-imaging.com.
- Zhejiang Engineering Research Center for Innovation and Application of Intelligent Radiotherapy Technology, Wenzhou, China. lecheng.jia@cri-united-imaging.com.
- Shenzhen United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China.
- Shanghai United Imaging Healthcare Co., Ltd. Shanghai, Shanghai, China.
- Peking University People's Hospital, Beijing, China. wang_yi@bjmu.edu.cn.
Förderung
- Ministry of Industry and Information Technology of the People's Republic of China
- Ministry of Industry and Information Technology of the People’s Republic of China
Zitieren
APA
Li, X., Jia, L., Lin, F., Chai, F., Liu, T., Zhang, W., Wei, Z., Xiong, W., Li, H., Zhang, M., & Wang, Y. (2024). Synthetic CT generation for pelvic cases based on deep learning in multi-center datasets. Radiation Oncology, 19(1). https://doi.org/10.1186/s13014-024-02467-w
Vancouver
Li X, Jia L, Lin F, Chai F, Liu T, Zhang W, et al. Synthetic CT generation for pelvic cases based on deep learning in multi-center datasets. Radiation Oncology. 2024;19(1). doi:10.1186/s13014-024-02467-w
BibTeX
@article{Li2024,
author = {Li, Xianan and Jia, Lecheng and Lin, Fengyu and Chai, Fan and Liu, Tao and Zhang, Wei and Wei, Ziquan and Xiong, Weiqi and Li, Hua and Zhang, Min and Wang, Yi},
title = {Synthetic CT generation for pelvic cases based on deep learning in multi-center datasets},
journal = {Radiation Oncology},
year = {2024},
volume = {19},
number = {1},
doi = {10.1186/s13014-024-02467-w}
}
EUVIMED