Comparison and evaluation of different deep learning models of synthetic CT generation from CBCT for nasopharynx cancer adaptive proton therapy
Medical Physics · 2023
DOI: 10.1002/mp.16777 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, 2023. Verfasst von Bo Pang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan, China. Hauptthemen laut MEDLINE: Deep Learning, Proton Therapy, Spiral Cone-Beam Computed Tomography, Nasopharyngeal Neoplasms. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: National Key R&D Program of China, Fundamental Research Funds for the Central Universities of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
Background
Cone‐beam computed tomography (CBCT) scanning is used for patient setup in image‐guided radiotherapy. However, its inaccurate CT numbers limit its applicability in dose calculation and treatment planning.
Purpose
This study compares four deep learning methods for generating synthetic CT (sCT) to determine which method is more appropriate and offers potential for further clinical exploration in adaptive proton therapy for nasopharynx cancer.
Methods
CBCTs and deformed planning CT (dCT) from 75 patients (60/5/10 for training, validation and testing) were used to compare cycle‐consistent Generative Adversarial Network (cycleGAN), Unet, Unet+cycleGAN and conditiona l Generative Adversarial Network (cGAN) for sCT generation. The sCT images generated by each method were evaluated against dCT images using mean absolute error (MAE), structural similarity (SSIM), peak signal‐to‐noise ratio (PSNR), spatial non‐uniformity (SNU) and radial averaging in the frequency domain. In addition, dosimetric accuracy was assessed through gamma analysis, differences in water equivalent thickness (WET), and dose‐volume histogram metrics.
Results
The cGAN model has demonstrated optimal performance in the four models across various indicators. In terms of image quality under global condition, the average MAE has been reduced to 16.39HU, SSIM has increased to 95.24%, and PSNR has increased to 28.98. Regarding dosimetric accuracy, the gamma passing rate (2%/2 mm) has reached 99.02%, and the WET difference is only 1.28 mm. The D 95 value of CTVs coverage and D max value of spinal cord, brainstem show no significant differences between dCT and sCT generated by cGAN model.
Conclusions
The cGAN model has been shown to be a more suitable approach for generating sCT using CBCT, considering its characteristics and concepts. The resulting sCT has the potential for application in adaptive proton therapy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan, China.
- Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
- Hubei Key Laboratory of Precision Radiation Oncology, Wuhan, China.
- Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
Förderung
- National Key R&D Program of China
- Fundamental Research Funds for the Central Universities of China
- National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Pang, B., Si, H., Liu, M., Fu, W., Zeng, Y., Liu, H., Cao, T., Chang, Y., Quan, H., & Yang, Z. (2023). Comparison and evaluation of different deep learning models of synthetic CT generation from CBCT for nasopharynx cancer adaptive proton therapy. Medical Physics. https://doi.org/10.1002/mp.16777
Vancouver
Pang B, Si H, Liu M, Fu W, Zeng Y, Liu H, et al. Comparison and evaluation of different deep learning models of synthetic CT generation from CBCT for nasopharynx cancer adaptive proton therapy. Medical Physics. 2023. doi:10.1002/mp.16777
BibTeX
@article{Pang2023,
author = {Pang, Bo and Si, Hang and Liu, Muyu and Fu, Wensheng and Zeng, Yiling and Liu, Hongyuan and Cao, Ting and Chang, Yu and Quan, Hong and Yang, Zhiyong},
title = {Comparison and evaluation of different deep learning models of synthetic CT generation from CBCT for nasopharynx cancer adaptive proton therapy},
journal = {Medical Physics},
year = {2023},
doi = {10.1002/mp.16777}
}
EUVIMED