中华放射肿瘤学杂志
Wednesday, Apr. 9, 2025   Home | Journal | Editorial | Instruction | Subscription | Advertisement | Academic | Index-in | Contact Us | Chinese
Chinese Journal of Radiation Oncology  2020, Vol. 29 Issue (4): 267-272    DOI: 10.3760/cma.j.cn113030-20190614-00004
Physics·Biology·Technique Current Issue| Next Issue| Archive| Adv Search [an error occurred while processing this directive] | [an error occurred while processing this directive]
Generative Adversarial Networks based synthetic-CT generation for patients with nasopharyngeal carcinoma
Qi Mengke1, Li Yongbao2, Wu Aiqian1, Guo Futong1, Jia Qiyuan1, Song Ting1, Zhou Linghong1
1Department of Biomedical Engineering,Southern Medical University,Guangzhou 510515,China;
2Sun Yat-sen University Cancer Center,Guangzhou 510060,China
Download: PDF (0 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      Supporting Info
Abstract  Objective To establish a correlation model between MRI and CT images to generatesynthetic-CT (sCT) of head and neck cancer during MRI-guided radiotherapy by using generative adversarial networks (GAN). Methods Images and IMRT plans of 45 patients with nasopharyngeal carcinoma were collected before treatment. Firstly, the MRI (T1) and CT images were preprocessed, including rigid registration, clipping, background removal and data enhancement, etc. Secondly, the cases were trained by GAN, of which 30 cases were randomly selected and put into the network as training set images for modeling and learning, and the other 15 cases were used for testing. The image quality of predicted sCT and real CT were statistically compared, and the dose distribution recalculated upon predicted sCT was statistically compared with that of real planned dose distribution. Results The mean absolute error of the predicted sCT of the testing set was (79.15±11.37) HU, and the SSIM value was 0.83±0.03. The MAE values of dose distribution difference at different regional levels were less than 1% compared to the prescription dose. The gamma passing rate of the sCT dose distribution was higher than 92% and 98% under the 2mm/2% and 3mm/3% criteria. Conclusions We have successfully proposed and realized the generation of sCT for head and neck cancer using GAN, which lays a foundation for the implementation of MRI-guided radiotherapy. The comparison of image quality and dosimetry shows the feasibility and accuracy of this method.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Qi Mengke
Li Yongbao
Wu Aiqian
Guo Futong
Jia Qiyuan
Song Ting
Zhou Linghong
Key wordsNasopharyngeal neoplasm/magnetic resonance-image guided radiotherapy      Generative adversarial networks      Synthetic-CT generation     
Received: 14 June 2019     
Fund:National Key Research & Development Program of China (2017YFC0113203); National Natural Science Foundation of China (11805292,81601577,81571771); Natural Science Foundation of Guangdong Province (2018A0303100020)
Corresponding Authors: Song Ting,Email:tingsong2015@smu.edu.cn;Zhou Linghong,Email:smart@smu.edu.cn   
Cite this article:   
Qi Mengke,Li Yongbao,Wu Aiqian et al. Generative Adversarial Networks based synthetic-CT generation for patients with nasopharyngeal carcinoma[J]. Chinese Journal of Radiation Oncology, 2020, 29(4): 267-272.
Qi Mengke,Li Yongbao,Wu Aiqian et al. Generative Adversarial Networks based synthetic-CT generation for patients with nasopharyngeal carcinoma[J]. Chinese Journal of Radiation Oncology, 2020, 29(4): 267-272.
URL:  
http://journal12.magtechjournal.com/Jweb_fszlx/EN/10.3760/cma.j.cn113030-20190614-00004     OR     http://journal12.magtechjournal.com/Jweb_fszlx/EN/Y2020/V29/I4/267
  Copyright © 2010 Editorial By Chinese Journal of Radiation Oncology
Support by Beijing Magtech Co.ltd  support@magtech.com.cn