MRI-Only Radiotherapy Planning for Nasopharyngeal Carcinoma Using Deep Learning

被引:15
|
作者
Ma, Xiangyu [1 ]
Chen, Xinyuan [1 ]
Li, Jingwen [2 ]
Wang, Yu [1 ]
Men, Kuo [1 ]
Dai, Jianrong [1 ]
机构
[1] Chinese Acad Med Sci & Peking Union Med Coll, Canc Hosp, Natl Clin Res Ctr Canc, Natl Canc Ctr, Beijing, Peoples R China
[2] China Acad Informat & Commun Technol, Cloud Comp & Big Date Res Inst, Beijing, Peoples R China
来源
FRONTIERS IN ONCOLOGY | 2021年 / 11卷
基金
中国国家自然科学基金;
关键词
nasopharyngeal carcinoma; radiotherapy; MRI-only planning; pseudo CT; deep learning; dosimetric evaluation; RADIATION-THERAPY; ATTENUATION CORRECTION; ELECTRON-DENSITY; PSEUDO-CT; GENERATION; BRAIN; VERIFICATION; SIMULATION; IMAGES; HEAD;
D O I
10.3389/fonc.2021.713617
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Background: Radical radiotherapy is the main treatment modality for early and locally advanced nasopharyngeal carcinoma (NPC). Magnetic resonance imaging (MRI) has the advantages of no ionizing radiation and high soft-tissue resolution compared to computed tomography (CT), but it does not provide electron density (ED) information for radiotherapy planning. Therefore, in this study, we developed a pseudo-CT (pCT) generation method to provide necessary ED information for MRI-only planning in NPC radiotherapy. Methods: Twenty patients with early-stage NPC who received radiotherapy in our hospital were investigated. First, 1433 sets of paired T1 weighted magnetic resonance (MR) simulation images and CT simulation images were rigidly registered and preprocessed. A 16-layer U-Net was used to train the pCT generative model and a "pix2pix" generative adversarial network (GAN) was also trained to compare with the pure U-Net regrading pCT quality. Second, the contours of all target volumes and organs at risk in the original CT were transferred to the pCT for planning, and the beams were copied back to the original CT for reference dose calculation. Finally, the dose distribution calculated on the pCT was compared with the reference dose distribution through gamma analysis and dose-volume indices. Results: The average time for pCT generation for each patient was 7.90 +/- 0.47 seconds. The average mean (absolute) error was -9.3 +/- 16.9 HU (102.6 +/- 11.4 HU), and the mean-root-square error was 209.8 +/- 22.6 HU. There was no significant difference between the pCT quality of pix2pix GAN and that of pure U-Net (p > 0.05). The dose distribution on the pCT was highly consistent with that on the original CT. The mean gamma pass rate (2 mm/3%, 10% low dose threshold) was 99.1% +/- 0.3%, and the mean absolute difference of nasopharyngeal PGTV D-99% and PTV V-95% were 0.4% +/- 0.2% and 0.1% +/- 0.1%. Conclusion: The proposed deep learning model can accurately predict CT from MRI, and the generated pCT can be employed in precise dose calculations. It is of great significance to realize MRI-only planning in NPC radiotherapy, which can improve structure delineation and considerably reduce additional imaging dose, especially when an MR-guided linear accelerator is adopted for treatment.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] A Learning-Based MRI Classification for MRI-Only Radiotherapy Treatment Planning
    Lei, Y.
    Shu, H.
    Tian, S.
    Wang, T.
    Dhabaan, A.
    Liu, T.
    Shim, H.
    Mao, H.
    Curran, W.
    Yang, X.
    [J]. MEDICAL PHYSICS, 2018, 45 (06) : E524 - E524
  • [2] Automatic generation of synthetic CT and bulk anatomical density map using deep learning for MRI-only radiotherapy treatment planning
    Choi, Jae Hyuk
    Welsh, James
    Chalup, Stephan
    Greer, Peter
    [J]. ASIA-PACIFIC JOURNAL OF CLINICAL ONCOLOGY, 2020, 16 : 23 - 23
  • [3] Validation of an MRI-only planning workflow for definitive pelvic radiotherapy
    O'Connor, Laura M.
    Dowling, Jason A.
    Choi, Jae Hyuk
    Martin, Jarad
    Warren-Forward, Helen
    Richardson, Haylea
    Best, Leah
    Skehan, Kate
    Kumar, Mahesh
    Govindarajulu, Geetha
    Sridharan, Swetha
    Greer, Peter B.
    [J]. RADIATION ONCOLOGY, 2022, 17 (01)
  • [4] Validation of an MRI-only planning workflow for definitive pelvic radiotherapy
    Laura M. O’Connor
    Jason A. Dowling
    Jae Hyuk Choi
    Jarad Martin
    Helen Warren-Forward
    Haylea Richardson
    Leah Best
    Kate Skehan
    Mahesh Kumar
    Geetha Govindarajulu
    Swetha Sridharan
    Peter B. Greer
    [J]. Radiation Oncology, 17
  • [5] MRI-only proton therapy treatment planning with synthetic CT images generated using deep learning
    Montero, A. M. Barragan
    Souris, K.
    Kazemifar, S.
    Timmerman, R.
    Jiang, S.
    Geets, X.
    Sterpin, E.
    Owrangi, A.
    [J]. RADIOTHERAPY AND ONCOLOGY, 2019, 133 : S349 - S350
  • [6] Clinical Evaluation of Deep Learning -Based AutoSegmentation toward MRI-Only Prostate Radiotherapy
    Perez-Sanchez, J. A.
    Brisson, R. J.
    Hitchcock, K. E.
    Zlotecki, R. A.
    Badyal, Y.
    Liu, C.
    Yan, G.
    [J]. INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS, 2023, 117 (02): : E481 - E482
  • [7] Deep Learning Based Synthetic CT Generation with Multi-Sequence MRI for MRI-Only Radiotherapy
    Wu, S.
    Peng, Y.
    Qian, D.
    Wang, R.
    Deng, X.
    [J]. MEDICAL PHYSICS, 2021, 48 (06)
  • [8] MRI-only in prostate radiotherapy planning using multiple individual atlases: a preliminary study
    Nici, S.
    Monti, A. F.
    Lizio, D.
    Pellegrini, R.
    Brambilla, M. G.
    Carbonini, C.
    Garces, M. J. Arias
    Felisi, M. M. J.
    Bortolato, B.
    Frassica, C.
    Coletti, C.
    Vanzulli, A.
    Torresin, A.
    [J]. RADIOTHERAPY AND ONCOLOGY, 2020, 152 : S222 - S223
  • [9] MRI-Based Synthetic CT for MRI-Only Proton Radiotherapy Treatment Planning
    Yang, X.
    Hedrick, S.
    Wang, T.
    Lei, Y.
    Jiang, X.
    Mao, H.
    Curran, W.
    McDonald, M.
    Liu, T.
    [J]. MEDICAL PHYSICS, 2018, 45 (06) : E360 - E360
  • [10] Synthetic CT Generation for MRI-Only Radiation Therapy Using Deep Learning
    Kazemifar, S.
    Nguyen, D.
    McGuire, S.
    Timmerman, R.
    Nedzi, L.
    Wardak, Z.
    Gu, X.
    Jiang, S.
    Owrangi, A.
    [J]. MEDICAL PHYSICS, 2018, 45 (06) : E700 - E700