A plan verification platform for online adaptive proton therapy using deep learning-based Monte–Carlo denoising

  • Guoliang Zhang
    National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China

    School of Physics and Technology, Wuhan University, 430072, China
    Search for articles by this author
  • Xinyuan Chen
    National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
    Search for articles by this author
  • Jianrong Dai
    National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
    Search for articles by this author
  • Kuo Men
    Corresponding author.
    National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
    Search for articles by this author
Published:October 03, 2022DOI:


      • The MC algorithm was able to offer an analogous E2E plan verification method.
      • The MC computation time increases linearly with the number of simulated particles.
      • A fast MC plan verification platform was developed via a dl-based denoising method.
      • It maintains the MC dose calculation accuracy while reducing the computation time.


      Background Purpose

      This study focused on developing a fast Monte Carlo (MC) plan verification platform via a deep learning (DL)-based denoising approach. It can maintain the MC dose calculation accuracy while significantly reducing the computation time. We also investigated its potential applications for online adaptive proton therapy (APT).


      First, we modeled an MC platform for proton therapy using the beam data library (BDL) required for treatment planning systems and then tested it with measured data. To accelerate the dose calculation, a dl-based denoising model with deep ResNet-deconvolution networks was developed. It was trained on the MC dose distribution of tumor sites obtained from 52 patients. The input MC dose distribution was with 1 × 106 simulated protons and the reference was 1 × 108. Fivefold cross-validation was performed.


      Comparing the MC model with measured data, the range agreement (point-to-point difference) was better than 0.85 mm, and the lateral dose profile difference was below 2.41 %. For the denoising approach, we found a significant improvement in the dose volume histogram (DVH) for predicted images compared with input images. The root mean squared error (RMSE) for predicted versus reference images was 3.94 times lower than that of the input versus reference images. Moreover, for the gamma passing rate (3 mm/3%), the predicted versus reference images have an average of 99 %, much higher than the 82 % of the input versus reference images. The MC model successfully denoised the test dose map (high noise) to approach the reference (low noise). The elapsed time can be reduced to < 60 s (simulation time [high noise] + predicted time), much lower than the simulation time of a low noise dose map (e.g., >100 min of simulation of 1 + E8 particles).


      We propose an analogous end-to-end fast plan verification platform using the combination of MC and DL methods. The platform yields dose calculation accuracy similar to MC codes while significantly reducing the elapsed time and can be used for online APT as an alternative to online plan verification.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Physica Medica: European Journal of Medical Physics
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Yan D.i.
        • Vicini F.
        • Wong J.
        • Martinez A.
        John Wong, Alvaro Martinez, Adaptive radiation therapy.
        Phys Med Biol. 1997; 42: 123-132
        • Paganetti H.
        • Botas P.
        • Sharp G.C.
        • Winey B.
        Gregory C sharp.
        Phys Med Biol. 2021; 66: 22TR01
        • Wu Q.J.
        • Li T.
        • Wu Q.
        • Yin F.-F.
        Adaptive radiation therapy: technical components and clinical applications.
        Cancer J. 2011; 17: 182-189
        • Albertini F.
        • et al.
        Online daily adaptive proton therapy.
        Br J Radiol. 2020; 93: 20190594
        • Meier G.
        • Besson R.
        • Nanz A.
        • Safai S.
        • Lomax A.J.
        Independent dose calculations for commissioning, quality assurance and dose reconstruction of PBS proton therapy.
        Phys Med Biol. 2015; 60: 2819-2836
        • Matter M.
        • Nenoff L.
        • Meier G.
        • Weber D.C.
        • Lomax A.J.
        • Albertini F.
        Alternatives to patient specific verification measurements in proton therapy: a comparative experimental study with intentional errors.
        Phys Med Biol. 2018; 63: 205014
        • Johnson J.E.
        • Beltran C.
        • Wan Chan Tseung H.
        • Mundy D.W.
        • Kruse J.J.
        • Whitaker T.J.
        • et al.
        Highly efficient and sensitive patient-specific quality assurance for spot-scanned proton therapy.
        Plos One. 2019; 14: e0212412
        • Mackin D.
        • Li Y.
        • Taylor M.B.
        • Kerr M.
        • Holmes C.
        • Sahoo N.
        • et al.
        Improving spot-scanning proton therapy patient specific quality assurance with HPlusQA, a second-check dose calculation engine: HPlusQA, an SSPT second-check dose calculation engine.
        Med Phys. 2013; 40: 121708
        • Zhu X.
        • Li Y.
        • Mackin D.
        • Li H.
        • Poenisch F.
        • Lee A.
        • et al.
        Towards effective and efficient patient-specific quality assurance for spot scanning proton therapy.
        Cancers (Basel). 2015; 7: 631-647
        • Yabe T.
        • Yamaguchi M.
        • Liu C.-C.
        • Toshito T.
        • Kawachi N.
        • Yamamoto S.
        Deep learning-based in vivo dose verification from proton-induced secondary-electron-bremsstrahlung images with various count level.
        Physica Medica. 2022; 99: 130-139
        • Bongrand A.
        • Koumeir C.
        • Villoing D.
        • Guertin A.
        • Haddad F.
        • Métivier V.
        • et al.
        A monte carlo determination of dose and range uncertainties for preclinical studies with a proton beam.
        Cancers. 2021; 13: 1889
        • Paganetti H.
        Range uncertainties in proton therapy and the role of Monte Carlo simulations.
        Phys Med Biol. 2012; 57: R99-R117
        • Sorriaux J.
        • et al.
        Experimental assessment of proton dose calculation accuracy in inhomogeneous media.
        Phys. Med. 2017; 38: 10
        • Yang J.
        • Li J.
        • Chen L.
        • Price R.
        • McNeeley S.
        • Qin L.
        • et al.
        Dosimetric verification of IMRT treatment planning using Monte Carlo simulations for prostate cancer.
        Phys Med Biol. 2005; 50: 869-878
      1. Taylor, P.A., S. Kry, and D. Followill, Pencil Beam Algorithms Are Unsuitable forProton Dose Calculations in Lung. International Journal of Radiation Oncology Biology Physics, 2017: p. S036030161731012X.

        • Chetty I.J.
        • Curran B.
        • Cygler J.E.
        • DeMarco J.J.
        • Ezzell G.
        • Faddegon B.A.
        • et al.
        Report of the AAPM Task Group No. 105: issues associated with clinical implementation of Monte Carlo-based photon and electron external beam treatment planning. Med Phys.
        Med Phys. 2007; 34: 4818-4853
        • Naqa I.E.
        • Kawrakow I.
        • Fippel M.
        • Siebers J.V.
        • Lindsay P.E.
        • Wickerhauser M.V.
        • et al.
        A comparison of Monte Carlo dose calculation denoising techniques.
        Phys Med Biol. 2005; 50: 909-922
        • Liao F.
        • et al.
        Evaluate the malignancy of pulmonary nodules using the 3D deep leaky noisy-or network.
        IEEE Trans Neural Networks Learn Syst. 2017;
        • Litjens G.
        • Kooi T.
        • Bejnordi B.E.
        • Setio A.A.A.
        • Ciompi F.
        • Ghafoorian M.
        • et al.
        A survey on deep learning in medical image analysis.
        Med Image Anal. 2017; 42: 60-88
        • Bako S.
        • Vogels T.
        • Mcwilliams B.
        • Meyer M.
        • NováK J.
        • Harvill A.
        • et al.
        Kernel-predicting convolutional networks for denoising Monte Carlo renderings.
        ACM Trans Graphics. 2017; 36: 1-14
        • Javaid U.
        • Souris K.
        • Huang S.
        • Lee J.A.
        Denoising proton therapy Monte Carlo dose distributions in multiple tumor sites: a comparative neural networks architecture study.
        Physica Medica. 2021; 89: 93-103
        • Shan H.
        • Zhang Y.i.
        • Yang Q.
        • Kruger U.
        • Kalra M.K.
        • Sun L.
        • et al.
        3D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2d trained network.
        IEEE Trans Med Imaging. 2018; 37: 1522-1534
        • Javaid U.
        • Souris K.
        • Dasnoy D.
        • Huang S.
        • Lee J.A.
        Mitigating inherent noise in monte carlo dose distributions using dilated U-Net.
        Med Phys. 2019; 46: 5790-5798
      2. Neph, R., et al., DeepMC: a deep learning method for efficient Monte Carlo beamlet dose calculation by predictive denoising in magnetic resonance-guided radiotherapy. Phys Med Biol, 2021. 66(3): p. 035022.

        • Bai T.
        • Wang B.
        • Nguyen D.
        • Jiang S.
        Deep dose plugin: towards real-time monte carlo dose calculation through a deep learning-based denoising algorithm.
        Mach Learn Sci Technol. 2021; 2025033
        • Grevillot L.
        • Bertrand D.
        • Dessy F.
        • Freud N.
        • Sarrut D.
        A Monte Carlo pencil beam scanning model for proton treatment plan simulation using GATE/GEANT4.
        Phys Med Biol. 2011; 56: 5203-5219
        • Souris K.
        • Lee J.A.
        • Sterpin E.
        Fast multipurpose Monte Carlo simulation for proton therapy using multi- and many-core CPU architectures.
        Med Phys. 2016; 43: 1700-1712
        • Chen X.
        • Men K.
        • Li Y.
        • Yi J.
        • Dai J.
        A feasibility study on an automated method to generate patient-specific dose distributions for radiotherapy using deep learning.
        Med Phys. 2019; 46: 56-64
        • Stankovskiy A.
        • Kerhoas-Cavata S.
        • Ferrand R.
        • Nauraye C.
        • Demarzi L.
        Monte Carlo modelling of the treatment line of the Proton Therapy Center in Orsay.
        Phys Med Biol. 2009; 54: 2377-2394
      3. Belosi, M.F., et al., Monte Carlo simulation of TrueBeam flattening-filter-free beams using varian phase-space files: comparison with experimental data. Med Phys, 2014. 41(5): p. 051707.

        • Jia X.
        • Schümann J.
        • Paganetti H.
        • Jiang S.B.
        GPU-based fast monte carlo dose calculation for proton therapy.
        Phys Med Biol. 2012; 57: 7783-7797
        • Beltran C.
        • Tseung H.W.C.
        • Augustine K.E.
        • Bues M.
        • Mundy D.W.
        • Walsh T.J.
        • et al.
        Clinical implementation of a proton dose verification system utilizing a GPU accelerated monte carlo engine.
        Int J Particle Ther. 2016; 3: 312-319
        • Wan Chan Tseung H.
        • Ma J.
        • Beltran C.
        A fast GPU-based Monte Carlo simulation of proton transport with detailed modeling of nonelastic interactions.
        Med Phys. 2015; 42: 2967-2978
        • Shan J.
        • Yang Y.
        • Schild S.E.
        • Daniels T.B.
        • Wong W.W.
        • Fatyga M.
        • et al.
        Intensity-modulated proton therapy (IMPT) interplay effect evaluation of asymmetric breathing with simultaneous uncertainty considerations in patients with non-small cell lung cancer.
        Med Phys. 2020; 47: 5428-5440