A convolution neural network for higher resolution dose prediction in prostate volumetric modulated arc therapy.

PURPOSE This study aims to investigate the feasibility of using convolutional neural networks to predict an accurate and high resolution dose distribution from an approximated and low resolution input dose. METHODS Sixty-six patients were treated for prostate cancer with VMAT. We created the treatment plans using the Acuros XB algorithm with 2 mm grid size, followed by the dose calculated using the anisotropic analytical algorithm with 5 mm grid with the same plan parameters. U-net model was used to predict 2 mm grid dose from 5 mm grid dose. We investigated the two models differing for the training data used as input, one used just the low resolution dose (D model) and the other combined the low resolution dose with CT data (DC model). Dice similarity coefficient (DSC) was calculated to ascertain how well the shape of the dose-volume is matched. We conducted gamma analysis for the following: DVH from the two models and the reference DVH for all prostate structures. RESULTS The DSC values in the DC model were significantly higher than those in the D model (p < 0.01). For the CTV, PTV, and bladder, the gamma passing rates in the DC model were significantly higher than those in the D model (p < 0.002-0.02). The mean doses in the CTV and PTV for the DC model were significantly better matched to those in the reference dose (p < 0.0001). CONCLUSIONS The proposed U-net model with dose and CT image used as input predicted more accurate dose.

[1]  Steve B. Jiang,et al.  Three-Dimensional Dose Prediction for Lung IMRT Patients with Deep Neural Networks: Robust Learning from Heterogeneous Beam Configurations , 2018, ArXiv.

[2]  K. Bush,et al.  Dosimetric validation of Acuros XB with Monte Carlo methods for photon dose calculations. , 2011, Medical physics.

[3]  Daniel A Low,et al.  A fourier analysis of the dose grid resolution required for accurate IMRT fluence map optimization. , 2005, Medical physics.

[4]  Ping Xia,et al.  Tolerance limits and methodologies for IMRT measurement‐based verification QA , 2018, Medical physics.

[5]  L. Cozzi,et al.  Critical appraisal of Acuros XB and Anisotropic Analytic Algorithm dose calculation in advanced non-small-cell lung cancer treatments. , 2012, International journal of radiation oncology, biology, physics.

[6]  J. Chung,et al.  Dosimetric effects of the acuros XB and anisotropic analytical algorithm on volumetric modulated arc therapy planning for prostate cancer using an endorectal balloon , 2015, Radiation Oncology.

[7]  Anthony Walsh,et al.  Accuracy and efficiency of graphics processing unit (GPU) based Acuros XB dose calculation within the Varian Eclipse treatment planning system. , 2019, Medical dosimetry : official journal of the American Association of Medical Dosimetrists.

[8]  A. Ahnesjö.  Collapsed cone convolution of radiant energy for photon dose calculation in heterogeneous media. , 1989, Medical physics.

[9]  Suresh Senan,et al.  Volumetric intensity-modulated arc therapy vs. conventional IMRT in head-and-neck cancer: a comparative planning and dosimetric study. , 2009, International journal of radiation oncology, biology, physics.

[10]  T. Suh,et al.  Dosimetric and radiobiological comparison in different dose calculation grid sizes between Acuros XB and anisotropic analytical algorithm for prostate VMAT , 2018, PloS one.

[11]  Katia Parodi,et al.  Development of the open‐source dose calculation and optimization toolkit matRad , 2017, Medical physics.

[12]  Steve B. Jiang,et al.  A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning , 2017, Scientific Reports.

[13]  Jae Sung Lee,et al.  Computed tomography super-resolution using deep convolutional neural network , 2018, Physics in medicine and biology.

[14]  Dietmar Georg,et al.  Evaluation of treatment plan quality of IMRT and VMAT with and without flattening filter using Pareto optimal fronts. , 2013, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[15]  Shihui Ying,et al.  MR Image Super-Resolution via Wide Residual Networks With Fixed Skip Connection , 2019, IEEE Journal of Biomedical and Health Informatics.

[16]  Yuan Tian,et al.  A deep learning method for prediction of three-dimensional dose distribution of helical tomotherapy. , 2019, Medical physics.

[17]  Karl Otto,et al.  Volumetric modulated arc therapy: IMRT in a single gantry arc. , 2007, Medical physics.

[18]  Benjamin E Nelms,et al.  Evaluating IMRT and VMAT dose accuracy: practical examples of failure to detect systematic errors when applying a commonly used metric and action levels. , 2013, Medical physics.

[19]  I. Das,et al.  The dosimetric and radiobiological impact of calculation grid size on head and neck IMRT. , 2017, Practical radiation oncology.

[20]  Jeffrey E Snyder,et al.  The commissioning and validation of Monaco treatment planning system on an Elekta VersaHD linear accelerator , 2018, Journal of applied clinical medical physics.

[21]  J L Bedford,et al.  Commissioning and quality assurance of the Pinnacle(3) radiotherapy treatment planning system for external beam photons. , 2003, The British journal of radiology.

[22]  Firas Mourtada,et al.  Validation of a new grid-based Boltzmann equation solver for dose calculation in radiotherapy with photon beams , 2010, Physics in medicine and biology.

[23]  Yifan He,et al.  Single Image Super-Resolution Based on Multi-Scale Competitive Convolutional Neural Network , 2018, Sensors.

[24]  D. Low,et al.  A technique for the quantitative evaluation of dose distributions. , 1998, Medical physics.

[25]  Jan Seuntjens,et al.  Novel knowledge-based treatment planning model for hypofractionated radiotherapy of prostate cancer patients. , 2019, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[26]  M. Schell,et al.  Stereotactic body radiation therapy: the report of AAPM Task Group 101. , 2010, Medical physics.

[27]  Jiawei Fan,et al.  Automatic treatment planning based on three‐dimensional dose distribution predicted from deep learning technique , 2018, Medical physics.

[28]  Shihui Ying,et al.  Super-resolution reconstruction of MR image with a novel residual learning network algorithm , 2018, Physics in medicine and biology.

[29]  C J Moore,et al.  Quantitative comparison of 3D and 2.5D gamma analysis: introducing gamma angle histograms , 2013, Physics in medicine and biology.