A Wagner1, K Brou Boni2, E Rault3, F Crop3, T Lacornerie3, D Van Gestel4, N Reynaert5. 1. Department of Medical Physics, Centre Oscar Lambret, Lille, France; Faculty of Biomedical Sciences, University of Brussels ULB, Belgium. Electronic address: a-wagner@o-lambret.fr. 2. Department of Medical Physics, Centre Oscar Lambret, Lille, France; University of Lille, CNRS, CRIStAL, Centrale Lille, France. 3. Department of Medical Physics, Centre Oscar Lambret, Lille, France. 4. Faculty of Biomedical Sciences, University of Brussels ULB, Belgium; Department of Radiation Therapy, Institut Jules Bordet, Brussels, Belgium. 5. Department of Medical Physics, Centre Oscar Lambret, Lille, France; Faculty of Biomedical Sciences, University of Brussels ULB, Belgium; Department of Medical Physics, Institut Jules Bordet, Brussels, Belgium.
Abstract
PURPOSE: This work describes the integration of the M6 Cyberknife in the Moderato Monte Carlo platform, and introduces a machine learning method to accelerate the modelling of a linac. METHODS: The MLC-equipped M6 Cyberknife was modelled and integrated in Moderato, our in-house platform offering independent verification of radiotherapy dose distributions. The model was validated by comparing TPS dose distributions with Moderato and by film measurements. Using this model, a machine learning algorithm was trained to find electron beam parameters for other M6 devices, by simulating dose curves with varying spot size and energy. The algorithm was optimized using cross-validation and tested with measurements from other institutions equipped with a M6 Cyberknife. RESULTS: Optimal agreement in the Monte Carlo model was reached for a monoenergetic electron beam of 6.75 MeV with Gaussian spatial distribution of 2.4 mm FWHM. Clinical plan dose distributions from Moderato agreed within 2% with the TPS, and film measurements confirmed the accuracy of the model. Cross-validation of the prediction algorithm produced mean absolute errors of 0.1 MeV and 0.3 mm for beam energy and spot size respectively. Prediction-based simulated dose curves for other centres agreed within 3% with measurements, except for one device where differences up to 6% were detected. CONCLUSIONS: The M6 Cyberknife was integrated in Moderato and validated through dose re-calculations and film measurements. The prediction algorithm was successfully applied to obtain electron beam parameters for other M6 devices. This method would prove useful to speed up modelling of new machines in Monte Carlo systems.
PURPOSE: This work describes the integration of the M6 Cyberknife in the Moderato Monte Carlo platform, and introduces a machine learning method to accelerate the modelling of a linac. METHODS: The MLC-equipped M6 Cyberknife was modelled and integrated in Moderato, our in-house platform offering independent verification of radiotherapy dose distributions. The model was validated by comparing TPS dose distributions with Moderato and by film measurements. Using this model, a machine learning algorithm was trained to find electron beam parameters for other M6 devices, by simulating dose curves with varying spot size and energy. The algorithm was optimized using cross-validation and tested with measurements from other institutions equipped with a M6 Cyberknife. RESULTS: Optimal agreement in the Monte Carlo model was reached for a monoenergetic electron beam of 6.75 MeV with Gaussian spatial distribution of 2.4 mm FWHM. Clinical plan dose distributions from Moderato agreed within 2% with the TPS, and film measurements confirmed the accuracy of the model. Cross-validation of the prediction algorithm produced mean absolute errors of 0.1 MeV and 0.3 mm for beam energy and spot size respectively. Prediction-based simulated dose curves for other centres agreed within 3% with measurements, except for one device where differences up to 6% were detected. CONCLUSIONS: The M6 Cyberknife was integrated in Moderato and validated through dose re-calculations and film measurements. The prediction algorithm was successfully applied to obtain electron beam parameters for other M6 devices. This method would prove useful to speed up modelling of new machines in Monte Carlo systems.