Online

ESTRO 2020

Session Item

Physics track: Dose measurement and dose calculation
9319
Poster
Physics
00:00 - 00:00
Prediction of electron beam parameters of a Monte Carlo model using machine learning
Antoine Wagner, France
PO-1352

Abstract

Prediction of electron beam parameters of a Monte Carlo model using machine learning
Authors: Kevin Brou Boni.(Centre Oscar Lambret, Department of Medical Physics, Lille, France), Frederik Crop.(Centre Oscar Lambret, Department of Medical Physics, Lille, France), Thomas Lacornerie.(Centre Oscar Lambret, Department of Medical Physics, Lille, France), Erwann Rault.(Centre Oscar Lambret, Department of Medical Physics, Lille, France), Nick Reynaert.(Institut Jules Bordet, Department of Medical Physics, Brussels, Belgium), Dirk Van Gestel.(Institut Jules Bordet, Department of Radiotherapy, Brussels, Belgium), Antoine Wagner.(Centre Oscar Lambret, Department of Medical Physics, Lille, France)
Show Affiliations
Purpose or Objective

The objective of this work is to propose a method to predict electron beam characteristics of a linear accelerator Monte Carlo model using machine learning, thus speeding up and automating the modelling process. The method is developed and tested based on a MLC-equipped stereotactic radiotherapy accelerator model.

Material and Methods

The M6 Cyberknife (Accuray, Sunnyvale CA) equipped with the Incise2 MLC is first modelled in BEAMnrc/DOSXYZnrc using water phantom measurements. The model is then integrated in our home-developed Monte Carlo (MC) 3D dose verification platform Moderato, and validated on patient plans. The general principle of the machine learning (ML) algorithm is described in Figure 1. To generate the data necessary to train the algorithm, a series of simulated dose profiles and percentage depth doses (PDD) are created from the MC model for the 115x100mm MLC field, while varying electron beam spot size (from 1 to 4 mm) and energy (from 4 to 8 MeV). A Ridge regression algorithm is first trained to predict energy and spot size by splitting the simulated curves into training and test sets, allowing to finetune the parameters of the algorithm. The ML model is then applied on measured data provided by five other M6-equipped institutions, and the predicted values are introduced in a MC model to generate simulated profiles for the 115x100mm MLC and 5 mm fixed beams, to be compared with the measurements.



Figure 1. Principle of the electron beam characteristics prediction.

Results

For our M6 device, optimal agreement between simulated and measured profiles in the water tank was reached for a monoenergetic electron beam of 6.75 MeV with a gaussian spatial distribution of 2.4 mm FWHM. Re-calculation of patient plans showed a good agreement (<2%) between the TPS algorithms and Moderato. During the optimization of the ML algorithm, cross-validation showed that electron beam energy and spot size could be predicted with a mean absolute error (MAE) of 0.1 MeV and 0.3 mm respectively. Predicted values for the five other M6 systems varied significantly from one device to another (Table 1). Simulations generated from these predicted values demonstrated a close agreement (<3%) between simulated and measured dose curves, except for centre #1 where differences went up to 6% (figure 2), which might be due to an asymmetry in the measured dose profiles for that specific machine.


Table 1. Predicted electron beam spot sizes and energies for the five M6 devices.

CentrePredicted spot size (mm)Predicted energy (MeV)
#12.77.1
#21.96.8
#31.86.6
#43.46.5
#52.06.5


Figure 2. Dose profiles for the five M6 devices, measured (red lines) and simulated (blue dots) for the 115x100mm MLC (top) and the fixed 5mm (bottom) beams.
Conclusion

A machine learning algorithm was developed and tested to validate the concept of predicting electron beam parameters from profile data. This method would allow significant time gain in the context of integrating multiple accelerator models in a Monte Carlo-based dose verification system.