Beam data modeling of linear accelerators (linacs) through machine learning and its potential applications in fast and robust linac commissioning and quality assurance

TL;DR

This paper introduces a machine learning approach for accurate modeling of linac beam data, enhancing the efficiency and precision of linac commissioning and quality assurance in radiation therapy.

Contribution

A novel machine learning framework that predicts linac beam data from inherent features, streamlining commissioning and QA processes.

Findings

Achieved mean absolute %RE of 0.19-0.35% for PDD predictions.

Profile prediction mean absolute %RE of 0.66-0.93%.

Prediction accuracy improves with more training data, up to 20 sets.

Abstract

Background and purpose: To propose a novel machine learning-based method for reliable and accurate modeling of linac beam data applicable to the processes of linac commissioning and QA. Materials and methods: We hypothesize that the beam data is a function of inherent linac features and percentage depth doses (PDDs) and profiles of different field sizes are correlated with each other. The correlation is formulated as a multivariable regression problem using a machine learning framework. Varian TrueBeam beam data sets (n=43) acquired from multiple institutions were used to evaluate the framework. The data sets included PDDs and profiles across different energies and field sizes. A multivariate regression model was trained for prediction of beam specific PDDs and profiles of different field sizes using a 10x10cm$^2$ field as input. Results: Predictions of PDDs were achieved with a mean absolute percent relative error (%RE) of 0.19-0.35% across the different beam energies investigated. The maximum mean absolute %RE was 0.93%. For profile prediction, the mean absolute %RE was 0.66-0.93% with a maximum absolute %RE of 3.76%. The largest uncertainties in the PDD and profile predictions were found at the build-up region and at the field penumbra, respectively. The prediction accuracy increased with the number of training sets up to around 20 training sets. Conclusions: Through this novel machine learning-based method we have shown accurate and reproducible generation of beam data for linac commissioning for routine radiation therapy. This method has the potential to simplify the linac commissioning procedure, save time and manpower while increasing the accuracy of the commissioning process.