Wei Zhao1, Ishan Patil2, Bin Han3, Yong Yang4, Lei Xing5, Emil Schüler6. 1. Stanford University, Department of Radiation Oncology, Stanford, CA 94305, USA. Electronic address: zhaow85@stanford.edu. 2. Stanford University, Department of Radiation Oncology, Stanford, CA 94305, USA. 3. Stanford University, Department of Radiation Oncology, Stanford, CA 94305, USA. Electronic address: hanbin@stanford.edu. 4. Stanford University, Department of Radiation Oncology, Stanford, CA 94305, USA. Electronic address: yongy66@stanford.edu. 5. Stanford University, Department of Radiation Oncology, Stanford, CA 94305, USA. Electronic address: lei@stanford.edu. 6. Stanford University, Department of Radiation Oncology, Stanford, CA 94305, USA; The University of Texas MD Anderson Cancer Center, Department of Radiation Physics, Houston, TX 77030, USA. Electronic address: eschueler@mdanderson.org.
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 10 × 10 cm2 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.
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 10 × 10 cm2 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.
Authors: P Troy Teo; Min-Sig Hwang; William Gary Shields; Pavel Kosterin; Si Young Jang; Dwight E Heron; Ronald J Lalonde; M Saiful Huq Journal: Med Phys Date: 2019-02-04 Impact factor: 4.071
Authors: C Glide-Hurst; M Bellon; R Foster; C Altunbas; M Speiser; M Altman; D Westerly; N Wen; B Zhao; M Miften; I J Chetty; T Solberg Journal: Med Phys Date: 2013-03 Impact factor: 4.071
Authors: Tucker Netherton; Yuting Li; Song Gao; Ann Klopp; Peter Balter; Laurence E Court; Ryan Scheuermann; Chris Kennedy; Lei Dong; James Metz; Dimitris Mihailidis; Clifton Ling; Mu Young Lee; Magdalena Constantin; Stephen Thompson; Juha Kauppinen; Pekka Uusitalo Journal: Med Phys Date: 2019-08-27 Impact factor: 4.071