Literature DB >> 33039427

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

Wei Zhao1, Ishan Patil2, Bin Han3, Yong Yang4, Lei Xing5, Emil Schüler6.   

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.
Copyright © 2020 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Beam data modeling; Linac commissioning; Machine learning; Quality assurance; Radiotherapy

Mesh:

Year:  2020        PMID: 33039427      PMCID: PMC7750276          DOI: 10.1016/j.radonc.2020.09.057

Source DB:  PubMed          Journal:  Radiother Oncol        ISSN: 0167-8140            Impact factor:   6.280


  33 in total

1.  Point/counterpoint: vendor provided machine data should never be used as a substitute for fully commissioning a linear accelerator.

Authors:  Indra J Das; Christopher F Njeh; Colin G Orton
Journal:  Med Phys       Date:  2012-02       Impact factor: 4.071

2.  Point/counterpoint. Radiotherapy physicists have become glorified technicians rather than clinical scientists.

Authors:  Howard I Amols; Frank Van den Heuvel; Colin G Orton
Journal:  Med Phys       Date:  2010-04       Impact factor: 4.071

3.  Application of TG-100 risk analysis methods to the acceptance testing and commissioning process of a Halcyon linear accelerator.

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

4.  Commissioning and dosimetric characteristics of TrueBeam system: composite data of three TrueBeam machines.

Authors:  Zheng Chang; Qiuwen Wu; Justus Adamson; Lei Ren; James Bowsher; Hui Yan; Andrew Thomas; Fang-Fang Yin
Journal:  Med Phys       Date:  2012-11       Impact factor: 4.071

5.  Commissioning of the Varian TrueBeam linear accelerator: a multi-institutional study.

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

6.  Technical Note: Flattening filter free beam from Halcyon linac: Evaluation of the profile parameters for quality assurance.

Authors:  A Fogliata; R Cayez; R Garcia; C Khamphan; G Reggiori; M Scorsetti; L Cozzi
Journal:  Med Phys       Date:  2020-05-23       Impact factor: 4.071

7.  Commissioning an Elekta Versa HD linear accelerator.

Authors:  Ganesh Narayanasamy; Daniel Saenz; Wilbert Cruz; Chul S Ha; Niko Papanikolaou; Sotirios Stathakis
Journal:  J Appl Clin Med Phys       Date:  2016-01-08       Impact factor: 2.102

8.  Design and clinical implementation of a TG-106 compliant linear accelerator data management system and MU calculator.

Authors:  Nabil Adnani
Journal:  J Appl Clin Med Phys       Date:  2010-04-30       Impact factor: 2.102

9.  Do the representative beam data for TrueBeam linear accelerators represent average data?

Authors:  Yoshihiro Tanaka; Hirokazu Mizuno; Yuichi Akino; Masaru Isono; Norimasa Masai; Toshijiro Yamamoto
Journal:  J Appl Clin Med Phys       Date:  2019-01-13       Impact factor: 2.102

10.  Experience in commissioning the halcyon linac.

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

View more
  1 in total

Review 1.  Integration of AI and Machine Learning in Radiotherapy QA.

Authors:  Maria F Chan; Alon Witztum; Gilmer Valdes
Journal:  Front Artif Intell       Date:  2020-09-29
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.