Modeling a 6 MV FFF Beam from the CyberKnife M6 to Produce Data for Training Artificial Neural Networks
Source abstract
Abstract
A Monte Carlo-based model of the CyberKnife M6 6 MV Flattening Filter-Free (FFF) beam was developed to produce the data that can be used to train artificial neural networks. The data include the energy spectra of the beam, its average energy, the spatial distributions of the beam, and the distributions of the photon propagation directions for two selected radiation fields—a large one with a diameter of 60 mm, and a small one with a diameter of 15 mm. The GEANT4 code was used to develop the beam model. The developed model was verified by comparing the depth-dose distributions along the beam axis and the profiles obtained in both simulations and measurements. The data included in this paper, intended for training neural networks, will be made available via Google Drive.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Radiotherapy Techniques · Radiation Therapy and Dosimetry · Radiation Shielding Materials Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Physics, University of Silesia in Katowice, 40-007 Katowice, Poland
Maria Sklodowska-Curie National Research Institute of Oncology, Gliwice Branch, Department of Medical Physics, 44-102 Gliwice, Poland
Faculty of Science and Technology, University of Silesia in Katowice, 40-007 Katowice, Poland
References (28)
Show source-provided references
1. Modeling silicon diode dose response factors for small photon fields10.1088/0031-9155/55/24/002 ↗
2. Monte Carlo calculated correction factors for diodes and ion chambers in small photon fields10.1088/0031-9155/58/8/2431 ↗
3. Small fields: Nonequilibrium radiation dosimetry10.1118/1.2815356 ↗
4. Comparison of depth-dose distributions of proton therapeutic beams calculated by means of logical detectors and ionization chamber modeled in Monte Carlo codes10.1016/j.nima.2016.04.090 ↗
5. Energy spectra in water for the 6 MV X-ray therapeutic beam generated by Clinac-2300 linac10.1016/j.radmeas.2014.11.008 ↗
6. Determination of Energy Spectra in Water for 6 MV X Rays from a Medical Linac10.5506/APhysPolB.47.783 ↗
7. Sarrut, D., Etxebeste, A., Muñoz, E., Krah, N., and Létang, J.M. (2021). Artificial Intelligence for Monte Carlo Simulation in Medical Physics. Front. Phys., 9.10.3389/fphy.2021.738112 ↗
8. X-ray dose profiles using artificial neural networks10.1016/j.apradiso.2022.110575 ↗
9. Deep MC: A deep learning method for efficient Monte Carlo beamlet dose calculation by predictive denoising in magnetic resonance-guided radiotherapy10.1088/1361-6560/abca01 ↗
10. Denoising proton therapy Monte Carlo dose distributions in multiple tumor sites: A comparative neural networks architecture study10.1016/j.ejmp.2021.07.022 ↗
11. Machine Learning-Based Denoising Techniques for Monte Carlo Rendering: A Literature Review
12. Machine learning-based denoising of surface solar irradiance simulated with Monte Carlo ray tracing
13. Measurement of linear accelerator spectra, reconstructed from percentage depth dose curves by neural networks10.1016/j.ejmp.2022.02.019 ↗
14. Radiotherapy dose prediction using off -the-shelf segmentation networks: A feasibility study with GammaPod planning10.1002/mp.17711 ↗
15. A narrative review on radiotherapy practice in the era of artificial intelligence: How relevant is the medical physicist?10.21037/jmai-22-27 ↗
16. (2025, December 03). GEANT4 Project Website. Available online: https://geant4.web.cern.ch/.
17. GEANT4—A simulation toolkit10.1016/S0168-9002(03)01368-8 ↗
18. GEANT4 developments and applications10.1109/TNS.2006.869826 ↗
19. (2025, December 03). IAEA Website. Available online: https://www.iaea.org/resources/databases/photon-and-electron-interaction-data.
20. GEANT4 simulation of electron energy deposition in extended media10.1016/j.nimb.2007.02.088 ↗
21. Validation of the GEANT4 electromagnetic photon cross sections for elements and compounds10.1016/j.nima.2010.02.112 ↗
22. Recent improvements in GEANT4 electromagnetic physics models and interfaces10.15669/pnst.2.898 ↗
23. Irradiation of gold nanoparticles by x-rays: Monte Carlo simulation of dose enhancements and the spatial properties of the secondary electrons production10.1118/1.3539623 ↗
24. A low energy bound atomic electron Compton scattering model for GEANT410.1016/j.nimb.2014.07.042 ↗
25. Fitting and benchmarking of dosimetry data for new brachytherapy sources10.1118/1.1308278 ↗
26. Monte Carlo calculation of nine megavoltage photon beam spectra using the BEAM code10.1118/1.1445413 ↗
27. Monte Carlo simulated correction factors for output factor measurement with the CyberKnife system-results for new detectors and correction factor dependence on measurement distance and detector orientation10.1088/0031-9155/59/6/N11 ↗
28. Monte Carlo simulated corrections for beam commissioning measurements with circular and MLC shaped fields on the CyberKnife M6 System: A study including diode, microchamber, point scintillator, and synthetic microdiamond detectors10.1088/1361-6560/aa5610 ↗