Radiation dose calculation in 3D heterogeneous media using artificial neural networks.

Journal: Medical physics
PMID:

Abstract

PURPOSE: External beam radiotherapy (EBRT) treatment planning requires a fast and accurate method of calculating the dose delivered by a clinical treatment plan. However, existing methods of calculating dose distributions have limitations. Monte Carlo (MC) methods are accurate but can take too long to be clinically viable. Deterministic approaches are quicker but can be inaccurate under certain conditions, particularly near heterogeneities and air interfaces. Neural networks trained on MC-derived data have the potential to reproduce dose distributions that agree closely with the MC method while being significantly quicker to deploy.

Authors

  • James Keal
    School of Physical Sciences, University of Adelaide, SA, 5005, Australia.
  • Alexandre Santos
    School of Physical Sciences, University of Adelaide, SA, 5005, Australia.
  • Scott Penfold
    School of Physical Sciences, University of Adelaide, SA, 5005, Australia.
  • Michael Douglass
    School of Physical Sciences, University of Adelaide, SA, 5005, Australia.