Single- versus multi-model in the deep learning prediction of monitor units per control point for automated treatment planning in prostate cancer.

Journal: Journal of applied clinical medical physics
Published Date: Sep 1, 2025

Abstract

BACKGROUND: In contemporary radiation therapy, the radiation is modulated to conform the prescription dose to the tumor and spare organs at risk. The modulation results from a complex mathematical calculation that requires several iterations to reach a satisfactory solution, delaying treatment. The monitor units (MU) per control point (CP) control the dose magnitude and may be predicted by deep learning, a type of artificial intelligence (AI).

Authors

  • Mathieu Gaudreault
    Peter MacCallum Cancer Centre, Melbourne, Victoria 3000, Australia; Sir Peter MacCallum Department of Oncology, The University of Melbourne, Victoria 3000, Australia. Electronic address: mathieu.gaudreault@petermac.org.
  • Lachlan McIntosh
    Department of Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, 3000, Australia.
  • Katrina Woodford
    Alfred Health Radiation Oncology, The Alfred, Melbourne, Victoria, Australia.
  • Jason Li
    Department of Bioinformatics, Genentech, Inc., South San Francisco, California.
  • Susan Harden
    Peter MacCallum Cancer Centre, Melbourne, Victoria 3000, Australia; Sir Peter MacCallum Department of Oncology, The University of Melbourne, Victoria 3000, Australia.
  • Sandro Porceddu
    Peter MacCallum Cancer Centre, Melbourne, Victoria 3000, Australia; Sir Peter MacCallum Department of Oncology, The University of Melbourne, Victoria 3000, Australia.
  • Vanessa Panettieri
    Alfred Health Radiation Oncology, The Alfred, Melbourne, Victoria, Australia.
  • Nicholas Hardcastle
    Department of Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, Victoria, Australia.

Keywords

External Resources

Popular Topics
Recent Journals