Treatment plan prediction for lung IMRT using deep learning based fluence map generation.

Journal: Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)
Published Date:

Abstract

PURPOSE: Recently, it has been shown that automated treatment planning can be executed by direct fluence prediction from patient anatomy using convolutional neural networks. Proof of principle publications utilise a fixed dose prescription and fixed collimator (0°) and gantry angles. The goal of this work is to further develop these principles for the challenging lung cancer indication with variable dose prescriptions, collimator and gantry angles. First we investigate the impact of clinical applicable collimator angles and various input parameters. Then, the model is tested in a complete user independent planning workflow.

Authors

  • Liesbeth Vandewinckele
    Department Oncology, Laboratory of Experimental Radiotherapy, KU Leuven, Belgium; Department of Radiation Oncology, UZ Leuven, Belgium. Electronic address: liesbeth.vandewinckele@uzleuven.be.
  • Siri Willems
    ESAT/PSI, KU Leuven Belgium & MIRC, UZ Leuven, Belgium.
  • Maarten Lambrecht
    Department of Oncology, Laboratory of Experimental Radiotherapy, KU Leuven, Belgium; Department of Radiation Oncology, UZ Leuven, Belgium.
  • Patrick Berkovic
    Department of Oncology, Laboratory of Experimental Radiotherapy, KU Leuven, Belgium; Department of Radiation Oncology, UZ Leuven, Belgium.
  • Frederik Maes
    Department of Electrical Engineering (ESAT/PSI), KU Leuven, Kasteelpark Arenberg 10/2446, 3001, Leuven, Belgium; Medical Imaging Research Center (MIRC), UZ Leuven, Herestraat 49, 3000, Leuven, Belgium. Electronic address: frederik.maes@kuleuven.be.
  • Wouter Crijns
    Department Oncology, Laboratory of Experimental Radiotherapy, KU Leuven, Belgium; Department of Radiation Oncology, UZ Leuven, Belgium. Electronic address: wouter.crijns@uzleuven.be.