Comparing deep learning-based auto-segmentation of organs at risk and clinical target volumes to expert inter-observer variability in radiotherapy planning.

Journal: Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology
Published Date: Dec 5, 2019

Abstract

BACKGROUND: Deep learning-based auto-segmented contours (DC) aim to alleviate labour intensive contouring of organs at risk (OAR) and clinical target volumes (CTV). Most previous DC validation studies have a limited number of expert observers for comparison and/or use a validation dataset related to the training dataset. We determine if DC models are comparable to Radiation Oncologist (RO) inter-observer variability on an independent dataset.

Authors

  • Jordan Wong
    BC Cancer - Vancouver Center, Canada. Electronic address: Jordan.wong@bccancer.bc.ca.
  • Allan Fong
    National Center for Human Factors in Healthcare, MedStar Health, Washington, District of Columbia.
  • Nevin McVicar
    BC Cancer - Vancouver Center, Canada. Electronic address: mcvicarn@rvh.on.ca.
  • Sally Smith
    BC Cancer - Victoria Center, Canada. Electronic address: ssmith11@bccancer.bc.ca.
  • Joshua Giambattista
    Saskatchewan Cancer Agency, Regina, Canada; Limbus AI Inc., Regina, Canada. Electronic address: joshua.giambattista@saskcancer.ca.
  • Derek Wells
    BC Cancer - Victoria Center, Canada. Electronic address: DWells@bccancer.bc.ca.
  • Carter Kolbeck
  • Jonathan Giambattista
    Limbus AI Inc., Regina, Canada. Electronic address: jon@limbus.ai.
  • Lovedeep Gondara
    British Columbia Cancer Agency, Vancouver, BC, Canada.
  • Abraham Alexander
    BC Cancer - Victoria Center, Canada. Electronic address: AAlexander3@bccancer.bc.ca.

Keywords

External Resources

Popular Topics
Recent Journals