Quantifying and visualising uncertainty in deep learning-based segmentation for radiation therapy treatment planning: What do radiation oncologists and therapists want?

Journal: Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology
Published Date: Sep 24, 2024

Abstract

BACKGROUND AND PURPOSE: During the ESTRO 2023 physics workshop on "AI for the fully automated radiotherapy treatment chain", the topic of deep learning (DL) segmentation was discussed. Despite its widespread use in radiotherapy, the time needed to evaluate and correct DL segmentations remains burdensome. While segmentation uncertainty could be beneficial for clinicians, there is a lack of understanding on what information should be presented to ease their task. This study aimed to gather insights from clinicians on uncertainty visualisation options.

Authors

  • M Huet-Dastarac
    Molecular Imaging, Radiation and Oncology lab (MIRO), UCLouvain, Brussels, Belgium. Electronic address: margerie.huet@uclouvain.be.
  • N M C van Acht
    Catharina Hospital Eindhoven - department of radiation oncology, Eindhoven, The Netherlands; Eindhoven University of Technology - Department of Electrical Engineering and Department of Applied Physics and Science Education, Eindhoven, The Netherlands.
  • F C Maruccio
    The Netherlands Cancer Institute (NKI), Department of Radiation Oncology, Amsterdam, The Netherlands.
  • J E van Aalst
    University of Groningen, University Medical Center Groningen, Department of Radiation Oncology, Groningen, The Netherlands; University of Twente, Department of Technical Medicine, Enschede, The Netherlands.
  • J C J van Oorschodt
    Catharina Hospital Eindhoven - department of radiation oncology, Eindhoven, The Netherlands; Eindhoven University of Technology - Department of Electrical Engineering and Department of Applied Physics and Science Education, Eindhoven, The Netherlands.
  • F Cnossen
    University of Groningen, Department of Artificial Intelligence, Groningen, The Netherlands.
  • T M Janssen
    The Netherlands Cancer Institute (NKI), Department of Radiation Oncology, Amsterdam, The Netherlands.
  • C L Brouwer
    University of Groningen, University Medical Center Groningen, Department of Radiation Oncology, Groningen, The Netherlands.
  • A Barragan Montero
    Molecular Imaging, Radiation and Oncology lab (MIRO), UCLouvain, Brussels, Belgium.
  • C W Hurkmans
    Catharina Hospital Eindhoven - department of radiation oncology, Eindhoven, The Netherlands; Eindhoven University of Technology - Department of Electrical Engineering and Department of Applied Physics and Science Education, Eindhoven, The Netherlands.

Keywords

External Resources

Popular Topics
Recent Journals