Automatic Quality Assessment of Transperineal Ultrasound Images of the Male Pelvic Region, Using Deep Learning.

Journal: Ultrasound in medicine & biology
Published Date: Nov 25, 2019

Abstract

Ultrasound guidance is not in widespread use in prostate cancer radiotherapy workflows. This can be partially attributed to the need for image interpretation by a trained operator during ultrasound image acquisition. In this work, a one-class regressor, based on DenseNet and Gaussian processes, was implemented to automatically assess the quality of transperineal ultrasound images of the male pelvic region. The implemented deep learning approach was tested on 300 transperineal ultrasound images and it achieved a scoring accuracy of 94%, a specificity of 95% and a sensitivity of 92% with respect to the majority vote of 3 experts, which was comparable with the results of these experts. This is the first step toward a fully automatic workflow, which could potentially remove the need for ultrasound image interpretation and make real-time volumetric organ tracking in the radiotherapy environment using ultrasound more appealing.

Authors

  • S M Camps
    Faculty of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands; Oncology Solutions Department, Philips Research, Eindhoven, The Netherlands.
  • T Houben
    Faculty of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
  • G Carneiro
    Australian Centre of Visual Technologies, The University of Adelaide, Adelaide, Australia.
  • C Edwards
    School of Clinical Sciences, Queensland University of Technology, Brisbane, Queensland, Australia.
  • M Antico
    Institute of Health & Biomedical Innovation, Queensland University of Technology, Brisbane, Queensland, Australia; School of Chemistry, Physics and Mechanical Engineering, Queensland University of Technology, Brisbane, Queensland, Australia.
  • M Dunnhofer
    Department of Mathematics, Computer Science and Physics, University of Udine, Udine, Italy.
  • E G H J Martens
    Department of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht, The Netherlands.
  • J A Baeza
    Department of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht, The Netherlands.
  • B G L Vanneste
    Department of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht, The Netherlands.
  • E J van Limbergen
    Department of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht, The Netherlands.
  • P H N de With
    Faculty of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
  • F Verhaegen
    Department of Radiation Oncology (MAASTRO), GROW-School for Oncology and Developmental Biology, Maastricht, The Netherlands.
  • D Fontanarosa
    School of Clinical Sciences, Queensland University of Technology, Brisbane, Queensland, Australia; Institute of Health & Biomedical Innovation, Queensland University of Technology, Brisbane, Queensland, Australia. Electronic address: d3.fontanarosa@qut.edu.au.

Keywords

External Resources

Popular Topics
Recent Journals