Deep learning-based digitization of prostate brachytherapy needles in ultrasound images.

Journal: Medical physics
Published Date:

Abstract

PURPOSE: To develop, and evaluate the performance of, a deep learning-based three-dimensional (3D) convolutional neural network (CNN) artificial intelligence (AI) algorithm aimed at finding needles in ultrasound images used in prostate brachytherapy.

Authors

  • Christoffer Andersén
    Department of Medical Physics, Faculty of Medicine and Health, Örebro University, Örebro, Sweden.
  • Tobias Rydén
    Department of Medical Physics and Bioengineering, Sahlgrenska University Hospital, Gothenburg, Sweden.
  • Per Thunberg
    Department of Medical Physics, Faculty of Medicine and Health, Örebro University, Örebro, Sweden.
  • Jakob H Lagerlöf
    Department of Medical Physics, Faculty of Medicine and Health, Örebro University, Örebro, Sweden.