Deep learning-based reconstruction of in vivo pelvis conductivity with a 3D patch-based convolutional neural network trained on simulated MR data.

Journal: Magnetic resonance in medicine
Published Date:

Abstract

PURPOSE: To demonstrate that mapping pelvis conductivity at 3T with deep learning (DL) is feasible.

Authors

  • Soraya Gavazzi
    Department of Radiotherapy, University Medical Center Utrecht, Utrecht, The Netherlands.
  • Cornelis A T van den Berg
    Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, The Netherlands.
  • Mark H F Savenije
    Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, The Netherlands.
  • H Petra Kok
    Department of Radiation Oncology, Amsterdam University Medical Center, Amsterdam, The Netherlands.
  • Peter de Boer
    Radiotherapy Institute Friesland, Leeuwarden, The Netherlands.
  • Lukas J A Stalpers
    Department of Radiation Oncology, Amsterdam University Medical Center, Amsterdam, The Netherlands.
  • Jan J W Lagendijk
    Department of Radiotherapy, University Medical Center Utrecht, Utrecht, The Netherlands.
  • Hans Crezee
    Department of Radiation Oncology, Amsterdam University Medical Center, Amsterdam, The Netherlands.
  • Astrid L H M W van Lier
    Department of Radiotherapy, University Medical Center Utrecht, Utrecht, The Netherlands.