en
Scientific article
English

A new deep convolutional neural network design with efficient learning capability: Application to CT image synthesis from MRI

Published inMedical Physics, vol. 47, no. 10, p. 5158-5171
Publication date2020
Abstract

Despite the proven utility of multiparametric magnetic resonance imaging (MRI) in radiation therapy, MRI-guided radiation treatment planning is limited by the fact that MRI does not directly provide the electron density map required for absorbed dose calculation. In this work, a new deep convolutional neural network model with efficient learning capability, suitable for applications where the number of training subjects is limited, is proposed to generate accurate synthetic CT (sCT) images from MRI.

Keywords
  • ATLAS
  • MRI
  • Deep learning
  • Machine learning
  • Pseudo-CT generation
Funding
Citation (ISO format)
BAHRAMI, Abass et al. A new deep convolutional neural network design with efficient learning capability: Application to CT image synthesis from MRI. In: Medical Physics, 2020, vol. 47, n° 10, p. 5158–5171. doi: 10.1002/mp.14418
Main files (1)
Article (Published version)
accessLevelRestricted
Identifiers
ISSN of the journal0094-2405
202views
0downloads

Technical informations

Creation09/07/2020 10:23:00 AM
First validation09/07/2020 10:23:00 AM
Update time03/15/2023 10:51:45 PM
Status update03/15/2023 10:51:44 PM
Last indexation01/17/2024 11:15:21 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack