Unsupervised reconstruction of accelerated cardiac cine MRI using neural fields.

Journal: Computers in biology and medicine
PMID:

Abstract

BACKGROUND: Cardiac cine MRI is the gold standard for cardiac functional assessment, but the inherently slow acquisition process creates the necessity of reconstruction approaches for accelerated undersampled acquisitions. Several regularization approaches that exploit spatial-temporal redundancy have been proposed to reconstruct undersampled cardiac cine MRI. More recently, methods based on supervised deep learning have been also proposed to further accelerate acquisition and reconstruction. However, these techniques rely on usually large dataset for training, which are not always available and might introduce biases.

Authors

  • Tabita Catalán
    Millennium Nucleus for Applied Control and Inverse Problems, Santiago, Chile; Millennium Institute for Intelligent Healthcare Engineering, Santiago, Chile.
  • Matías Courdurier
    Department of Mathematics, Pontificia Universidad Católica de Chile, Santiago, Chile.
  • Axel Osses
    Center for Mathematical Modeling and Department of Mathematical Engineering, Universidad de Chile, Santiago, Chile.
  • Anastasia Fotaki
    School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK; Royal Brompton Hospital, Guy's and St Thomas' NHS Foundation Trust, London, UK. Electronic address: anastasia.fotaki@kcl.ac.uk.
  • Rene Botnar
    School of Biomedical Engineering & Imaging Sciences, King's College, London, UK.
  • Francisco Sahli-Costabal
    Department of Mechanical and Metallurgical Engineering, Institute for Biological and Medical Engineering, Pontificia Universidad Catolica de Chile, Santiago, Chile.
  • Claudia Prieto
    School of Biomedical Engineering & Imaging Sciences, King's College, London, UK.