A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction

The acquisition of Magnetic Resonance Imaging (MRI) is inherently slow. Inspired by recent advances in deep learning, we propose a framework for reconstructing MR images from undersampled data using a deep cascade of convolutional neural networks to accelerate the data acquisition process. We show t...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Schlemper, Jo, Caballero, Jose, Hajnal, Joseph V, Price, Anthony, Rueckert, Daniel
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 01.03.2017
Subjects
Artificial neural networks
Image acquisition
Image reconstruction
Machine learning
Magnetic resonance imaging
Neural networks
NMR
Nuclear magnetic resonance
Online AccessGet full text

Cover

More Information
Summary:The acquisition of Magnetic Resonance Imaging (MRI) is inherently slow. Inspired by recent advances in deep learning, we propose a framework for reconstructing MR images from undersampled data using a deep cascade of convolutional neural networks to accelerate the data acquisition process. We show that for Cartesian undersampling of 2D cardiac MR images, the proposed method outperforms the state-of-the-art compressed sensing approaches, such as dictionary learning-based MRI (DLMRI) reconstruction, in terms of reconstruction error, perceptual quality and reconstruction speed for both 3-fold and 6-fold undersampling. Compared to DLMRI, the error produced by the method proposed is approximately twice as small, allowing to preserve anatomical structures more faithfully. Using our method, each image can be reconstructed in 23 ms, which is fast enough to enable real-time applications.
ISSN:2331-8422