Altmetric

Convolutional recurrent neural networks for dynamic MR image reconstruction

File Description SizeFormat 
clean-copy-convolutional (2).pdfAccepted version3.02 MBAdobe PDFView/Open
Title: Convolutional recurrent neural networks for dynamic MR image reconstruction
Authors: Qin, C
Hajnal, JV
Rueckert, D
Schlemper, J
Caballero, J
Price, AN
Item Type: Journal Article
Abstract: Accelerating the data acquisition of dynamic magnetic resonance imaging (MRI) leads to a challenging ill-posed inverse problem, which has received great interest from both the signal processing and machine learning communities over the last decades. The key ingredient to the problem is how to exploit the temporal correlations of the MR sequence to resolve aliasing artefacts. Traditionally, such observation led to a formulation of an optimisation problem, which was solved using iterative algorithms. Recently, however, deep learning based-approaches have gained significant popularity due to their ability to solve general inverse problems. In this work, we propose a unique, novel convolutional recurrent neural network (CRNN) architecture which reconstructs high quality cardiac MR images from highly undersampled k-space data by jointly exploiting the dependencies of the temporal sequences as well as the iterative nature of the traditional optimisation algorithms. In particular, the proposed architecture embeds the structure of the traditional iterative algorithms, efficiently modelling the recurrence of the iterative reconstruction stages by using recurrent hidden connections over such iterations. In addition, spatio-temporal dependencies are simultaneously learnt by exploiting bidirectional recurrent hidden connections across time sequences. The proposed method is able to learn both the temporal dependency and the iterative reconstruction process effectively with only a very small number of parameters, while outperforming current MR reconstruction methods in terms of reconstruction accuracy and speed.
Issue Date: 1-Jan-2019
Date of Acceptance: 1-Aug-2018
URI: http://hdl.handle.net/10044/1/61981
DOI: https://dx.doi.org/10.1109/TMI.2018.2863670
ISSN: 0278-0062
Publisher: Institute of Electrical and Electronics Engineers
Start Page: 280
End Page: 290
Journal / Book Title: IEEE Transactions on Medical Imaging
Volume: 38
Issue: 1
Copyright Statement: © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: EP/P001009/1
Keywords: Science & Technology
Technology
Life Sciences & Biomedicine
Computer Science, Interdisciplinary Applications
Engineering, Biomedical
Engineering, Electrical & Electronic
Imaging Science & Photographic Technology
Radiology, Nuclear Medicine & Medical Imaging
Computer Science
Engineering
Recurrent neural network
convolutional neural network
dynamic magnetic resonance imaging
cardiac image reconstruction
K-T BLAST
LOW-RANK
SENSE
SPARSITY
08 Information and Computing Sciences
09 Engineering
Nuclear Medicine & Medical Imaging
Publication Status: Published
Conference Place: United States
Online Publication Date: 2018-08-06
Appears in Collections:Faculty of Engineering
Computing



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons