Deep learning-based single image super-resolution for low-field MR brain images

Scientific Reports, vol. 12, pp. 6362

Abstract

Low-field MRI scanners are significantly less expensive than their high-field counterparts, which gives them the potential to make MRI technology more accessible all around the world. In general, images acquired using low-field MRI scanners tend to be of a relatively low resolution, as signal-to-noise ratios are lower. The aim of this work is to improve the resolution of these images. To this end, we present a deep learning-based approach to transform low-resolution low-field MR images into high-resolution ones. A convolutional neural network was trained to carry out single image super-resolution reconstruction using pairs of noisy low-resolution images and their noise-free high-resolution counterparts, which were obtained from the publicly available NYU fastMRI database. This network was subsequently applied to noisy images acquired using a low-field MRI scanner. The trained convolutional network yielded sharp super-resolution images in which most of the high-frequency components were recovered. In conclusion, we showed that a deep learning-based approach has great potential when it comes to increasing the resolution of low-field MR images.

Authors 6

1. M. L. de Leeuw den Bouter corresponding

   Delft University of Technology

   Affiliation as printed

   Delft Institute of Applied Mathematics, Delft University of Technology, Delft, The Netherlands. M.L.deLeeuwdenBouter-1@tudelft.nl

   Delft Institute of Applied Mathematics, Delft University of Technology, Delft, The Netherlands

2. Giuseppe Ippolito

   ASML (Netherlands)

   Affiliation as printed

   Department of Metrology, ASML Netherlands, Veldhoven, The Netherlands

3. Thomas O’Reilly Aachen C.J. Gorter Center for High Field MRI

   Leiden University Medical Center

   Affiliation as printed

   C.J. Gorter Center for High-Field MRI, Leiden University Medical Center, Leiden, The Netherlands

4. Rob Remis

   Delft University of Technology

   Affiliation as printed

   Circuits and Systems, Delft University of Technology, Delft, The Netherlands

5. Martin B. van Gijzen

   Delft University of Technology

   Affiliation as printed

   Delft Institute of Applied Mathematics, Delft University of Technology, Delft, The Netherlands

6. ANDREW G. WEBB Aachen C.J. Gorter Center for High Field MRI

   Leiden University Medical Center · Delft University of Technology

   Affiliation as printed

   C.J. Gorter Center for High-Field MRI, Leiden University Medical Center, Leiden, The Netherlands

   Circuits and Systems, Delft University of Technology, Delft, The Netherlands