IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 34, NO. 12, DECEMBER 2015 2459
LRTV: MR Image Super-Resolution With Low-Rank
and Total Variation Regularizations
Feng Shi, Jian Cheng, Li Wang, Pew-Thian Yap, Senior Member, IEEE, and Dinggang Shen*, Senior Member, IEEE
Abstract—Image super-resolution (SR) aims to recover
high-resolution images from their low-resolution counterparts
for improving image analysis and visualization. Interpolation
methods, widely used for this purpose, often result in images
with blurred edges and blocking effects. More advanced methods
such as total variation (TV) retain edge sharpness during image
recovery. However, these methods only utilize information from
local neighborhoods, neglecting useful information from remote
voxels. In this paper, we propose a novel image SR method that
integrates both local and global information for effective image
recovery. This is achieved by, in addition to TV, low-rank regu-
larization that enables utilization of information throughout the
image. The optimization problem can be solved effectively via al-
ternating direction method of multipliers (ADMM). Experiments
on MR images of both adult and pediatric subjects demonstrate
that the proposed method enhances the details in the recovered
high-resolution images, and outperforms methods such as the
nearest-neighbor interpolation, cubic interpolation, iterative
back projection (IBP), non-local means (NLM), and TV-based
up-sampling.
Index Terms—Image enhancement, image sampling, matrix
completion, sparse learning, spatial resolution.
I. INTRODUCTION
H
IGH-RESOLUTION (HR) medical images provide rich
structural details that
are critical for accurate image
post-processing and pathological assessment of bodily organs
[1]–[10]. However, image resolution is limited by factors such
Manuscript received January 22, 2015; revised May 05, 2015; accepted May
17, 2015. Date of publication June 01, 2015; date of current version November
25, 2015. This work was supported in part by National Institutes of Health
Grants MH100217, EB006733, EB008374, EB009634, AG041721, AG042599,
MH088520, and the National Research Foundation under Grant 2012-005741
from the Korean government. F. Shi and J. Cheng contributed equally to this
work. Asterisk indicates corresponding author.
F. Shi, L. Wang, and P.-T. Yap are with the Department of Radiology and
Biomedical Research Imaging Center, University of North Carolina, Chapel
Hill, NC 27599 USA (e-mail: fengshi@med.unc.edu; li_wang@med.unc.edu;
pewthian_yap@med.unc.edu).
J. Cheng is with Department of Radiology and Biomedical Research Imaging
Center, University of North Carolina, Chapel Hill, NC 27599 USA, and also
with the Section on Tissue Biophysics and Biomimetics, Program on Pediatric
Imaging and Tissue Sciences, National Institute of Child Health and Human
Development, National Institutes of Health, Bethesda, MD 20892 USA (e-mail:
jian.cheng.1983@gmail.com).
*D. Shen is with the Department of Radiology and Biomedical Research
Imaging Center (BRIC), University of North Carolina at Chapel Hill, NC
27599 USA, and also with the Department of Brain and Cognitive Engineering,
Korea University, Seoul 136-713, Korea and also with the Department of Brain
and Cognitive Engineering, Korea University, Seoul 136-713, Korea (e-mail:
dinggang_shen@med.unc.edu).
Color versions of one or more of the figures in this paper are available online
at http://ieeexplore.ieee.org.
Digital Object Identifier 10.1109/TMI.2015.2437894
as imaging hardware, signal to noise ratio (SNR), and time con-
straints. Image SNR is proportional to voxel size and the square
root of the number of averages in the voxel. Reducing the
voxel size from 2
2 2 to 1 1 1 will require
64 averages for similar SNR [11]. This requires significantly
longer scanning time, which may not be practical clinically.
A possible alternative approach to this problem is image post-
processing. For this, interpolation methods (nearest neighbor,
linear, and spine) are generally employed due to their simplicity.
However, as pointed out in [1], interpolation methods gener-
ally blur the sharp edges, introduce blocking artifacts in lines,
and are unable to recover fine details. In view of this, we take
a super-resolution (SR) approach for resolution enhancement
of LR images [3]. Interpolation methods are not considered as
SR methods since they do not consider the image degradation
process (e.g., blurring, and down-sampling). Multi-frame SR
algorithms reconstruct a HR image from multiple LR im
ages
[12], [13]. These LR images are typically acquired repeatedly
with slightly shifted field of view (FOV). In this paper, we pro-
pose a single-frame SR algorithm that requires t
he acquisition
of only one LR image. A number of methods have been pro-
posed for single-image SR [3]. For example, iterative back-pro-
jection (IBP) was proposed to estimate the H
R image by back
projecting the difference between the LR image simulated based
on the estimated HR image via imaging blur and the input LR
image [14]. This process is repeate
d to minimize the energy of
the difference. Non-local means (NLM) is a method proposed
to take advantage of image self-similarity [15]. Specifically, the
input LR image is first denoised
and the similar patches are used
to reconstruct to a HR image. A correction step is then applied to
ensure that the down-sampled HR image is close to the denoised
LR image. The reconstruc
tion and correction steps are iterated
in a multi-scale manner. In another work, NLM was employed
to enhance the resolution of a single LR T2 image with the guid-
ance from an HR T1 ima
ge [16].
Matrix completion algorithms have recently been shown to
be effective in estimating missing values in a matrix from a
small sample of
known entries [17]–[19]. For instance, it has
been applied to the famous Netflix problem where one needs to
infer user preference for unrated movies based on only a small
number of r
ated movies [20]. Matrix completion methods as-
sume that the recovered matrix has low rank and then uses this
property as a constraint or regularization to minimize the dif-
ferenc
e between the given incomplete matrix and the estimated
matrix. Candes et al. proved that, low-rank matrices can be per-
fectly recovered from a small number of given entries under
som
e conditions [18]. In image processing, one advantage of
matrix completion is that the remote information from the whole
0278-0062 © 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.
See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.