Although tremendous progress has been made in
the past to get High resolution 3D cardiac MRI but still it is
considered as area of concern in the medical image
processing filed. The existing anisotropic 2D stack volumes
are typical, and improving the resolution of these is strongly
motivated by both visualization and analysis. The lack of
suitable reconstruction techniques that handle non-rigid
motion means that cardiac image enhancement is still often
attained by simple interpolation. A novel approach is
proposed in this paper which accurately precise the High
resolution 3D cardiac MRI in easy way. We explore the use of
example-based super-resolution, to enable high fidelity patchbased
reconstruction, using training data that does not need
to be accurately aligned with the target data.
P.Hari Prasad : post graduate student of
ASIST,Paritala,His area of interest
image processing.
N.Suresh : worked as an assistant professor in
ECE Dept of ASIST,Paritala,His area of I
nterests are EDC,Signal processing.
S.Koteswararao : Graduated in Electronics
Communication Engineering from
Dr.S.G.I.E.T and post graduated in
instrumentation and Control Systems from
JNTUK, Kakinada, Submitted his thesis to
JNTUK, Kakinada his research interests
includes optimized routing for Wireless sensor
networks and Digital communication.
MRI Analysis, Patch, Super resolution,
Reconstruction, Dictionary building
A novel approach is proposed in this paper which
accurately precise the High resolution 3D cardiac MRI in
easy way. We explore the use of example-based superresolution,
to enable high fidelity patch-based
reconstruction, using training data that does not need to be
accurately aligned with the target data. By moving to a
patch scale, we are able to exploit the data redundancy
present in cardiac image sequences, without the need for
registration. To do this, dictionaries of high-resolution and
low-resolution patches are co-trained on high-resolution
sequences, in order to enforce a common relationship
between high- and low-resolution patch representations.
These dictionaries are then used to reconstruct from a lowresolution
view of the same anatomy. We demonstrate
marked improvements of the reconstruction algorithm over
standard interpolation.
[1] J. Caballero, D. Rueckert, and J. V. Hajnal, “Dictionary
learning and time sparsity in dynamic mri,” in MICCAI
(1), 2012, pp. 256–263.
[2] S. U. Rahman and S. Wesarg, “Combining short-axis
and long-axis cardiac mr images by applying a
superresolution reconstruction algorithm,” in SPIE
Med. Im., 2010, p. 7623.
[3] A. Gholipour, J. A. Estroff, and S. K. Warfield,
“Robust super-resolution volume reconstruction from
sliceacquisitions: application to fetal brain mri,” IEEE
Trans. Med. Imag., vol. 29(10), pp. 1739–1758, 2010.
[4] J. V. Manjon, P. Coupe, A. Buades, D. L. Collins, and
M. Robles, “Mri superresolution using self-similarity
and image priors,” Int J. Biomed. Imaging, 2010. Fig.
4. Example reconstruction of real MRI frames. First
two rows: adult dataset. Bottom two rows: neonatal
dataset. (j) Original (k) Bicubic (l) Proposed
[5] F. Rousseau, “A non-local approach for image
superresolution using intermodality priors,” Medical
Image Analysis, vol. 14, pp. 594–605, 2010.
[6] W. Shi, J. Caballero, C. Ledig, X. Zhuang, W. Bai, K.
Bhatia, A. Marvao, T. Dawes, D. O’Regan, and D.
Rueckert, “Cardiac image super-resolution with global
correspondence using multi-atlas patchmatch,” in
MICCAI, 2013.
[7] R. Zeyde, M. Elad, and M. Protter, “On single image
scale-up using sparse-representations,” in 7th International Conference on Curves and Survaces,
2012.
[8] A. Rueda, N. Malpica, and E. Romero, “Single-image
super-resolution of brain mr images using
overcomplete dictionaries,” Medical Image Analysis,
vol. 17(1), pp. 113–132, 2013.
[9] H. Greenspan, “Super-resolution in medical imaging,”
The Computer Journal, vol. 52(1), 2009.
[10] M. Aharon, M. Elad, and A. Bruckstein, “Ksvd: an
aglorithm for designing overcomplete dictionaries
for sparse representation,” IEEE Trans. Sig. Proc.,
vol. 54(11), 2006.