Region of Interest Compressed Sensing MRI

Amaresha Shridhar Konar, Jain A. Divyaa, Shamshia Tabassum, Rajagopalan Sundaresan, Julianna Czum, Barjor Gimi, Ramesh D.R. Babu, Sairam Geethanatha


Compressed Sensing (CS) based Magnetic Resonance Imaging(MRI) reconstruction relies on data sparsity. Region of Interest Compressed Sensing (ROICS) is based on the hypothesis that superior CS performance can be obtained by limiting the sparsity objective and data consistency in CS to a Region of Interest (ROI). This relaxation is justified in most applications where the anatomy of interest such as the heart, has surrounding structures, typically not used for further analyses. ROICS has been proposed as an extension of CS that is ROI weighted CS. Current work demonstrates the implementation of ROICS for the first time on MR cardiac and brain data. Reconstructed images and performance evaluation metrics show that ROICS technique performs better than conventiona lCS technique. CS and Parallel Imaging (PI) are widely used to reduce MRI scan time and their combination yields better performance than used individually. The proposed method also implements the combination of ROICS and SENSitivity Encoding (SENSE), which applies weighted CSto a particular ROI, and the resulting output is then reconstructed using SENSE for arbitrary k-space. Proposed ROICS-PI performs better as comparedto PI and CS + PI.

Full Text:



Lustig, Michael, David Donoho, and John M. Pauly. Sparse

MRI: The application of compressed sensing for rapid MR

imaging. Magnetic resonance in medicine 58.6 (2007):


Sairam Geethanath, Rashmi Reddy, Amaresha Shridhar

Konar, Shaikh Imam, Rajagopalan Sundaresan, Ramesh

Babu D.R, Ramesh Venkatesan. Compressed Sensing MRI:

A review. Critical reviews in biomedical engineering 41.3

(2013): 183–204.

Larkman, David J., and Rita G. Nunes. Parallel magnetic

resonance imaging. Physics in medicine and biology 52.7

(2007): R15.

Candès, Emmanuel J., Justin Romberg, and Terence Tao.

Robust uncertainty principles: Exact signal reconstruction

from highly incomplete frequency information.

Information Theory, IEEE Transactions on 52.2 (2006):


Jung Hong, Kyunghyun Sung, Krishna S Nayak, Eung

Yeop Kim, and Jong Chul Ye. k-t FOCUSS: A general compressed sensing framework for high resolution dynamic

MRI. Magnetic Resonance in Medicine 61, no. 1 (2009):


Amaresha Shridhar Konar, Steen Moeller, Julianna

Czum, Barjor Gimi, Sairam Geethanath. Region of interest

compressive sensing (ROICS). In Proceedings of the

st Annual Meeting of ISMRM, Salt Lake City, USA,

p. 3801.

Kim, Yoon-Chul, Shrikanth S. Narayanan, and Krishna S

Nayak. Accelerated 3D MRI of vocal tract shaping using

compressed sensing and parallel imaging. IEEE, International

Conference on Acoustics, Speech and Signal

Processing (ICASSP) (2009) 389–392.

Murphy, Mark, Marcus Alley, James Demmel, Kurt

Keutzer, Shreyas Vasanawala, and Michael Lustig. Fast

-SPIRiT Compressed Sensing Parallel Imaging MRI:

Scalable Parallel Implementation and Clinically Feasible

Runtime. IEEE Transactions on Medical Imaging 31, no. 6

(2012): 1250–1262.

Liang D, Liu B, Wang JJ, and Ying L. Accelerating SENSE

using compressed sensing. Magnetic Resonance in Medicine

(2009): 1574–1584.

Wu B, Millane RP, Watts R, Bones P. Prior estimate-based

compressed sensing in parallel MRI. Magnetic Resonance

in Medicine 63(2011): 83 –95.

Fischer A, Seiberlich N, Blaimer M, Jakob P, Breuer F, and

Griswold M. A combination of Nonconvex Compressed

Sensing and GRAPPA (CS-GRAPPA). In proceedings

of the 17th annual meeting of ISMRM, Hawaii (2009)

P 2813.

Beatty PJ, King KF, Marinelli L, Hardy CJ, Lustig M.

Sequential application of parallel imaging and compressed

sensing. In proceedings of the 17th annual meeting

of ISMRM, Hawaii (2009) P 2824.

Liu B, Sebert FM, ZouY, Ying L, SparseSENSE: Randomly-

sampled parallel imaging using compressed sensing.

In proceedings of the 16th annual meeting of ISMRM,

Toronto, 2008, P 3154.

Zhao C, Lang T, Ji J. Compressed sensing parallel imaging. In proceedings of the 16th annual meeting of ISMRM,

Toronto (2008) P 1478.

King KF. Combining compressed sensing and parallel

imaging. In proceedings of the 16th annual meeting of

ISMRM, Toronto, (2008) P 1488.

Amaresha Shridhar Konar, Divya Jain, Shamshia

Tabassum, Rajagopalan Sundaresan, Ramesh Venkatesan,

Sairam Geethanath. ROICS-PI: Combination of Region

of Interest Compressed Sensing and Parallel Imaging

for Arbitrary k-space Trajectories to Achieve Highly

Accelerated MRI.In Proceedings of the 22nd Annual

Meeting of ISMRM, Milan, Italy, 2014, P 1558.

Hansen, Per Christian, and Dianne Prost O’Leary. The use

of the L-curve in the regularization of discrete ill-posed

problems. SIAM Journal on Scientific Computing 14,

no. 6 (1993): 1487–1503.

Grissom, William, Chun-yu Yip, Zhenghui Zhang,

V Andrew Stenger, Jeffrey A Fessler, and Douglas C Noll.

Spatial domain method for the design of RF pulses in

multicoil parallel excitation. Magnetic resonance in

medicine 56, no. 3 (2006): 620–629.

Pruessmann, Klaas P., Markus Weiger, Markus B.

Scheidegger, and Peter Boesiger. SENSE: Sensitivity

encoding for fast MRI. Magnetic resonance in medicine

, no. 5 (1999): 952–962.

Griswold, Mark A, Peter M Jakob, Robin MHeidemann,

Mathias Nittka, Vladimir Jellus, Jianmin Wang, Berthold

Kiefer, and Axel Haase. Generalized autocalibrating

partially parallel acquisitions (GRAPPA). Magnetic

Resonance in Medicine 47, no. 6 (2002): 1202–1210.

Fessler, Jeffrey A, and Bradley P Sutton. Nonuniform fast

Fourier transforms using min-max interpolation.IEEE

Transactions on Signal Processing 51, no. 2(2003): 560–574.

Pruessmann, Klaas P., Markus Weiger, Peter Börnert, and

Peter Boesiger. Advances in sensitivity encoding with

arbitrary k-space trajectories. Magnetic Resonance in

Medicine 46, no. 4 (2001): 638–651.

Dai, Yu-Hong, and Yaxiang Yuan. A nonlinear conjugate

gradient method with a strong global convergence property.

SIAM Journal on Optimization 10, no. 1 (1999):


Chen, Guang-Hong, Jie Tang, and ShuaiLeng. Prior image

constrained compressed sensing (PICCS): a method to

accurately reconstruct dynamic CT images from highly

undersampled projection data sets. Medical physics 35,

no. 2 (2008): 660–663.

Choi, Kihwan, Jing Wang, Lei Zhu, Tae-Suk Suh, Stephen

Boyd, and Lei Xing. Compressed sensing based cone-beam

computed tomography reconstruction with a first-order

method. Medical Physics 37, no. 9 (2010): 5113–5125.


  • There are currently no refbacks.