TY - GEN
T1 - A kernel-based compressed sensing approach to dynamic MRI from highly undersampled data
AU - Zhou, Yihang
AU - Wang, Yanhua
AU - Ying, Leslie
PY - 2013
Y1 - 2013
N2 - Compressed sensing (CS) has been used in dynamic MRI to reduce the data acquisition time. Several sparsifying transforms have been investigated to sparsify the dynamic image sequence. Most existing works have studied linear transformations only. In this paper, we proposed a novel kernel-based compressed sensing approach to dynamic MRI. The method represents the image sequence sparsely and adaptively using nonlinear transformations. Such nonlinearity is implemented using the kernel method, which maps the acquired undersampled k-space data onto a high dimensional feature space, then reconstructs the image sequence in the corresponding feature space using the conventional compressed sensing, and finally convert the image sequence back into the original space. Experimental results demonstrate that the proposed method improves the reconstruction quality of dynamic ASL-based perfusion MRI over the state-of-the-art method where linear transform is used.
AB - Compressed sensing (CS) has been used in dynamic MRI to reduce the data acquisition time. Several sparsifying transforms have been investigated to sparsify the dynamic image sequence. Most existing works have studied linear transformations only. In this paper, we proposed a novel kernel-based compressed sensing approach to dynamic MRI. The method represents the image sequence sparsely and adaptively using nonlinear transformations. Such nonlinearity is implemented using the kernel method, which maps the acquired undersampled k-space data onto a high dimensional feature space, then reconstructs the image sequence in the corresponding feature space using the conventional compressed sensing, and finally convert the image sequence back into the original space. Experimental results demonstrate that the proposed method improves the reconstruction quality of dynamic ASL-based perfusion MRI over the state-of-the-art method where linear transform is used.
KW - compressed sensing
KW - Dynamic MRI
KW - feature space
KW - kernel method
KW - nonlinear transformation
KW - principle component analysis
UR - http://www.scopus.com/inward/record.url?scp=84881646443&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2013.6556474
DO - 10.1109/ISBI.2013.6556474
M3 - Conference contribution
AN - SCOPUS:84881646443
SN - 9781467364546
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 310
EP - 313
BT - ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging
T2 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013
Y2 - 7 April 2013 through 11 April 2013
ER -