Paper Info
Title
A kernel-based compressed sensing approach to dynamic MRI from highly undersampled data
Abstract
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.
Year
DOI
Venue
2013
10.1109/ISBI.2013.6556474
ISBI
Keywords
Field
DocType
state-of-the-art method,dynamic asl-based perfusion mri,dynamic image sequence reconstruction,dynamic mri,image reconstruction,compressed sensing,feature extraction,biomedical mri,image sequences,kernel-based compressed sensing approach,high dimensional feature space,feature space,principle component analysis,kernel method,data acquisition time,medical image processing,nonlinear transformation,magnetic resonance imaging,kernel
Iterative reconstruction,Kernel (linear algebra),Computer vision,Feature vector,Pattern recognition,Computer science,Feature extraction,Linear map,Artificial intelligence,Kernel method,Dynamic contrast-enhanced MRI,Compressed sensing
Conference
ISSN
ISBN
Citations 
1945-7928
978-1-4673-6456-0
7
PageRank 
References 
Authors
0.54
5
3
Name
Order
Citations
PageRank
Yihang Zhou1113.04
Yanhua Wang2476.35
Leslie Ying324029.08