Dong Liang1, Edward V. R. DiBella2,
Rong-Rong Chen3, Leslie Ying1
1Department of Electrical
Engineering & Computer Science,University of Wisconsin Milwaukee,
MIlwaukee, WI, United States; 2Department of Radiology,University
of Utah, Salt Lake City, UT, United States; 3Department of
Electrical & Computer Engineering,University of Utah, Salt Lake City, UT,
United States
We study how to obtain and exploit the additional prior information on the support of sparse signals in compressed sensing (CS) reconstruction. We propose a k-t Iterative Support Detection (k-t ISD) method for dynamic cardiac MRI to iteratively learn and utilize the support knowledge in x-f space to improve CS reconstruction. The learned support is incorporated in CS reconstruction by excluding part of the signal at the known support from the cost function in the constrained minimization process. Experiments demonstrate k-t ISD improves the reconstruction quality over the basic CS method in which support information is not exploited.