Meeting Banner
Abstract #0605

Compressed Sensing ASL Perfusion Imaging Using Adaptive Nonlinear Sparsifying Transforms

Yihang Zhou1, 2, Yanhua Wang1, 2, Jie Zheng3, Leslie Ying1, 2

1Department of Electrical Engineering, University at Buffalo, Buffalo, NY, United States; 2Department of Biomedical Engineering, University at Buffalo, Buffalo, NY, United States; 3Department of Radiology, Washington University, St. Louis, MO, United States

In this study, a broader family of nonlinear transforms is investigated for sparse representation of dynamic images in compressed sensing (CS). We propose a novel kernel-based CS method that implicitly and adaptively sparsifies the dynamic image series of interest using nonlinear transforms. The proposed method is evaluated using accelerated arterial spin labeled perfusion data. It is shown to be able to better preserve the spatial and temporal information than the conventional CS method with linear transforms.

Abstract PDF Presentation Video

Keywords

able abrupt acquisition adapt adaptive aliasing although among applied arterial artifacts better biomedical blood broader buffalo calf central certain circles column component components compressed conjugate conversion converted curves denotes designed details dictionaries difficulty dimensional domain driven dynamic electrical enabled engineering equations evaluated expected exploit expressed family fashion feature final finite form frame full fully function gained gradient highly holds implicitly indicated intensity investigated involves kernel kernels kinetic learned learning least linear machine mapped mapping maps matrix muscle myocardial needs nonlinear novel onto optimization orange original parallel particular pattern patterns performance perfusion popularity preserve preserving principal principle problem propose proposed radiology random rapid reconstruct reconstructed reconstruction reconstructions reduced reduction relationship represent representing represents resolution restricted retrospectively sampled scalar sensing series serious sets since solve solving space sparely sparsely sparseness sparser spatial specifically spin square still suggest superior suppress take taken temporal thereby tissue training transform transforms variation variations vector wavelet widely worth