Enhao Gong1, Tao Zhang1, Joseph Cheng1, Shreyas Vasanawala2, and John Pauly1
1Electrical Engineering, Stanford University, Stanford, CA, United States, 2Radiology, Stanford University, Stanford, CA, United States
Low-Rank
methods are widely applied to improve reconstruction for Dynamic Contrast
Enhanced (DCE) MRI by imposing linear spatial-temporal correlation in
global, local or multiple scales. This assumption does not fully capture the highly
nonlinear spatial-temporal dynamics of DCE signals. We proposed a generalized
Kernelized-Low-Rank model, assumed Low-Rank property after nonlinear transform and
solved it by Regularizing singular-values with Adaptive Nonlinear Kernels. The
proposed method captures the spatial-temporal dynamics as a sparser
representation and achieves more accurate reconstruction results.
Kernelized-Low-Rank model can be easily integrated to provide
significant improvements to Global Low-Rank, Locally Low-Rank, LR+S and
Multi-scale LR models.
