摘要：Non-Cartesian sampling is widely used for fast magnetic
resonance imaging (MRI). Accurate and fast image reconstruction from
non-Cartesian k-space data becomes a challenge and gains a lot
of attention. Images provided by conventional direct reconstruction
methods usually bear ringing, streaking, and other leakage artifacts
caused by discontinuous structures. In this paper, we tackle these
problems by analyzing the principal point spread function (PSF) of
non-Cartesian reconstruction and propose a leakage reduction
reconstruction scheme based on discontinuity subtraction. Data
fidelity in k-space is enforced during each iteration.
Multidimensional nonuniform fast Fourier transform (NUFFT)
algorithms are utilized to simulate the k-space samples as well as to reconstruct images. The proposed method is
compared to the direct reconstruction method on computer-simulated
phantoms and physical scans. Non-Cartesian sampling trajectories
including 2D spiral, 2D and 3D radial trajectories are studied. The
proposed method is found useful on reducing artifacts due to high
image discontinuities. It also improves the quality of images
reconstructed from undersampled data.
