Real Time Dynamic Magnetic Resonance Imaging via Dictionary Learning and Combined Fourier Transform

Real time dynamic magnetic resonance imaging (dMRI) requires that the image acquisition and reconstruction are carried out simultaneously and the reconstruction speed catches up with imaging speed. In this paper, a novel compressed sensing (CS) reconstruction algorithm for real time dynamic MRI is proposed. The first frame with more k-space measurements is reconstructed precisely as the reference image. Different from previous methods who start their reconstructions from zero-filled k-space measurements, a Combined Fourier Transform (CFT) algorithm is implemented in our method, which can dynamically aggregate the k-space measurements from previous sampled frames to create a highly accurate predictive image for the current frame. We then combine the CFT algorithm with a 3D path-based dictionary leaning algorithm, which is named as DLCFT in our work for fast real time dMRI reconstruction. The proposed algorithm is compared with four state-of-the-art online and offline methods on two real and complex perfusion MR sequences and a real functional brain MR sequence. Experimental results show that the proposed algorithm outperforms these methods with faster convergence and higher reconstruction accuracy.