High Resolution MR Reconstruction with Functionally Separate Neural Networks

The authors propose a new reconstruction method to obtain higher resolution images from an MR acquisition. The method incorporates MR physics and two neural networks, which are functionally separate, for denoising and upsampling. The proposed method was evaluated by applying it to both retrospectively and prospectively undersampled data. The result showed that the proposed technique is capable of reconstructing higher resolution images over a conventional method, by multiplying the matrix size while keeping more detail structure in the originally sampled data.