DeepcomplexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution

Word count: 4980 Abstract Purpose: To accelerate MR scan, this paper incorporates deep learning into fast MR imaging by exploiting deep residual neural network with complex convolution for parallel MR image (DeepMRI) reconstruction from undersampled multi-coil measurements. Methods: DeepMRI draws and utilizes prior knowledge from a large number of existing fullysampled multi-coil measurements for accurate online fast imaging. It designs and trains an offline deep residual convolutional neural network to describe the mapping relationship between the MR images reconstructed from the undersampled and fully-sampled k-space data. Specifically, complex convolution was proposed to consider the intercorrelation between the real and imaginary parts. Furthermore, both k-space data fidelity and image space proximity are considered for the network training. Results: The evaluations on in vivo datasets show that the proposed DeepMRI has strong capability in capturing image information that are lost in the zero-filled MR images. The comparison with the classical SPIRiT and L1-SPIRiT has demonstrated that DeepMRI can reconstruct MR images more accurately.