Deep Parallel MRI Reconstruction Network Without Coil Sensitivities
This addresses a major bottleneck in real-world parallel MRI applications by eliminating the need for error-prone sensitivity map estimation, potentially improving image reconstruction reliability.
The paper tackles the problem of parallel MRI reconstruction without needing coil sensitivity maps, which are difficult to estimate accurately, by proposing a deep neural network that adaptively combines multi-coil images and uses a nonlinear encoder for sparse feature extraction, achieving promising performance on various datasets.
We propose a novel deep neural network architecture by mapping the robust proximal gradient scheme for fast image reconstruction in parallel MRI (pMRI) with regularization function trained from data. The proposed network learns to adaptively combine the multi-coil images from incomplete pMRI data into a single image with homogeneous contrast, which is then passed to a nonlinear encoder to efficiently extract sparse features of the image. Unlike most of existing deep image reconstruction networks, our network does not require knowledge of sensitivity maps, which can be difficult to estimate accurately, and have been a major bottleneck of image reconstruction in real-world pMRI applications. The experimental results demonstrate the promising performance of our method on a variety of pMRI imaging data sets.