Model-based Convolutional De-Aliasing Network Learning for Parallel MR Imaging
This work addresses the challenge of limited acceleration rates in parallel MR imaging for medical diagnostics, representing an incremental improvement by combining deep learning with model-based reconstruction.
The paper tackled the problem of accelerating parallel MR imaging by proposing a model-based convolutional de-aliasing network to reconstruct images from undersampled k-space data without explicit sensitivity calculation, achieving superior performance in quantitative and qualitative analysis compared to state-of-the-art methods.
Parallel imaging has been an essential technique to accelerate MR imaging. Nevertheless, the acceleration rate is still limited due to the ill-condition and challenges associated with the undersampled reconstruction. In this paper, we propose a model-based convolutional de-aliasing network with adaptive parameter learning to achieve accurate reconstruction from multi-coil undersampled k-space data. Three main contributions have been made: a de-aliasing reconstruction model was proposed to accelerate parallel MR imaging with deep learning exploring both spatial redundancy and multi-coil correlations; a split Bregman iteration algorithm was developed to solve the model efficiently; and unlike most existing parallel imaging methods which rely on the accuracy of the estimated multi-coil sensitivity, the proposed method can perform parallel reconstruction from undersampled data without explicit sensitivity calculation. Evaluations were conducted on \emph{in vivo} brain dataset with a variety of undersampling patterns and different acceleration factors. Our results demonstrated that this method could achieve superior performance in both quantitative and qualitative analysis, compared to three state-of-the-art methods.