Abstract
In this paper, we introduce a dictionary learning based approach applied to the problem of real-time reconstruction of MR image sequences that are highly undersampled in k-space. Unlike traditional dictionary learning, our method integrates both global and patch-wise (local) sparsity information and incorporates some priori information into the reconstruction process. Moreover, we use a Dependent Hierarchical Beta-process as the prior for the group-based dictionary learning, which adaptively infers the dictionary size and the sparsity of each patch; and also ensures that similar patches are manifested in terms of similar dictionary atoms. An efficient numerical algorithm based on the alternating direction method of multipliers (ADMM) is also presented. Through extensive experimental results we show that our proposed method achieves superior reconstruction quality, compared to the other state-of-the- art DL-based methods.
[Display omitted]
•A novel dictionary learning-based algorithm for online reconstruction of dynamic MR images is proposed.•The algorithm consists of both patch-based (local) and global sparsity terms.•The group patching is employed to classify the patches based on their similarities.•A modified dependent hierarchical beta process (dHBP) is utilized as the prior for the dictionary learning process.