Dependent Nonparametric Bayesian Group Dictionary Learning for online reconstruction of Dynamic MR images

TL;DR

This paper presents a novel dependent nonparametric Bayesian group dictionary learning method for real-time, highly undersampled dynamic MR image reconstruction, integrating global and local sparsity with adaptive dictionary inference.

Contribution

It introduces a hierarchical Bayesian framework with a Dependent Hierarchical Beta-process for adaptive dictionary learning, improving reconstruction quality over existing methods.

Findings

Achieves superior image reconstruction quality.

Effectively infers dictionary size and sparsity.

Handles highly undersampled MR data efficiently.

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.