Low-rank Tensor Assisted K-space Generative Model for Parallel Imaging Reconstruction

TL;DR

This paper introduces LR-KGM, a novel low-rank tensor-based generative model that enhances high-dimensional MRI reconstruction by leveraging tensor structures and low-rank constraints, outperforming existing methods.

Contribution

The paper proposes a new low-rank tensor assisted generative model for parallel MRI reconstruction, transforming multi-channel data into high-dimensional tensors for improved learning and reconstruction.

Findings

Achieved better reconstruction performance than state-of-the-art methods.

Utilized low-rank tensor constraints to improve generative modeling.

Demonstrated effectiveness on high-dimensional MRI data.

Abstract

Although recent deep learning methods, especially generative models, have shown good performance in fast magnetic resonance imaging, there is still much room for improvement in high-dimensional generation. Considering that internal dimensions in score-based generative models have a critical impact on estimating the gradient of the data distribution, we present a new idea, low-rank tensor assisted k-space generative model (LR-KGM), for parallel imaging reconstruction. This means that we transform original prior information into high-dimensional prior information for learning. More specifically, the multi-channel data is constructed into a large Hankel matrix and the matrix is subsequently folded into tensor for prior learning. In the testing phase, the low-rank rotation strategy is utilized to impose low-rank constraints on tensor output of the generative network. Furthermore, we alternately use traditional generative iterations and low-rank high-dimensional tensor iterations for reconstruction. Experimental comparisons with the state-of-the-arts demonstrated that the proposed LR-KGM method achieved better performance.