Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction

TL;DR

This paper introduces a two-stage MRI reconstruction method that fills missing k-space data and refines images using prompt-based learning, effectively handling multi-contrast and dynamic MRI data with improved performance.

Contribution

The paper proposes PromptMR, a flexible prompt-based learning approach for all-in-one MRI reconstruction across various contrasts and views, addressing limitations of existing unrolled models.

Findings

Significantly outperforms previous MRI reconstruction methods.

Effectively handles multi-contrast and dynamic MRI data.

Reduces the need for separate models for different input types.

Abstract

The key to dynamic or multi-contrast magnetic resonance imaging (MRI) reconstruction lies in exploring inter-frame or inter-contrast information. Currently, the unrolled model, an approach combining iterative MRI reconstruction steps with learnable neural network layers, stands as the best-performing method for MRI reconstruction. However, there are two main limitations to overcome: firstly, the unrolled model structure and GPU memory constraints restrict the capacity of each denoising block in the network, impeding the effective extraction of detailed features for reconstruction; secondly, the existing model lacks the flexibility to adapt to variations in the input, such as different contrasts, resolutions or views, necessitating the training of separate models for each input type, which is inefficient and may lead to insufficient reconstruction. In this paper, we propose a two-stage MRI reconstruction pipeline to address these limitations. The first stage involves filling the missing k-space data, which we approach as a physics-based reconstruction problem. We first propose a simple yet efficient baseline model, which utilizes adjacent frames/contrasts and channel attention to capture the inherent inter-frame/-contrast correlation. Then, we extend the baseline model to a prompt-based learning approach, PromptMR, for all-in-one MRI reconstruction from different views, contrasts, adjacent types, and acceleration factors. The second stage is to refine the reconstruction from the first stage, which we treat as a general video restoration problem to further fuse features from neighboring frames/contrasts in the image domain. Extensive experiments show that our proposed method significantly outperforms previous state-of-the-art accelerated MRI reconstruction methods.