Re-Visible Dual-Domain Self-Supervised Deep Unfolding Network for MRI Reconstruction

TL;DR

This paper introduces a self-supervised deep unfolding network for MRI reconstruction that effectively utilizes all under-sampled data and incorporates image priors, leading to superior performance without requiring fully-sampled datasets.

Contribution

It proposes a re-visible dual-domain self-supervised learning framework with a novel loss and a deep unfolding network that leverages imaging physics and priors for improved MRI reconstruction.

Findings

Outperforms state-of-the-art methods on fastMRI and IXI datasets.

Effectively utilizes all under-sampled data during training.

Enhances reconstruction quality by integrating image priors and physics-based modeling.

Abstract

Magnetic Resonance Imaging (MRI) is widely used in clinical practice, but suffered from prolonged acquisition time. Although deep learning methods have been proposed to accelerate acquisition and demonstrate promising performance, they rely on high-quality fully-sampled datasets for training in a supervised manner. However, such datasets are time-consuming and expensive-to-collect, which constrains their broader applications. On the other hand, self-supervised methods offer an alternative by enabling learning from under-sampled data alone, but most existing methods rely on further partitioned under-sampled k-space data as model's input for training, resulting in a loss of valuable information. Additionally, their models have not fully incorporated image priors, leading to degraded reconstruction performance. In this paper, we propose a novel re-visible dual-domain self-supervised deep unfolding network to address these issues when only under-sampled datasets are available. Specifically, by incorporating re-visible dual-domain loss, all under-sampled k-space data are utilized during training to mitigate information loss caused by further partitioning. This design enables the model to implicitly adapt to all under-sampled k-space data as input. Additionally, we design a deep unfolding network based on Chambolle and Pock Proximal Point Algorithm (DUN-CP-PPA) to achieve end-to-end reconstruction, incorporating imaging physics and image priors to guide the reconstruction process. By employing a Spatial-Frequency Feature Extraction (SFFE) block to capture global and local feature representation, we enhance the model's efficiency to learn comprehensive image priors. Experiments conducted on the fastMRI and IXI datasets demonstrate that our method significantly outperforms state-of-the-art approaches in terms of reconstruction performance.