Guided MRI Reconstruction via Schr\"odinger Bridge

TL;DR

This paper introduces a novel MRI reconstruction method using Schr"odinger Bridge that explicitly models structural correspondence between contrasts, significantly improving reconstruction quality from undersampled data.

Contribution

It proposes $ ext{I}^2$SB-Inversion, a multi-contrast guided MRI reconstruction framework based on Schr"odinger Bridge with an inversion strategy for misalignment correction.

Findings

Achieves up to 14.4x acceleration in MRI reconstruction.

Outperforms existing methods in quantitative evaluations.

Effectively mitigates artifacts and improves accuracy.

Abstract

Magnetic Resonance Imaging (MRI) is an inherently multi-contrast modality, where cross-contrast priors can be exploited to improve image reconstruction from undersampled data. Recently, diffusion models have shown remarkable performance in MRI reconstruction. However, they still struggle to effectively utilize such priors, mainly because existing methods rely on feature-level fusion in image or latent spaces, which lacks explicit structural correspondence and thus leads to suboptimal performance. To address this issue, we propose $\mathbf{I}^2$SB-Inversion, a multi-contrast guided reconstruction framework based on the Schr\"odinger Bridge (SB). The proposed method performs pixel-wise translation between paired contrasts, providing explicit structural constraints between the guidance and target images. Furthermore, an Inversion strategy is introduced to correct inter-modality misalignment, which often occurs in guided reconstruction, thereby mitigating artifacts and improving reconstruction accuracy. Experiments on paired T1- and T2-weighted datasets demonstrate that $\mathbf{I}^2$SB-Inversion achieves a high acceleration factor of up to 14.4 and consistently outperforms existing methods in both quantitative and qualitative evaluations.