Back to Physics: Operator-Guided Generative Paths for SMS MRI Reconstruction

TL;DR

This paper introduces an operator-guided framework and a novel neural network architecture for improved SMS MRI reconstruction, explicitly modeling acquisition operators to enhance fidelity and reduce slice leakage.

Contribution

It proposes an operator-guided approach with OCDI-Net that models degradation trajectories and performs chained inference for better SMS MRI reconstruction.

Findings

Improved fidelity over conventional methods

Reduced slice leakage in MRI reconstructions

Effective on both brain and diffusion MRI data

Abstract

Simultaneous multi-slice (SMS) imaging with in-plane undersampling enables highly accelerated MRI but yields a strongly coupled inverse problem with deterministic inter-slice interference and missing k-space data. Most diffusion-based reconstructions are formulated around Gaussian-noise corruption and rely on additional consistency steps to incorporate SMS physics, which can be mismatched to the operator-governed degradations in SMS acquisition. We propose an operator-guided framework that models the degradation trajectory using known acquisition operators and inverts this process via deterministic updates. Within this framework, we introduce an operator-conditional dual-stream interaction network (OCDI-Net) that explicitly disentangles target-slice content from inter-slice interference and predicts structured degradations for operator-aligned inversion, and we instantiate reconstruction as a two-stage chained inference procedure that performs SMS slice separation followed by in-plane completion. Experiments on fastMRI brain data and prospectively acquired in vivo diffusion MRI data demonstrate improved fidelity and reduced slice leakage over conventional and learning-based SMS reconstructions.