Physics-driven deep learning for medical image reconstruction

Abstract

Medical image reconstruction from undersampled acquisitions is an ill-posed problem involving inversion of the imaging operator linking measurement and image domains. Physics-driven (PD) models have gained prominence in reconstruction tasks due to their desirable performance and generalization. These models jointly promote data fidelity and artifact suppression, typically by combining data-consistency mechanisms with learned network modules. Artifact suppression depends on the network’s ability to disentangle artifacts from true tissue signals, both of which can exhibit contextual structure across diverse spatial scales. Convolutional neural networks (CNNs) are strong in capturing local correlations, albeit relatively insensitive to non-local context. While transformers promise to alleviate this limitation, practical implementations frequently involve design compromises to reduce computational cost by balancing local and non-local sensitivity, occasionally resulting in performance comparable to or trailing that of CNNs. To enhance contextual sensitivity without incurring high complexity, we introduce a novel physics-driven autoregressive state-space model (MambaRoll) for medical image reconstruction. In each cascade of its unrolled architecture, MambaRoll employs a physics-driven state-space module (PD-SSM) to aggregate contextual features efficiently at a given spatial scale, and autoregressively predicts finer scale feature maps conditioned on coarser-scale features to capture multi-scale context. Learning across scales is further enhanced via a deep multi-scale decoding (DMSD) loss tailored to the autoregressive prediction task. Demonstrations on accelerated MRI and sparse-view CT reconstructions show that MambaRoll consistently outperforms state-of-the-art data-driven and physics-driven methods based on CNN, transformer, and SSM backbones.