DUN-SRE: Deep Unrolling Network with Spatiotemporal Rotation Equivariance for Dynamic MRI Reconstruction

2025-06-12

AI Summary

To address the challenge of modeling spatiotemporal rotational symmetry under highly undersampled dynamic MRI, this paper proposes the first deep unrolling network with joint spatiotemporal rotational equivariance. Methodologically, we design a (2+1)D equivariant convolution that unifies data consistency and proximal mapping, and introduce a high-fidelity group-filter parameterization to preserve representational capacity under stringent symmetry constraints. Our core contribution is the first formulation of joint rotational equivariance across both spatial and temporal dimensions for dynamic MRI reconstruction. Evaluated on cardiac CINE MRI, our method achieves state-of-the-art performance, significantly improving reconstruction fidelity—particularly for rotationally symmetric structures such as myocardium—while demonstrating strong generalizability to diverse dynamic MRI reconstruction tasks.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Learning with Manifolds
• Computer Vision: Multi-modal Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Dynamic Magnetic Resonance Imaging (MRI) exhibits transformation symmetries, including spatial rotation symmetry within individual frames and temporal symmetry along the time dimension. Explicit incorporation of these symmetry priors in the reconstruction model can significantly improve image quality, especially under aggressive undersampling scenarios. Recently, Equivariant convolutional neural network (ECNN) has shown great promise in exploiting spatial symmetry priors. However, existing ECNNs critically fail to model temporal symmetry, arguably the most universal and informative structural prior in dynamic MRI reconstruction. To tackle this issue, we propose a novel Deep Unrolling Network with Spatiotemporal Rotation Equivariance (DUN-SRE) for Dynamic MRI Reconstruction. The DUN-SRE establishes spatiotemporal equivariance through a (2+1)D equivariant convolutional architecture. In particular, it integrates both the data consistency and proximal mapping module into a unified deep unrolling framework. This architecture ensures rigorous propagation of spatiotemporal rotation symmetry constraints throughout the reconstruction process, enabling more physically accurate modeling of cardiac motion dynamics in cine MRI. In addition, a high-fidelity group filter parameterization mechanism is developed to maintain representation precision while enforcing symmetry constraints. Comprehensive experiments on Cardiac CINE MRI datasets demonstrate that DUN-SRE achieves state-of-the-art performance, particularly in preserving rotation-symmetric structures, offering strong generalization capability to a broad range of dynamic MRI reconstruction tasks.

Problem

• Incorporating spatiotemporal symmetry in dynamic MRI reconstruction
• Modeling temporal symmetry for accurate cardiac motion dynamics
• Improving image quality under aggressive undersampling scenarios

Innovation

• Spatiotemporal equivariant convolutional architecture
• Deep unrolling framework integration
• High-fidelity group filter parameterization