SRE-CNN: A Spatiotemporal Rotation-Equivariant CNN for Cardiac Cine MR Imaging

TL;DR

This paper introduces SRE-CNN, a novel spatiotemporal rotation-equivariant CNN that leverages symmetry priors in dynamic MR images to improve high-resolution cardiac cine image reconstruction, especially under high undersampling.

Contribution

The paper proposes a new framework that fully exploits rotation symmetries in both spatial and temporal dimensions for dynamic MR imaging, including a high-precision filter design and a temporal-equivariant convolutional module.

Findings

Outperforms existing methods in reconstructing detailed cardiac images

Effective in highly undersampled (up to 20X) dynamic MR data

Demonstrates superior quantitative and qualitative results

Abstract

Dynamic MR images possess various transformation symmetries,including the rotation symmetry of local features within the image and along the temporal dimension. Utilizing these symmetries as prior knowledge can facilitate dynamic MR imaging with high spatiotemporal resolution. Equivariant CNN is an effective tool to leverage the symmetry priors. However, current equivariant CNN methods fail to fully exploit these symmetry priors in dynamic MR imaging. In this work, we propose a novel framework of Spatiotemporal Rotation-Equivariant CNN (SRE-CNN), spanning from the underlying high-precision filter design to the construction of the temporal-equivariant convolutional module and imaging model, to fully harness the rotation symmetries inherent in dynamic MR images. The temporal-equivariant convolutional module enables exploitation the rotation symmetries in both spatial and temporal dimensions, while the high-precision convolutional filter, based on parametrization strategy, enhances the utilization of rotation symmetry of local features to improve the reconstruction of detailed anatomical structures. Experiments conducted on highly undersampled dynamic cardiac cine data (up to 20X) have demonstrated the superior performance of our proposed approach, both quantitatively and qualitatively.