Gabor Primitives for Accelerated Cardiac Cine MRI Reconstruction

TL;DR

This paper introduces Gabor primitives for accelerated cardiac MRI reconstruction, enabling efficient, interpretable, and high-frequency representation of dynamic cardiac images from undersampled data.

Contribution

It proposes Gabor primitives with spectral support at arbitrary k-space locations, improving over Gaussian primitives and INRs for cardiac cine MRI reconstruction.

Findings

Gabor primitives outperform compressed sensing and Gaussian primitives.

They provide a compact, continuous-resolution, physically meaningful representation.

The method effectively captures both smooth structures and sharp boundaries.

Abstract

Accelerated cardiac cine MRI requires reconstructing spatiotemporal images from highly undersampled k-space data. Implicit neural representations (INRs) enable scan-specific reconstruction without large training datasets, but encode content implicitly in network weights without physically interpretable parameters. Gaussian primitives provide an explicit and geometrically interpretable alternative, but their spectra are confined near the k-space origin, limiting high-frequency representation. We propose Gabor primitives for MRI reconstruction, modulating each Gaussian envelope with a complex exponential to place its spectral support at an arbitrary k-space location, enabling efficient representation of both smooth structures and sharp boundaries. To exploit spatiotemporal redundancy in cardiac cine, we decompose per-primitive temporal variation into a low-rank geometry basis capturing cardiac motion and a signal-intensity basis modeling contrast changes. Experiments on cardiac cine data with Cartesian and radial trajectories show that Gabor primitives consistently outperform compressed sensing, Gaussian primitives, and hash-grid INR baselines, while providing a compact, continuous-resolution representation with physically meaningful parameters.