Gabor Primitives for Accelerated Cardiac Cine MRI Reconstruction

2026-03-05

AI Summary

This work proposes an explicit neural representation method based on Gabor atoms for reconstructing cardiac cine MRI from highly undersampled k-space data. By employing complex exponential-modulated Gaussian envelopes, the approach flexibly localizes spectral support to arbitrary k-space locations and integrates spatiotemporal low-rank decomposition to efficiently model cardiac motion and contrast dynamics. As the first study to introduce Gabor atoms into MRI reconstruction, the method achieves both high-frequency detail preservation and physical interpretability. It consistently outperforms compressed sensing, Gaussian atom-based representations, and hash-grid implicit neural representations under both Cartesian and radial sampling schemes, yielding more compact, continuous, and physically consistent high-quality reconstructions.

Technology Category

• Machine Learning: Representation Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Representation Learning for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

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.

Problem

• accelerated MRI
• cardiac cine
• k-space undersampling
• image reconstruction
• spatiotemporal redundancy

Innovation

• Gabor primitives
• cardiac cine MRI
• implicit neural representations
• k-space reconstruction
• spatiotemporal redundancy