Complex extension of optical flow and its practical evaluation for undersampled dynamic MRI

TL;DR

This paper extends optical flow to complex-valued images for undersampled dynamic MRI, demonstrating improved image quality in cardiac MRI datasets by incorporating a motion model into reconstruction.

Contribution

It introduces a complex-valued optical flow model for MRI, enhancing motion estimation and image reconstruction from undersampled data.

Findings

Improved image quality in cardiac MRI datasets.

Effective motion modeling for undersampled MRI data.

Abstract

Reconstructing high-quality images from undersampled dynamic MRI data is a challenging task and important for the success of this imaging modality. To remedy the naturally occurring artifacts due to measurement undersampling, one can incorporate a motion model into the reconstruction so that information can propagate across time frames. Current models for MRI imaging are using the optical flow equation. However, they are based on real-valued images. Here, we generalise the optical flow equation to complex-valued images and demonstrate, based on two real cardiac MRI datasets, that the new model is capable of improving image quality.