Learning-based and unrolled motion-compensated reconstruction for cardiac MR CINE imaging

TL;DR

This paper introduces a learning-based, self-supervised, unrolled motion-compensated reconstruction framework for cardiac MR imaging that jointly estimates motion and reconstructs high-quality images from highly undersampled data.

Contribution

It presents a novel dynamic motion estimation integrated into an unrolled optimization, improving cardiac MR reconstruction under high acceleration rates.

Findings

Reconstructs high-quality images at high acceleration rates.

Joint optimization benefits both motion estimation and image reconstruction.

Outperforms state-of-the-art methods on cardiac MR datasets.

Abstract

Motion-compensated MR reconstruction (MCMR) is a powerful concept with considerable potential, consisting of two coupled sub-problems: Motion estimation, assuming a known image, and image reconstruction, assuming known motion. In this work, we propose a learning-based self-supervised framework for MCMR, to efficiently deal with non-rigid motion corruption in cardiac MR imaging. Contrary to conventional MCMR methods in which the motion is estimated prior to reconstruction and remains unchanged during the iterative optimization process, we introduce a dynamic motion estimation process and embed it into the unrolled optimization. We establish a cardiac motion estimation network that leverages temporal information via a group-wise registration approach, and carry out a joint optimization between the motion estimation and reconstruction. Experiments on 40 acquired 2D cardiac MR CINE datasets demonstrate that the proposed unrolled MCMR framework can reconstruct high quality MR images at high acceleration rates where other state-of-the-art methods fail. We also show that the joint optimization mechanism is mutually beneficial for both sub-tasks, i.e., motion estimation and image reconstruction, especially when the MR image is highly undersampled.