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

arXiv: https://arxiv.org/abs/2209.03671 · HTML: https://mlsanity.com/paper/2209.03671/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 8 Sep 2022.

## Builds on (most cited first, 10 of 10)

- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Learning a Variational Network for Reconstruction of Accelerated MRI Data](https://mlsanity.com/paper/1704.00447/) (2017)
- [Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces](https://mlsanity.com/paper/1903.03545/) (2019)
- [An Unsupervised Learning Model for Deformable Medical Image Registration](https://mlsanity.com/paper/1802.02604/) (2018)
- [Conditional Deformable Image Registration with Convolutional Neural Network](https://mlsanity.com/paper/2106.12673/) (2021)
- [Deep Low-rank plus Sparse Network for Dynamic MR Imaging](https://mlsanity.com/paper/2010.13677/) (2020)
- [Complementary Time-Frequency Domain Networks for Dynamic Parallel MR Image Reconstruction](https://mlsanity.com/paper/2012.11974/) (2020)
- [Compressed Sensing Plus Motion (CS+M): A New Perspective for Improving Undersampled MR Image Reconstruction](https://mlsanity.com/paper/1810.10828/) (2018)
- [Learning Optical Flow for Fast MRI Reconstruction](https://mlsanity.com/paper/2004.10464/) (2020)

## Built on by (most cited first, 11 of 11)

- [Deep Learning for Retrospective Motion Correction in MRI: A Comprehensive Review](https://mlsanity.com/paper/2305.06739/) (2023)
- [Towards Cardiac MRI Foundation Models: Comprehensive Visual-Tabular Representations for Whole-Heart Assessment and Beyond](https://mlsanity.com/paper/2504.13037/) (2025)
- [Accelerated Motion Correction with Deep Generative Diffusion Models](https://mlsanity.com/paper/2211.00199/) (2022)
- [Mamba? Catch The Hype Or Rethink What Really Helps for Image Registration](https://mlsanity.com/paper/2407.19274/) (2024)
- [Motion-compensated MR CINE reconstruction with reconstruction-driven motion estimation](https://mlsanity.com/paper/2302.02504/) (2023)
- [Global k-Space Interpolation for Dynamic MRI Reconstruction using Masked Image Modeling](https://mlsanity.com/paper/2307.12672/) (2023)
- [Classification, Regression and Segmentation directly from k-Space in Cardiac MRI](https://mlsanity.com/paper/2407.20108/) (2024)
- [Attention-aware non-rigid image registration for accelerated MR imaging](https://mlsanity.com/paper/2404.17621/) (2024)
- [SRE-CNN: A Spatiotemporal Rotation-Equivariant CNN for Cardiac Cine MR Imaging](https://mlsanity.com/paper/2409.08537/) (2024)
- [Reconstruction of Cardiac Cine MRI Using Motion-Guided Deformable Alignment and Multi-Resolution Fusion](https://mlsanity.com/paper/2303.04968/) (2023)
- [Prospective Dynamic 3D MRI Reconstruction via Latent-Space Motion Tracking from Single Measurement](https://mlsanity.com/paper/2606.04249/) (2026)

## Abstract (arXiv)

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.