Reconstruction of Cardiac Cine MRI Using Motion-Guided Deformable Alignment and Multi-Resolution Fusion
Not on the map. Why?
Abstract (arXiv)
Cardiac cine magnetic resonance imaging (MRI) is one of the important means to assess cardiac functions and vascular abnormalities. Mitigating artifacts arising during image reconstruction and accelerating cardiac cine MRI acquisition to obtain high-quality images is important. A novel end-to-end deep learning network is developed to improve cardiac cine MRI reconstruction. First, a U-Net is adopted to obtain the initial reconstructed images in k-space. Further to remove the motion artifacts, the motion-guided deformable alignment (MGDA) module with second-order bidirectional propagation is introduced to align the adjacent cine MRI frames by maximizing spatial-temporal information to alleviate motion artifacts. Finally, the multi-resolution fusion (MRF) module is designed to correct the blur and artifacts generated from alignment operation and obtain the last high-quality reconstructed cardiac images. At an 8× acceleration rate, the numerical measurements on the ACDC dataset are structural similarity index (SSIM) of 78.40%±.57%, peak signal-to-noise ratio (PSNR) of 30.46±1.22dB, and normalized mean squared error (NMSE) of 0.0468±0.0075. On the ACMRI dataset, the results are SSIM of 87.65%±4.20%, PSNR of 30.04±1.18dB, and NMSE of 0.0473±0.0072. The proposed method exhibits high-quality results with richer details and fewer artifacts for cardiac cine MRI reconstruction on different accelerations.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 53 references that are in the map. First posted on arXiv 9 Mar 2023.
Builds on
22 of 53 references.
References · 22
- 2017Attention Is All You Needcited by 60,361
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2017Deformable Convolutional Networkscited by 1,488
- 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
- 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 494
- 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 424
- 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 342
- 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 232
- 2017Image reconstruction by domain transform manifold learningcited by 232
- 2018TDAN: Temporally Deformable Alignment Network for Video Super-Resolutioncited by 226
- 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
10 more
- 2020Understanding Deformable Alignment in Video Super-Resolutioncited by 78
- 2018Deep Residual Learning for Accelerated MRI using Magnitude and Phase Networkscited by 53
- 2021Recurrent Variational Network: A Deep Learning Inverse Problem Solver applied to the task of Accelerated MRI Reconstructioncited by 34
- 2021Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledgecited by 11
- 2022Learning-based and unrolled motion-compensated reconstruction for cardiac MR CINE imagingcited by 11
- 2018Denoising of 3-D Magnetic Resonance Images Using a Residual Encoder-Decoder Wasserstein Generative Adversarial Networkcited by 7
- 2018Compressed Sensing Plus Motion (CS+M): A New Perspective for Improving Undersampled MR Image Reconstructioncited by 7
- 2023EDMAE: An Efficient Decoupled Masked Autoencoder for Standard View Identification in Pediatric Echocardiographycited by 4
- 2018Model-based free-breathing cardiac MRI reconstruction using deep learned & STORM priors: MoDL-STORMcited by 2
- 2022LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Imagescited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.