Self-supervised Learning for MRI Reconstruction with a Parallel Network Training Framework

  title={Self-supervised Learning for MRI Reconstruction with a Parallel Network Training Framework},
  author={Chen Hu and Cheng Li and Haifeng Wang and Qiegen Liu and Hairong Zheng and Shanshan Wang},
  • Chen Hu, Cheng Li, +3 authors Shanshan Wang
  • Published in MICCAI 26 September 2021
  • Computer Science, Engineering
Image reconstruction from undersampled k-space data plays an important role in accelerating the acquisition of MR data, and a lot of deep learning-based methods have been exploited recently. Despite the achieved inspiring results, the optimization of these methods commonly relies on the fully-sampled reference data, which are time-consuming and difficult to collect. To address this issue, we propose a novel selfsupervised learning method. Specifically, during model optimization, two subsets are… Expand

Figures and Tables from this paper


Deep learning for fast MR imaging: A review for learning reconstruction from incomplete k-space data
This survey aims to review deep learning based MR image reconstruction works from 2016- June 2020 and will discuss merits, limitations and challenges associated with such methods, as a starting point for researchers interested in contributing to this field. Expand
DeepcomplexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution
This paper proposes a multi-channel image reconstruction method, named DeepcomplexMRI, to accelerate parallel MR imaging with residual complex convolutional neural network, and takes advantage of the availability of a large number of existing multi-Channel groudtruth images and uses them as target data to train the deep residual convolutionAL neural network offline. Expand
Deep ADMM-Net for Compressive Sensing MRI
Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that the proposed novel ADMM-Net algorithm significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed. Expand
MoDL: Model-Based Deep Learning Architecture for Inverse Problems
This work introduces a model-based image reconstruction framework with a convolution neural network (CNN)-based regularization prior, and proposes to enforce data-consistency by using numerical optimization blocks, such as conjugate gradients algorithm within the network. Expand
Accelerating magnetic resonance imaging via deep learning
This paper proposes a deep learning approach for accelerating magnetic resonance imaging (MRI) using a large number of existing high quality MR images as the training datasets. An off-lineExpand
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
  • J. Zhang, Bernard Ghanem
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
This paper proposes a novel structured deep network, dubbed ISTA-Net, which is inspired by the Iterative Shrinkage-Thresholding Algorithm (ISTA) for optimizing a general $$ norm CS reconstruction model and develops an effective strategy to solve the proximal mapping associated with the sparsity-inducing regularizer using nonlinear transforms. Expand
Deep Generative Adversarial Neural Networks for Compressive Sensing MRI
A novel CS framework that uses generative adversarial networks (GAN) to model the (low-dimensional) manifold of high-quality MR images that retrieves higher quality images with improved fine texture details compared with conventional Wavelet-based and dictionary- learning-based CS schemes as well as with deep-learning-based schemes using pixel-wise training. Expand
Learning Joint-Sparse Codes for Calibration-Free Parallel MR Imaging
LINDBERG has presented strong capability in suppressing noise and artifacts while reconstructing MR images from highly undersampled multichannel measurements, and is comparable and even superior to state-of-the-art CS-PI reconstruction approaches. Expand
Adam: A Method for Stochastic Optimization
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Expand