• Corpus ID: 246867265

Joint Frequency and Image Space Learning for MRI Reconstruction and Analysis

  title={Joint Frequency and Image Space Learning for MRI Reconstruction and Analysis},
  author={Nalini M. Singh and Juan Eugenio Iglesias and Elfar Adalsteinsson and Adrian V. Dalca and Polina Golland},
We propose neural network layers that explicitly combine frequency and image feature representations and show that they can be used as a versatile building block for reconstruction from frequency space data. Our work is motivated by the challenges arising in MRI acquisition where the signal is a corrupted Fourier transform of the desired image. The proposed joint learning schemes enable both correction of artifacts native to the frequency space and manipulation of image space representations to… 



A Hybrid Frequency-Domain/Image-Domain Deep Network for Magnetic Resonance Image Reconstruction

  • R. SouzaR. Frayne
  • Computer Science
    2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)
  • 2019
This work proposes a hybrid architecture, termed W-net, that works both in the k-space (or frequency-domain) and the image domain, and demonstrates that the proposed hybrid approach can potentially improve CS reconstruction compared to deep-learning networks that operate only in the imagedomain.

A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction

A framework for reconstructing dynamic sequences of 2-D cardiac magnetic resonance images from undersampled data using a deep cascade of convolutional neural networks (CNNs) to accelerate the data acquisition process is proposed and it is demonstrated that CNNs can learn spatio-temporal correlations efficiently by combining convolution and data sharing approaches.

Deep learning for undersampled MRI reconstruction

A deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and a rationale for why the proposed approach works well is provided.

DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction With Deep T1 Prior

  • Bo ZhouS. K. Zhou
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
A Dual Domain Recurrent Network (DuDoRNet) with deep T1 prior embedded to simultaneously recover k-space and images for accelerating the acquisition of MRI with a long imaging protocol and is customized for dual domain restorations from undersampled MRI data.

Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets

The main finding of this benchmark is that it is beneficial to perform more iterations between the image and the measurement spaces compared to having a deeper per-space network.

Deep residual learning for compressed sensing MRI

A novel deep residual learning algorithm to reconstruct MR images from sparsely sampled k-space data is proposed and a deep convolutional neural network is proposed to learn the aliasing artifacts.

Image reconstruction by domain-transform manifold learning

A unified framework for image reconstruction—automated transform by manifold approximation (AUTOMAP)—which recasts image reconstruction as a data-driven supervised learning task that allows a mapping between the sensor and the image domain to emerge from an appropriate corpus of training data is presented.

Retrospective Motion Correction in Multishot MRI using Generative Adversarial Network

A novel generative adversarial network (GAN)-based conjugate gradient SENSE (CG-SENSE) reconstruction framework for motion correction in multishot MRI is proposed, which reduces several-fold the computational time reported by the current state-of-the-art technique.

Accelerated MRI Reconstruction with Dual-Domain Generative Adversarial Network

Evaluation on multiple datasets proved that the dual-domain GAN approach is an effective way to improve the quality of accelerated MR reconstruction.