mlsanityData to 7 Oct 2026

DONet: Dual-Octave Network for Fast MR Image Reconstruction

arXiv 2105.05980 ↗First posted 12 May 2021eess.IV cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration has long been the subject of research. This is commonly achieved by obtaining multiple undersampled images, simultaneously, through parallel imaging. In this paper, we propose the Dual-Octave Network (DONet), which is capable of learning multi-scale spatial-frequency features from both the real and imaginary components of MR data, for fast parallel MR image reconstruction. More specifically, our DONet consists of a series of Dual-Octave convolutions (Dual-OctConv), which are connected in a dense manner for better reuse of features. In each Dual-OctConv, the input feature maps and convolutional kernels are first split into two components (ie, real and imaginary), and then divided into four groups according to their spatial frequencies. Then, our Dual-OctConv conducts intra-group information updating and inter-group information exchange to aggregate the contextual information across different groups. Our framework provides three appealing benefits: (i) It encourages information interaction and fusion between the real and imaginary components at various spatial frequencies to achieve richer representational capacity. (ii) The dense connections between the real and imaginary groups in each Dual-OctConv make the propagation of features more efficient by feature reuse. (iii) DONet enlarges the receptive field by learning multiple spatial-frequency features of both the real and imaginary components. Extensive experiments on two popular datasets (ie, clinical knee and fastMRI), under different undersampling patterns and acceleration factors, demonstrate the superiority of our model in accelerated parallel MR image reconstruction.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 21 of its 61 references that are in the map. First posted on arXiv 12 May 2021.

Builds on

21 of 61 references.

References · 21

  1. 2016Densely Connected Convolutional Networkscited by 6,691
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  3. 2014Going Deeper with Convolutionscited by 4,231
  4. 2016Pyramid Scene Parsing Networkcited by 2,472
  5. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  6. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  7. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  8. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
  9. 2017Image reconstruction by domain transform manifold learningcited by 231
  10. 2017Deep Complex Networkscited by 215
  11. 2019Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolutioncited by 140
  12. 2017Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Losscited by 82
9 more
  1. 2020Motion-Attentive Transition for Zero-Shot Video Object Segmentationcited by 62
  2. 2018Deep Residual Learning for Accelerated MRI using Magnitude and Phase Networkscited by 53
  3. 2019GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstructioncited by 45
  4. 2017Deep Learning with Domain Adaptation for Accelerated Projection-Reconstruction MRcited by 31
  5. 2018A Deep Information Sharing Network for Multi-contrast Compressed Sensing MRI Reconstructioncited by 22
  6. 2021Dual-Octave Convolution for Accelerated Parallel MR Image Reconstructioncited by 12
  7. 2019Model-based Convolutional De-Aliasing Network Learning for Parallel MR Imagingcited by 4
  8. 2019Data consistency networks for (calibration-less) accelerated parallel MR image reconstructioncited by 2
  9. 2015Compressed sensing MRI using masked DCT and DFT measurementscited by 1

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 3; 2023: 3.

9 papers.

  1. 2022Adaptive Diffusion Priors for Accelerated MRI Reconstructioncited by 117
  2. 2021Multi-Modal Transformer for Accelerated MR Imagingcited by 42
  3. 2023Learning Federated Visual Prompt in Null Space for MRI Reconstructioncited by 40
  4. 2021Specificity-Preserving Federated Learning for MR Image Reconstructioncited by 35
  5. 2022Federated Learning of Generative Image Priors for MRI Reconstructioncited by 33
  6. 2021Exploring Separable Attention for Multi-Contrast MR Image Super-Resolutioncited by 13
  7. 2022PARCEL: Physics-based Unsupervised Contrastive Representation Learning for Multi-coil MR Imagingcited by 8
  8. 2023FAM: fast adaptive federated meta-learningcited by 1
  9. 2023Dual-Domain Multi-Contrast MRI Reconstruction with Synthesis-based Fusion Networkcited by 0