mlsanityData to 7 Oct 2026

DuDoUniNeXt: Dual-domain unified hybrid model for single and multi-contrast undersampled MRI reconstruction

arXiv 2403.05256 ↗First posted 8 Mar 2024eess.IV cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Multi-contrast (MC) Magnetic Resonance Imaging (MRI) reconstruction aims to incorporate a reference image of auxiliary modality to guide the reconstruction process of the target modality. Known MC reconstruction methods perform well with a fully sampled reference image, but usually exhibit inferior performance, compared to single-contrast (SC) methods, when the reference image is missing or of low quality. To address this issue, we propose DuDoUniNeXt, a unified dual-domain MRI reconstruction network that can accommodate to scenarios involving absent, low-quality, and high-quality reference images. DuDoUniNeXt adopts a hybrid backbone that combines CNN and ViT, enabling specific adjustment of image domain and k-space reconstruction. Specifically, an adaptive coarse-to-fine feature fusion module (AdaC2F) is devised to dynamically process the information from reference images of varying qualities. Besides, a partially shared shallow feature extractor (PaSS) is proposed, which uses shared and distinct parameters to handle consistent and discrepancy information among contrasts. Experimental results demonstrate that the proposed model surpasses state-of-the-art SC and MC models significantly. Ablation studies show the effectiveness of the proposed hybrid backbone, AdaC2F, PaSS, and the dual-domain unified learning scheme.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 8 Mar 2024.

Builds on

29 of 40 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  5. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  6. 2021Score-based diffusion models for accelerated MRIcited by 308
  7. 2022How Do Vision Transformers Work?cited by 305
  8. 2022Adaptive Diffusion Priors for Accelerated MRI Reconstructioncited by 117
  9. 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
  10. 2016HeMIS: Hetero-Modal Image Segmentationcited by 102
  11. 2017Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Losscited by 82
  12. 2021Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformerscited by 76
17 more
  1. 2017A Deep Cascade of Convolutional Neural Networks for MR Image Reconstructioncited by 74
  2. 2020DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction with Deep T1 Priorcited by 72
  3. 2022Towards performant and reliable undersampled MR reconstruction via diffusion model samplingcited by 59
  4. 2022Swin Transformer for Fast MRIcited by 56
  5. 2019Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisitioncited by 55
  6. 2022ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformercited by 52
  7. 2021Multi-Modal Transformer for Accelerated MR Imagingcited by 42
  8. 2023Unified Multi-Modal Image Synthesis for Missing Modality Imputationcited by 39
  9. 2023Self-Supervised MRI Reconstruction with Unrolled Diffusion Modelscited by 37
  10. 2022DSFormer: A Dual-domain Self-supervised Transformer for Accelerated Multi-contrast MRI Reconstructioncited by 30
  11. 2021Over-and-Under Complete Convolutional RNN for MRI Reconstructioncited by 29
  12. 2019Model Learning: Primal Dual Networks for Fast MR imagingcited by 22
  13. 2021Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Networkcited by 16
  14. 2022Swin Deformable Attention U-Net Transformer (SDAUT) for Explainable Fast MRIcited by 14
  15. 2023CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?cited by 11
  16. 2019Towards multi-sequence MR image recovery from undersampled k-space datacited by 1
  17. 2023Rethinking Dual-Domain Undersampled MRI reconstruction: domain-specific design from the perspective of the receptive fieldcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Accelerated Patient-specific Non-Cartesian MRI Reconstruction using Implicit Neural Representationscited by 2