mlsanityData to 7 Oct 2026

AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysis

arXiv 2112.12744 ↗First posted 23 Dec 2021eess.IV cs.AI cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

Compressed sensing (CS) has been playing a key role in accelerating the magnetic resonance imaging (MRI) acquisition process. With the resurgence of artificial intelligence, deep neural networks and CS algorithms are being integrated to redefine the state of the art of fast MRI. The past several years have witnessed substantial growth in the complexity, diversity, and performance of deep learning-based CS techniques that are dedicated to fast MRI. In this meta-analysis, we systematically review the deep learning-based CS techniques for fast MRI, describe key model designs, highlight breakthroughs, and discuss promising directions. We have also introduced a comprehensive analysis framework and a classification system to assess the pivotal role of deep learning in CS-based acceleration for MRI.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 51 of its 157 references that are in the map. First posted on arXiv 23 Dec 2021.

Builds on

51 of 157 references.

References · 51

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  3. 2017Deep Image Priorcited by 1,097
  4. 2017Wasserstein GANcited by 635
  5. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  6. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  7. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
  8. 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 231
  9. 2017Image reconstruction by domain transform manifold learningcited by 231
  10. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  11. 2016Unrolled Generative Adversarial Networkscited by 208
  12. 2019Deep learning-based electroencephalography analysis: a systematic reviewcited by 155
38 more
  1. 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
  2. 2017Deep learning for undersampled MRI reconstructioncited by 91
  3. 2017Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Losscited by 82
  4. 2019RARE: Image Reconstruction using Deep Priors Learned without Ground Truthcited by 64
  5. 2019Stabilizing Generative Adversarial Networks: A Surveycited by 57
  6. 2018Deep Residual Learning for Accelerated MRI using Magnitude and Phase Networkscited by 53
  7. 2019Uncertainty Quantification in Deep MRI Reconstructioncited by 49
  8. 2017A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networkscited by 43
  9. 2017Unrolled Optimization with Deep Priorscited by 40
  10. 2017MR image reconstruction using deep density priorscited by 37
  11. 2019Learning-based Optimization of the Under-sampling Pattern in MRIcited by 32
  12. 2017Deep Learning with Domain Adaptation for Accelerated Projection-Reconstruction MRcited by 31
  13. 2018Wavelet Convolutional Neural Networkscited by 29
  14. 2019Deep Generalization of Structured Low-Rank Algorithms (Deep-SLR)cited by 29
  15. 2017ADMM-Net: A Deep Learning Approach for Compressive Sensing MRIcited by 28
  16. 2019MRI Reconstruction Using Deep Bayesian Estimationcited by 28
  17. 2020Unpaired Deep Learning for Accelerated MRI using Optimal Transport Driven CycleGANcited by 28
  18. 2018A Deep Information Sharing Network for Multi-contrast Compressed Sensing MRI Reconstructioncited by 22
  19. 2019A Review on Deep Learning in Medical Image Reconstructioncited by 17
  20. 2019Fidelity Imposed Network Edit (FINE) for Solving Ill-Posed Image Reconstructioncited by 16
  21. 2019Spatio-Temporal Deep Learning-Based Undersampling Artefact Reduction for 2D Radial Cine MRI with Limited Datacited by 14
  22. 2019Deep MRI Reconstruction: Unrolled Optimization Algorithms Meet Neural Networkscited by 13
  23. 2019IFR-Net: Iterative Feature Refinement Network for Compressed Sensing MRIcited by 13
  24. 2019Dual-domain Cascade of U-nets for Multi-channel Magnetic Resonance Image Reconstructioncited by 12
  25. 2019Joint multi-contrast Variational Network reconstruction (jVN) with application to rapid 2D and 3D imagingcited by 11
  26. 2020Deep variational network for rapid 4D flow MRI reconstructioncited by 11
  27. 2015Fast Multi-class Dictionaries Learning with Geometrical Directions in MRI Reconstructioncited by 10
  28. 2018SANTIS: Sampling-Augmented Neural neTwork with Incoherent Structure for MR image reconstructioncited by 10
  29. 2019pISTA-SENSE-ResNet for Parallel MRI Reconstructioncited by 10
  30. 2017Face Super-Resolution Through Wasserstein GANscited by 9
  31. 2020Machine Learning in Magnetic Resonance Imaging: Image Reconstructioncited by 8
  32. 2019Accelerated Coronary MRI with sRAKI: A Database-Free Self-Consistent Neural Network k-space Reconstruction for Arbitrary Undersamplingcited by 6
  33. 2019Reconstruction of Undersampled 3D Non-Cartesian Image-Based Navigators for Coronary MRA Using an Unrolled Deep Learning Modelcited by 5
  34. 2019RODEO: Robust DE-aliasing autoencOder for Real-time Medical Image Reconstructioncited by 5
  35. 2018A Deep Error Correction Network for Compressed Sensing MRIcited by 3
  36. 2019Compressed Sensing MRI via a Multi-scale Dilated Residual Convolution Networkcited by 3
  37. 2020Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstructioncited by 3
  38. 2019Compressed MRI Reconstruction Exploiting a Rotation-Invariant Total Variation Discretizationcited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 12; 2023: 9; 2024: 7; 2025: 10.

38 papers.

Sort:

By area:

  1. 2022Swin Transformer for Fast MRIcited by 56
  2. 2024BrainSegFounder: Towards 3D Foundation Models for Neuroimage Segmentationcited by 36
  3. 2022A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2Noisecited by 29
  4. 2022Swin Deformable Attention U-Net Transformer (SDAUT) for Explainable Fast MRIcited by 14
  5. 2023One for Multiple: Physics-informed Synthetic Data Boosts Generalizable Deep Learning for Fast MRI Reconstructioncited by 14
  6. 2023Learning Fourier-Constrained Diffusion Bridges for MRI Reconstructioncited by 13
  7. 2023CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?cited by 11
  8. 2025MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shiftingcited by 10
  9. 2022Fast MRI Reconstruction: How Powerful Transformers Are?cited by 7
  10. 2024A Unified Model for Compressed Sensing MRI Across Undersampling Patternscited by 7
  11. 2022PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRIcited by 5
  12. 2023K-band: Self-supervised MRI Reconstruction via Stochastic Gradient Descent over K-space Subsetscited by 5
26 more
  1. 2023ViGU: Vision GNN U-Net for Fast MRIcited by 4
  2. 2023CL-MRI: Self-Supervised Contrastive Learning to Improve the Accuracy of Undersampled MRI Reconstructioncited by 4
  3. 2025Generative Autoregressive Transformers for Model-Agnostic Federated MRI Reconstructioncited by 4
  4. 2025Benchmarking Self-Supervised Learning Methods for Accelerated MRI Reconstructioncited by 4
  5. 2022MA-RECON: Mask-aware deep-neural-network for robust fast MRI k-space interpolationcited by 3
  6. 2023Hierarchical Perception Adversarial Learning Framework for Compressed Sensing MRIcited by 3
  7. 2023Deep Learning-based Diffusion Tensor Cardiac Magnetic Resonance Reconstruction: A Comparison Studycited by 3
  8. 2023Fast MRI Reconstruction via Edge Attentioncited by 3
  9. 2024MOST: MR reconstruction Optimization for multiple downStream Tasks via continual learningcited by 3
  10. 2022Data and Physics Driven Learning Models for Fast MRI -- Fundamentals and Methodologies from CNN, GAN to Attention and Transformerscited by 2
  11. 2022Localized adversarial artifacts for compressed sensing MRIcited by 2
  12. 2025MRpro: open framework for model-based, learned, and quantitative MR imagingcited by 2
  13. 2025Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanismcited by 2
  14. 2025Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with A Generalist Foundation Model and Multimodal Databasecited by 2
  15. 2022ICRICS: Iterative Compensation Recovery for Image Compressive Sensingcited by 1
  16. 2022Tiny-HR: Towards an interpretable machine learning pipeline for heart rate estimation on edge devicescited by 1
  17. 2022Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CTcited by 1
  18. 2024NeRF Solves Undersampled MRI Reconstructioncited by 1
  19. 2024Decoding the human brain tissue response to radiofrequency excitation using a biophysical-model-free deep MRI on a chip frameworkcited by 1
  20. 2022A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstructioncited by 0
  21. 2024TC-KANRecon: High-Quality and Accelerated MRI Reconstruction via Adaptive KAN Mechanisms and Intelligent Feature Scalingcited by 0
  22. 2024Deep End-to-end Adaptive k-Space Sampling, Reconstruction, and Registration for Dynamic MRIcited by 0
  23. 2025Advancing MRI Reconstruction: A Systematic Review of Deep Learning and Compressed Sensing Integrationcited by 0
  24. 2025Efficient Noise Calculation in Deep Learning-based MRI Reconstructionscited by 0
  25. 2025DUN-SRE: Deep Unrolling Network with Spatiotemporal Rotation Equivariance for Dynamic MRI Reconstructioncited by 0
  26. 2025Towards Seeing Bones at Radio Frequencycited by 0