mlsanityData to 14 Oct 2026

Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction

arXiv 2111.15498 ↗First posted 30 Nov 2021eess.IV cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Machine Learning methods can learn how to reconstruct Magnetic Resonance Images and thereby accelerate acquisition, which is of paramount importance to the clinical workflow. Physics-informed networks incorporate the forward model of accelerated MRI reconstruction in the learning process. With increasing network complexity, robustness is not ensured when reconstructing data unseen during training. We aim to embed data consistency (DC) in deep networks while balancing the degree of network complexity. While doing so, we will assess whether either explicit or implicit enforcement of DC in varying network architectures is preferred to optimize performance. We propose a scheme called Cascades of Independently Recurrent Inference Machines (CIRIM) to assess DC through unrolled optimization. Herein we assess DC both implicitly by gradient descent and explicitly by a designed term. Extensive comparison of the CIRIM to CS as well as to other methods is performed: the E2EVN, CascadeNet, KIKINet, LPDNet, RIM, IRIM, and UNet. Models were trained and evaluated on T1-weighted and FLAIR contrast brain data, and T2-weighted knee data. Both 1D and 2D undersampling patterns were evaluated. Robustness was tested by reconstructing 7.5x prospectively undersampled 3D FLAIR MRI data of Multiple Sclerosis (MS) patients with white matter lesions. The CIRIM performed best when implicitly enforcing DC, while the E2EVN required an explicit DC formulation. In reconstructing MS patient data, prospectively acquired with a sampling pattern unseen during model training, the CIRIM maintained lesion contrast while efficiently denoising the images. The CIRIM showed highly promising generalization capabilities maintaining a very fair trade-off between reconstructed image quality and fast reconstruction times, which is crucial in the clinical workflow.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 35 of its 86 references that are in the map. First posted on arXiv 30 Nov 2021.

Builds on

35 of 86 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  5. 2016Learning to learn by gradient descent by gradient descentcited by 620
  6. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
  7. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 387
  8. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 342
  9. 2017Learned Primal-dual Reconstructioncited by 251
  10. 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 232
  11. 2017Image reconstruction by domain transform manifold learningcited by 232
  12. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 202
23 more
  1. 2018Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNNcited by 143
  2. 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
  3. 2017Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Losscited by 82
  4. 2021Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformerscited by 77
  5. 2020Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challengecited by 59
  6. 2019GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstructioncited by 45
  7. 2017A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networkscited by 43
  8. 2017Recurrent Inference Machines for Solving Inverse Problemscited by 33
  9. 2019VS-Net: Variable splitting network for accelerated parallel MRI reconstructioncited by 31
  10. 2021fastMRI+: Clinical Pathology Annotations for Knee and Brain Fully Sampled Multi-Coil MRI Datacited by 29
  11. 2017ADMM-Net: A Deep Learning Approach for Compressive Sensing MRIcited by 28
  12. 2019LORAKI: Autocalibrated Recurrent Neural Networks for Autoregressive MRI Reconstruction in k-Spacecited by 28
  13. 2015On learning optimized reaction diffusion processes for effective image restorationcited by 25
  14. 2020Unsupervised MRI Reconstruction with Generative Adversarial Networkscited by 24
  15. 2018MRI Reconstruction via Cascaded Channel-wise Attention Networkcited by 20
  16. 2020An Adaptive Intelligence Algorithm for Undersampled Knee MRI Reconstructioncited by 19
  17. 2019i-RIM applied to the fastMRI challengecited by 16
  18. 2019Pyramid Convolutional RNN for MRI Image Reconstructioncited by 14
  19. 2020Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstructioncited by 14
  20. 2019Dual-domain Cascade of U-nets for Multi-channel Magnetic Resonance Image Reconstructioncited by 12
  21. 2021Memory-efficient Learning for High-Dimensional MRI Reconstructioncited by 5
  22. 2015Learning Representations Using Complex-Valued Netscited by 4
  23. 2019Sigma-net: Ensembled Iterative Deep Neural Networks for Accelerated Parallel MR Image Reconstructioncited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2.

3 papers.

  1. 2024Recurrent Inference Machine for Medical Image Registrationcited by 2
  2. 2023Impact of Disentanglement on Pruning Neural Networkscited by 1
  3. 2024ATOMMIC: An Advanced Toolbox for Multitask Medical Imaging Consistency to facilitate Artificial Intelligence applications from acquisition to analysis in Magnetic Resonance Imagingcited by 1