mlsanityData to 14 Oct 2026

SMUG: Towards robust MRI reconstruction by smoothed unrolling

arXiv 2303.12735 ↗First posted 14 Mar 2023eess.IV cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Although deep learning (DL) has gained much popularity for accelerated magnetic resonance imaging (MRI), recent studies have shown that DL-based MRI reconstruction models could be oversensitive to tiny input perturbations (that are called 'adversarial perturbations'), which cause unstable, low-quality reconstructed images. This raises the question of how to design robust DL methods for MRI reconstruction. To address this problem, we propose a novel image reconstruction framework, termed SMOOTHED UNROLLING (SMUG), which advances a deep unrolling-based MRI reconstruction model using a randomized smoothing (RS)-based robust learning operation. RS, which improves the tolerance of a model against input noises, has been widely used in the design of adversarial defense for image classification. Yet, we find that the conventional design that applies RS to the entire DL process is ineffective for MRI reconstruction. We show that SMUG addresses the above issue by customizing the RS operation based on the unrolling architecture of the DL-based MRI reconstruction model. Compared to the vanilla RS approach and several variants of SMUG, we show that SMUG improves the robustness of MRI reconstruction with respect to a diverse set of perturbation sources, including perturbations to the input measurements, different measurement sampling rates, and different unrolling steps. Code for SMUG will be available at https://github.com/LGM70/SMUG.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 15 of its 24 references that are in the map. First posted on arXiv 14 Mar 2023.

Builds on

15 of 24 references.

References · 15

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  5. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  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. 2020Rethinking Pre-training and Self-trainingcited by 352
  9. 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 232
  10. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 212
  11. 2021Deep Equilibrium Architectures for Inverse Problems in Imagingcited by 127
  12. 2017Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CTcited by 88
3 more
  1. 2018Deep Residual Learning for Accelerated MRI using Magnitude and Phase Networkscited by 53
  2. 2022How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspectivecited by 39
  3. 2021On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbationscited by 4

Built on by

Cited by year

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

3 papers.

  1. 2023Robust Physics-based Deep MRI Reconstruction Via Diffusion Purificationcited by 4
  2. 2024Pruning Unrolled Networks (PUN) at Initialization for MRI Reconstruction Improves Generalizationcited by 3
  3. 2023Robust MRI Reconstruction by Smoothed Unrolling (SMUG)cited by 1