SMUG: Towards Robust Mri Reconstruction by Smoothed Unrolling

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.

[1]  Jinfeng Yi,et al.  How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective , 2022, ICLR.

[2]  Steen Moeller,et al.  On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations , 2021, ArXiv.

[3]  R. Willett,et al.  Deep Equilibrium Architectures for Inverse Problems in Imaging , 2021, IEEE Transactions on Computational Imaging.

[4]  Quoc V. Le,et al.  Rethinking Pre-training and Self-training , 2020, NeurIPS.

[5]  Mingjie Sun,et al.  Denoised Smoothing: A Provable Defense for Pretrained Classifiers , 2020, NeurIPS.

[6]  Jechang Jeong,et al.  Deep Iterative Down-Up CNN for Image Denoising , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[7]  Francesco Renna,et al.  On instabilities of deep learning in image reconstruction and the potential costs of AI , 2019, Proceedings of the National Academy of Sciences.

[8]  J. Zico Kolter,et al.  Certified Adversarial Robustness via Randomized Smoothing , 2019, ICML.

[9]  Michael I. Jordan,et al.  Theoretically Principled Trade-off between Robustness and Accuracy , 2019, ICML.

[10]  Pascal Vincent,et al.  fastMRI: An Open Dataset and Benchmarks for Accelerated MRI , 2018, ArXiv.

[11]  Jeffrey A. Fessler,et al.  Deep dictionary-transform learning for image reconstruction , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[12]  Jaejun Yoo,et al.  Deep Residual Learning for Accelerated MRI Using Magnitude and Phase Networks , 2018, IEEE Transactions on Biomedical Engineering.

[13]  Mathews Jacob,et al.  MoDL: Model-Based Deep Learning Architecture for Inverse Problems , 2017, IEEE Transactions on Medical Imaging.

[14]  Jong Chul Ye,et al.  Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT , 2017, IEEE Transactions on Medical Imaging.

[15]  Aleksander Madry,et al.  Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[16]  Daniel Rueckert,et al.  A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[17]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[18]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[19]  Junfeng Yang,et al.  A Fast Alternating Direction Method for TVL1-L2 Signal Reconstruction From Partial Fourier Data , 2010, IEEE Journal of Selected Topics in Signal Processing.

[20]  M. Lustig,et al.  Compressed Sensing MRI , 2008, IEEE Signal Processing Magazine.

[21]  Y. Carmon,et al.  Making Medical Image Reconstruction Adversarially Robust , 2019 .

[22]  Gitta Kutyniok.  Compressed Sensing , 2012 .