Equilibrated Zeroth-Order Unrolled Deep Networks for Accelerated MRI
Preprint
Abstract
Recently, model-driven deep learning unrolls a certain iterative algorithm of a regularization model into a cascade network by replacing the first-order information (i.e., (sub)gradient or proximal operator) of the regularizer with a network module, which appears more explainable and predictable compared to common data-driven networks. Conversely, in theory, there is not necessarily such a functional regularizer whose first-order information matches the replaced network module, which means the network output may not be covered by the original regularization model. Moreover, up to now, there is also no theory to guarantee the global convergence and robustness (regularity) of unrolled networks under realistic assumptions. To bridge this gap, this paper propose to present a safeguarded methodology on network unrolling. Specifically, focusing on accelerated MRI, we unroll a zeroth-order algorithm, of which the network module represents the regularizer itself, so that the network output can be still covered by the regularization model. Furthermore, inspired by the ideal of deep equilibrium models, before backpropagating, we carry out the unrolled iterative network to converge to a fixed point to ensure the convergence. In case the measurement data contains noise, we prove that the proposed network is robust against noisy interference. Finally, numerical experiments show that the proposed network consistently outperforms the state-of-the-art MRI reconstruction methods including traditional regularization methods and other deep learning methods.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Deep Magnetic Resonance Image Reconstruction: Inverse Problems Meet Neural NetworksIEEE Signal Processing Magazine, 2020
- Scan‐specific robust artificial‐neural‐networks for k‐space interpolation (RAKI) reconstruction: Database‐free deep learning for fast imagingMagnetic Resonance in Medicine, 2018
- Image reconstruction by domain-transform manifold learningNature, 2018
- Learning a variational network for reconstruction of accelerated MRI dataMagnetic Resonance in Medicine, 2017
- Sparse BLIP: BLind Iterative Parallel imaging reconstruction using compressed sensingMagnetic Resonance in Medicine, 2013
- A Mathematical Introduction to Compressive Sensing2013
- Parallel imaging with nonlinear reconstruction using variational penaltiesMagnetic Resonance in Medicine, 2011
- SPIRiT: Iterative self‐consistent parallel imaging reconstruction from arbitrary k‐spaceMagnetic Resonance in Medicine, 2010
- Sparse MRI: The application of compressed sensing for rapid MR imagingMagnetic Resonance in Medicine, 2007
- Generalized autocalibrating partially parallel acquisitions (GRAPPA)Magnetic Resonance in Medicine, 2002