A Model-Based Deep Network for MRI Reconstruction Using Approximate Message Passing Algorithm

We propose a novel model-based network to reconstruct the magnetic resonance (MR) image. In this network, the Approximate Message Passing (AMP) algorithm is unrolled to solve the optimization problem of compressed sensing MR imaging, and several CNN blocks is embedded as de-aliasing steps. We relax the restriction on the parameter selection of AMP algorithm, and enable the parameters trainable in our proposed method. Each CNN block and AMP block is followed by a data consistency (DC) operation, which can efficiently accelerate the convergence of the reconstruction network. The trainable parameters of our DC share the weights and can automatically adapt to the error pattern. Experimental results show that the proposed method obtains faster convergence speed and achieves a new state-of-the-art MR image reconstruction performance.

[1]  Dong Liang,et al.  Model-based Deep MR Imaging: the roadmap of generalizing compressed sensing model using deep learning , 2019, ArXiv.

[2]  Andrea Montanari,et al.  Message-passing algorithms for compressed sensing , 2009, Proceedings of the National Academy of Sciences.

[3]  Philip Schniter,et al.  Onsager-corrected deep learning for sparse linear inverse problems , 2016, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[4]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[5]  Leslie Ying,et al.  Accelerating magnetic resonance imaging via deep learning , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[6]  Daniel K Sodickson,et al.  Low‐rank plus sparse matrix decomposition for accelerated dynamic MRI with separation of background and dynamic components , 2015, Magnetic resonance in medicine.

[7]  Thomas Pock,et al.  Learning a variational network for reconstruction of accelerated MRI data , 2017, Magnetic resonance in medicine.

[8]  Jian Sun,et al.  Deep ADMM-Net for Compressive Sensing MRI , 2016, NIPS.

[9]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[10]  Zhongshi He,et al.  Super-resolution reconstruction of single anisotropic 3D MR images using residual convolutional neural network , 2020, Neurocomputing.

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

[12]  Guang Yang,et al.  DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction , 2018, IEEE Transactions on Medical Imaging.

[13]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[14]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

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

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  P. Boesiger,et al.  SENSE: Sensitivity encoding for fast MRI , 1999, Magnetic resonance in medicine.

[19]  Daniel Rueckert,et al.  A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction , 2017, IPMI.