Improved Supervised Training of Physics-Guided Deep Learning Image Reconstruction with Multi-Masking

Physics-guided deep learning (PG-DL) via algorithm unrolling has received significant interest for improved image reconstruction, including MRI applications. These methods unroll an iterative optimization algorithm into a series of regularizer and data consistency units. The unrolled networks are typically trained end-to-end using a supervised approach. Current supervised PG-DL approaches use all of the available sub-sampled measurements in their data consistency units. Thus, the network learns to fit the rest of the measurements. In this study, we propose to improve the performance and robustness of supervised training by utilizing randomness by retrospectively selecting only a subset of all the available measurements for data consistency units. The process is repeated multiple times using different random masks during training for further enhancement. Results on knee MRI show that the proposed multi-mask supervised PG-DL enhances reconstruction performance compared to conventional supervised PG-DL approaches.

[1]  Michael Elad,et al.  ESPIRiT—an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPA , 2014, Magnetic resonance in medicine.

[2]  Ulugbek S. Kamilov,et al.  RARE: Image Reconstruction Using Deep Priors Learned Without Groundtruth , 2019, IEEE Journal of Selected Topics in Signal Processing.

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

[4]  Yonina C. Eldar,et al.  Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing , 2019, IEEE Signal Processing Magazine.

[5]  Daniel Rueckert,et al.  Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction , 2017, IEEE Transactions on Medical Imaging.

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

[7]  Steen Moeller,et al.  High-Fidelity Accelerated MRI Reconstruction by Scan-Specific Fine-Tuning of Physics-Based Neural Networks , 2020, 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

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

[9]  Michael Rabbat,et al.  fastMRI: A Publicly Available Raw k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning. , 2020, Radiology. Artificial intelligence.

[10]  Taghi M. Khoshgoftaar,et al.  A survey on Image Data Augmentation for Deep Learning , 2019, Journal of Big Data.

[11]  Morteza Mardani,et al.  Deep Generative Adversarial Neural Networks for Compressive Sensing MRI , 2019, IEEE Transactions on Medical Imaging.

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

[13]  Steen Moeller,et al.  Self‐supervised learning of physics‐guided reconstruction neural networks without fully sampled reference data , 2019, Magnetic resonance in medicine.

[14]  Dong Liang,et al.  Deep Magnetic Resonance Image Reconstruction: Inverse Problems Meet Neural Networks , 2020, IEEE Signal Processing Magazine.

[15]  Steen Moeller,et al.  Dense Recurrent Neural Networks for Accelerated MRI: History-Cognizant Unrolling of Optimization Algorithms , 2020, IEEE Journal of Selected Topics in Signal Processing.

[16]  Steen Moeller,et al.  Deep-Learning Methods for Parallel Magnetic Resonance Imaging Reconstruction: A Survey of the Current Approaches, Trends, and Issues , 2020, IEEE Signal Processing Magazine.

[17]  Dong Liang,et al.  DeepcomplexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution. , 2020, Magnetic resonance imaging.

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

[19]  Steen Moeller,et al.  Scan‐specific robust artificial‐neural‐networks for k‐space interpolation (RAKI) reconstruction: Database‐free deep learning for fast imaging , 2018, Magnetic resonance in medicine.

[20]  Jeffrey A. Fessler,et al.  Optimization Methods for Magnetic Resonance Image Reconstruction: Key Models and Optimization Algorithms , 2020, IEEE Signal Processing Magazine.

[21]  P. Boesiger,et al.  Advances in sensitivity encoding with arbitrary k‐space trajectories , 2001, Magnetic resonance in medicine.

[22]  Mert R. Sabuncu,et al.  Deep-Learning-Based Optimization of the Under-Sampling Pattern in MRI , 2020, IEEE Transactions on Computational Imaging.

[23]  Steen Moeller,et al.  Multi-Mask Self-Supervised Learning for Physics-Guided Neural Networks in Highly Accelerated MRI , 2020, ArXiv.