Compressed Sensing: From Research to Clinical Practice with Data-Driven Learning

Compressed sensing in MRI enables high subsampling factors while maintaining diagnostic image quality. This technique enables shortened scan durations and/or improved image resolution. Further, compressed sensing can increase the diagnostic information and value from each scan performed. Overall, compressed sensing has significant clinical impact in improving the diagnostic quality and patient experience for imaging exams. However, a number of challenges exist when moving compressed sensing from research to the clinic. These challenges include hand-crafted image priors, sensitive tuning parameters, and long reconstruction times. Data-driven learning provides a solution to address these challenges. As a result, compressed sensing can have greater clinical impact. In this tutorial, we will review the compressed sensing formulation and outline steps needed to transform this formulation to a deep learning framework. Supplementary open source code in python will be used to demonstrate this approach with open databases. Further, we will discuss considerations in applying data-driven compressed sensing in the clinical setting.

[1]  Michael Lustig,et al.  Comprehensive motion‐compensated highly accelerated 4D flow MRI with ferumoxytol enhancement for pediatric congenital heart disease , 2016, Journal of magnetic resonance imaging : JMRI.

[2]  Sandeep Subramanian,et al.  Deep Complex Networks , 2017, ICLR.

[3]  Erich Kobler,et al.  Variational Adversarial Networks for Accelerated MR Image Reconstruction , 2018 .

[4]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[5]  Jonas Adler,et al.  Learned Primal-Dual Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[6]  Jian Sun,et al.  ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI , 2017, ArXiv.

[7]  I. Daubechies,et al.  An iterative thresholding algorithm for linear inverse problems with a sparsity constraint , 2003, math/0307152.

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

[9]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[10]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[11]  Morteza Mardani,et al.  Neural Proximal Gradient Descent for Compressive Imaging , 2018, NeurIPS.

[12]  M. Lustig,et al.  Improved pediatric MR imaging with compressed sensing. , 2010, Radiology.

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

[14]  Feiyu Chen,et al.  Highly Scalable Image Reconstruction using Deep Neural Networks with Bandpass Filtering , 2018, ArXiv.

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

[16]  Leon Axel,et al.  XD‐GRASP: Golden‐angle radial MRI with reconstruction of extra motion‐state dimensions using compressed sensing , 2016, Magnetic resonance in medicine.

[17]  Li Feng,et al.  Highly accelerated real‐time cardiac cine MRI using k–t SPARSE‐SENSE , 2013, Magnetic resonance in medicine.

[18]  Shreyas S Vasanawala,et al.  Congenital heart disease assessment with 4D flow MRI , 2015, Journal of magnetic resonance imaging : JMRI.

[19]  Jong Chul Ye,et al.  k‐t FOCUSS: A general compressed sensing framework for high resolution dynamic MRI , 2009, Magnetic resonance in medicine.

[20]  Leslie Ying,et al.  Joint image reconstruction and sensitivity estimation in SENSE (JSENSE) , 2007, Magnetic resonance in medicine.

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

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

[23]  Michael Lustig,et al.  Comprehensive Multi-Dimensional MRI for the Simultaneous Assessment of Cardiopulmonary Anatomy and Physiology , 2017, Scientific Reports.

[24]  Jonathan I. Tamir,et al.  Variable-Density Single-Shot Fast Spin-Echo MRI with Deep Learning Reconstruction by Using Variational Networks. , 2018, Radiology.

[25]  Michael Lustig,et al.  Fast pediatric 3D free‐breathing abdominal dynamic contrast enhanced MRI with high spatiotemporal resolution , 2015, Journal of magnetic resonance imaging : JMRI.

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

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

[28]  Jeffrey A. Fessler,et al.  Regularization Parameter Selection for Nonlinear Iterative Image Restoration and MRI Reconstruction Using GCV and SURE-Based Methods , 2012, IEEE Transactions on Image Processing.

[29]  Mathews Jacob,et al.  Accelerated Dynamic MRI Exploiting Sparsity and Low-Rank Structure: k-t SLR , 2011, IEEE Transactions on Medical Imaging.

[30]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[31]  D. Donoho,et al.  Sparse MRI: The application of compressed sensing for rapid MR imaging , 2007, Magnetic resonance in medicine.

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