Compressive MRI quantification using convex spatiotemporal priors and deep auto-encoders
arXiv:2001.08746
Abstract
We propose a dictionary-matching-free pipeline for multi-parametric quantitative MRI image computing. Our approach has two stages based on compressed sensing reconstruction and deep learned quantitative inference. The reconstruction phase is convex and incorporates efficient spatiotemporal regularisations within an accelerated iterative shrinkage algorithm. This minimises the under-sampling (aliasing) artefacts from aggressively short scan times. The learned quantitative inference phase is purely trained on physical simulations (Bloch equations) that are flexible for producing rich training samples. We propose a deep and compact auto-encoder network with residual blocks in order to embed Bloch manifold projections through multiscale piecewise affine approximations, and to replace the nonscalable dictionary-matching baseline. Tested on a number of datasets we demonstrate effectiveness of the proposed scheme for recovering accurate and consistent quantitative information from novel and aggressively subsampled 2D/3D quantitative MRI acquisition protocols.
References in corpus (14)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- On the Number of Linear Regions of Deep Neural Networks
- MR fingerprinting Deep RecOnstruction NEtwork (DRONE)
- Low Rank Alternating Direction Method of Multipliers Reconstruction for MR Fingerprinting
- Computational and Statistical Tradeoffs via Convex Relaxation
- Low Rank Magnetic Resonance Fingerprinting
- Dictionary-Free MRI PERK: Parameter Estimation via Regression with Kernels
- The Practicality of Stochastic Optimization in Imaging Inverse Problems
- Spatially Regularized Parametric Map Reconstruction for Fast Magnetic Resonance Fingerprinting
- Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares
- Multi-shot Echo Planar Imaging for accelerated Cartesian MR Fingerprinting: an alternative to conventional spiral MR Fingerprinting
- Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery
- Greedy Approximate Projection for Magnetic Resonance Fingerprinting with Partial Volumes
- Deep MR Fingerprinting with total-variation and low-rank subspace priors