Compressive MRI quantification using convex spatiotemporal priors and deep auto-encoders
This work addresses the need for faster and more accurate quantitative MRI scans in medical imaging, though it appears incremental as it builds on existing compressed sensing and deep learning methods.
The authors tackled the problem of recovering accurate quantitative MRI information from aggressively subsampled scans by proposing a two-stage pipeline combining convex compressed sensing reconstruction and deep auto-encoder inference, demonstrating effectiveness on 2D/3D datasets with reduced aliasing artifacts from short scan times.
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.