Compressive MRI quantification using convex spatiotemporal priors and deep auto-encoders

摘要: 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 inference. The phase is convex incorporates efficient spatiotemporal regularisations within an accelerated iterative shrinkage algorithm. This minimises the under-sampling (aliasing) artefacts from aggressively short scan times. inference purely trained physical simulations (Bloch equations) that are flexible producing rich training samples. compact auto-encoder network with residual blocks in order to embed Bloch manifold projections through multiscale piecewise affine approximations, replace nonscalable dictionary-matching baseline. Tested number of datasets we demonstrate effectiveness proposed scheme recovering accurate consistent information novel subsampled 2D/3D acquisition protocols.