Tensor-decomposition regularized learning for fast and high-fidelity multi-parametric microstructural MR imaging

Deep learning (DL) has emerged as a promising approach for learning the nonlinear mapping between diffusion-weighted MR images and tissue parameters, enabling automatic and in-depth understanding of brain microstructures. However, the efficiency and accuracy of jointly estimating multiple microstructural parameters derived from various diffusion models remain limited due to isolated signal modeling and dense sampling requirements.

This study aims to develop a unified DL framework for fast and high-fidelity estimation of multiple microstructural parameters derived from different diffusion models using sparsely sampled q-space data.

We propose DeepMpMRI, an efficient and extendable framework equipped with a novel tensor-decomposition-based regularizer that captures fine structural details by exploiting high-dimensional correlations across parameters. In addition, a Nesterov-based adaptive learning algorithm is introduced to dynamically optimize the regularization parameter, improving both efficiency and reconstruction accuracy.

Experimental results on the Human Connectome Project (HCP) dataset and an Alzheimer's disease dataset demonstrate that DeepMpMRI outperforms five state-of-the-art methods in simultaneously estimating DKI- and NODDI-derived parameter maps, achieving 4.5-15 $\times$ acceleration compared to dense sampling with 270 diffusion gradients.

DeepMpMRI enables accurate and robust multi-parametric microstructural imaging under sparse sampling conditions, showing strong potential for clinical translation in efficient diffusion MRI-based tissue characterization.