Super‐resolved q‐space learning of diffusion MRI

Abstract Background Diffusion magnetic resonance imaging (dMRI) provides a powerful tool to non‐invasively investigate neural structures in the living human brain. Nevertheless, its reconstruction performance on neural structures relies on the number of diffusion gradients in the q‐space. High‐angular (HA) dMRI requires a long scan time, limiting its use in clinical practice, whereas directly reducing the number of diffusion gradients would lead to the underestimation of neural structures. Purpose We propose a deep compressive sensing‐based q‐space learning (DCS‐qL) approach to estimate HA dMRI from low‐angular dMRI. Methods In DCS‐qL, we design the deep network architecture by unfolding the proximal gradient descent procedure that addresses the compressive sense problem. In addition, we exploit a lifting scheme to design a network structure with reversible transform properties. For implementation, we apply a self‐supervised regression to enhance the signal‐to‐noise ratio of diffusion data. Then, we utilize a semantic information‐guided patch‐based mapping strategy for feature extraction, which introduces multiple network branches to handle patches with different tissue labels. Results Experimental results show that the proposed approach can yield a promising performance on the tasks of reconstructed HA dMRI images, microstructural indices of neurite orientation dispersion and density imaging, fiber orientation distribution, and fiber bundle estimation. Conclusions The proposed method achieves more accurate neural structures than competing approaches.