Comparison of sampling strategies and sparsifying transforms to improve compressed sensing diffusion spectrum imaging

Abstract

It is important to jointly optimize the sampling scheme and the sparsifying transform to obtain accelerated compressive sensing-diffusion spectrum imaging. Experiments on synthetic and real human brain data show that one can robustly recover both radial and angular EAP features while undersampling the acquisition to 64 measurements (undersampling factor of 4).

q-Space Deep Learning for Twelve-Fold Shorter and Model-Free Diffusion MRI Scans

“…While state-of-the-art methods [12,22] require 30 DWIs for NODDI and 64 for radial kurtosis, we require only 8 and 12, respectively. Our results indicate that a considerable amount of information is contained in a limited number of DWIs, and that this information can be better retrieved by deep learning than by model fitting.…”

A 4D hyperspherical interpretation of q-space

“…This, however, leads to the important question of what is the best way to sample N diffusion measurements in q -space, which have started to be addressed (Assemlal et al, 2009b; Merlet et al, 2011; Koay et al, 2012; Caruyer et al, 2013). Although the HSH framework’s efficient representation of the dODF may also make it conducive to compressed sensing (Menzel et al, 2011; Merlet and Deriche, 2013; Paquette et al, 2014), the HSH basis is global; localized functions, by virtue of possessing compact support, will have better sparsity than global bases. Future work includes optimizing the HYDI q -space sampling and exploring the sparsibility of the HSH basis.…”

Exponential Wavelet Iterative Shrinkage Thresholding Algorithm for compressed sensing magnetic resonance imaging

“…Kayvanrad et al [20] showed that the visual pseudo-Gibbs artifacts can be greatly reduced by penalizing the translation-invariant stationary wavelet transform (SWT) coefficients; hence, they applied SWT for under-sampled MRI reconstruction. Paquette et al [32] compared different sampling strategies and sparsifying transforms. They found that the DWT with Cohen-Daubechies-Feauveau 9/7 wavelets and uniform angular sampling in combination with random radial sampling showed better than other tested techniques to accurately reconstruct the ensemble average propagator (EAP) and its features.…”