Low‐dimensional‐structure self‐learning and thresholding: Regularization beyond compressed sensing for MRI Reconstruction

Abstract

An improved image reconstruction method from undersampled k-space data, “LOw-dimensional-structure Self-learning and Thresholding (LOST),” which utilizes the structure from the underlying image is presented. A low resolution image from the fully-sampled k-space center is reconstructed to learn image patches of similar anatomical characteristics. These patches are arranged into “similarity clusters,” which are subsequently processed for de-aliasing and artifact removal, using underlying low-dimensional properties. The efficacy of the proposed method in scan time reduction was assessed in a pilot coronary MRI study. Initially, in a retrospective study on 10 healthy adult subjects, we evaluated retrospective undersampling and reconstruction using LOST, wavelet-based l1-norm minimization and total variation compressed-sensing (CS). Quantitative measures of vessel sharpness and mean square error, and qualitative image scores were used to compare reconstruction for rates of 2, 3 and 4. Subsequently, in a prospective study, coronary MRI data were acquired using these rates, and LOST-reconstructed images were compared with an accelerated data acquisition using uniform undersampling and sensitivity-encoding (SENSE) reconstruction. Subjective image quality and sharpness data indicate that LOST outperforms the alternative techniques for all rates. The prospective LOST yields images with superior quality compared to SENSE or l1-minimization CS. The proposed LOST technique greatly improves image reconstruction for accelerated coronary MRI acquisitions.

Accelerated Late Gadolinium Enhancement Cardiac MR Imaging with Isotropic Spatial Resolution Using Compressed Sensing: Initial Experience

“…and thresholding (LOST) (20). This technique uses patient-and anatomicspecific information from low-spatialresolution images reconstructed from the fully sampled central k-space data to adaptively generate a sparse representation for the undersampled image.…”

“…This technique uses patient-and anatomicspecific information from low-spatialresolution images reconstructed from the fully sampled central k-space data to adaptively generate a sparse representation for the undersampled image. This reconstruction reduces blurring artifacts associated with conventional compressed sensing reconstruction for high-spatial-resolution cardiac MR imaging (20).…”

Compressed sensing MRI with Bayesian dictionary learning

“…CS-MRI reconstruction algorithms tend to fall into two categories: Those which enforce sparsity withing an imagelevel transform domain (e.g., [3]- [7]), and those which en- force sparsity on a patch-level (e.g., [8]- [11]). Most CS-MRI reconstruction algorithms belong to the first category.…”

Accelerated Dynamic Cardiac MRI Using Motion-Guided Compressed Sensing with Regional Sparsity

“…Next, as also illustrated, the tracked blocks are gathered into a 3D cluster and rearranged into a 2D matrix, where each block becomes one column and blocks corresponding to separate time points are placed into separate columns. The 2D matrix is then 24 subject to SVD to exploit low-rank sparsity. The 2D matrix is expected to have greater spatiotemporal sparsity compared to the whole image or to untracked blocks because the blocks have a smaller scope with decreased spatiotemporal variations, and motion tracking leads to less motion contamination.…”

“…In these studies matrix rank sparsity was applied to the entire image dataset. In addition, recent studies such as Low-dimensional-structure Selflearning and thresholding (LOST) (24,62) and compartment-based k-t Principal Component…”