Enhancing MR Image Reconstruction Using Block Dictionary Learning

Abstract

While representing a class of signals in term of sparsifying transform, it is better to use a adapted learned dictionary instead of using a predefined dictionary as proposed in the recent literature. With this improved method, one can represent the sparsest representation for the given set of signals. In order to ease the approximation, atoms of the learned dictionary can further be grouped together to make blocks inside the dictionary that act as a union of small number of subspaces. The block structure of a dictionary can be learned by exploiting the latent structure of the desired signals. Such type of block dictionary leads to block sparse representation of the given signals which can be good for reconstruction of the medical images. In this article, we suggest a framework for MRI reconstruction based upon block sparsifying transform (dictionary). Our technique develops automatic detection of underlying block structure of MR images given maximum block sizes. This is done by iteratively alternating between updating the block structure of the sparsifying transform (dictionary) and block-sparse representation of the MR images. Empirically it is shown that blocksparse representation performs better for recovery of the given MR image with minimum errors. INDEX TERMS Compressed sensing (CS), sparsifying transforms, magnetic resonance imaging (MRI), block k-singular value decomposition (BLKSVD).

Efficient Reconstruction Technique for Multi-Slice CS-MRI Using Novel Interpolation and 2D Sampling Scheme

“…The CS-MRI trends can be broadly categorized as methods focused on improving the reconstruction strategies [23,24], and parallel CS-MRI techniques [25]. For successful CS-MRI, the sparse regularization can be achieved in a specific transform domain or using some dictionary learning techniques [26][27][28][29][30][31]. The classic CS-MRI uses fixed sparsifying transforms like total variation (TV) [32], discrete cosine transforms (DCT) and discrete wavelet transforms (DWT) [33].…”

Multi-Layer Basis Pursuit for Compressed Sensing MR Image Reconstruction

“…Optimization-based or objective function based reconstruction approaches use sparse regularization to design transform sparsity for CS reconstruction. These methods employ the transform sparsity in transform domain [8], [9], and dictionary learning based subspace [10]- [12] for CS reconstruction. Methods based on these techniques have the advantage of fast optimization at the cost of introducing staircase artifacts in images constructed from compressive measurements [13].…”

“…The traditional ISTA formulation cannot be applied to (12) due to presence of no separable composite term in g(.). In order to tackle this issue and solve (12), gradient mapping 1 approach [46] is analyzed. Given a function of the form F = f +g, the gradient mapping operator is given by:…”

“…is gradient of the data fidelity term in Equation (12). The objective function of ML-BP, can be generally expressed as minimization problem of the form,…”

Radial Undersampling-Based Interpolation Scheme for Multislice CSMRI Reconstruction Techniques

“…The recent trends of CSMRI can be classified as techniques dedicated to improved reconstruction techniques [43][44][45] and parallel CSMRI approaches [4,5,40,42,46,47]. In CSMRI, the sparse regularization has been accomplished BioMed Research International through a particular transform domain, such as the wavelet [10] and curvelet [48], or through some dictionary learning approaches [49][50][51][52][53][54][55]. The traditional CSMRI uses the fixed sparsifying transforms [56,57].…”