A Weighted Kernel Norm MRI Reconstruction Method Based on Generalized Tree Sparse
A magnetic resonance imaging and nuclear norm technology, applied in the field of medical image processing, can solve problems such as difficult to accurately reconstruct magnetic resonance MRI images, difficult medical diagnosis, and does not take into account the sparsity of the internal structure of the signal, so as to achieve less aliasing artifacts , fast recovery, good fidelity effect
Active Publication Date: 2019-06-18
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the existing CS-MRI image reconstruction methods mainly use the sparsity of the magnetic resonance MRI image to reconstruct the image, and do not take into account the inherent structural sparsity of the signal, so it is difficult to accurately reconstruct the original real magnetic resonance MRI image. make medical diagnosis difficult
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0045] The present invention will be further described below in conjunction with specific embodiments.
[0046] Such as figure 1 As shown, the weighted nuclear norm magnetic resonance imaging (MRI) reconstruction method based on generalized tree sparseness described in this embodiment is specifically: first, obtain a test magnetic resonance imaging (MRI) sampling data sample and perform Fourier transform; then according to the sampling The sparse signal of the tree structure is constructed from the signal, and the sparse expression of the constrained objective function is approximated by the weighted nuclear norm; then the constrained objective function is optimized by the augmented Lagrangian multiplier method and the Alternate Direction Search (ADMM) algorithm The test data is updated iteratively until the estimated restored data is obtained; finally, the final restored image is obtained by constructing tree sparse inverse transformation. It includes the following steps:
...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a weighted kernel norm magnetic resonance imaging reconstruction method based on generalized tree sparseness. First, test magnetic resonance imaging sampling data samples are obtained and Fourier transform is performed; and a tree-structured sparse signal is constructed based on the sampled signal, and the band is used to construct a tree-structured sparse signal. The nuclear norm of the weight approximates the sparse expression of the constrained objective function; the test data is then iteratively updated through the augmented Lagrangian multiplier method to optimize the constrained objective function and the alternating direction search algorithm until the estimated recovery data is obtained ;Then the final restored image is obtained by constructing a tree sparse inverse transform. This invention fully exploits the internal structural relationship of the image signal, combines the generalized tree sparse structural characteristics of the image block with the weight kernel norm, and uses the ADMM algorithm to simplify the calculation process, reduce the algorithm complexity, and improve the performance of partial spatial data reconstruction of the image. , reconstruct images more accurately with fewer scan measurements, reduce artifacts in reconstructed images, and achieve fast magnetic resonance imaging.
Description
technical field [0001] The present invention relates to the technical field of medical image processing, in particular to a weighted nuclear norm magnetic resonance imaging (MRI) reconstruction method based on generalized tree sparseness, which is mainly used for clear and rapid recovery of medical images, reducing artifacts of reconstructed images, Recover more image details. Background technique [0002] Magnetic resonance imaging (MRI) is widely used in the medical field because of its low damage and high diagnostic significance. Magnetic resonance MRI is based on the principle of magnetic resonance. The basic physical concepts involved in magnetic resonance mainly include the spin and magnetic moment of atoms, the energy state of spin magnetic moment in an external magnetic field, the conditions for generating magnetic resonance, Larmor precession, magnetization vector, and radio frequency field to magnetization vector. and relaxation process. [0003] Traditional magn...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00
CPCG06T2207/10088G06T2207/30016G06T2207/20192G06T2207/20056G06T5/73
Inventor 傅予力陈真徐俊伟向友君周正龙
Owner SOUTH CHINA UNIV OF TECH