Unlock instant, AI-driven research and patent intelligence for your innovation.
A Compressed Sensing MRI Reconstruction Method with Modified Regularization Parameters
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A magnetic resonance imaging and compressed sensing technology, applied in the field of image processing, can solve the problems of reducing clinical throughput, reducing equipment utilization rate in scanning time and reconstruction time, and high operating costs, so as to reduce the time of magnetic resonance imaging and reduce sampling Quantity, reducing the effect of data transmission
Active Publication Date: 2020-12-25
HARBIN UNIV OF SCI & TECH
View PDF11 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
Excessive scan and reconstitution times also reduce equipment utilization, reduce clinical throughput, and result in expensive operations
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0047] A compressive sensing MRI reconstruction method with modified regularization parameters, such as figure 1 shown, including the following steps:
[0048] Step a, obtaining part of K-space data;
[0049] Step b. Constructing a magnetic resonance image reconstruction objective function by using the total variational transformation model theory;
[0050] Step c. According to the constructed objective function, the solution method of the alternating direction multiplier algorithm is used, and the auxiliary variable regularization coefficient is introduced to balance the regular term and the data constraint term, and the optimization problem of the objective function is transformed into a sub-function solution problem;
[0051] Step d, update the alternate direction multiplier algorithm sub-problem;
[0052] Step e, update the Lagrange multiplier;
[0053] Step f, adding correction factor and , correcting the regularization parameter The value of , balance the regula...
specific Embodiment approach 2
[0105] The embodiment reconstruction algorithm selects the ADMM algorithm, and the reconstructed image selects the brain MRI image, and the image size is , and its implementation steps are as follows:
[0106] 1. The known measurement matrix uses a radial measurement matrix to initialize the under-sampled K-space observation data, perform inverse Fourier transform on it, and obtain the reconstructed initialization image x.
[0108] 3. Use the Alternate Multiplier Algorithm to solve the subproblem and update the initial value of the Lagrange multiplier , :
[0109]
[0110] 4. Use regularization parameters Solve the subproblems:
[0111]
[0112] 5. Add correction factor , modifying the regularization coefficient to solve the subproblem:
[0113]
[0114] 6. Set the dual reconstruction index of peak signal-to-noise ratio and structural similarity, and judge whether to add the correcti...
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, which belongs to the field of image processing, provides a compressed-sensing magnetic resonance imaging reconstruction method for correcting regularization parameters. The method comprises: acquiring partial K-space data; constructing a magnetic resonance image reconstruction objective function by using a total variation transformation model theory; on the basis of a solution method of an alternating direction multiplier algorithm, transforming an optimization problem of the objective function into a problem of solving a sub-function by introducing an auxiliary variable regularization coefficient balance regular term and a data constraint term; updating an alternating direction multiplier algorithm sub problem; updating a Lagrangian multiplier; adding a correction factor, correcting regularization parameters, and balancing the regular term and the data item; determining whether a correction factor needs to be added and the value of the correction factor, updating a subproblem solution result and the regularization parameters, and updating the lagrangian multiplier; and determining whether to meet an iteration termination condition and if so, terminating iteration and obtaining a finally reconstructed magnetic resonance image. Therefore, magnetic resonance imaging time can be effectively reduced, so that the technical problem caused by the long time of magneticresonance imaging is solved.
Description
technical field [0001] The invention belongs to the field of image processing, and in particular relates to a compressed sensing magnetic resonance imaging reconstruction method for correcting regularization parameters. Background technique [0002] Magnetic Resonance Imaging (MRI) is one of the most important medical aids in contemporary times. However, MRI imaging technology has problems that need to be solved urgently. The main drawback of MRI is that the signal acquisition time is too long, and the patient is required to be completely still during the scan, otherwise motion artifacts will occur. Excessive scan times and reconfiguration times also reduce equipment utilization and reduce clinical throughput, resulting in expensive operating costs. For this reason, rapid MRI imaging needs to be studied. SUMMARY OF THE INVENTION [0003] The present invention overcomes the above-mentioned deficiencies of the prior art, and provides a compressed sensing magnetic resonanc...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More