A Simultaneous Sparse Coding Method for MRI Image Reconstruction Based on Orthogonal Dictionary
A sparse coding and image reconstruction technology, applied in image data processing, 2D image generation, character and pattern recognition, etc., can solve problems such as slow imaging speed, image artifacts, and diagnostic information interference, and improve estimation accuracy. , the visual effect is good, the effect of optimizing the performance of sparse representation
Active Publication Date: 2022-02-18
深圳中物光子科技有限公司
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, there are still some problems to be solved in MRI technology, such as the slow imaging speed, and the images obtained are often accompanied by artifacts, which greatly interfere with the diagnostic information. Therefore, the main improvement of MRI aims to solve these two main problems
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
[0032] refer to figure 1 , the present invention is based on the MRI image reconstruction method of simultaneous sparse coding under the orthogonal dictionary, and concrete steps comprise as follows:
[0033] Step 1. Acquisition of structure group
[0034] The input original K-space data y is initially reconstructed using the total variation method to obtain the initial reconstructed image x (0) , and then in the reconstructed image x (0) Extract the target image block x from i , and then take the target image block x i As the search center, compare the image block with the target image block x one by one within the search range i The Euclidean distance of , the smaller the Euclidean distance is, the more similar it is, through this similar image block matching to find the target image block x i Similar image blocks of , and use the structure group to extract the matrix Get the structure group corresponding to the target image block
[0035] Step 2. Establishment of ...
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 an MRI image reconstruction method based on simultaneous sparse coding under an orthogonal dictionary. It belongs to the technical field of digital image processing. It is an MRI image reconstruction method that utilizes an orthogonal dictionary to sparsely represent the image and simultaneously sparsely encode the sparse coefficients. First find the similar image block set of the target image block, that is, the structure group, and then establish the image reconstruction model based on the simultaneous sparse coding of the structure group under the orthogonal dictionary, and finally use the generalized soft threshold method to solve the sparse coefficient of the structure group in the model and reconstruct the image; the present invention performs sparse representation of the structure group through an orthogonal dictionary, which can optimize the sparse representation performance of the structure group, and uses simultaneous sparse coding and generalized soft threshold method to constrain and solve the sparse coefficients, which can be more efficient and accurate By estimating sparse coefficients, the MRI image reconstructed by the present invention is clearer overall, has richer detail information, and has higher reconstruction accuracy, so it can be used for medical image reconstruction.
Description
technical field [0001] The invention belongs to the technical field of digital image processing, and particularly relates to an MRI image reconstruction method using orthogonal dictionaries to perform sparse representation on structural groups and simultaneous sparse coding to perform coefficient constraints, which is used for high-quality restoration of medical images. Background technique [0002] Magnetic resonance imaging (MRI) is a method that uses the principle of nuclear magnetic resonance to draw the internal image of an object through electromagnetic waves emitted by an external gradient magnetic field, and has been widely used in medical, archaeological, petrochemical and other fields. Compared with the previous medical imaging technology, magnetic resonance imaging has the advantages of higher resolution of soft tissue, no ionizing radiation damage to the human body, higher imaging flexibility and more imaging parameters, so it has become one of the most important ...
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): G06T11/00G06K9/62
CPCG06T11/003G06V10/40G06V10/513G06F18/28G06F18/22
Inventor 刘书君沈晓东曹建鑫张新征李勇明张奎
Owner 深圳中物光子科技有限公司