Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Magnetic resonance image processing method and device, storage medium and magnetic resonance imaging system

A magnetic resonance image and processing method technology, applied in the field of medical image processing, can solve the problems of difficult control of restraint, unnatural details of magnetic resonance images, poor mosaic effect suppression effect, etc., to improve the degree of suppression and correct artifacts good effect

Active Publication Date: 2020-07-24
SHANGHAI UNITED IMAGING INTELLIGENT MEDICAL TECH CO LTD
View PDF15 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the interpolation method of magnetic resonance image domain data is not effective in suppressing the mosaic effect due to insufficient resolution; and the constraint strength of the k-space data extrapolation method is not easy to control. If the constraint is too loose, it cannot be effective. Suppresses heavy truncation artifacts, if the constraints are too heavy, it will modify the appearance of the MRI image, making the details of the MRI image look unnatural

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
  • Magnetic resonance image processing method and device, storage medium and magnetic resonance imaging system
  • Magnetic resonance image processing method and device, storage medium and magnetic resonance imaging system
  • Magnetic resonance image processing method and device, storage medium and magnetic resonance imaging system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] In the process of magnetic resonance imaging, due to the absence of high-frequency components in k-space, serious Gibbs artifacts will be generated in the final image. The magnetic resonance image processing method provided in this embodiment can be applied to the artifacts in magnetic resonance images. Shadow correction, especially suitable for reducing Gibbs artifacts or truncation artifacts in magnetic resonance images. The method can be executed by a magnetic resonance image processing device, which can be realized by software and / or hardware, and which can be integrated in a device with image processing functions, such as a notebook computer, a desktop computer or a server. see figure 1 , the method of this embodiment specifically includes the following steps:

[0031] S110. Acquire the data to be corrected, and input the data to be corrected into the artifact correction model to generate initial correction data.

[0032] Among them, the collection of data to be ...

Embodiment 2

[0049] In this embodiment, on the basis of the foregoing embodiments, "generate the first weight matrix and the second weight matrix according to the preset weight value distribution rule" is added. On this basis, it is also possible to further optimize the "weighting processing on the data to be corrected and the initial corrected data respectively to generate a weighted result". The explanations of terms that are the same as or corresponding to the above-mentioned embodiments will not be repeated here. see Figure 3A , the magnetic resonance image processing method provided in this embodiment includes:

[0050] S210. Acquire data to be corrected, and input the data to be corrected into the artifact correction model to generate initial correction data.

[0051] Such as Figure 3B is a schematic diagram of an exemplary artifact correction model described according to some embodiments of the present application. The artifact correction model may adopt a neural network model...

Embodiment 3

[0074] This embodiment provides a magnetic resonance image processing device, see Figure 4 , the device specifically includes:

[0075] The initial correction data generation module 410 is used to obtain the data to be corrected, and input the data to be corrected into the artifact correction model to generate initial correction data, wherein the artifact correction model is obtained based on the pre-training of the neural network model, and k corresponding to the initial correction data The space includes more high-frequency components than the k-space corresponding to the data to be corrected;

[0076] The weighted fusion module 420 is used to perform weighted processing on the data to be corrected and the initial corrected data respectively, generate a weighted result, and perform fusion processing on the two weighted results to generate target corrected k-space data;

[0077] A reconstruction module 430, configured to reconstruct target-corrected k-space data, and genera...

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

No PUM Login to View More

Abstract

The embodiment of the invention discloses a magnetic resonance image processing method and device, a storage medium and a magnetic resonance imaging system. The method comprises the steps of obtainingto-be-corrected data, inputting the to-be-corrected data into an artifact correction model, and generating initial correction data, wherein the artifact correction model is obtained through pre-training based on a neural network model, and a k space corresponding to the initial correction data comprises more high-frequency components than the k space corresponding to the to-be-corrected data; performing weighting processing on the to-be-corrected data and the initial correction data to generate weighting results, and performing fusion processing on the two weighting results to generate targetcorrection k space data; and reconstructing the target correction k space data to generate an artifact-corrected target correction magnetic resonance image. Through the technical scheme, the magneticresonance image with a better artifact correction effect is obtained under the condition that the resolution and the signal-to-noise ratio of the artifact-corrected magnetic resonance image are basically unchanged and the scanning time is not increased.

Description

technical field [0001] Embodiments of the present invention relate to medical image processing technologies, and in particular to a magnetic resonance image processing method, device, storage medium, and magnetic resonance imaging system. Background technique [0002] A magnetic resonance image taken by an imaging system, such as a magnetic resonance imaging (MRI) system, can be represented as magnetic resonance image data in the spatial domain or as magnetic resonance image-related data in k-space, ie the frequency domain. Sharp transitions in magnetic resonance images, such as transitions near boundaries of organs, can be demonstrated in k-space using relatively high frequency components. However, limited sampling time or poor signal-to-noise ratio (SNR) may lead to undersampling of magnetic resonance image-related data in k-space (referred to as k-space data). This can lead to insufficient high-frequency components in the MR image data, leading to "edge ringing" phenomen...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01R33/58G06T11/00
CPCG01R33/58G06T11/008
Inventor 李国斌刘楠黄小倩廖术
Owner SHANGHAI UNITED IMAGING INTELLIGENT MEDICAL TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products