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

Multi-nuclide magnetic resonance multi-scale image registration method

A magnetic resonance image and image registration technology, which is applied in the field of medical image processing, achieves the effect of simple calculation method and reduced error

Pending Publication Date: 2022-01-14
HARBIN MEDICAL UNIVERSITY
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the problems existing in the image registration of the above-mentioned multi-nuclide magnetic resonance and the shortcomings of the existing technology, the present invention proposes a method for multi-scale image registration of multi-nuclide magnetic resonance, which can solve the problem of multi-nuclide image registration. Issues in the registration application

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
  • Multi-nuclide magnetic resonance multi-scale image registration method
  • Multi-nuclide magnetic resonance multi-scale image registration method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] like figure 1 As shown, a multi-parentin magnetic resonance multi-scale image registration method, including the following steps:

[0023] Step 1: Using a multinuclein synchronously integrated imaging magnetic resonance system, including including 1 H, 19 F, 23 NA, 31 Pyrovination of magnetic resonance images for collecting; the multiklane synchronous integrated imaging magnetic resonance system using patented CN107329100B;

[0024] Step 2: Select 1 H Magnetic resonance image as a reference image, 19 F magnetic resonance image as a floating image;

[0025] Step 3: Extract the reference image and the floating image, the feature point extraction includes the following steps: 1 H, 19 The F magnetic resonance image performs pyramid segmentation, using adjacent scale Gaussian filter smooth images, and further derives the processed image, reduce the image to the previous 1 / 4; repeat the above process, obtain a series of divisions Net structure;

[0026] Step 4: The reference imag...

Embodiment 2

[0028] A multi-parentin magnetic resonance multi-scale image registration method, including the following steps:

[0029] Step 1: Using a multinuclein synchronously integrated imaging magnetic resonance system, including 1 H, 19 F, 23 NA, 31 P and other magnetic resonance images are collected;

[0030] Step 2: Select 1 H Magnetic resonance image as a reference image, 23 Na magnetic resonance image as a floating image;

[0031] Step 3: Extract the reference image and the floating image, the feature point extraction includes the following steps: 1 H, 23 NA magnetic resonance image performs pyramid segmentation, using adjacent scale Gaussian filter smooth images, and further depends on the processed image, minimizing the image is previously 1 / 4, and repeats the above process, obtain a series of sections After the mesh structure;

[0032] Step 4: The reference image and the floating image are image registration by using the B-spline deformation method. The specific steps are as follow...

Embodiment 3

[0034] A multi-parentin magnetic resonance multi-scale image registration method, including the following steps:

[0035] Step 1: Using a multinuclein synchronously integrated imaging magnetic resonance system, including 1 H, 19 F, 23 NA, 31 P and other magnetic resonance images are collected;

[0036] Step 2: Select 1 H Magnetic resonance image as a reference image, 31 P magnetic resonance image as a floating image;

[0037] Step 3: Extract the reference image and the floating image, the feature point extraction includes the following steps: 1 H, 31 The P magnetic resonance image performs pyramid segmentation, using adjacent scale Gaussian filter smooth images, and further derives the processed image, minimize the image to 1 / 4, and repeat the above process multiple times, obtain a series of sections After the mesh structure;

[0038] Step 4: The reference image and the floating image are image registration by using the B-spline deformation method. The specific steps are as follow...

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 invention provides a multi-nuclide magnetic resonance multi-scale image registration method. The method comprises the following steps: step 1, collecting magnetic resonance images of 1H and X nuclides; step 2, selecting a 1H magnetic resonance image as a reference image, and selecting a magnetic resonance image of X nuclide as a floating image; step 3, carrying out feature point extraction on the reference image and the floating image; and step 4, carrying out image registration on the reference image and the floating image by adopting a B spline deformation method. According to the method, characteristic registration is carried out on the 1H image and the X nuclear image (19F, 23Na and 31P) in the multi-nuclide synchronous integrated magnetic resonance scanning image, the calculation method is simple and convenient, and errors caused by manual registration are reduced to a certain extent.

Description

Technical field [0001] The present invention relates to the field of medical image processing, in particular, refers to a method for multi-americen magnetic resonance multi-scale image registration. Background technique [0002] Magnetic resonance imaging (MRI) has an advantage of excellent soft tissue resolution, multi-parameter imaging capability, 3D reconstruction arbitrary aspect and function imaging, play a huge role in early diagnosis and efficacy monitoring of diseases. MRI can provide rich information for the diagnosis of the disease, and there is no disadvantages such as ionizing radiation injury. However, traditional magnetic resonance imaging is mononagne 1 H imaging, including information, unable to reveal the development of the disease from a deeper level. Multikin synchronous integrated chemical imaging provides a multi-molecular event analysis technique for disease mechanism, which can systematically reveal the molecular mechanism in the process of disease developm...

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): G06T7/11G06T7/33G06T5/00
CPCG06T7/33G06T7/11G06T2207/10088G06T2207/20016G06T5/70
Inventor 孙夕林杨春升王凯李迎波杨洁徐佐宇杨丽丽吴丽娜方芳
Owner HARBIN MEDICAL UNIVERSITY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com