Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

The cGAN-based adaptive network is used for enhancement method of low-dose PET image

An adaptive network and image enhancement technology, applied in the field of image processing and deep learning, to achieve the effect of enhancement and good effect

Active Publication Date: 2021-03-12
HEBEI UNIVERSITY
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a GAN-based adaptive network enhancement method for low-dose PET images to solve the problem that the existing network can only target a single type of low-dose PET image and cannot generate low-dose PET images at different doses. Problems with dose PET images

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
  • The cGAN-based adaptive network is used for enhancement method of low-dose PET image
  • The cGAN-based adaptive network is used for enhancement method of low-dose PET image
  • The cGAN-based adaptive network is used for enhancement method of low-dose PET image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Such as figure 1 Shown, the present invention is based on cGAN adaptive network and is used for the enhancement method of low-dose PET image and comprises the following steps:

[0043] 1. Scan the whole body of the patient who is injected with the tracer that meets the standard dose, so as to obtain the PET image of the whole body of the patient under the standard dose;

[0044]2. Random partial sampling of the raw data of the PET image under the standard dose to simulate the real situation of injecting the patient with a tracer lower than the standard dose;

[0045] 3. Using the same reconstruction parameters as those used for PET image reconstruction under standard doses, reconstruct the sampling data obtained by the above random partial sampling, and reconstruct all physical corrections including attenuation correction, scatter correction and random correction;

[0046] 4. Input the reconstructed PET images under different doses and PET images under standard doses ...

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 relates to a cGAN-based adaptive network enhancement method for a low-dose PET image, and the method comprises the following steps: carrying out the whole-body scanning of a patient injected with a 18F-FDG tracer agent meeting a standard dose, so as to obtain a whole-body PET image of the patient under the standard dose; random partial sampling being carried out on PET original datato reduce the dosage so as to simulate the situation of low-dosage tracer agent injection under the real situation, and then reconstruction parameters which are the same as those during full-dosage PET image reconstruction being adopted to reconstruct the data, including all physical corrections; inputting the reconstructed PET images with different doses and the reconstructed full-dose standard image into a network for training, so that the network can automatically match the PET images with different low doses and obtain an image close to the standard dose; carrying out whole-body scanning on the patient injected with the tracer agent with the dose lower than the standard dose to obtain a PET image under a low dose; and inputting the low-dose PET image into the network model for enhancement, so as to obtain a clear whole-body PET image.

Description

technical field [0001] The invention relates to a method of image processing and deep learning, in particular to an enhancement method for low-dose PET images using a cGAN-based adaptive network. Background technique [0002] With the continuous development of science and technology, artificial intelligence technology is more and more used in medical diagnosis, hoping to help doctors make better diagnoses through artificial intelligence technology. Positron emission tomography, a nuclear medicine imaging technique, enables the visualization of metabolic processes in the human body. At present, this technology has been applied clinically, such as diagnosis, staging and treatment monitoring. In order to obtain high-quality PET images for diagnosis, patients are usually injected with 18F-FDG tracer at a dose of 5–10 mCi according to the patient’s weight. However, PET scanning generally requires a long time exposure to the radioactive environment, and there is radiation damage...

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
IPC IPC(8): G06T11/00G16H30/20G06N3/04G06N3/08
CPCG06T11/005G16H30/20G06N3/08G06T2211/424G06N3/045
Inventor 杨昆刘琨钱武侠杜禹薛林雁刘爽
Owner HEBEI UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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