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

Dynamic PET image tracer kinetic macro parameter estimation method based on stacked autoencoder

A stack-type auto-encoder and auto-encoder technology is applied in the field of dynamic PET image tracer dynamics macro parameter estimation, which can solve the problem of low stability of results and achieve the effect of fast and accurate estimation

Active Publication Date: 2018-12-11
ZHEJIANG UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The former depends on the number of compartment models, and the estimated results are not stable; the latter does not depend on the number of compartment models, but it needs to be determined in advance whether the tracer belongs to a reversible compartment model or an irreversible compartment model, and This method also depends on the fitting method, the quality of the fitting method directly determines the accuracy of the physiological parameters

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
  • Dynamic PET image tracer kinetic macro parameter estimation method based on stacked autoencoder
  • Dynamic PET image tracer kinetic macro parameter estimation method based on stacked autoencoder
  • Dynamic PET image tracer kinetic macro parameter estimation method based on stacked autoencoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043]In order to describe the present invention more specifically, the technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0044] The present invention is based on the stacked autoencoder dynamic PET image tracer dynamics macro parameter estimation method, the overall framework is as follows figure 1 As shown, it specifically includes the following steps:

[0045] S1. Inject the tracer into the biological tissue, use the detector to detect the biological tissue injected with the radiopharmaceutical, collect the coincidence count vector of each crystal block corresponding to the detector, and then construct the coincidence count matrix y of the dynamic PET.

[0046] S2. According to the PET imaging principle, the PET concentration distribution image x of the tracer is obtained by solving the following equation through the ML-EM algorithm:

[0047] y=Gx+noise

[0048] Where: G...

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 discloses a dynamic PET image tracer kinetic macro parameter estimation method based on a stacked autoencoder. The method first introduces the idea of deep learning into the dynamic PETtracer kinetic macro parameter estimation, and has a process mainly divided into a training stage and an estimation stage. In the training stage, the stacked autoencoder is constructed by using a dynamic PET tracer concentration distribution image as an input and using a dynamic PET tracer macro parameter as a label training autoencoder. In the estimation stage, the dynamic PET tracer concentration distribution image is input into the trained stacked autoencoder so as to estimate the kinetic macro parameter of the tracer. The method achieves rapidly and accurately estimates the kinetic macro parameter of the dynamic PET image from the data driving perspective without a compartment model.

Description

technical field [0001] The invention belongs to the technical field of PET imaging, and in particular relates to a method for estimating macro-parameters of dynamic PET image tracer dynamics based on a stacked autoencoder. Background technique [0002] Positron emission tomography (PET) is a nuclear medicine functional imaging technique that plays a vital role in biomedical research and clinical diagnosis. PET imaging generally uses short-lived radioisotopes (such as 18 F. 11 C, etc.) to mark biomolecules, these biomolecules decay in the metabolic activities of the organism to produce positrons, and the annihilation reaction between the generated positrons and the negative electrons in the body produces a pair of gamma photon pairs with opposite directions and energy of 511keV, Gamma Horse photons are captured by ring-shaped detectors, resulting in emission data that are then analyzed by a computer to construct an image of the tracer concentration in the body. [0003] Co...

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): G16H50/50G06T11/00A61B6/03
CPCA61B6/037A61B6/5211G06T11/003G16H50/50
Inventor 刘华锋阮东升
Owner ZHEJIANG UNIV
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