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

Dynamic PET image reconstruction method based on self-encoder image fusion

A self-encoder and image reconstruction technology, which is applied in the field of PET imaging, can solve the problems of inaccurate solution, noisy reconstructed image, and low number of iterations, so as to achieve good reconstruction effect and improve the effect of PET reconstruction

Active Publication Date: 2016-06-15
ZHEJIANG UNIV
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the MLEM method is not able to obtain accurate reconstruction results. Due to the ill-conditioned nature of the problem, the obtained results are closely related to the number of iterations.
If the number of iterations is too low, the obtained solution is not accurate enough, which is manifested in the blurring of the entire image; if the number of iterations is too high, there will be more noise in the entire reconstructed image

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 reconstruction method based on self-encoder image fusion
  • Dynamic PET image reconstruction method based on self-encoder image fusion
  • Dynamic PET image reconstruction method based on self-encoder image fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to describe the present invention more clearly, the technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0048] The present invention is based on the dynamic PET image reconstruction method of self-encoder image fusion, and concrete implementation steps are as follows:

[0049] S1. Initialize the number of frames N, the number of iterations M, the number of self-encoding layers S, the number of nodes in each layer, and the block size;

[0050] S2. For each x i , i=i 1 ,i 2 ,…i N , to simulate the dynamic PET emission data y i ;

[0051] S3. Reconstruct y according to the MLEM algorithm i Corresponding to the reconstruction result with iteration number k, k=k 1 ,k 2 …k M ;

[0052] S4. If figure 1 As shown, the block of the reconstruction result is used as the first layer of the self-encoder image, and the true value is used as the last layer, and the pa...

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 reconstruction method based on self-encoder image fusion. The method learns from the theory of integrated learning in machine learning, takes an MLEM algorithm as a weak classifier, obtains a strong classifier through integration of different weak classifiers, and improves the PET reconstruction effect. The method improves an existing MLEM algorithm, adopts a self-encoder structure to carry out image fusion on reconstruction results of different iterations, so that obtains an optimized reconstruction result. Compared with reconstruction methods in the prior art, the method has better reconstruction effect.

Description

technical field [0001] The invention belongs to the technical field of PET imaging, and in particular relates to a dynamic PET image reconstruction method based on autoencoder image fusion. Background technique [0002] Positron Emission Tomography (PET) is a relatively advanced clinical examination imaging technology in the field of nuclear medicine. Its basic principle is: combine some short-lived radioactive substances, such as 18 F. 11 C is marked into some necessary substances in human metabolism, such as protein, glucose, nucleic acid, etc., through the metabolism of these substances to reflect the condition of the human body and achieve the purpose of diagnosis. [0003] In the metabolic process, the decay of radioactive substances will produce positrons, and a positron will annihilate when it meets an electron after flying for a certain distance, producing a pair of photons with energy of 511KeV in opposite directions, which can be detected by high sensitivity The ...

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): G06T11/00
CPCG06T11/00G06T2207/10104G06T2211/416G06T2211/424
Inventor 刘华锋王祎乐
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