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

Fast imaging method and device based on neural network positioning algorithm

A neural network and localization algorithm technology, applied in the field of fast imaging methods and devices based on neural network localization algorithm, can solve the problems of high electronic noise and increase of reconstruction time, etc.

Active Publication Date: 2021-04-20
CHENGDU UNIVERSITY OF TECHNOLOGY
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the low-activity internal pollution imaging simulation, the number of photons received by the detector is small, and the obtained projection data will be accompanied by high electronic noise, requiring a large number of iterations to reconstruct the internal pollution image, which increases the reconstruction time

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
  • Fast imaging method and device based on neural network positioning algorithm
  • Fast imaging method and device based on neural network positioning algorithm
  • Fast imaging method and device based on neural network positioning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] Embodiment 1: see Figure 1 to Figure 6 , a fast imaging method based on a neural network positioning algorithm, applied to a fast imaging device based on a neural network positioning algorithm, the device includes a coded aperture collimator, a detector and a signal readout unit connected in sequence, the detector Including the scintillator, the rays act on the surface of the scintillator through the coded hole collimator, the detector is converted into a pulse signal array, and then converted into a detector array response matrix through a signal readout unit, and the method includes the following steps:

[0076] (1) Determine the size of the coded hole collimator and detector according to the detection range, establish a coordinate system on the surface of the scintillator, and divide the surface of the scintillator into several grids, each grid corresponds to a coordinate;

[0077] (2) Train an MLP neural network to obtain a network model, specifically:

[0078] (2...

Embodiment 2

[0110] Example 2: see Figure 1 to Figure 6 , in this embodiment, we need to detect and quickly image the pollution in the lungs of adults. In this embodiment, we first establish a fast imaging device based on the neural network positioning algorithm, and its structure is the same as the one in embodiment 1. Fast imaging device based on neural network localization algorithm. The specific imaging method applied to the device includes the following steps:

[0111] (1) Determine the size of the coded hole collimator and detector according to the detection range, and establish a fast imaging device based on the neural network positioning algorithm, which can be realized through steps (11)-(18);

[0112] (11) We preset the square range covering the entire lung as the imaging range, and the size is FoV =300 mm ×300 mm ;

[0113] (12) Select the detector as a monolithic LaBr3 detector with a thickness of side length d d =301 mm , the detection range is 301 mm ×301 mm...

Embodiment 3

[0139] Embodiment 3: see Figure 6-Figure 9c , based on Example 2, Figure 7a , 7b , 7c are three diagrams of radioactive sources. In this implementation, we have selected three radioactive sources of different shapes, which are Figure 7a : point radioactive source; Figure 7b : circular radioactive source; Figure 7c , a radioactive source of irregular shape. And for better illustration effect, Figure 7c In , we use the pattern of the letter "CDUT" to demonstrate, in fact, it is not limited to this pattern.

[0140] we take Figure 7b Taking the radioactive source as an example, the radioactive source passes through the code hole collimator, the crystal, and the neural network to obtain the coded image of the radioactive source, such as Figure 8a As shown in the figure on the left, it is extended and filled with zeros around it, such as Figure 8a As shown on the right; Figure 8b It is to process the matrix function of the MPA-MURA coded aperture collimator;

[...

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 fast imaging method and device based on a neural network positioning algorithm. The device includes a coding hole collimator, a detector, a signal readout unit, an MLP type neural network, an event statistics unit, and an image reconstruction unit. In the present invention, the surface of the scintillator of the detector is first gridded so that each grid corresponds to a coordinate, and then the MLP type neural network is trained so that the input is the response matrix of the detector array and the output is the coordinate of the ray action position. ability. During imaging, the positive and negative coding patterns corresponding to the coding hole collimator at the initial position and 90° rotation are respectively obtained; and then respectively reconstructed, combined with subtraction operation, wavelet transform, and high-frequency and low-frequency denoising, to obtain the image of the present invention. The invention can effectively reduce the interference of near-field artifacts on reconstructed images, increase image clarity, and has the advantages of simple structure, small volume, convenient operation, high detection efficiency and fast reconstruction speed.

Description

technical field [0001] The invention relates to an imaging method and an imaging device, in particular to a fast imaging method and device based on a neural network positioning algorithm. Background technique [0002] Gamma-ray imaging technology is a nuclear radiation detection technology that "photographs" radioactive substances. Since the advent of the "Anger" camera, people have started research on gamma-ray imaging technology. Existing gamma cameras are mainly used in astronomical research, nuclear medicine and nuclear radiation monitoring. [0003] In the field of medical imaging, gamma cameras mostly use parallel beam collimators for imaging, which have high spatial resolution, but low detection efficiency, large volume, and limited applicable environments; and the activity of tracer nuclides introduced into patients in medical diagnosis Generally reach 10 6 Bq level, the activity is too high. Not only that, but gamma cameras in the field of nuclear medicine requi...

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 Patents(China)
IPC IPC(8): G06T11/00G06T5/00G06F17/14G01T1/20G06N3/04G06N3/08
CPCG06T11/008G06T5/002G06F17/148G01T1/20G06N3/08G06T2207/20081G06T2207/20084G06T2207/30061G06N3/045
Inventor 王磊张婷卢位李浩炫杨月周英杰
Owner CHENGDU UNIVERSITY OF TECHNOLOGY
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