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

Near-infrared spectral tomography reconstruction method based on neural network

A technology of near-infrared spectroscopy and tomography, which is applied in the field of medical image processing and can solve the problems of long imaging reconstruction time and so on.

Inactive Publication Date: 2018-11-16
BEIJING UNIV OF TECH
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the ability of traditional regularization methods to suppress artifacts in reconstructed images is weak, and the imaging and reconstruction time is relatively long. Therefore, the present invention considers the use of neural networks for near-infrared spectrum image reconstruction.

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
  • Near-infrared spectral tomography reconstruction method based on neural network
  • Near-infrared spectral tomography reconstruction method based on neural network
  • Near-infrared spectral tomography reconstruction method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be described below based on specific implementation examples and accompanying drawings.

[0046] First of all, through the Matlab toolbox nirfast to establish the phantom and complete the finite element meshing of the phantom. This experiment uses a circular phantom, and the finite element meshing results are as follows figure 2 shown. A total of 16 light sources and 16 light detectors were set up in the experiment, and these detectors were image 3 As shown, it is placed on the outer boundary of a circular phantom with a diameter of 90 mm. A total of 256 measured values ​​can be obtained through light sources and detectors. The imaging pixels are 2001 uniform finite element nodes on the circle. The measured values ​​and each The absorption coefficient value of the finite element node is used as the input and output of the BP neural network. The initial absorption coefficient distribution is as Figure 4 shown. The data set used for netwo...

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 near-infrared spectral tomography reconstruction method based on a neural network and belongs to the field of medical image processing. In a Boltzmann radiation transmissionequation, a light transmission process is regarded as an absorption and scattering process of photons in a medium, the interaction between light and tissue is determined by absorption coefficients, scattering coefficients and phase functions of reactive scattering distribution, only particle properties of the light are considered in transmission, and the volatility of the light is not considered;therefore, phenomena of polarization and interference correlated with the volatility of the light are not considered, and only the energy transmission of the light is tracked. The reconstruction method based on the BP neural network is used for reconstructing the distribution of the absorption coefficients of the light, and a reconstruction result of the distribution of the absorption coefficientscan be obtained through calculation. By means of the method, not only can the distribution of the absorption coefficients be accurately reconstructed, but also high computational efficiency is achieved.

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to a neural network-based near-infrared spectral tomography reconstruction method. Background technique [0002] Near-infrared spectroscopy (NIRS) tomography is a new imaging technology proposed internationally. As a non-destructive testing method, near-infrared spectroscopy is used as an imaging source for imaging, and it has gained widespread attention. The main basis of this technology is that the content of blood sugar, blood oxygen and other substances in different tissues in the body is different, which leads to differences in the absorption coefficient μa and other optical parameters of different tissues for near-infrared light, and optical parameters are used to describe biological tissues. Optical characteristic parameters are related to different physiological states of biological tissues. Using such characteristics, measuring optical characteristic parameters in livi...

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): A61B5/00
CPCA61B5/0075A61B5/7264G06N3/084Y04S10/50A61B5/0073G06N20/00G06N5/046G06T11/006G06T2210/41
Inventor 冯金超孙秋婉贾克斌李哲孙中华
Owner BEIJING UNIV OF TECH
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