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

Echinococcosis patient serum spectral recognition method based on principal component analysis and BP neural network

A principal component analysis and neural network technology, applied in material excitation analysis, Raman scattering, etc., can solve the problems of clinical diagnosis that have not been reported, and achieve the effect of easy implementation, convenient operation and high diagnostic accuracy.

Inactive Publication Date: 2017-04-26
THE FIRST TEACHING HOSPITAL OF XINJIANG MEDICAL UNIVERCITY
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Zhou Xue et al. performed statistical analysis on the hemoglobin surface Raman spectra of patients with esophageal cancer and healthy people combined with normalization and principal component analysis. However, the application of Raman spectroscopy to the clinical diagnosis of echinococcosis has not been reported.

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
  • Echinococcosis patient serum spectral recognition method based on principal component analysis and BP neural network
  • Echinococcosis patient serum spectral recognition method based on principal component analysis and BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0018] Embodiment 1, the spectral identification method of the echinococcosis patient's serum based on the principal component analysis-BP neural network, is carried out according to the following steps: the first step, absorb the blood of at least 20 healthy people and at least 20 echinococcosis patients respectively Serum, and the absorbed serum is placed in a Raman spectrometer for full-wavelength scanning and data collection; the Raman spectrometer can use the Raman spectrometer of horiba company, and use the supporting software LabSpec 6 to collect data;

[0019] The second step is to normalize the collected data; in order to eliminate the noise generated by light source interference and collection methods when the instrument collects the spectrum, it is necessary to preprocess the collected raw data before analysis. Pre-process the collected raw data to eliminate the effects of light scattering, sample inhomogeneity, etc.;

[0020] The third step is to conduct principal ...

Embodiment 2

[0022] Embodiment 2, according to the hidden layer of the BP neural network, the required input parameters of the s-type activation function logsig are distributed between [0,1], and the input and output values ​​are defined in the range of [0,1], normalized The algorithm adopts the formula: χ i ’=(χ i -χ min ) / (χ max -χ min ), where χ i is the data that needs to be normalized, χ i ’ is the normalized sample data, χ min for χ i The minimum value in χ max for χ i the maximum value in .

[0023] 1. Experiments and methods

[0024] 1.1 Blood samples and instruments

[0025] Blood: 38 cases of healthy people with clear diagnosis and complete data were taken randomly, and 28 cases of echinococcosis patients were provided by the First Affiliated Hospital of Xinjiang Medical University.

[0026] Instrument: The Raman spectrometer of Horiba Company was used in the experiment, the measured wavelength range was 101.298nm to 3999.76nm, and the resolution was less than 0.02nm....

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 the technical field of spectral recognition, and provides an echinococcosis patient serum spectral recognition method based on principal component analysis and a BP neural network. The method is implemented according to the steps that 1, serum of at least 20 healthy persons and serum of at least 20 echinococcosis patients are sucked separately and placed in a raman spectrometer for full-wavelength scanning and data collecting; 2, collected data is subjected to normalization processing; 3, the data obtained after normalization is subjected to principle component analysis, and scores of all principle components of which the accumulated contribution rates reach 80% are taken as input layer nodes of the BP neural network. According to the method, an echinococcosis spectral diagnosis technical scheme with the high accuracy is established by adopting the method of combining principle component analysis (PCA) with the BP neural network, the diagnosis accuracy rate is high, and operation and implementation are convenient.

Description

technical field [0001] The invention relates to the technical field of spectral recognition, and relates to a method for spectral recognition of echinococcosis patient serum based on principal component analysis-BP neural network. Background technique [0002] Echinococcosis is a zoonotic disease that spreads around the world. There are 500,000 cases of echinococcosis in my country, and the threatened population is more than 66 million. Especially in Xinjiang, the average annual surgical treatment is only 2,000 cases above. [0003] At present, the diagnostic methods of echinococcosis mainly include imaging diagnosis, but the biggest disadvantage of imaging diagnosis method is that the equipment is expensive, the operation is time-consuming, and professional operation is required, which brings great difficulties to the census work of echinococcosis and some atypical imaging cases , and not suitable for grassroots and field operations. In addition, some new serum-based metho...

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): G01N21/65
CPCG01N21/65
Inventor 温浩吕国栋程金盈吕小毅莫家庆刘辉林仁勇卢晓梅李亮毕晓娟张传山杨宁
Owner THE FIRST TEACHING HOSPITAL OF XINJIANG MEDICAL UNIVERCITY
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