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

Breast cancer feature information identification method

A technology of feature information and recognition methods, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve problems such as being unsuitable for large-scale data applications, slow in solving speed, etc., and achieve high classification accuracy and convergence speed. Fast, robust effects

Pending Publication Date: 2022-06-03
SOUTH CHINA UNIV OF TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the support vector machine is easy to use, the traditional parameter solution method is a serial solution algorithm, the solution speed is slow, and it is not suitable for large-scale data applications.

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
  • Breast cancer feature information identification method
  • Breast cancer feature information identification method
  • Breast cancer feature information identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] figure 1 A method for identifying breast cancer feature information of the present invention, comprising the following steps:

[0096] 1) Obtain the patient's feature information through the electronic medical record system, select 6 features, namely radius average, texture average, smoothness average, tightness average, symmetry average, and fractal dimension average, and then Data transfer on a computer for data analysis;

[0097] 2) Data preprocessing, including data cleaning and data normalization;

[0098] 3) According to the support vector machine theory, the standard matrix convex quadratic programming problem of the classification model is established based on the data in step 2);

[0099] 4) According to the recursive neural dynamics design method, design a recursive neural network solver for the standard matrix convex quadratic programming problem;

[0100] 5) passing the solution result of step 4) to the classification model, and the classification decisio...

Embodiment 2

[0174] A breast cancer feature information identification method, comprising the following steps:

[0175] 1) Obtain the patient's characteristic information through the electronic medical record system, and select 6 characteristics, which are the average tumor circumference, average texture, average smoothness, average concavity, average symmetry, and average fractal dimension, Then transfer the data to the computer for data analysis;

[0176] The data is preprocessed, including data cleaning, and filling in the default values ​​in the characteristic information corresponding to the collected patients. Normalization, the specific method of z-score normalization is where x represents the input data feature, μ represents the mean value of the feature corresponding to the feature vector, and σ represents the standard deviation of the feature corresponding to the feature vector;

[0177] After preprocessing the data, the data set T will be obtained, and then the decision funct...

Embodiment 3

[0189] A breast cancer feature information identification method, comprising the following steps:

[0190] 1) Obtain the patient's characteristic information through the electronic medical record system, and select 6 characteristics, namely, the average tumor area, the average texture, the average smoothness, the average of the pits, the average of the symmetry, and the average of the fractal dimension, and then transfer the data to a computer for data analysis;

[0191] The data is preprocessed, including data cleaning, and filling in the default values ​​in the characteristic information corresponding to the collected patients. Normalization, the specific method of z-score normalization is where x represents the input data feature, μ represents the mean value of the feature corresponding to the feature vector, and σ represents the standard deviation of the feature corresponding to the feature vector;

[0192] After preprocessing the data, the data set T will be obtained, ...

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 provides a breast cancer feature information identification method, which comprises the following steps of: 1) acquiring feature information of a patient through an electronic medical record system, and then transmitting data to a computer for data analysis; 2) preprocessing the data, including data cleaning and data normalization; 3) establishing a standard matrix convex quadratic programming problem of the classification model based on data according to a support vector machine theory; 4) designing a recurrent neural network solver of the standard matrix convex quadratic programming problem according to a recurrent neural dynamics design method; 5) transmitting the solving result of the step 4) to a classification model to obtain a classification decision function; and 6) judging whether the patient has the characteristic information of the breast cancer or not through the decision function, and displaying the result on a screen. The method is based on a recurrent neurodynamics method, can quickly and accurately converge to a correct solution of a problem, and effectively improves the accuracy of breast cancer classification and recognition.

Description

technical field [0001] The invention belongs to a breast cancer identification and classification method, in particular to a breast cancer characteristic information identification method. Background technique [0002] In recent years, the disease recognition system based on pattern recognition has been developed rapidly. The expert system can replace the doctor to analyze the collected data and obtain the recognition result quickly, which has broad application prospects. With the wide application of breast cancer disease identification systems, the design of efficient and accurate breast cancer classifiers has attracted the attention of many researchers, and breast cancer classifiers are generally designed based on support vector machine algorithms and corresponding improved classification algorithms (Asri H. , MousannifH, Moatassime H A, et al.Using Machine Learning Algorithms for Breast CancerRisk Prediction and Diagnosis[J].Procedia Computer Science,2016,83:1064-1069.). ...

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): G06K9/62G06N3/04G06V10/764G06V10/82
CPCG06N3/044G06F18/2411
Inventor 张智军陈广强黄灿辉
Owner SOUTH CHINA 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