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

Cell classification result correction method based on multi-peak fitting analysis

A cell classification and multi-peak fitting technology, applied in the field of medical diagnosis, can solve problems such as low accuracy of results and the inability of automatic classification algorithms to accurately separate two types of cells, and achieve the effect of improving accuracy

Pending Publication Date: 2021-07-20
URIT MEDICAL ELECTRONICS CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a cell classification result correction method based on multi-peak fitting analysis, aiming to solve the problem that when two or more types of cells in a sample have similar characteristics, the automatic classification algorithm cannot accurately separate the two types of cells, resulting in accurate results. low degree problem

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
  • Cell classification result correction method based on multi-peak fitting analysis
  • Cell classification result correction method based on multi-peak fitting analysis
  • Cell classification result correction method based on multi-peak fitting analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] like figure 1 As shown, the present invention discloses a cell classification result correction method based on multi-peak fitting analysis.

[0038] S101. Classify the characteristic data of the sample cells collected by the cell analyzer according to the automatic classification algorithm, extract the characteristic histogram of the sample cells, and obtain the characteristic peak function to which each type of cell belongs.

[0039] Taking the five classifications of white blood cells as an example, the characteristic data of white blood cells collected by the cell analyzer are classified, and the scatter diagram is obtained by the automatic classification algorithm as follows: figure 2 shown. Shown in the figure are neutrophils 1, monocytes 2, lymphocytes 3, eosinophils 4, and basophils 5. Taking the overlap correction between neutrophil 1 and monocyte 2 as an example, calculate the principal direction histogram of its classification features. Perform a median f...

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 cell classification result correction method based on multi-peak fitting analysis, and the method comprises the following steps: classifying various cells by using an automatic classification algorithm according to sample cell characteristics collected by a cell analyzer; according to an automatic classification result, extracting a feature histogram of overlapped cell classification, and extracting a noise signal obtained by Gaussian filtering elimination sampling with a step length of 3 or 5 in the process; estimating Gaussian distribution parameters according to the cell distribution, and respectively executing coarse Gaussian distribution fitting on each wave crest; on the basis of the rough fitting result, executing overlapped Gaussian distribution fitting, and obtaining the distribution parameters of cell peaks; selecting an overlapping region of each cell peak, calculating the area ratio of the overlapping region, completing cell content correction, and improving the classification accuracy.

Description

technical field [0001] The invention relates to the field of medical diagnosis, in particular to a method for correcting cell classification results. Background technique [0002] Blood routine is one of the three routine items in medical clinical examination. By analyzing the content of different cells in human blood and comparing the range of various cell content in normal human blood, it can provide doctors with the basis for disease diagnosis and is an important factor in judging human health. in accordance with. [0003] Usually, a cell analyzer is used to detect blood routine. The existing cell analyzer usually counts tens of thousands of cells in the sample to be tested, and at the same time extracts the characteristic signals such as the volume, complexity, and diopter of each cell to obtain a one-dimensional histogram of the counted sample. graph or 2D or 3D scatterplot. By setting the boundary range in the histogram or scatter plot, the cells whose characteristic...

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): G06K9/00G06K9/40G06K9/46
CPCG06V20/69G06V20/698G06V10/30G06V10/50G06V2201/03
Inventor 韦笑王梦龙秦鑫龙
Owner URIT MEDICAL ELECTRONICS CO LTD
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