Simple neural network-based automatic AV analysis method and system

A neural network and analysis method technology, applied in the field of micro-ecological morphological analysis, can solve the problem of not finding patents, and achieve the effect of improving the accuracy rate

Pending Publication Date: 2022-03-04
JIANGSU BIOPERFECTUS TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] No relevant paten

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
  • Simple neural network-based automatic AV analysis method and system
  • Simple neural network-based automatic AV analysis method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] According to a kind of simple automatic AV analysis method based on neural network provided by the present invention, as Figure 1-Figure 2 shown, including:

[0056] Step S1: collecting multiple micrographs of multiple samples;

[0057] Step S2: According to the scoring standard, mark the data of the four modules respectively;

[0058] Step S3: training according to modules, one model for each module;

[0059] Step S4: Each image enters four modules for identification respectively;

[0060] Step S5: The recognition results of each model are counted independently to obtain a single module scoring result;

[0061] Step S6: Accumulate the results of each module as the analysis result of the entire sample.

[0062] Specifically, in the step S1:

[0063] The collection uses an automatic biological microscope, 100 times oil lens, and collects 80 to 100 fields of view for each sample as the basis for judgment.

[0064] Specifically, in the step S2:

[0065] Modules wer...

Embodiment 2

[0076] Embodiment 2 is a preferred example of Embodiment 1 to describe the present invention more specifically.

[0077] Those skilled in the art can understand a simple neural network-based automatic AV analysis method provided by the present invention as a specific implementation of the simple neural network-based automatic AV analysis method, that is, the simple neural network-based automatic AV analysis method The AV analysis method can be realized by executing the steps of the simple neural network-based automatic AV analysis method.

[0078] A kind of simple automatic AV analysis system based on neural network provided by the present invention comprises:

[0079] Module M1: Collect multiple micrographs of multiple samples;

[0080] Module M2: according to the scoring standard, mark the data of the four modules respectively;

[0081] Module M3: training according to the modules, one model for each module;

[0082] Module M4: each picture enters four modules for identif...

Embodiment 3

[0099] Embodiment 3 is a preferred example of Embodiment 1 to describe the present invention more specifically.

[0100] The present invention uses a neural network to perform multi-angle identification and classification on multiple micrographs collected from a glass slide, modular scoring, and simulates manual scoring ideas to comprehensively obtain the evaluation results of aerobic vaginitis.

[0101] Manual scoring is performed according to the method in the attached table. Simulating manual means dividing the 4 goals of manual evaluation into 4 modules. After each module is evaluated separately, it is then accumulated to obtain the final result. Each module will have three scores from 0 to 3, and the proportion of the scores of each module will be counted. The score with the highest proportion will be the score of the entire module. The scores of the four modules will be added together to form the final overall AV score.

[0102] The collection uses our company's automati...

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 simple automatic AV analysis method based on a neural network. The method comprises the following steps: S1, collecting a plurality of microscopic pictures; s2, according to a scoring standard, performing data marking on the four modules; s3, training is carried out according to the modules, and each module is a model; and S4, each image enters four modules to be identified respectively. S5, the recognition result of each model is subjected to independent statistics, and a single module scoring result is obtained; and S6, accumulating the results of each module as the analysis result of the whole sample. According to the method, multiple neural network models are adopted for recognition, and each model result is combined with a statistical principle, so that the problems of excessive levels, difficulty in marking and the like of AV discrimination targets are solved, and the mapping problem that each sample has multiple graphs but only one result is effectively solved; the method can effectively avoid the problem that mistaken recognition of one piece affects the whole, and greatly improves the accuracy.

Description

technical field [0001] The invention relates to the field of micro-ecological morphology analysis, in particular to a simple neural network-based automatic AV analysis method and system. Background technique [0002] AV, the full name of aerobic vaginitis (aerobic vaginitis) is a kind of vaginal inflammation characterized by the decrease of Lactobacillus in the vagina and the increase of aerobic bacteria, and it is easy to be combined with other vaginal inflammations. In addition to causing vulvovaginal discomfort, AV can also increase the risk of adverse pregnancy outcomes and sexually transmitted diseases, and seriously endanger women's reproductive health. [0003] At present, there is no standardized diagnostic standard for this disease, and Donders et al. put forward the diagnostic standard of AV in 2002, which is only used as the diagnostic standard of vaginal discharge microscope wet film. In March 2021, Professor Xue Fengxia and her students published "Expert Recomm...

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): G06V20/69G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/2414
Inventor 朱慧敏娄博华鞠佳伟沈海东刘中华王国强
Owner JIANGSU BIOPERFECTUS TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap