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

An automatic identification method for abnormal cervical cells based on a novel Pap staining method

A cervical cell and Papanicolaou staining technique, which is applied in the field of automatic identification of abnormal cervical cells, can solve the problems of low contrast in nuclear and cytoplasmic staining of basal cervical cells, poor control of hydrochloric acid ethanol differentiation time, and high work intensity, so as to shorten the staining time , Suppress the gradient disappearance problem, improve the effect of contrast

Active Publication Date: 2021-02-09
WUHAN LANDING INTELLIGENCE MEDICAL CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, the staining method used in cervical cytology is mainly Papanicolaou staining. There are two main disadvantages in the Papanicolaou staining method: 1. The contrast of nuclear and cytoplasmic staining of basal cervical cells is low;
In addition, the traditional Pap manual reading technology relies on manpower to find some diseased cells from a large number of cells under the microscope. The work intensity is huge, which is easy to cause fatigue, and requires operators to have high pathological knowledge and clinical experience. The diagnosis result is affected by many aspects such as the operator's subjective factors, and human error is inevitable

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
  • An automatic identification method for abnormal cervical cells based on a novel Pap staining method
  • An automatic identification method for abnormal cervical cells based on a novel Pap staining method
  • An automatic identification method for abnormal cervical cells based on a novel Pap staining method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0066] see Figure 1-8 , the present invention provides the following technical solution: a method for automatic identification of abnormal cervical cells based on a novel Pap staining method, comprising the following steps: including two modules:

[0067] Module 1: Training cervical cell classification model based on cervical cell data set;

[0068] Module 2: Use the trained classification model to identify abnormal cervical cells.

[0069] The ...

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 novel Pap staining method and an automatic identification method for abnormal cervical cells, including two modules: module 1: training a cervical cell classification model based on a massive cervical cell data set; module 2: using the trained classification model to identify abnormalities cervical cells. The present invention proposes a novel Papanicolaou staining method, thereby well solving the problems existing in the traditional Papanicolaou staining method, and providing the possibility for automatic high-precision localization of cervical cell nuclei by computer. A method for automatic identification of abnormal cervical cells is also proposed. Experiments show that this method realizes ultra-high-precision automatic identification of abnormal cervical cells. Therefore, the present invention greatly reduces the diagnostic burden of pathologists and improves the diagnosis of cervical diseases. Diagnosis efficiency and accuracy have great practical value and huge social benefits.

Description

technical field [0001] The invention relates to the technical field of medical image diagnosis, in particular to an automatic identification method for abnormal cervical cells based on a novel Pap staining method. Background technique [0002] In recent years, the development of deep learning is in full swing, especially since the proposal of the convolutional neural network model represented by ResNet and DenseNet, the convolutional neural network has become the earliest and most widely used deep learning model. The reason why ResNet and DenseNet can achieve such a large performance improvement is actually due to the idea of ​​​​"crossing connections" used in the network structure. Although both use "spanning connections", their design ideas are different. Among them, ResNet's crossing connection is mainly to solve the problem that the deep network is not easy to fit the identity mapping. ResNet is the output of the residual block through the crossing connection. Provide a...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/32G06K9/62G01N1/30
Inventor 庞宝川柳家胜陈哲刘娟
Owner WUHAN LANDING INTELLIGENCE MEDICAL 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