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

Cervical cell image classification method based on convolutional neural network

A convolutional neural network and cervical cell technology, which is applied in the field of cell image processing, can solve the problems of fatigue, high work intensity, low recognition accuracy and low recognition efficiency, and achieves improved feature reuse, accuracy and efficiency. The effect of application value and market prospect

Inactive Publication Date: 2019-10-22
MOTIC XIAMEN MEDICAL DIAGNOSTICS SYST +1
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In my country, the current traditional cervical cell image recognition method is mainly Pap manual film reading technology. Pap manual film reading technology relies on people observing a large number of cell images under a microscope, which is labor-intensive and easy to make people feel tired. The accuracy and recognition efficiency are low

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
  • Cervical cell image classification method based on convolutional neural network
  • Cervical cell image classification method based on convolutional neural network
  • Cervical cell image classification method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to better understand the technical solution of the present invention, the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0028] The present invention is a kind of cervical cell image classification method based on convolutional neural network, and this method mainly comprises the following several steps:

[0029] Step 1: Prepare training samples and classify the training samples to obtain eleven types of samples; wherein, the training samples are labeled images of cervical cells, and the eleven types of samples include normal superficial cells, normal middle and bottom cells, granulosa cells, glandular cells, atypical squamous cells, koilocytes, high N / C cells, lymphocytes, clumps, monocytes, and trash.

[0030] Step 2: Build a dense convolutional neural network; including the following sub-steps: input the three-channel cervical cell image with label information into the convolution...

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 cervical cell image classification method based on a convolutional neural network. The method comprises the following steps: preparing a training sample, classifying the training sample to obtain eleven types of samples, constructing a convolutional neural network, inputting the training sample into a convolutional neural network model for training, iterating for a certain number of times, stopping training, and storing network weight parameters. When the method is used, a target image is segmented into a to-be-predicted area with cell nucleuses, and then weight parameters and a network structure obtained through training are loaded. The to-be-predicted area is input into the to-be-predicted area. A classification result can be obtained through calculation. The method improves the accuracy and efficiency of cervical cell diagnosis, and has strong adaptive capacity.

Description

technical field [0001] The invention relates to the technical field of cell image processing, in particular to a method for classifying cervical cell images based on a convolutional neural network. Background technique [0002] In my country, the current traditional cervical cell image recognition method is mainly Pap manual film reading technology. Pap manual film reading technology relies on people observing a large number of cell images under a microscope, which is labor-intensive and easy to make people feel tired. The accuracy and recognition efficiency are low. [0003] Convolutional Neural Networks (CNN) is a feed-forward deep neural network that contains convolution operations and is specially designed to process data with a grid-like structure. The convolutional layer and pooling layer contained in the network are the core modules to realize the feature extraction function of the convolutional neural network. The input of the convolution is a two-dimensional featur...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/69G06N3/045G06F18/214
Inventor 史骏代杰
Owner MOTIC XIAMEN MEDICAL DIAGNOSTICS SYST
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