Cervical cell classification method based on double attention mechanism and multi-scale feature fusion

A multi-scale feature and cervical cell technology, applied in the field of computer vision, can solve problems such as misdiagnosis and missed diagnosis

Active Publication Date: 2021-09-10
HEFEI UNIV OF TECH
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The traditional method of film reading relies entirely on the subjective judgment of pathologists, which will be l...

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 classification method based on double attention mechanism and multi-scale feature fusion
  • Cervical cell classification method based on double attention mechanism and multi-scale feature fusion
  • Cervical cell classification method based on double attention mechanism and multi-scale feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In this example, a cervical liquid-based cell classification method based on double-attention mechanism and multi-scale feature fusion, such as figure 1 As shown, the specific steps are as follows:

[0038] Step 1. Obtain training samples:

[0039] Obtain N types of cervical cell image samples with dimensions H×W×C and perform normalization processing to obtain a normalized training sample set, which is denoted as S={S 1 ,S 2 ,...,S n ,...,S N}; where, S n Represents the nth type of cervical cell image samples, and Indicates the p-th image in the cervical cell image sample after nth normalization; H represents the image height, W represents the image width, C represents the image channel, n=1,2,...,N; this embodiment Use the public cervical cell image dataset Sipakmed for training and testing, such as Figure 4 As shown, it contains 5 categories of cervical cell images, including: surface middle layer cells, parabasal cells, knockout cells, dyskeratotic cells, a...

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 liquid-based cell classification method based on a double attention mechanism and multi-scale feature fusion. The method comprises the following steps: 1, acquiring labeled N types of cervical cell images; 2, establishing a deep learning network based on multi-head self-attention, channel attention and multi-scale feature fusion; 3, constructing a cervical cell image classifier; and 4, realizing image category prediction by using the established classifier. Capturing of correlation of internal features of the image is enhanced through a self-attention mechanism, the defect that the self-attention mechanism lacks channel and multi-scale information is overcome by combining channel attention and multi-scale feature fusion, and accurate classification of cervical cells is completed.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to image classification technology, in particular to a cervical liquid-based cell classification method based on a double-attention mechanism and multi-scale feature fusion. Background technique [0002] Cervical cell classification has important clinical significance in early screening of cervical cancer. At present, the diagnosis of cervical cancer is mainly based on manual reading by pathologists under a microscope. However, at present, the degree of automation of pathology departments in my country is low, the diagnosis time is long, and the overloaded workload greatly increases the work pressure of pathologists, which affects pathology. Doctor's reading efficiency. Therefore, there is a need for a digital cervical cell classification method to assist pathologists in the classification of cervical cells, reduce the burden of film reading on pathologists, relieve the work pressure ...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/253G06F18/214
Inventor 唐昆铭史骏贺雨欣祝新宇王垚孙宇郑利平
Owner HEFEI UNIV OF TECH
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