Supercharge Your Innovation With Domain-Expert AI Agents!

A white blood cell automatic classification method and system based on a mixed attention residual network

A network implementation and automatic classification technology, applied in the field of medical image analysis, can solve the problems of not being able to make full use of key features and important information, limit the performance of neural networks, etc., achieve the effect of improving classification accuracy, improving classification accuracy, and reducing loss

Pending Publication Date: 2021-09-03
SHANDONG NORMAL UNIV
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most deep learning methods cannot make full use of key features and important information when performing convolution operations, which largely limits the performance of neural networks.

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
  • A white blood cell automatic classification method and system based on a mixed attention residual network
  • A white blood cell automatic classification method and system based on a mixed attention residual network
  • A white blood cell automatic classification method and system based on a mixed attention residual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] This embodiment provides a method for automatically classifying white blood cells based on a mixed attention residual network.

[0037] Such as Figure 5 As shown, the automatic classification method of white blood cells is realized based on the mixed attention residual network, including:

[0038] Step (1): Obtain the original white blood cell image and perform preprocessing;

[0039] Step (2): Input the preprocessed leukocyte image into the improved residual network model for training, and the obtained improved residual network model meets the requirement of the accuracy rate of leukocyte type judgment.

[0040] Among them, the construction process of the improved residual network model includes:

[0041] Based on the input branch of the original residual network, a lightweight input sub-network is introduced;

[0042] Improve mixed attention residual network, introduce channel attention module and spatial attention module;

[0043] Improve the downsampling networ...

Embodiment 2

[0061] This embodiment provides an automatic white blood cell classification system based on a mixed attention residual network.

[0062] Realization of white blood cell automatic classification system based on mixed attention residual network, including:

[0063] A preprocessing module, which is configured to: acquire the original white blood cell image, and perform preprocessing;

[0064] The model building module is configured to: input the preprocessed white blood cell image into the improved residual network model for training, and the obtained improved residual network model meets the requirement of the accuracy rate of white blood cell type judgment.

[0065] Wherein, the preprocessing module is configured to: select a certain number of representative peripheral blood leukocyte images as network training data, and divide the data into a training set and a test set according to a ratio of 10:1. Data enhancement is performed by means of rotation, mirroring, color contras...

Embodiment 3

[0097] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method for automatically classifying white blood cells based on the mixed attention residual network as described in the first embodiment is realized. step.

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 white blood cell automatic classification method and system based on a mixed attention residual network, and the method comprises the following steps: (1), obtaining an original white blood cell image, and carrying out the preprocessing; and (2) inputting the preprocessed leukocyte image into an improved residual network model for training, wherein the obtained improved residual network model meets the requirement of leukocyte type judgment accuracy.

Description

technical field [0001] The invention belongs to the field of medical image analysis, and in particular relates to a method and system for automatically classifying white blood cells based on a mixed attention residual network. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] White blood cells are critical in maintaining the body's immunity and destroying invading bacteria and pathogens. In general, white blood cells can be divided into granulosa cells: neutrophils (neutrophils are further subdivided into segmented and rod-shaped neutrophils), eosinophils, basophils, and Granulocytes: monocytes and lymphocytes. Accurate identification of different types of white blood cells is of great significance for the auxiliary diagnosis of certain diseases. When the number of certain types of cells in white blood cells exceeds the normal range, it o...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241G06F18/214
Inventor 李登旺刘聪卢志明黄浦姜泽坤张健王晶沈亚娟吴上上宋卫清
Owner SHANDONG NORMAL UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com