Method for expanding digital pathology image dataset sample based on dyeing component adjusting

An image data set, digital pathology technology, applied in character and pattern recognition, instruments, understanding of medical/anatomical patterns, etc., can solve problems such as insufficient number of samples and large differences in staining, and achieve the effect of expanding data sets and improving accuracy

Inactive Publication Date: 2018-06-29
MOTIC XIAMEN MEDICAL DIAGNOSTICS SYST
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a pathological image data set used to alleviate the problems caused by the insufficient number of samples and large staining differences when the existing machine learning method is applied to pathological image analysis, and to improve the accuracy of pathological image analysis algorithms extension method

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
  • Method for expanding digital pathology image dataset sample based on dyeing component adjusting
  • Method for expanding digital pathology image dataset sample based on dyeing component adjusting
  • Method for expanding digital pathology image dataset sample based on dyeing component adjusting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0022] figure 1 As shown, the digital pathology image data set sample expansion method based on the adjustment of staining components includes the following steps:

[0023] Step 1: Collect pathological images into the computer to form digital pathological images. In the computer, each digital pathological image is displayed with RGB channels, and each digital pathological image is marked as I(x, y). Several digital pathological images form machine learning Model training sample set, denoted by X;

[0024] Step 2: Set the dynamic adjustment parameter θ, where θ∈(0,1);

[0025] Step 3: Before each training of the machine learning model, dynamically adjust the dyeing ratio of each digital pathology image in the training sample set X to obtain the adjusted training sample set

[0026] Step 4: Use the adjusted training sample set One round of...

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 method for expanding a digital pathology image dataset sample based on dyeing component adjusting. The method is characterized by comprising the following steps of before training by a machine learning algorithm each time, firstly performing dyeing separating on each digital pathology image of a training set, randomly adjusting the ratio of images of each type of dyeing component, integrating, and simulating to generate the digital pathology image at different preparation ratio of dyeing agents, so as to reach the purpose of sample expanding. The method has the advantages that the method is a data dynamic expanding method, and the expanded sample is produced by a random number, so that the samples used by the machine learning algorithm are different during trainingeach time, thereby reaching the purpose of expanding the data set; the accuracy of a pathology image auxiliary diagnosis method which is developed on the basis of the machine learning method is improved, the market prospect is broad, and the application value is high.

Description

technical field [0001] The invention relates to the field of digital image processing, in particular to a pathological image data set expansion method based on a staining component adjustment algorithm. Background technique [0002] Digital pathological images are high-resolution digital images obtained by scanning pathological slices through automatic microscopes or optical magnification systems, and have been widely used in pathological clinical diagnosis. Pathological image analysis algorithms based on machine learning, especially deep learning, have developed rapidly in recent years and have become the mainstream method of pathological image analysis. The machine learning method allows the computer to repeatedly learn the pathological images clearly marked by pathologists, so as to simulate the analysis of pathological images by pathologists. Different from natural scene image analysis, the use of machine learning methods for pathological image analysis has the followin...

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): G06K9/62
CPCG06V2201/03G06F18/214
Inventor 姜志国郑钰山
Owner MOTIC XIAMEN MEDICAL DIAGNOSTICS SYST
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