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

A membrane-based classification method for pathological microscopic images

A microscopic image and film computing technology, applied in the field of image processing, can solve problems such as lack of systematization, loss of image data, and multi-category information, achieve accurate classification results, and improve accuracy

Pending Publication Date: 2019-03-22
NORTHEASTERN UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This processing method does not perform various basic image processing systematically, and it is difficult to fully highlight the features used for classification in the image
In the case of multiple preprocessing methods covered, the image data will lose more information that is beneficial to classification

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 membrane-based classification method for pathological microscopic images
  • A membrane-based classification method for pathological microscopic images
  • A membrane-based classification method for pathological microscopic images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to better explain the present invention and facilitate understanding, the following describes the present invention in detail through specific embodiments in conjunction with the accompanying drawings.

[0037] At present, in the prior art, before using deep learning to classify images, images are generally preprocessed. The preprocessing methods mainly include mean filtering, median filtering, sobel edge detection, etc., which can emphasize the texture characteristics and shape of the image. Feature method to improve the effect of image classification using deep learning. Specifically, such as figure 1 As shown, there are three steps: Step 1: Input the image; Step 2: Preprocess the image. The preprocessing algorithm includes grayscale, inverse color transformation, HSV conversion, binarization, and k-means clustering and segmentation. , Sobel edge detection, etc.; Step 3: Output image processing results. Classical image processing methods have a greater impact o...

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 pathological microscopic image classification method based on membrane calculation. The method comprises the following steps: S1, training the pathological microscopic image database based on depth learning to obtain a trained neural network; S2, using the trained neural network to establish the computational structure model of the image processing membrane; S3, inputtingthe microscopic image to be processed into the membrane calculation structure model to obtain the classification result of the microscopic image to be processed. The membrane computing method is introduced into the field of microscopic image analysis to improve the accuracy of pathological microscopic image classification.

Description

Technical field [0001] The invention relates to image processing technology, in particular to a pathological microscopic image classification method based on membrane calculation. Background technique [0002] At present, in deep learning image classification work, most researches focus on optimizing neural networks and do not pay attention to the preprocessing part of image classification. Existing preprocessing techniques generally preprocess image data multiple times, and use the final image data to perform classification. This processing method does not systematically perform various basic image processing, and it is difficult to fully highlight the features used for classification in the image. In the case of multiple preprocessing methods, the image data will lose more information that is beneficial to classification. [0003] Therefore, there is an urgent need for a processing method that can measure the actual benefits of each processing algorithm to the classification re...

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): G06K9/00G06K9/34G06K9/62
CPCG06V20/698G06V10/267G06F18/23213G06F18/2413
Inventor 李晨张昊薛丹孙洪赞张乐许宁姚育东
Owner NORTHEASTERN UNIV
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