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

Method for constructing virtual case library of cancer pathological images and multi-scale cancer detection system based on convolutional neural network

A convolutional neural network, pathological image technology, applied in biological neural network models, image enhancement, neural architecture, etc., can solve problems such as low work efficiency, difficult diagnosis in the medical field, and inability to meet the needs of image reading, and improve time efficiency. , the effect of reducing computing resources

Active Publication Date: 2018-11-06
杭州同绘科技有限公司
View PDF6 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A large number of pathological images are generated in hospitals every day. However, pathologists can only view them one by one through a microscope at present. The work efficiency is low and cannot meet the needs of large-scale image reading.
Moreover, due to the existence of many difficult and miscellaneous diseases, doctors with relatively little experience cannot effectively diagnose this part of the image, and there are also some difficult-to-diagnose problems in the medical field

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 constructing virtual case library of cancer pathological images and multi-scale cancer detection system based on convolutional neural network
  • Method for constructing virtual case library of cancer pathological images and multi-scale cancer detection system based on convolutional neural network
  • Method for constructing virtual case library of cancer pathological images and multi-scale cancer detection system based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Example 1 Taking the multi-scale detection method of breast cancer lymphatic metastasis as an example

[0036]The specific meaning of the breast cancer lymphatic metastasis task is to automatically detect whole-section pathological images of lymphatic metastasis stained by hematoxylin and eosin (H&E). This task is of high clinical interest, but requires significant time-consuming manual reading by pathologists. Therefore, an effective computer vision automatic detection scheme can reduce the workload of pathologists while improving the objectivity of diagnosis.

[0037] Such as figure 1 and figure 2 The flow chart shown is a multi-scale detection system for lymphatic metastasis of breast cancer based on convolutional neural network. Based on the method of convolutional neural network, it detects the cancer mass area on the pathological full scan slice, including the following modules:

[0038] Pathological slice image preprocessing module: on a high scale, convert ...

Embodiment 2

[0092] Similarly, the convolutional neural network-based multi-scale cancer detection system described in Example 1 can also be used for the detection of gastric cancer, and the breast cancer tissue is replaced by gastric cancer tissue, and the detection method is to use the above-mentioned detection system, Take the following steps:

[0093] Step (1), tissue area extraction: obtain gastric cancer patient tissue, preprocess the pathological full-scan slice image, convert the full-scan slice image from RGB color space to HSL color space, use the high-scale whole slice image, and use the S-channel The Otsu algorithm was used to perform threshold segmentation on it to obtain tissue regions. ;

[0094] Step (2), construction of virtual case database: use the deep convolutional generative confrontation network algorithm to train the generative model, and use the generative model to generate low-scale sliced ​​images, then down-sample the generated images, generate a series of slic...

Embodiment 3

[0102]Similarly, the convolutional neural network-based multi-scale cancer detection system described in Example 1 can also be used for the detection of rectal cancer, and breast cancer tissue is replaced by rectal cancer tissue, and the detection method is to use the above-mentioned detection system, the following steps are taken:

[0103] Step (1), tissue area extraction: obtain rectal cancer patient tissue, preprocess the pathological full-scan slice image, convert the full-scan slice image from RGB color space to HSL color space, use the high-scale whole slice image, and use S Channels were thresholded using the Otsu algorithm to obtain tissue regions. ;

[0104] Step (2), construction of virtual case database: use the deep convolutional generative confrontation network algorithm to train the generative model, and use the generative model to generate low-scale sliced ​​images, then down-sample the generated images, generate a series of sliced ​​images and compare them to ...

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 establishment of a virtual case library of cancer pathological images and a multi-scale cancer detection system based on a convolutional neural network. The system is based ona method of a convolution neural network, a cancer mass region is detected on a pathological full-scan section, and the system includes four modules: 1) a pathological section image preprocessing module; 2) a virtual case database construction module; 3) a high-scale cancer mass detection module; and 4) a small-scale cancer mass classification module. The multi-scale cancer detection system provided by the invention can make full use of the multi-scale information of a pathological image, on different scales, according to the characteristics of the image, different strategies are designed to detect a suspected cancer area, and at the same time, under the condition of insufficient training data, the virtual case library method established by the invention can provide more training data setsfor an existing data-driven deep learning method. The multi-scale cancer detection system based on a convolutional neural network has the characteristics of multi-scale detection, driving of a relatively small amount of data and the like, and has the characteristic of reducing computing resources required for one-time recognition and improving time efficiency of an algorithm on the basis of ensuring the overall recall rate and accuracy.

Description

technical field [0001] The invention belongs to the technical field of medical images, and establishes a virtual case database based on pathological full-scan images and a multi-scale cancer detection system based on pathological images, and specifically relates to the establishment of a virtual case database of cancer pathological images and cancer detection based on convolutional neural networks. Multi-scale detection method. Background technique [0002] Medical image processing is one of the hot research fields in the world today, and related research and applications are increasingly appearing in top conferences in the direction of computer vision. Medical image processing belongs to the cause of human health, and the research in this field has important practical significance. A large number of pathological images are generated in hospitals every day. However, at present, pathologists can only view them one by one through a microscope. And because there are many diff...

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): G06T7/00G06T7/136G06N3/04
CPCG06T7/0012G06T7/136G06T2207/20081G06T2207/30096G06N3/045
Inventor 郝爱民李帅梁晓辉杨文军
Owner 杭州同绘科技有限公司
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