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

Cancer auxiliary analysis system and device based on HE staining pathological image

An auxiliary analysis and pathological image technology, applied in the field of medical imaging, can solve the problem of inability to accurately segment cytoplasm, achieve effective network model parameters, ensure segmentation accuracy, and ensure the effect of accuracy

Active Publication Date: 2021-08-13
湖南医药学院
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention is to solve the problem that the existing cell segmentation neural network model cannot accurately segment the cytoplasm

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
  • Cancer auxiliary analysis system and device based on HE staining pathological image
  • Cancer auxiliary analysis system and device based on HE staining pathological image
  • Cancer auxiliary analysis system and device based on HE staining pathological image

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0050] The existing cell segmentation methods cannot accurately segment the cytoplasm. On the one hand, the existing segmentation network model itself cannot accurately segment the cytoplasm. That is, for complex and difficult-to-divide images, the segmentation result of the network model itself is There are inaccurate problems; on the other hand, due to the current HE staining, the layers are not clear enough, the nucleus and cytoplasm are not clearly distinguished, and the layers of cytoplasm and extracellular space are even less clear, and the distinction is even less obvious, which further reduces the staining image of the neural network. Processing accuracy.

[0051] This embodiment is a cancer auxiliary analysis system based on HE-stained pathological images, including:

[0052] The dyed slice image acquisition module is used to acquire the stained slice image stained with HE, and perform image block segmentation on the image;

[0053] The cell nucleus segmentation module...

specific Embodiment approach 2

[0091] This embodiment is a cancer auxiliary analysis system based on HE-stained pathological images, which also includes:

[0092] The overall cell unit determination module, for the image block corresponding to the stained slice image, maps the segmentation result of the cytoplasmic segmentation module to the corresponding image block, and maps the segmentation result of the cell nucleus segmentation module to the same image block, and finally forms the stained slice The segmented image of the image, such as Figure 4 shown.

[0093] In fact, the segmentation results of the cytoplasmic segmentation module are mapped to the corresponding image blocks, and in the process of mapping the segmentation results of the cell nucleus segmentation module to the same image block, sometimes multiple nuclei are mapped in the same cytoplasmic division area. As long as the situation occurs when cells accumulate or become cancerous, such effects will not affect the auxiliary analysis of can...

specific Embodiment approach 3

[0095] This embodiment is a cancer auxiliary analysis system based on HE-stained pathological images, which also includes:

[0096] The auxiliary cancer analysis module is used to identify and classify cancerous cells based on the results of the overall cell unit determination module using the expert database. The identification and classification process is carried out in the form of an expert database, which stores the judgment rules of cancerous cells. The judgment rules of cancerous cells are the morphological characteristics of cancerous cells determined by experts based on the big data of pathological images, such as the arrangement of nuclei or cells state (whether disordered, clustered into pieces, etc.), nucleus size state (the size of each nucleus, and whether multiple nuclei are of different sizes), nucleus shape, etc., the feature of this embodiment is that it can also include Morphological characteristics, such as nuclear-cytoplasmic ratio, can improve the accurac...

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 cancer auxiliary analysis system and device based on an HE staining pathological image, and belongs to the technical field of medical imaging. The problem that an existing cell segmentation neural network model cannot accurately segment cytoplasm is solved. The system comprises a staining slice image acquisition module for acquiring a staining slice image of HE staining, a cell nucleus segmentation module for calling a cell nucleus segmentation network model to perform cell nucleus segmentation on an image block, and a cell nucleus masking module for masking a cell nucleus, a cytoplasm segmentation module used for calling a cytoplasm segmentation network model to carry out cytoplasm segmentation on the image masked by the cell nucleus masking module, a cell overall unit determination module used for mapping the segmentation results of the cytoplasm and the cell nucleus segmentation module into the same image block, and a cancer assisted analysis module for providing assisted analysis. The method is mainly used for providing auxiliary analysis for cancer recognition.

Description

technical field [0001] The invention relates to a cancer auxiliary analysis system and device, belonging to the technical field of medical imaging. Background technique [0002] At present, the further judgment and analysis of many cancers basically rely on the analysis of the stained images of cancer sections. For the section staining process, hematoxylin-eosin (HE) staining is a commonly used staining method. . Due to the differences in HE staining operations and procedures, the staining effects are not the same, so there are differences in the accuracy of judgment based on HE staining pathological images. [0003] At the same time, with the development of the field of artificial intelligence, deep learning technology has become the mainstream technology or research direction in many application fields, and has achieved very good recognition and detection results in many fields. At present, many researchers and scholars use deep learning technology to identify cancer cel...

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): G06T7/00G06T7/11G06K9/38G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06N3/084G06T2207/10024G06T2207/10056G06T2207/20081G06T2207/20084G06T2207/30024G06T2207/30096G06V10/28G06N3/048G06N3/045G06F18/241
Inventor 王晓乔张在其尹辉明阳大庆唐娜萍
Owner 湖南医药学院
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