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

Method and device for predicting colorectal cancer mismatch repair function

A mismatch repair and colorectal cancer technology, applied in the field of biomedical engineering processing, can solve the problems of misjudgment and misreading, time-consuming and labor-consuming, and the overall incidence of colorectal cancer MMR is not high, so as to reduce dependence and improve efficiency Effect

Inactive Publication Date: 2021-09-07
SUN YAT SEN UNIV CANCER CENT
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing technology relies on the manual interpretation of pathologists, which is highly subjective and has some misjudgments and misinterpretations; on the other hand, the overall incidence of MMR function loss in colorectal cancer is not high, about 10-15%. Interpretation of immunohistochemical staining for all patients is time-consuming and labor-intensive, and does not conform to health economics

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 and device for predicting colorectal cancer mismatch repair function
  • Method and device for predicting colorectal cancer mismatch repair function

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] see figure 1 , figure 1 It is a schematic flowchart of an embodiment of the method for predicting the mismatch repair function of colorectal cancer provided by the present invention, such as figure 1 As shown, the method includes steps 101 to 104, specifically as follows:

[0044] Step 101: Obtain HE-stained pathological sections of colorectal tissue, and generate digital pathological images of the HE-stained pathological sections.

[0045] In this embodiment, HE staining is performed on the pathological sections of colorectal tissues obtained during surgery or colonoscopy, and each pathological section is ensured to have a significant invasive cancer area, so as to obtain the HE staining pathology of the colorectal tissue The HE-stained pathological sections of the acquired colorectal tissue were scanned in full to generate corresponding digital pathological images.

[0046] Step 102: Divide the digital pathology image into multiple sub-regions, and extract tissue r...

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 colorectal cancer mismatch repair function prediction method and device, and the method comprises the steps: obtaining an HE staining pathological section of a colorectal tissue, generating a digital pathological image of the HE staining pathological section, dividing the digital pathological image into a plurality of sub-regions, extracting tissue regions in the plurality of sub-regions, classifying tumor areas in a tissue area through a tissue classifier, dividing all tumor areas into MSI areas and MSS areas through an MSI / MSS classification model, calculating the ratio of the number of the MSI areas to the number of the tumor areas, and outputting a prediction result of an HE staining pathological section according to the ratio. Compared with the prior art, the method and the device for predicting the colorectal cancer mismatch repair function have the advantages that the dependence on manpower is reduced, and the efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of biomedical engineering processing, in particular to a method and device for predicting the mismatch repair function of colorectal cancer. Background technique [0002] Colorectal cancer is the most common malignant digestive system tumor. Identifying its mismatch repair (MMR) function is helpful for evaluating disease prognosis, guiding adjuvant chemotherapy and immunotherapy, and screening patients with Lynch syndrome. Grouped according to MMR status, it is divided into How to evaluate the MMR status of the tumor in the MMR-deficient group and the MMR-normal group, the current commonly used detection method is to detect the expression of important MMR-related proteins by immunohistochemistry; [0003] The existing technology relies on the manual interpretation of pathologists, which is highly subjective and has some misjudgments and misinterpretations; on the other hand, the overall incidence of MMR func...

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): G06K9/62G06T7/11G06T7/136G06T7/194
CPCG06T7/11G06T7/136G06T7/194G06T2207/30096G06T2207/10024G06T2207/20081G06F18/2415
Inventor 丁培荣姜武李立张惠忠凌逸虹梅伟健
Owner SUN YAT SEN UNIV CANCER CENT
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