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

Automatic segmentation method for oral cancer epithelial tissue region of pathology image

An epithelial tissue and pathology technology, applied in the fields of medical image processing and machine learning, which can solve the problems of time-consuming and boring, and difficulty in gathering information of staining variability.

Inactive Publication Date: 2021-02-02
SHAANXI NORMAL UNIV
View PDF1 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when applying ML / DL to more specific regions, in WSI epithelial segmentation, it may encounter time-consuming and boring issues such as GroundTruth annotation, variability of staining, and difficulty in processing image information based on patches. gathering challenge

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
  • Automatic segmentation method for oral cancer epithelial tissue region of pathology image
  • Automatic segmentation method for oral cancer epithelial tissue region of pathology image
  • Automatic segmentation method for oral cancer epithelial tissue region of pathology image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In one embodiment, such as figure 1 As shown, a method for automatic segmentation of oral cancer epithelial tissue regions that provides a pathological image is disclosed, which includes the following steps:

[0020] S100: Preprocessing the pathology image and the pathologist's label by using a method of extracting a pixel block patch;

[0021] S200: selecting part of the preprocessed pathological images as training samples to form a training set, and the rest as verification samples to form a verification set;

[0022] S300: Construct a convolutional neural network UNet model, use the training set and verification set in step S200 to train and verify the UNet model, and obtain the final UNet model;

[0023] S400: Apply the above final UNet model to a multi-center external test set to automatically generate epithelial tissue regions.

[0024] For this example, a UNet-based deep learning framework was used to segment epithelial regions from two types of histopathology ...

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 an automatic segmentation method for an oral cancer epithelial tissue region of a pathological image. The method comprises the following steps: S100, preprocessing the pathological image and a label of a pathologist by using a method for extracting a pixel block patch; S200, selecting part of the preprocessed pathological images as training samples to form a training set, and taking the rest pathological images as verification samples to form a verification set; S300, constructing a convolutional neural network UNet model, and training and verifying the UNet model by adopting the training set and the verification set in the step S200 to obtain a final UNet model; and S400, applying the final UNet model to a multi-center external test set to automatically generate anepithelial tissue region. According to the method, training, verification and testing are not carried out on each data set in head and neck cancer detection, only TMA data is used for training, testing is carried out on a multi-center external WSI data set, and the method is more persuasive to unknown images.

Description

technical field [0001] The disclosure belongs to the technical fields of medical image processing and machine learning, and in particular relates to a method for automatically segmenting oral cancer epithelial tissue regions of pathological images. Background technique [0002] Oral squamous cell carcinoma (OC-SCC) is the most common malignancy of the head and neck worldwide, with high invasiveness to adjacent tissues and metastatic potential to distant organs. Better diagnostic and risk stratification tools are therefore needed for personalized treatment of OC-SCC patients. [0003] The pathologist's approach to diagnosis and risk factor stratification begins with the identification of the tumor region. These areas are usually analyzed by a pathologist by light microscopy using routinely stained tissue. The entire tumor area is composed of cancer cells and their supporting tissue matrix. In the case of carcinoma, the epithelial tumor area is the most evaluated part. His...

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): G06T7/00G06T7/11G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06N3/08G06T2207/30096G06N3/048G06N3/045
Inventor 吴玉欣陆铖
Owner SHAANXI NORMAL 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

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