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

Cancer metastasis panoramic pathological section analysis method based on deep cascade network

A cascading network and pathological slice technology, which is applied in pathological reference, image analysis, image data processing, etc., can solve the problems of cancer metastasis area and cancer cell segmentation, and reduce the probability of over-treatment and inappropriate treatment. Improve work efficiency and enhance effectiveness

Active Publication Date: 2020-07-14
NANJING UNIV OF INFORMATION SCI & TECH
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is difficult to segment cancer metastases and cancer cells

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 metastasis panoramic pathological section analysis method based on deep cascade network
  • Cancer metastasis panoramic pathological section analysis method based on deep cascade network
  • Cancer metastasis panoramic pathological section analysis method based on deep cascade network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to further clarify the scheme and principle of the present invention, the present invention will be further introduced below in conjunction with the accompanying drawings and specific embodiments.

[0037] A deep cascade network-based panoramic pathological slice analysis method for cancer metastasis, using a cascade network (CNN) to complete the analysis and judgment of the cancer metastasis area. In this embodiment, the panoramic pathological slice image of breast lymph node cancer metastasis is taken as an example, such as figure 1 As shown, the process of creating the cascaded network includes a training phase and a testing phase. The following will describe the design and implementation of the cascaded network from these two phases.

[0038] The specific process is as follows:

[0039] 1. Build the model

[0040] 1.1) Create a training set

[0041] The cascaded network includes a coarse segmentation neural network and a fine segmentation neural network,...

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 metastasis panoramic pathological section analysis method based on a deep cascade network, and the method is characterized in that a cascade network composed of a coarse segmentation neural network and a fine segmentation neural network is used for completing the analysis of a cancer metastasis panoramic pathological section to obtain a probability heat value graphof a section positive class. According to the invention, accurate detection and positioning of a cancer metastasis area can be completed, the malignant degree of all lymph nodes of a patient is synthesized to be quantitatively evaluated by an auxiliary doctor, a support basis is provided for diagnosis consistency, the purposes of reducing missed diagnosis and misdiagnosis, reducing the occurrenceprobability of excessive treatment and improper treatment and finally assisting the doctor to make an optimal clinical treatment scheme are achieved, and the method has important significance for clinicians and patients.

Description

technical field [0001] The invention belongs to the technical fields of computer vision, image processing and analysis, etc., and specifically relates to a method for analyzing panoramic pathological slices of cancer metastasis based on a deep cascade network. Background technique [0002] In recent years, with the rapid development of artificial intelligence technologies such as computer vision and machine learning, especially deep learning, and the improvement of digital full-slide scanner technology, high-quality full-scan histopathological images can be obtained through rapid digitization of slices, which is not only convenient Preservation, and it is possible to analyze digitized slices using artificial intelligence technology. Although the computer-aided diagnosis system based on pathological image analysis has many advantages, pathological images are highly complex, and there are still big problems in the digitization and analysis of pathological images. For example, ...

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): G06T7/00G06K9/32G06K9/46G16H70/60
CPCG06T7/0012G16H70/60G06T2207/30068G06V10/25G06V10/56Y02A90/10
Inventor 徐军胡佳瑞徐海俊朱涵
Owner NANJING UNIV OF INFORMATION SCI & TECH
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