Tumor lymphatic infiltration detection method based on cascade network

A cascade network and detection method technology, applied in the direction of measuring devices, medical data mining, image data processing, etc., can solve the problems of positioning accuracy loss, fuzzy position information, etc., and achieve the effect of reducing the number

Active Publication Date: 2021-07-23
杭州迪英加科技有限公司
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such a method easily leads to the loss of positioning accuracy, and the doctor can only get a vague position information

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
  • Tumor lymphatic infiltration detection method based on cascade network
  • Tumor lymphatic infiltration detection method based on cascade network
  • Tumor lymphatic infiltration detection method based on cascade network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described below in conjunction with accompanying drawing:

[0042] A cascaded network-based detection method for lymphatic vessel invasion of tumors, such asfigure 1 , figure 2 shown, including the following steps:

[0043] S10, obtaining D2-40 immunohistochemical digital pathology full-field image;

[0044] S20, performing data preprocessing on the digital pathology full-field image, and segmenting a plurality of independent tissue regions on the preprocessed image;

[0045] S30. Calculate the circumscribed rectangle of each of the segmented independent tissue regions, and use the tissue region framed by the circumscribed rectangle as a rectangular subgraph;

[0046] S40. Perform small image processing on the rectangular sub-images by using a sliding window, and split each of the rectangular sub-images into multiple first small images of fixed sizes and non-overlapping each other;

[0047] S50. Detect the first position informa...

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 relates to a tumor lymphatic infiltration detection method based on a cascade network, and provides automatic detection of a lymphatic infiltration area in a D2-40 immunohistochemical digital pathological full-field graph by utilizing a cascade structure of a lymphatic infiltration detection model and a difficult-to-distinguish sample mining network. In order to achieve the purpose that after a difficult-to-distinguish sample mining network filters a detection network output result, the number of false positive parts can be reduced as much as possible, and missing detection of true positive parts does not occur, the difficult-to-distinguish sample mining network needs to learn features of the false positive parts and the true positive parts, and the deep learning network learns the features through data. Therefore, the emphasis is how to acquire representative data, that is to say, training data are selected in the steps 3) and 4) in the step S70 of false positive filtering, and a classification model is trained through the selected two types of data to obtain a difficult-to-classify sample mining model.

Description

technical field [0001] The invention relates to the field of immunohistochemical image processing, in particular to a method for detecting tumor lymphatic vessel infiltration based on a cascade network. Background technique [0002] Today, cancer is still the "number one killer" of human health, and it is also one of the major public health problems in China. According to the estimates of "China Cancer Statistics" in 2015, there are 4.292 million cancer patients in my country, and 2.814 million cancer patients died. In 2018, an estimated 18.1 million new cases of cancer were added worldwide, resulting in 9.6 million deaths. Cancer metastasis is the most important cause of cancer death. The three major pathways of malignant tumor metastasis include hematologic metastasis, lymphatic metastasis and direct spread, among which lymphatic metastasis is the main pathway of cancer metastasis, and lymphatic invasion (Lymphatic Invasion, LI) It is also one of the important manifestat...

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): G06T7/00G06T7/11G06T7/13G06T7/136G06T7/62G16H30/40G16H50/20G16H50/70G01N21/84
CPCG06T7/0012G06T7/11G06T7/136G06T7/13G06T7/62G16H30/40G16H50/20G16H50/70G01N21/84G06T2207/20081G06T2207/20084G06T2207/30096
Inventor 韩鑫田雪叶王春宝杨林崔磊
Owner 杭州迪英加科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap