Method and system for detecting breast cancer area of pathological image based on DenseNet network

A technology for pathological images and breast cancer, applied in mammography, neural learning methods, biological neural network models, etc., can solve time-consuming problems and achieve the effect of suppressing isolated noise

Active Publication Date: 2022-02-11
XINXIANG MEDICAL UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Pathology images are very large gigapixel images with an image size of 10 6

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 system for detecting breast cancer area of pathological image based on DenseNet network
  • Method and system for detecting breast cancer area of pathological image based on DenseNet network
  • Method and system for detecting breast cancer area of pathological image based on DenseNet network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] This example presents a breast cancer area detection method based on a DenseNet network-based full-field breast cancer sentinel lymph node pathological image. The DenseNet network model is used to learn the characteristics of breast cancer pathological image blocks, generate a full-field breast cancer probability heat map, and calculate breast cancer. Cancer feature vector, using SVM to predict the probability of occurrence of breast cancer regions, to achieve automatic detection of breast cancer regions.

[0065] The hardware environment of this embodiment is: Intel Xeon E5-2678v3 dual processors, memory 32.0GB, graphics card RTX2080Ti 2 pieces, software environment Ubuntu 16.04, Python 3.5, Tensorflow, OpenSlide, SciKit, NumPy.

[0066] This embodiment presents a breast cancer region detection method based on a DenseNet network-based full-field breast cancer sentinel lymph node pathological image, and its flow chart is as follows figure 1 As shown, follow the steps b...

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 breast cancer area detection method and system for a full-view breast cancer sentinel node pathological image based on a DenseNet network, and the method comprises the steps: 1) obtaining the full-view breast cancer sentinel node pathological image, and manually marking a breast cancer metastasis area; 2) automatically generating a training set and a verification set by using the full-view breast cancer sentinel lymph node pathological image and the labeling result, and training by using a DenseNet network model; 3) predicting a single full-view breast cancer pathology image to obtain a breast cancer probability heat map; 4) calculating breast cancer probability heat maps of the full-view breast cancer pathological images of all the training sets, performing binaryzation and isolated noise suppression, calculating breast cancer feature vectors, and performing training by using a linear classifier; 5) calculating a breast cancer probability heat map for the full-view pathological image of the test set, carrying out binaryzation and isolated noise suppression, calculating a breast cancer feature vector, and predicting the occurrence probability of the breast cancer region, thereby realizing automatic detection of the breast cancer region.

Description

technical field [0001] The invention belongs to the technical field of pathological image processing, and specifically relates to a breast cancer region detection method and system based on a DenseNet network-based full-field sentinel lymph node pathological image of breast cancer. The method can automatically analyze the full-field sentinel lymph node pathological image of breast cancer, Automated detection of breast cancer regions. Background technique [0002] Breast cancer is the one with the highest incidence rate among all malignant tumors in women, accounting for about 17% of all malignant tumors in China, seriously endangering women's health and even life-threatening. The cause of breast cancer is not yet fully understood, and the incidence rate is high, but if detected early, the possibility of cure is very high. Early detection and diagnosis of breast cancer is the key to improving the curative effect. In the process of diagnosis and treatment of breast cancer, m...

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): A61B5/00G06V10/25G06V10/22G06V10/42G06K9/62G06N3/04G06N3/08
CPCA61B5/7264A61B5/7267A61B5/7203A61B5/4312G06N3/08G06N3/045G06F18/2414G06F18/2411G06F18/2415Y02A90/10
Inventor 王昌张文超闫岑张业宏申杰奋秦鑫赵俊强于毅吴阳王辰
Owner XINXIANG MEDICAL UNIV
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