Supercharge Your Innovation With Domain-Expert AI Agents!

Pathological image segmentation method and device

A pathological image and image technology, applied in the field of pathological image segmentation methods and devices, can solve the problems of inability to better pay attention to the patient's condition, surgery, heavy workload for pathologists, and misdiagnosis.

Pending Publication Date: 2022-05-31
EAST CHINA NORMAL UNIV +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the current manual diagnosis method, the workload of pathologists is relatively large, which makes pathologists unable to better pay attention to the patient's condition and perform surgery; moreover, due to subjective factors in manual diagnosis, there will be differences of opinion among doctors, and at the same time Misdiagnosis can occur

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
  • Pathological image segmentation method and device
  • Pathological image segmentation method and device
  • Pathological image segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] figure 1 It is a flow chart of the pathological image segmentation method provided in Embodiment 1 of the present application. This embodiment is applicable to the scene of segmenting pathological images. The method can be executed by the pathological image segmentation device provided in the embodiment of the present application. The device It can be implemented by means of software and / or hardware, and can be integrated into electronic equipment.

[0066] Such as figure 1 As shown, the segmentation method of the pathological image comprises:

[0067] S110, acquiring a pathological image of the tissue, performing preprocessing on the pathological image to obtain a preprocessed image, and using the preprocessed image as a sample and dividing it into a training set and a verification set according to a preset ratio.

[0068] Among them, in order to allow the prior classification network and the segmentation network to process various types of histopathological images, ...

Embodiment 2

[0133] This embodiment is a preferred embodiment provided on the basis of the above-mentioned embodiments. Figure 4 is a schematic diagram of the semantic segmentation network provided in Embodiment 2 of the present application. The implementation example of the weakly supervised histopathological image segmentation method based on pseudo-label correction provided by this program includes the following steps:

[0134] Step 1: Read the histopathological image data, flip along the x-axis with a probability of 0.5, called vertical flip, flip along the y-axis with a probability of 0.5, called horizontal flip, and then perform random angles on the flipped data The rotation direction is counterclockwise, and the degree of rotation is one of the following four types: 0°, 90°, 180°, and 270°. If the degree of rotation is 0, then no rotation occurs.

[0135] The way to standardize the image is Z-Score standardization, which converts the distribution of histopathological images into a...

Embodiment 3

[0168] Figure 5 It is a structural block diagram of a pathological image segmentation device provided in Embodiment 3 of the present invention. The device can execute the pathological image segmentation method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0169] The device can include:

[0170] A preprocessed image acquiring unit 510, configured to acquire a pathological image of the tissue, perform preprocessing on the pathological image to obtain a preprocessed image, and divide the preprocessed image into a training set and a verification set according to a preset ratio by taking the preprocessed image as a sample;

[0171] A priori classification loss calculation unit 520, configured to input the training set sample to the prior classification network to obtain the predicted category of the sample; calculate the binary cross-entropy loss according to the predicted category a...

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 pathological image segmentation method and device. The method comprises the following steps: inputting a training set sample into a prior classification network to obtain a prediction category of the sample; according to the prediction category and the real category, calculating binary cross entropy loss as prior classification loss; generating a class activation graph according to the prior classification network, and regularizing the class activation graph by using a twin network to obtain a corrected class activation graph; converting into a pseudo-pixel-level label according to the correction type activation graph; inputting the training set sample into a preset semantic segmentation network to obtain a segmentation result of the training set sample; and Dice loss is calculated based on the segmentation result and the pseudo-pixel-level label so as to optimize the semantic segmentation network, and pathological image segmentation is carried out through the optimized semantic segmentation network. According to the scheme, the tissue pathology image of the image-level label with a small labeling amount can be used, the tissue pathology image is quickly and accurately segmented in a weak supervised learning mode, and automatic positioning of the canceration area in the pathology image is completed.

Description

technical field [0001] The present invention relates to the technical fields of machine learning and image processing, in particular to a method and device for segmenting pathological images. Background technique [0002] In recent years, with the rapid development of medical technology and the rapid increase of patient data in hospitals, a large amount of medical image data urgently needs to be processed. In the current manual diagnosis method, the workload of pathologists is relatively large, which makes pathologists unable to better pay attention to the patient's condition and perform surgery; moreover, due to subjective factors in manual diagnosis, there will be differences of opinion among doctors, and at the same time Misdiagnosis may occur. Therefore, how to make better use of some histopathological data, better assist diagnosis, improve the efficiency of pathological diagnosis, and make the diagnosis result more objective is a technical problem to be solved urgently...

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): G06T7/00G06V10/26G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06N3/08G06T2207/30024G06N3/045G06F18/241
Inventor 王祥丰邓样金博李郁欣胡斌朱凤平
Owner EAST CHINA NORMAL UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com