Construction method of image segmentation model and image segmentation method and system

An image segmentation and construction method technology, applied in the field of image processing, can solve the problem of unclear segmentation of oral leukoplakia

Active Publication Date: 2020-05-15
NORTHWEST UNIV(CN)
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned problems or defects in the prior art, the purpose of the present invention is to provide a method for constructing an image segmentation model, an image segmentation method and a system, so as to solve the problem of unclear segmentation of oral leukoplakia in the prior art

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
  • Construction method of image segmentation model and image segmentation method and system
  • Construction method of image segmentation model and image segmentation method and system
  • Construction method of image segmentation model and image segmentation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] A construction method of an image segmentation model, wherein the construction method comprises the following steps:

[0054] Step S1, collecting a plurality of stomatological images to obtain a sample set of stomatological images;

[0055] Such as Figure 5 As shown, in the present embodiment, 90 cases of medical images of oral leukoplakia are first selected as cases for analysis, wherein 78 cases are used as training sets for training neural network models, and 12 cases are used as test sets for detecting the accuracy of neural network model segmentation results. Correct rate.

[0056] Step S2, labeling the leukoplakia area of ​​the stomatological image to obtain a sample set of annotated leukoplakia areas of the stomatological image;

[0057] Specifically, the following annotation methods are used to annotate the leukoplakia area of ​​the stomatological image:

[0058] 1) Use the VIA annotation tool (VGG Image Annotator) to annotate the target region on each image...

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 the technical field of image segmentation, and discloses a construction method of an image segmentation model, and an image segmentation method and system, and the method comprises the steps: collecting a plurality of oral medical images, and obtaining an oral medical image sample set; labeling the leukoplakia area of the oral medical image to obtain a leukoplakia area labeling sample set of the oral medical image; inputting the oral medical image leukoplakia region labeling sample set into a Mask R-CNN-S neural network to obtain a binary mask image set of leukoplakiaregions; training a pre-constructed Mask R-CNN-S neural network model, so as to obtain a trained Mask R-CNN-S neural network model; collecting a to-be-segmented oral medical image and labeling the to-be-segmented oral medical image to obtain a labeled sample set of the to-be-segmented oral medical image; and segmenting the oral medical image to finally obtain a segmented image. According to the invention, the accuracy of segmenting the leukoplakia area from the oral medical image can be improved.

Description

technical field [0001] The invention relates to image processing, in particular to a method for constructing an image segmentation model, an image segmentation method and a system. Background technique [0002] With the development of medical imaging technology, medical imaging plays an indispensable role in medical diagnosis. The rapid development of computer-aided diagnosis technology can use computer-aided processing and analysis of medical images to help doctors make correct judgments on diseases. . As the first stage of medical image processing, medical image segmentation is of great significance to medical image analysis and visualization. Medical image segmentation is the basis of lesion area extraction, organ tissue measurement and 3D reconstruction. Standards and other aspects also played an irreplaceable role. [0003] Oral leukoplakia (OLK) is a precancerous condition that doctors usually assess in patients by observing them for the presence or absence of OLK. ...

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): G06T7/12G06N3/04
CPCG06T7/12G06T2207/30004G06N3/045
Inventor 穆昱管子玉章盼盼许鹏飞
Owner NORTHWEST UNIV(CN)
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