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

Method for segmenting tooth root image by using key point detection polynomial fitting curve

A polynomial fitting and image segmentation technology, which is applied in image analysis, image enhancement, image data processing, etc., can solve problems such as treatment plan accidents, interference with physician judgment, and inapplicability of root canal head segmentation, so as to improve efficiency and reliability Evaluation indicators, the effect of small resource consumption

Pending Publication Date: 2021-08-27
ZHEJIANG UNIVERSITY OF MEDIA AND COMMUNICATIONS
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] These existing algorithm models are not suitable for the segmentation of the root canal head, and their shortcomings will bring a greater negative effect on the accurate evaluation of the root canal treatment effect, which may interfere with the doctor's judgment and even affect the follow-up treatment plan. making accidents

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 for segmenting tooth root image by using key point detection polynomial fitting curve
  • Method for segmenting tooth root image by using key point detection polynomial fitting curve
  • Method for segmenting tooth root image by using key point detection polynomial fitting curve

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Such as figure 1 As shown, the method of segmenting tooth root image by using key point detection polynomial fitting curve includes the following steps:

[0032] S1. The original root canal image is used as the input of the model.

[0033] S2. Use the automatic rotation module to adjust the angle of the root canal in the picture to generate a standard image with a vertical root canal angle, and rotate the read picture by a certain angle to generate a standard image so that the root canal is in a vertical direction.

[0034] S3. The standard image generated in step S2 is used as the input of the high-resolution deep neural network (HRNet). A multi-scale fusion method is implemented to enhance high-resolution representations. With these two advantages, HRNet achieves superior performance in keypoint detection. Therefore, the present invention utilizes the advantages of HRNet multi-resolution convolution to detect the coordinates of 19 feature points on the root head bou...

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 method for segmenting a tooth root image by using a key point detection polynomial fitting curve. The method comprises the following steps: taking an original root canal image as the input of a model, adjusting the root canal angle in the image through an automatic rotation module, and generating a standard image with the vertical root canal angle; taking the generated standard image as the input of a high-resolution deep neural network (HRNet), and detecting the coordinates of a plurality of feature points of the head boundary of the tooth root by using the multi-resolution convolution advantage of the HRNet neural network; solving the average value of the distances between all the feature points and the adjacent feature points, and traversing and calculating the distances between each feature point and the two adjacent feature points; and traversing all conditions of randomly removing 1-5 feature points by using a short-distance sensitive algorithm, and taking a curve corresponding to the condition of the minimum short-distance sensitive distance as a final output tooth root head boundary curve.

Description

technical field [0001] The invention relates to the fields of segmentation of tooth root fuzzy boundaries and detection of tooth root boundaries in stomatology, and in particular to a method for segmenting tooth root images by using key point detection polynomial fitting curves. Background technique [0002] Root canal therapy is the most commonly used effective treatment for endodontic and periapical diseases. The principle of root canal treatment is to remove most of the infection in the patient's root canal by mechanical and chemical methods, and to prevent the occurrence of periapical lesions or promote the healing of periapical lesions that have occurred by filling the root canal and sealing the crown. heal. In order to determine the method to be used in the subsequent treatment, the physician needs to evaluate the X-ray images of the patient's treatment area to determine the effect of root canal filling and sealing. In stomatology, overfilling, just right, and too sh...

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): G06T7/12
CPCG06T7/12G06T2207/30036G06T2207/20084
Inventor 李云响王亚奇章一帆唐凯俞定国夏能彭睿孜张随雨
Owner ZHEJIANG UNIVERSITY OF MEDIA AND COMMUNICATIONS
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com