Three-dimensional dentition segmentation and labeling method

A three-dimensional dentition, three-dimensional technology, applied in the field of crown segmentation and labeling of three-dimensional dentition grid model, can solve problems such as irregular dentition, no clear interdental boundary, and crowding in two-dimensional images, and eliminate wrong segmentation areas , Improve the confusion of the crown boundary segmentation and improve the accuracy

Active Publication Date: 2021-07-20
PEKING UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The projection-based method transforms the problem of 3D tooth segmentation into the boundary detection problem of 2D images, but the uneven dentition caused by crowding and impaction does not have a clear boundary between teeth on the 2D image

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
  • Three-dimensional dentition segmentation and labeling method
  • Three-dimensional dentition segmentation and labeling method
  • Three-dimensional dentition segmentation and labeling method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0016] The present invention proposes a method for automatic segmentation and labeling of a three-dimensional dentition grid model based on a feature-oriented graph convolutional network, effectively extracts the features of the three-dimensional dentition grid model, and performs segmentation and labeling on the three-dimensional dentition grid model to obtain a single Accurate segmentation of each tooth and marking the tooth position.

[0017] The present invention will be further described through the examples below with reference to the accompanying drawings. In this example, the digital scanning model of the human dentition gypsum model is used. The data form is a three-dimensional grid, and the original model is down-sampled using the quadratic edge contraction simplification algorithm. , resul...

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 three-dimensional dentition segmentation and labeling method. The problem of confusion of dental crown boundary segmentation is improved by constraining dental crown shape distribution and dental crown boundary curvature. Meanwhile, an apparent similarity relationship between local vertexes is utilized to further eliminate an error segmentation region. The segmentation of the dental crown and the boundary thereof can be used for further enhancing the feature extraction and vertex classification performance of the network model. For the three-dimensional dentition grid model, N is the number of vertexes of the three-dimensional dentition model, features of the three-dimensional dentition grid model are effectively extracted, the three-dimensional dentition grid model is segmented and labeled, and a category label of each vertex on the grid model is obtained, wherein K is the number of the category labels; the accurate segmentation of the single tooth is obtained, and the tooth position is marked.

Description

technical field [0001] The invention relates to the technical fields of oral clinical medical image processing and computer vision, in particular to a three-dimensional dentition grid model tooth crown segmentation and labeling method. Background technique [0002] Computer-aided stomatology has developed rapidly in recent years. The three-dimensional dentition grid model can intuitively and clearly display the patient's dentition arrangement and tooth shape. It is widely used in clinical orthodontic treatment and is an important basis for doctors to diagnose and formulate orthodontic plans. Accurate segmentation and labeling of 3D dentition models are key steps in computer-aided orthodontic treatment. The morphological changes of the dentition caused by tooth deformity bring challenges to the accurate segmentation and labeling of the 3D dentition model. [0003] Automatic tooth segmentation and annotation is a challenging problem in computer-aided dental image processing....

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): G06T5/00G06T5/40G06T7/11G06T17/00G16H30/40G16H50/20G06K9/62G06N3/04
CPCG06T7/11G06T5/40G06T17/00G06T5/002G16H50/20G16H30/40G06T2207/30036G06N3/045G06F18/214
Inventor 裴玉茹孙迪雅许天民查红彬
Owner PEKING 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