CBCT alveolar bone segmentation system and method based on deep learning

A technology of deep learning and alveolar bone, which is applied in the field of artificial intelligence medical image processing and orthodontics, can solve the problems of blurred boundaries, differences in alveolar bone between layers, and low accuracy of threshold segmentation method, and achieve highly automated alveolar bone Segmentation, the effect of high-precision alveolar bone segmentation

Pending Publication Date: 2022-07-15
杭州隐捷适生物科技有限公司
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In dental CBCT images, the density of teeth and alveolar bone is similar, the boundary is blurred, and there are differences in alveolar bone between layers. These factors lead to low accuracy of traditional threshold segmentation method

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
  • CBCT alveolar bone segmentation system and method based on deep learning
  • CBCT alveolar bone segmentation system and method based on deep learning
  • CBCT alveolar bone segmentation system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment example 1

[0051] like figure 1 As shown, the present invention provides a technical scheme: a deep learning-based CBCT alveolar bone segmentation system and method, comprising the following steps:

[0052] S1. Dental CBCT data set acquisition and labeling: collect multiple patient CBCT images, and then use ITK-SNAP software to label the alveolar bone;

[0053] S2, CBCT image and labeled sample preprocessing: normalize the sample and store it as a specific data structure;

[0054] S3. Construction of deep semantic segmentation model: U-shaped semantic segmentation network model based on Swin-transformer and skip connection;

[0055] S4. Model training and evaluation: Use the CrossEntropyLoss and Diceloss loss functions to evaluate the model training effect;

[0056] S5. Dental CBCT data segmentation and reconstruction.

specific Embodiment example 2

[0058] S1. Dental CBCT data set acquisition and labeling

[0059] S11. Obtain the CBCT image data of 10 patients from the dental hospital, and the CBCT data of each patient is a collection of 512 512x512 dcm format images;

[0060]S12, such as figure 2 As shown, the alveolar bone annotation was performed on all images of each patient's CBCT dataset using the ITK-SNAP software, the label files were saved in the nii file format, and the CBCT images and labels were visualized.

[0061] S2, CBCT image and labeled sample preprocessing

[0062] S21. Convert the DICOM format of the CBCT image to PNG format, and then normalize the image to correct the grayscale to be between 0 and 255. The normalization formula is as follows:

[0063] x'=(x-min(cbct)) / (max(cbct)-min(cbct))

[0064] where min(cbct) is the minimum gray value of each CBCT dataset; max(cbct) is the maximum gray value of each CBCT dataset;

[0065] S22. Extract the 2D slice images in turn from the 3D nii annotation fi...

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 CBCT alveolar bone segmentation system and method based on deep learning, and relates to the technical field of artificial intelligence medical image processing and tooth correction, in particular to a CBCT alveolar bone segmentation system and method based on deep learning, and the method comprises the following steps: S1, obtaining and marking a dental CBCT data set; s2, preprocessing the CBCT image and the annotation sample; s3, constructing a deep semantic segmentation model; s4, performing model training and evaluation; and S5, segmenting and reconstructing the dental CBCT data. The invention aims to provide the deep learning method for automatically segmenting the alveolar bone of the CBCT image, a low-efficiency mode of manual segmentation of dentists and a low-precision method of a traditional threshold segmentation method are replaced, and the orthodontic efficiency and effectiveness are improved.

Description

technical field [0001] The invention relates to the technical fields of artificial intelligence medical image processing and orthodontics, in particular to a deep learning-based CBCT alveolar bone segmentation system and method. Background technique [0002] With the gradual improvement of modern people's living standards, people's needs and requirements for orthodontics are also getting higher and higher, and CBCT scanning technology is also widely used in the field of orthodontics. CBCT scanning technology is a cone-beam computed tomography scan. Through CBCT images, the three-dimensional stereo of teeth and alveolar bone can be reconstructed, providing accurate and reliable information and scientific basis for dentists to design dental treatment plans. [0003] In dental CBCT images, teeth and alveolar bone have similar densities, blurred boundaries, and differences in alveolar bone between layers. These factors lead to the inaccuracy of traditional threshold segmentation...

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): G06V10/26G06T17/00G06V10/764G06K9/62G06N20/00A61C7/00
CPCG06T17/00G06N20/00A61C7/002G06T2207/20081G06T2207/30036G06F18/241
Inventor 何慧竹韦虎
Owner 杭州隐捷适生物科技有限公司
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