Oral palate soft and hard tissue segmentation method based on attention mechanism and integrated registration

A technology of attention and oral cavity, which is applied in the interdisciplinary field of stomatology and computer science, can solve the problems of inaccurate tissue segmentation and large individual differences in CBCT images, so as to solve the problem of individual differences, reduce the time of implantation sites, and reduce the network The effect of increasing the number of parameters

Active Publication Date: 2022-03-15
SICHUAN UNIV
View PDF23 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The present invention fills in the gaps in the automatic segmentation of hard and soft tissues in the mouth and palate, improves the distinguishability and robustness of captured tissue features, and solves the problems of large individual differences in CBCT images and inaccurate tissue segmentation in existing cases. The technical solution is: a method for segmenting soft and hard tissues of the oral cavity and palate based on the residual perceptual attention mechanism and integrated registration, including the following steps:

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
  • Oral palate soft and hard tissue segmentation method based on attention mechanism and integrated registration
  • Oral palate soft and hard tissue segmentation method based on attention mechanism and integrated registration
  • Oral palate soft and hard tissue segmentation method based on attention mechanism and integrated registration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] A method for automatic segmentation of soft and hard tissues in the oral cavity and palate provided by this embodiment, the overall flow diagram is shown in figure 2 , the main steps include: data acquisition, model building, model training and model network testing.

[0053] 1. Data acquisition, specifically including the following steps:

[0054] (a) Collect a data set, including CBCT images and soft and hard tissues of the oral and palate outlined by doctors;

[0055] (b) Preprocessing the target image data set, wherein the target image data set includes a CBCT image data set and a delineation label data set, and the preprocessing includes:

[0056] Normalized. Image normalization is a pixel-level operation. Different CBCT scanning equipment may have different configurations. In order to eliminate differences, these images are normalized. The formula is as follows:

[0057] (13)

[0058] where x i Represents the image pixel point value, min(x), max(x) repres...

Embodiment 2

[0104] Firstly, the target image data set is preprocessed, wherein the target image data set includes a CBCT image data set and a delineation label data set, and the preprocessing includes: normalization, grayscale and ROI extraction.

[0105] Secondly, the random augmentation method is added to the segmentation network model training to take all possible types of transformations, the number of sequentially applied enhancement transformations, and the magnitude of all transformations into the algorithm. The augmentation transformation methods include X-axis translation and Y-axis translation. , X-axis shearing, Y-axis shearing, and image rotation. The augmenting transformation strengths include constant amplitude, random amplitude, linearly increasing amplitude, and random amplitude with an increasing upper limit. The before and after comparison of the augmented data is as follows: the structural similarity of the segmented soft and hard tissues of the palate before adding rand...

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

An oral cavity palate soft and hard tissue segmentation method based on an attention mechanism and integrated registration comprises the steps that firstly, CBCT images are acquired, and after data labeling, the images are divided into a training set, a verification set and a test set; secondly, inputting the training set into a built oral palate soft and hard tissue segmentation network model; in addition, a random augmentation method is added during network training, and random scale and different transformation type enhancement is carried out on input data; predicting a tissue segmentation result, and quantitatively evaluating a prediction effect of the model on a test set; and finally, performing integrated registration according to a multi-palate soft and hard tissue segmentation result. The oral cavity palate soft and hard tissue segmentation and registration method fills the blank of oral cavity palate soft and hard tissue segmentation and registration, solves the problem that tissue segmentation is not accurate enough, shortens the time for searching implantation sites of different cases, and provides technical support for case analysis and design of orthodontic implantation nails.

Description

technical field [0001] The invention relates to the cross field of stomatology and computer science, in particular to a method for segmenting soft and hard tissues of the oral cavity and palate based on an attention mechanism and integrated registration. Background technique [0002] This study is mainly aimed at the soft and hard tissue segmentation of the palate in the field of stomatology. It mainly comes from the discussion of the implantable area of ​​oral implant nails. Generally speaking, the segmentation and registration research of this area has the following guiding significance. (1) Assisting in the diagnosis of some oral diseases, including cleft lip and palate, oral cysts, and tumors; (2) Assisting in guiding the precise extraction of impacted canines; (3) Due to individual differences, the integration of soft and hard tissue images in the palate Registration solves the problem of selecting the best implant site for oral micro-implant anchorage. [0003] In the...

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): G06T7/00G06V10/25G06V10/26G06V10/762G06V10/82G06K9/62G06N3/04
CPCG06T7/0012G06T2207/10081G06T2207/30008G06N3/045G06F18/23
Inventor 袁学东邹可邹联军陶天金龙虎赖文莉李沿宏江茜
Owner SICHUAN 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