Method for establishing oral diagnosis neural network model and oral diagnosis method

A technology of neural network model and diagnostic method, which is applied in the field of oral diagnosis and establishment of neural network model for oral diagnosis, which can solve the problems of many inspection steps, low efficiency of patient diagnosis, long inspection time, etc.

Pending Publication Date: 2020-11-10
STOMATOLOGICAL HOSPITAL OF CHONGQING MEDICAL UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to propose a method for establishing a neural network model for oral cavity diagnosis and a method for oral cavity diagnosis, so as to solve the problem of many inspection steps and long inspection time in the oral cavity diagnosis process in the prior art, and the diagnosis efficiency is not high for patients.

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 establishing oral diagnosis neural network model and oral diagnosis method
  • Method for establishing oral diagnosis neural network model and oral diagnosis method
  • Method for establishing oral diagnosis neural network model and oral diagnosis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Such as figure 1 As shown, the embodiment of the present invention provides a method for establishing an oral diagnosis neural network model, which aims to establish an oral diagnosis neural network model for obtaining preliminary oral diagnosis results, saving patient examination time, and improving diagnosis efficiency. The method includes but is not limited to the following steps:

[0048] S101. Obtain a training set containing an oral image of a classified patient.

[0049] In the above step S101, the classified patient image is taken from the intraoral photograph of the patient in the clinical diagnosis, and the classified image data is obtained by classifying it.

[0050] In specific applications, rapid modeling and testing can be used to classify intraoral photos taken from patients in clinical diagnosis. In order to improve classification accuracy, images with preset oral defects can also be screened at the same time, marked and added noise , And finally obtain the t...

Embodiment 2

[0092] Such as figure 2 As shown, the embodiment of the present invention also provides an apparatus 20 for establishing a neural network model for oral diagnosis, including:

[0093] The training set acquisition module 21 is used to acquire a training set containing the oral images of the classified patient;

[0094] The sample set obtaining module 22 is configured to obtain preset oral defect images from the training set to construct a sample set;

[0095] The basic neural network model setting module 23 is used to apply the loss function and activation function on the basis of the structure of the VGG16 convolutional neural network model;

[0096] The oral diagnosis neural network model establishment module 24 is configured to input the training set and the sample set into the VGG16 neural network for training to generate an oral diagnosis neural network model.

Embodiment 3

[0098] Such as image 3 As shown, the embodiment of the present invention also provides an oral diagnosis method, including:

[0099] S301. Obtain an oral image of the patient to be diagnosed;

[0100] S302, use as above figure 1 The oral diagnosis neural network model in the oral cavity image of the patient to be diagnosed performs preliminary diagnosis of preset oral defects.

[0101] In practical applications, the foregoing step S301 may be to obtain an oral image of the patient to be diagnosed through the terminal.

[0102] It is conceivable that according to the above figure 1 The obtained oral diagnosis neural network model is stored in the cloud server. After the terminal obtains the oral image of the patient to be diagnosed, it uploads it to the cloud server, and the oral diagnosis neural network module stored in the cloud server uses the oral image of the patient to be diagnosed. It is determined whether the patient has a predetermined oral defect, and based on the patient,...

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 is suitable for the technical field of oral medicine, and provides a method for establishing an oral diagnosis neural network model and an oral diagnosis method, and the method for establishing the oral diagnosis neural network model comprises the steps: obtaining a training set comprising oral images of classified patients; obtaining a preset oral defect image from the training setto construct a sample set; on the basis of the structure of the VGG16 convolutional neural network model, applying a loss function and an activation function; and putting the training set and the sample set into a VGG16 neural network for training to generate an oral diagnosis neural network model. According to the invention, image recognition and preliminary diagnosis of oral defects such as wrong occlusion can be realized, so that the examination steps are simplified, the examination time is shortened, and the overall diagnosis efficiency of patient treatment is improved.

Description

Technical field [0001] The invention relates to the technical field of stomatology, in particular to a method for establishing a neural network model for oral cavity diagnosis and an oral cavity diagnosis method. Background technique [0002] The number of malocclusion patients in my country is large, and there is an increasing situation. Among them, children's malocclusion deformity should be prevented and corrected with oral treatment methods for the cause, mechanism, occurrence and development process of malocclusion at an early stage. At this time, correction is less difficult. After correction, the aesthetics and function of the craniofacial occlusion can usually be perfectly coordinated. [0003] The current oral diagnosis process mainly uses dental mirrors to penetrate the patient’s mouth to detect the patient’s oral conditions. Among them, dental mirrors are divided into many types, and each dental mirror has a single function. If multiple tools are used in rotation, it will...

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): G06K9/62G06N3/04G06N3/08G16H50/20A61C19/05
CPCG06N3/08G16H50/20A61C19/05G06N3/045G06F18/241
Inventor 宋锦璘柴召午张超
Owner STOMATOLOGICAL HOSPITAL OF CHONGQING MEDICAL 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