KR102311385B1 - Oral Health Prediction Device and Method Using Dental Caries Detection - Google Patents

Abstract

Oral using dental caries detection, which allows users to accurately predict the user's oral health by comprehensively analyzing the presence or absence of orthodontics, the state of dental caries, and the state of prostheses through photo analysis using a machine learning algorithm when the user uploads an oral photograph. A health prediction device and method, wherein the user provides an oral image of the user through a network using a user terminal and requests an oral health determination result, the oral health condition is predicted by analyzing the oral image with a machine learning algorithm. , analyzes dental caries status and prosthesis status through the analysis of oral photos, predicts oral health status based on the analyzed dental caries status information and prosthesis status information, and provides oral health status prediction information to users.

Description

Oral Health Prediction Device and Method Using Dental Caries Detection

The present invention relates to oral health prediction using dental caries detection, and more particularly, when a user uploads an oral photograph, the presence or absence of correction, dental caries state, and prosthesis through photo analysis using a machine learning algorithm It relates to a device and method for predicting oral health using dental caries detection, which enables accurate prediction of a user's oral health by comprehensively analyzing the condition.

Although oral diseases can be highly preventable through proper preventive treatment and continuous management, many patients with oral diseases are still aware of oral prevention, such as not receiving a diagnosis or referral to a doctor unless there is a problem with oral health. This is insufficient.

In addition, in predicting the patient's current oral condition, accurate examination and diagnosis results and objective numerical information are required, not the subjective opinion of a dentist or dental hygienist, but there is no system for objectively calculating the oral health condition. .

The two major diseases of the oral cavity are tooth decay (dental caries) and periodontal disease. In particular, periodontal disease, which means periodontitis and gingivitis, is difficult to prevent in advance because there is no pain in the initial stage and is delayed because it progresses chronically.

Therefore, various methods for diagnosing the condition of oral diseases in advance, and based on this, various methods for improving oral health and preventing oral diseases have been studied and proposed. to <Patent Document 3> are disclosed.

<Patent Document 1> receives user condition information including information on at least one of a user's gender, age, periodontal disease, and goal setting information from a user terminal and treatment information at a user's affiliated medical institution. In addition, information on oral care products is received from an oral care product store. Thereafter, information on a specific oral care product included in a specific category corresponding to the user's condition information and treatment information is provided to the user terminal to provide a user-customized oral care service.

In addition, <Patent Document 2> examines the oral condition of the patient, converts the oral examination index calculation standard data including the oral examination data of the patient into big data, and analyzes it to analyze the patient's The influence of the oral examination index calculation standard data on oral health is determined according to the region of residence and age. Then, weight is given to the oral examination index calculation standard data to make the oral examination index calculation standard data current to manage oral health.

In addition, <Patent Document 3> collects the user's personal information, the user's oral hygiene behavior data and oral questionnaire data, and oral examination data generated by the user visiting a specialized medical institution. By integrating and analyzing each information collected in this way, the user's risk of oral disease is evaluated and personalized service is provided.

However, the conventional oral disease management systems as described above are a method of generating oral disease management information by analyzing the user's personal information, oral data and questionnaire data, and oral examination data generated through a specialized medical institution. Since it is not a method to analyze oral images of

In addition, conventional techniques have a disadvantage in that it is difficult for a user to recognize his or her periodontal disease state in real time.

Republic of Korea Patent Publication 10-2017-0050467 (published on May 11, 2017) (User-customized oral care service providing method and oral care service providing server) Republic of Korea Patent Registration 10-1868979 (registered on June 12, 2018) (Oral health management system and method using deep learning algorithm) Republic of Korea Patent Registration 10-1788030 (Registered on October 13, 2017) (Oral disease risk diagnosis and oral care system and method)

Therefore, the present invention has been proposed to solve the problems occurring in the prior art as described above, and when a user uploads an oral photograph, the presence or absence of correction, dental caries state, and prosthesis state through photo analysis using a machine learning algorithm An object of the present invention is to provide an oral health prediction device and method using dental caries detection that can accurately predict a user's oral health by comprehensively analyzing the

In order to achieve the above object, "oral health prediction device using dental caries detection" according to the present invention, provides a user's oral image, a user terminal for requesting the oral health determination result; An oral health prediction server for predicting oral health status by analyzing the oral image provided from the user terminal with a machine learning algorithm,

The oral health prediction server analyzes the dental caries state and the prosthesis state through the analysis of the oral photograph, and predicts the oral health state based on the analyzed dental caries state information and the prosthesis state information.

In the above, the oral health prediction server learns the user's oral image with a CNN (Convolutional Neural Network) algorithm to determine whether the picture can be analyzed, whether to correct it, and whether to extract it, and analyze the determined result information with object detection. It is characterized in that it includes an oral health prediction unit that acquires dental caries state information and prosthesis state information, and determines the oral health state by learning the acquired dental caries state information and prosthesis state information with an Artificial Neural Network (ANN) algorithm.

The oral health prediction server is characterized in that it further comprises an oral health information providing unit for transmitting the oral health state information determined by the oral health prediction unit to the user terminal as oral health prediction information.

The oral health prediction unit includes: a photo registration unit for registering an oral photograph transmitted from the user terminal as an oral health prediction target; a correction determination unit that learns the image registered in the photo registration unit with a Convolutional Neural Network (CNN) algorithm to determine whether a photo can be analyzed, whether or not to be corrected, and whether or not to be extracted; an oral disease and prosthesis detection unit for obtaining dental caries status information and prosthesis status information by analyzing the result information determined by the orthodontic presence/absence determination unit through object detection; Oral health status is determined by learning the orthodontic status information and tooth extraction information acquired from the orthodontic presence determination unit, and the dental caries status information and prosthesis status information acquired from the oral disease and prosthesis detection unit using an Artificial Neural Network (ANN) algorithm. It is characterized in that it includes an oral health determination unit.

In addition, the oral health prediction method using dental caries detection according to the present invention,

(a) registering the oral image provided from the user terminal as an oral health prediction target in the oral health prediction server that predicts the oral health state by analyzing the oral image provided from the user terminal with a machine learning algorithm; (b) determining the presence or absence of an oral photograph by learning the oral image in the oral health prediction server with a CNN (Convolutional Neural Network) algorithm; (c) if the oral health prediction server is an oral photograph, learning an oral image using a CNN (Convolutional Neural Network) algorithm to determine whether or not to correct or not; (d) obtaining dental caries status information and prosthesis status information by analyzing the orthodontic information and tooth extraction information determined by the oral health prediction server by object detection; (e) determining the oral health state by learning the orthodontic information, tooth extraction information, dental caries state information, and prosthesis state information from the oral health prediction server with an Artificial Neural Network (ANN) algorithm do.

In the above, the dental caries state information is characterized in that it includes information on the presence or absence of dental caries and the number of dental caries when there is dental caries.

In the above, the prosthesis state information is characterized in that it includes information on the presence or absence of the prosthesis and information on the number of prostheses when the prosthesis exists.

In addition, the oral health prediction method using dental caries detection according to the present invention,

(f) it characterized in that it further comprises the step of transmitting the oral health prediction information obtained through the determination in step (e) to the user terminal.

In the above (b), instead of step (b), it is characterized in that it can be replaced with a step of providing a guide phrase to induce the user not to register an image other than an oral photograph.

In the step (c), the user is guided to select whether or not to calibrate by creating a questionnaire, thereby omitting the learning process of a Convolutional Neural Network (CNN) algorithm for determining whether to calibrate.

According to the present invention, when a user uploads an oral photograph, it is possible to accurately predict the user's oral health by comprehensively real-time analysis of the presence or absence of orthodontics, the state of dental caries, the state of prostheses, etc. through photo analysis using a machine learning algorithm. have.

In addition, by providing the predicted oral health status information to the user, there is an advantage in that the user can recognize and manage his or her oral health in real time to prevent deterioration of oral health in advance.

1 is an overall configuration diagram of an oral health prediction device using dental caries detection according to the present invention;
Figure 2 is a configuration diagram of an embodiment of the oral health prediction server of Figure 1;
3 is a flowchart showing a method for predicting oral health using dental caries detection according to the present invention;
4 is an example of determining the presence or absence of an oral photograph by learning an oral photograph with a CNN algorithm in the present invention;
5 is an example of determining whether or not correction by learning an oral photograph with a CNN algorithm in the present invention;
6 is an exemplary diagram for detecting oral diseases and prostheses by learning an oral photograph with an object detection algorithm in the present invention;
7 is an exemplary diagram for determining the oral health state by learning the correction information, the detected oral disease information, and the prosthesis information using the DNN algorithm in the present invention.

Hereinafter, an apparatus and method for predicting oral health using dental caries detection according to a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings.

The terms or words used in the present invention described below should not be construed as being limited to conventional or dictionary meanings, and the inventor may appropriately define the concept of terms in order to best describe his invention. It should be interpreted as meaning and concept consistent with the technical idea of the present invention based on the principle that it can be

Therefore, the embodiments described in this specification and the configurations shown in the drawings are only preferred embodiments of the present invention, and do not represent all of the technical spirit of the present invention, so various equivalents and It should be understood that there may be variations.

1 is an overall configuration diagram of an oral health prediction apparatus using dental caries detection according to a preferred embodiment of the present invention, and may include a user terminal 100 and an oral health prediction server 200 .

The user terminal 100 and the oral health prediction server 200 may be connected to various wired and wireless networks, and a communication interface may be formed with real-time properties.

The user terminal 100 is a terminal used by a user who wants to check the oral health state, and serves to provide an oral image of the user and to request an oral health determination result. Here, the user may provide user personal information and general data such as questionnaire data using the user terminal 100 .

The user receives the oral health state report through the user terminal 100, recognizes his or her oral health state through this, and if it is predicted that the oral health state is not good, visit a dental hospital and take follow-up measures to improve oral health It is desirable to manage The user terminal 100 may be implemented as a mobile device such as a smart phone and a smart pad, a personal computer or a notebook computer capable of the Internet, and the like, and it is assumed that the user terminal 100 is implemented as a smart phone as an embodiment of the present invention.

The oral health prediction server 200 serves to predict the oral health state by analyzing the oral image provided from the user terminal 100 with a machine learning algorithm (CNN, DNN, etc.). The oral health prediction server 200 may analyze the dental caries state and the prosthesis state through the analysis of the oral photograph, and predict the oral health state based on the analyzed dental caries state information and the prosthesis state information.

The oral health prediction server 200 learns the user's oral image with a CNN (Convolutional Neural Network) algorithm to determine whether a photo can be analyzed, whether to correct, and whether to extract, and converts the determined result information into object detection. An oral health prediction unit 210 that analyzes to obtain dental caries state information and prosthesis state information, and determines the oral health state by learning the acquired dental caries state information and prosthesis state information with an Artificial Neural Network (ANN) algorithm. It may include an oral health information provider 220 that transmits the oral health state information determined by the oral health prediction unit 210 to the user terminal 100 as oral health prediction information.

In addition, the oral health prediction unit 210, as shown in FIG. 2, a photo registration unit 211 for registering an oral photograph transmitted from the user terminal 100 as an oral health prediction target, the photograph registration unit 211. By learning the registered image with a CNN (Convolutional Neural Network) algorithm, the correction result determination unit 212 that determines whether the photo can be analyzed, whether or not to correct it, and whether or not to extract the image, and the result information determined by the correction determination unit 212 as an object Oral disease and prosthesis detection unit 213 that obtains dental caries status information and prosthesis status information by analyzing with object detection, orthodontic information and tooth extraction information obtained from the orthodontic presence determination unit 212, and the oral cavity The disease and prosthesis detection unit 213 may include an oral health determination unit 214 that determines the oral health state by learning the dental caries state information and the prosthesis state information obtained by the ANN (Artificial Neural Network) algorithm.

3 is a flowchart showing a method for predicting oral health using dental caries detection according to the present invention, where S represents a step.

In the oral health prediction method using dental caries detection according to the present invention, (a) the oral health prediction server 200 predicts the oral health state by analyzing the oral image provided from the user terminal 100 with a machine learning algorithm. Registering the oral image provided from the user terminal 100 as an oral health prediction target (S101), (b) learning the oral image from the oral health prediction server 200 with a CNN (Convolutional Neural Network) algorithm Steps (S102 - S103) of determining the presence of a photograph (S102 - S103), (c) In the case of an oral photograph in the oral health prediction server 200, the oral image is learned by a CNN (Convolutional Neural Network) algorithm to determine whether or not to correct or not Steps (S104 - S105), (d) obtaining dental caries status information and prosthesis status information by analyzing the orthodontic information and tooth extraction information determined by the oral health prediction server 200 by object detection ( S106 - S110), (e) the oral health prediction server 200 determines the oral health status by learning the orthodontic information, tooth extraction information, dental caries status information, and prosthesis status information with an ANN (Artificial Neural Network) algorithm. It includes a step (S111) to.

The dental caries status information may include information on the presence or absence of dental caries and information on the number of dental caries when there is dental caries, and the prosthesis status information includes information on the presence or absence of a prosthesis and information on the number of prostheses when there is a prosthesis. .

In addition, the oral health prediction method using dental caries detection according to the present invention, (f) transmitting the oral health prediction information obtained through the determination in step (e) to the user terminal 100 (S112) further may include

The oral health prediction apparatus and method using the dental caries detection according to the present invention configured as described above will be described in detail as follows.

First, the user downloads an oral health prediction application for checking and managing his or her oral health condition from the oral health prediction server 200 and stores it in the user terminal 100 .

Next, in order to check the oral health state, the oral health application is executed, and oral health diagnosis is requested while providing an oral photograph, personal information, and the like. Here, if necessary, questionnaire data for oral health diagnosis may be prepared and provided. The questionnaire data is a questionnaire, and may be made in a check format. The questionnaire may include items for checking whether or not corrections are made.

A photograph of the oral cavity is preferably a photograph of the entire oral cavity, and a photograph of only a part of the oral cavity may be used.

When the oral health prediction server 200 receives an oral photograph and personal information and/or questionnaire data through the user terminal 100 accessed through the network, the oral health prediction unit 210 CNNs the oral photograph (image). (Convolutional Neural Network) learns with algorithm to determine whether a photo can be analyzed, whether correction is made, and whether or not tooth extraction is performed Oral health status is determined by learning dental caries status information and prosthesis status information with an Artificial Neural Network (ANN) algorithm.

For example, the photo registration unit 211 of the oral health prediction unit 210 registers the oral photograph transmitted by the user as an oral health prediction target image in the internal database. Here, since the oral image is taken by an individual, the shooting environment is different, so there is no standard for the color of the actual shot image. Therefore, it is possible to take a reference point, automatically perform color correction so that all photos are identical to the reference point, and then store it (S101).

Next, the orthodontic presence determination unit 212 determines the presence or absence of an oral photograph by learning the oral image with a CNN (Convolutional Neural Network) algorithm (S102). Here, as a result of the determination, if there is no oral photograph, a guide text for registering an oral photograph is transmitted to the user terminal 100 because it is not an oral photograph (S103).

The process of determining the presence or absence of an oral photograph by learning the oral image with a CNN algorithm is shown in FIG. For this purpose, it is assumed that a CNN model that determines whether a photo taken in advance and requested to be registered is an oral photo is built. It is preferable to use the pre-trained CNN model by adding the oral picture category to the already known CNN models such as VGG16 (https://neurohive.io/en/popular-networks/vgg16/) and ResNet50. The training data may be oral photo data or photo data of a category to be added.

The presence or absence of an oral photograph can be determined by learning with a CNN model using this oral photograph data, but in this case, it may cause a disadvantage in that it takes a lot of learning time depending on the amount of added learning data.

Therefore, as another method of determining the presence or absence of an oral photograph, the oral health prediction application is used instead of using the CNN algorithm to induce the user not to register an image other than an oral photograph, thereby omitting the process of determining the presence or absence of an oral photograph. can Here, as a method of inducing not to register an image other than an oral photograph, a guide phrase may be used.

As a result of the confirmation of step S102, if it is determined as an oral image, then the correction is determined by learning the oral image in the presence or absence determination unit 212 with the CNN (Convolutional Neural Network) algorithm shown in FIG. 5 to determine whether correction (S104 - S105). Here, Figure 5 is an example of a CNN model that determines whether or not correction from the input oral image. These CNN models can be built using AutoKeras. Transfer learning using pre-trained VGG16, ResNet50, etc. can also be used. Required data is oral photo data with/without braces, and by adding two categories of oral photos (with/without braces) to the CNN model, it is possible to simply determine whether or not correction is made.

Correction can be determined using this CNN model, but this also requires sufficient learning time and data, and an increase in the training data results in an increase in the amount of computation. Therefore, it is possible to omit the learning process of a CNN (Convolutional Neural Network) algorithm for determining whether or not to calibrate by inducing the user to select whether or not to calibrate by creating a questionnaire.

When the questionnaire information is provided through the preparation of the questionnaire, the questionnaire information is classified by the FFNN (Feed Forward Neural Network) algorithm. Here, the FFNN algorithm is a machine learning algorithm in which a questionnaire response (user information) is an input and a diagnosis result is an output. It is desirable to design and use an FFNN suitable for the input/output structure using a Python-based library such as Tensorflow or Keras. For activation function, loss function, optimization method, parallel computing structure, overfitting problem, etc., FFNN algorithms that have been recently studied and analyzed can be used. The input data (survey response) is preprocessed, and the preprocessed data is divided into training data and verification data. Then, learning data is learned through neural network learning, and the validation data and learning result data are verified and supplemented through a newly designed neural network. And when verification and supplementation are completed, the final model is output as a questionnaire diagnosis result.

It is also possible to determine whether or not correction is made using the CNN model constructed here, but it can be additionally determined whether tooth extraction is performed using the same CNN model. By adding the category of extracted oral photos to the CNN model, it is possible to simply determine whether or not the tooth has been extracted.

Next, the oral disease and prosthesis detection unit 213 obtains the dental caries status information and the prosthesis status information by analyzing the determined orthodontic information and the tooth extraction information by object detection (S106 - S110). To this end, an object detection algorithm for determining oral disease (dental caries) and prosthesis detection from the input section photo (image) as shown in FIG. 6 is constructed. The object detection algorithm that determines the detection of oral diseases and prostheses uses the previously developed Faster R-CNN, SSD, and YOLO (W.Liu et al., 2015, arXiv (http://arxiv.org/abs/1512.02325)). Available. As data required for obtaining dental caries status information and prosthesis status information with the object detection algorithm, photo data showing oral diseases and prostheses may be used. Accuracy can be improved by classifying whether or not to wear braces and learning. It has the advantage of being able to detect both dental caries and prostheses with one algorithm. Here, the dental caries status information may include information on the presence or absence of dental caries and information on the number of dental caries when there is dental caries, and the prosthesis status information includes information on the presence or absence of a prosthesis and information on the number of prostheses when there is a prosthesis. . Dental caries image learning checks which part of the entire oral region the oral photo provided by the user is, and performs image learning after confirming the position of the oral region image, and through this, the presence or absence of dental caries and the number of dental caries are extracted. . In the same way, the presence or absence of the prosthesis and the number of prostheses are also extracted.

Next, the oral health determination unit 214 uses the ANN (Artificial Neural Network) algorithm (2019 NIMS Industrial Mathematics Problem Solving Workshop Proposal Model) as shown in FIG. ) to determine the state of oral health. Here, the ANN algorithm, which is a machine learning algorithm, determines an oral health state (oral health) by inputting the orthodontic information, tooth extraction information, dental caries state information, and prosthesis state information as inputs. For this purpose, the patient's oral health evaluation data corresponding to reliable photographic data obtained from a specialist or a specialist may be used. When the oral health state determination is completed, oral health prediction information is generated and stored in an internal database.

Next, the oral health information providing unit 220 transmits the oral health prediction information obtained through the determination to the user terminal 100 . Here, the oral health prediction information may be in the form of a report. To this end, the oral health information providing unit 220 may include a communication module capable of transmitting and receiving data to and from the user terminal 100 .

Here, the oral health prediction information is provided with a professional monitoring service for everyday oral care. Oral health prediction information is a report for the purpose of prevention, not medical treatment performed remotely or digitally. That is, it simply provides only the user's oral health status in the form of a report. When the user sees the oral health report provided and determines that a visit to the hospital is necessary, it is preferable to visit the hospital and quickly treat oral problems to manage oral health.

According to the present invention, when a user takes a picture of his/her oral cavity, uploads it, creates and transmits a questionnaire, uses a machine learning algorithm to detect oral diseases and prostheses, and uses this to predict oral health status to improve oral health By providing the report to the user in real time, the user can easily manage their oral health and prevent deterioration of their oral health in advance.

Although the invention made by the present inventor has been described in detail according to the above embodiment, the present invention is not limited to the above embodiment, and it is common knowledge in the art that various changes can be made without departing from the gist of the present invention. self-evident to those who have

100: user terminal
200: oral health prediction server
210: oral health prediction unit
211: photo register
212: calibration presence determination unit
213: oral disease and prosthesis detection unit
214: oral health judgment unit
220: oral health information provider

Claims (9)

As a device for predicting oral health by analyzing oral photos with a machine learning algorithm,
A user terminal that provides an oral image taken by the user and requests an oral health determination result; and
An oral health prediction server for predicting oral health status by analyzing the oral image provided from the user terminal with a machine learning algorithm,
The oral health prediction server analyzes the dental caries state and prosthesis state through the analysis of the oral photograph, and predicts the oral health state based on the analyzed dental caries state information and prosthesis state information,
The oral health prediction server captures a reference point for the oral image provided from the user terminal, automatically performs color correction to be the same as the reference point, and then stores it. is classified as an FFNN (Feed Forward Neural Network) algorithm to determine whether to correct it,
The oral health prediction server provides oral health prediction information, which is the result of oral health state prediction, to the user terminal in the form of a report for the purpose of prevention, the oral health prediction information includes professional monitoring service information for everyday oral care. Oral health prediction device using dental caries detection, characterized in that provided to the user terminal.
The method according to claim 1, The oral health prediction server learns the user's oral image with a CNN (Convolutional Neural Network) algorithm to determine whether the picture can be analyzed, whether to correct it, and whether or not to extract, and use the determined result information to detect an object (Object Detection). to obtain dental caries state information and prosthesis state information by analyzing it with an oral health Oral health prediction device using dental caries detection.
The method according to claim 2, The oral health prediction server using dental caries detection, characterized in that it further comprises an oral health information providing unit for transmitting the oral health state information determined by the oral health prediction unit to the user terminal as oral health prediction information Oral health prediction device.
The method according to claim 2, wherein the oral health prediction unit orthodontic presence determination unit for learning the registered oral image with a CNN (Convolutional Neural Network) algorithm to determine whether the picture can be analyzed and whether or not correction and tooth extraction; an oral disease and prosthesis detection unit for obtaining dental caries status information and prosthesis status information by analyzing the result information determined by the orthodontic presence/absence determination unit through object detection; Oral health status is determined by learning the orthodontic status information and tooth extraction information acquired from the orthodontic presence determination unit, and the dental caries status information and prosthesis status information acquired from the oral disease and prosthesis detection unit using an Artificial Neural Network (ANN) algorithm. Oral health prediction device using dental caries detection, characterized in that it comprises an oral health determination unit.
A method of predicting oral health by analyzing an oral photograph with a machine learning algorithm using the oral health prediction device using the dental caries detection according to any one of claims 1 to 4,
(a) registering the oral image provided from the user terminal as an oral health prediction target in the oral health prediction server that predicts the oral health state by analyzing the oral image provided from the user terminal with a machine learning algorithm;
(b) learning the oral image in the oral health prediction server with a CNN (Convolutional Neural Network) algorithm to determine whether an oral photograph is present;
(c) if the oral health prediction server is an oral photograph, learning an oral image with a CNN (Convolutional Neural Network) algorithm to determine whether or not to correct or not;
(d) obtaining dental caries status information and prosthesis status information by analyzing the orthodontic information and tooth extraction information determined by the oral health prediction server by object detection; and
(e) determining the oral health status by learning the orthodontic information and tooth extraction information, dental caries status information, and prosthesis status information in the oral health prediction server with an Artificial Neural Network (ANN) algorithm,
The step (a) is stored after automatically performing color correction to be the same as the reference point by capturing the reference point for the oral image provided from the user terminal,
In the step (c), when the questionnaire information is provided through the creation of a questionnaire in the user terminal, the process of determining whether or not correction is performed using the CNN is omitted and the provided questionnaire information is classified into an FFNN (Feed Forward Neural Network) algorithm to determine whether or not the questionnaire is corrected. to judge,
In step (e), the oral health prediction information, which is the result of determining the oral health condition, is provided to the user terminal in the form of a report for the purpose of prevention, and the oral health prediction information includes professional monitoring service information for everyday oral care. Oral health prediction method using dental caries detection, characterized in that provided to the user terminal, including.
The method for predicting oral health using dental caries detection according to claim 5, wherein the dental caries status information includes information on the presence or absence of dental caries and information on the number of dental caries if there is dental caries.
The method for predicting oral health using dental caries detection as set forth in claim 5 , wherein the prosthetic state information includes information on the presence or absence of the prosthesis and information on the number of prostheses if the prosthesis exists.
The method for predicting oral health using dental caries detection according to claim 5, (f) further comprising the step of transmitting the oral health prediction information obtained through the determination in step (e) to the user terminal.
In claim 5, instead of step (b), CNN (Convolutional Convolutional An oral health prediction method using dental caries detection, characterized in that the learning process of the Neural Network) algorithm is omitted.

Images