Child oral health management system based on three-dimensional modeling and digital restoration

Abstract

The invention discloses a child oral health management system based on three-dimensional modeling and digital restoration, and belongs to the technical field of oral medical treatment. According to the system, a three-dimensional information acquisition module scans teeth of a child, and an oral cavity three-dimensional model is constructed; the tooth feature analysis module analyzes tooth features and identifies a caries region; the decayed tooth data quantification module quantifies the caries area features to generate a decayed tooth data set; the individual information collection module collects child individual information and generates an individual data set; the health risk assessment module establishes an oral health model and assesses the oral health degree; the personalized scheme generation module generates a personalized nursing scheme based on the evaluation result. According to the method, the three-dimensional shape, the surface characteristics and the caries information of the teeth of the child can be accurately acquired and quantified, individual risk factors are comprehensively considered, precision and individualization of oral health management of the child are realized, the caries risk is effectively reduced, and the oral health level is improved.

Description

Technical Field

[0001] The present invention belongs to the field of oral medical technology, and in particular relates to a children's oral health management system based on three-dimensional modeling and digital restoration. Background Art

[0002] Oral health is an important part of children's healthy growth, directly affecting their nutritional intake, language development and mental health. Dental caries is the most common oral disease in children, seriously affecting their health level and quality of life, and bringing a heavy burden to families and society. Therefore, how to effectively prevent and control children's dental caries has become an important issue in the field of stomatology that needs to be solved urgently.

[0003] At present, traditional children's oral health management mainly relies on regular oral examinations and doctors' subjective judgments, which makes it difficult to achieve accurate assessment of caries risk and individualized intervention. Existing caries risk assessment methods, such as the Caries Risk Assessment Tool (CAT), although taking individual factors into account, lack objective quantitative analysis of tooth morphology and surface characteristics. In addition, traditional oral care plans are often stereotyped and fail to fully consider the individual differences of children, resulting in limited care effects.

[0004] Therefore, there is an urgent need for a children's oral health management system that can accurately obtain dental information, comprehensively assess individual risks, and provide personalized care plans. Summary of the invention

[0005] The present invention overcomes the deficiencies of the prior art and provides a children's oral health management system based on three-dimensional modeling and digital restoration.

[0006] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a children's oral health management system based on three-dimensional modeling and digital restoration, comprising:

[0007] A three-dimensional information acquisition module is used to obtain three-dimensional information of children's teeth and construct a three-dimensional model of the oral cavity;

[0008] A tooth feature analysis module, connected to the three-dimensional information acquisition module, is used to analyze tooth features and identify carious areas based on the three-dimensional model of the oral cavity;

[0009] A dental caries data quantification module, connected to the tooth feature analysis module, is used to quantify the features of the carious area and generate a dental caries data set;

[0010] An individual information collection module is used to collect individual information of children and generate an individual data set;

[0011] A health risk assessment module, which is respectively connected to a dental caries data quantification module and an individual information collection module, is used to establish an oral health model, and input a dental caries data set and an individual data set into the oral health model to evaluate the oral health level of children;

[0012] A personalized plan generation module, which is connected to the health risk assessment module, is used to generate a personalized care plan based on the evaluation result of the oral health level.

[0013] In a preferred embodiment of the present invention, the three-dimensional information acquisition module includes:

[0014] A scanning unit, which is used to scan the teeth of children with an intraoral scanner to obtain point cloud data on the tooth surface;

[0015] A reconstruction unit, which is connected to the scanning unit, is used to process the point cloud data and perform surface reconstruction to obtain an oral three-dimensional model.

[0016] In a preferred embodiment of the present invention, the tooth feature analysis module includes:

[0017] A curvature calculation unit, which is used to calculate the Gaussian curvature of the tooth surface to reflect the concave and convex changes on the tooth surface;

[0018] A texture extraction unit, which is used to extract the texture features on the tooth surface to quantify the roughness of the enamel;

[0019] An optical analysis unit, which is used to analyze the optical properties of the tooth surface to obtain the spectral information on the tooth surface.

[0020] In a preferred embodiment of the present invention, the dental caries data quantification module includes:

[0021] A region segmentation unit, which is used to identify and segment the carious regions on the tooth surface according to the analysis result of the tooth feature analysis module;

[0022] A volume and depth calculation unit, which is connected to the region segmentation unit, is used to quantify the volume and depth of the carious regions;

[0023] A data integration unit, which is connected to the volume and depth calculation unit, is used to integrate the three-dimensional position information, carious volume and carious depth of the carious regions to generate a dental caries data set.

[0024] In a preferred embodiment of the present invention, the individual information collection module includes:

[0025] An information extraction unit, which is used to obtain individual information related to the oral health status of children from a database or a questionnaire survey;

[0026] An information preprocessing unit, which is connected to the information extraction unit, is used to clean, transform and encode the individual information to generate an individual data set.

[0027] In a preferred embodiment of the present invention, the health risk assessment module includes:

[0028] A data merging unit, configured to merge the dental caries dataset and the individual dataset into a single dataset according to the unique individual identifier.

[0029] A model construction unit, connected to the data merging unit, for establishing an oral health model, where the oral health model is a gradient boosting machine model for evaluating the oral health level of children.

[0030] In a preferred embodiment of the present invention, the oral health model outputs a value, which represents the probability of dental caries risk.

[0031] In a preferred embodiment of the present invention, the personalized plan generation module includes:

[0032] A risk level classification unit, configured to classify the oral health risk into different levels based on the output result of the oral health model.

[0033] A plan formulation unit, connected to the risk level classification unit, for generating a personalized care plan according to the risk level.

[0034] In a preferred embodiment of the present invention, the personalized care plan includes suggestions for oral hygiene maintenance, diet, regular reexamination, and fluoride application.

[0035] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0036] (1) Through precise three-dimensional data collection and analysis, combined with individualized risk assessment, the present invention realizes the comprehensive management of children's oral health, thereby effectively reducing the risk of dental caries and improving the oral health level.

[0037] (2) The present invention adopts three-dimensional scanning technology to perform high-precision modeling on children's teeth and extract the curvature, texture, and optical characteristics of the tooth surface. Traditional oral examinations rely on subjective judgments and it is difficult to quantify the degree and scope of dental caries. The present invention converts the tooth surface information into quantifiable data to more objectively evaluate the risk of dental caries. Compared with traditional X-rays, the three-dimensional model of the present invention provides more comprehensive tooth morphology information; compared with subjective probe examinations, the present invention quantifies the dental caries characteristics and reduces errors. The present invention improves the early detection rate of dental caries, provides a more reliable basis for precise treatment, and is conducive to reducing the misdiagnosis rate.

[0038] (3) The present invention conducts risk assessment by collecting individual information of children such as age, habits, medical history, etc., and combining it with quantified dental caries data. Dental caries is affected by multiple factors and has large individual differences. Traditional solutions lack pertinence and have limited effects. The present invention customizes personalized care plans for different children, which is more practical. It avoids the limitations of one-size-fits-all solutions, improves the pertinence and effectiveness of the care plan, and enhances children's compliance with the care plan, effectively controlling the risk of dental caries.

[0039] (4) The present invention combines objective dental data with individual risk factors and conducts comprehensive assessment through an oral health model. Based on more accurate assessment results, it generates more targeted personalized care plans, achieving precision and individuation in oral health management. By continuously tracking the care effects and feeding back the actual effect data to the system, it optimizes the oral health model and the personalized plan generation strategy, forming a virtuous cycle of data-driven continuous improvement, thereby continuously improving the level of children's oral health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings;

[0041] Figure 1 is a flowchart of a children's oral health management method based on three-dimensional modeling and digital restoration;

[0042] Figure 2 is a schematic structural diagram of a children's oral health management system based on three-dimensional modeling and digital restoration. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0044] Many specific details are set forth in the following description in order to fully understand the present invention, but the present invention can also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited by the specific embodiments disclosed below.

[0045] In the description of the present application, it should be understood that the orientation or positional relationships indicated by the terms "center", "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings. These are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation on the protection scope of the present application. In addition, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Therefore, the features defined with "first", "second", etc. may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more.

[0046] In the description of the present application, it should be noted that unless otherwise clearly specified and limited, the terms "mounted", "connected", "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0047] Exemplary method:

[0048] As Figure 1 shown, a method for children's oral health management based on three-dimensional modeling and digital restoration includes the following steps:

[0049] S1. Obtain the three-dimensional information of children's teeth and construct an oral three-dimensional model;

[0050] S2. Analyze the tooth characteristics based on the oral three-dimensional model and identify the carious areas;

[0051] S3. Quantify the carious characteristics and generate a dental caries data set;

[0052] S4. Collect individual information and generate an individual data set;

[0053] S5. Establish an oral health model, input the dental caries data set and the individual data set into the oral health model, and evaluate the oral health level;

[0054] S6. Generate a personalized care plan based on the oral health assessment.

[0055] Next, the above method for children's oral health management based on three-dimensional modeling and digital restoration will be introduced in detail.

[0056] In step S1, the method for obtaining the three-dimensional information of a child's teeth is to use an intraoral scanner to scan the child's teeth, and obtain the point cloud data of the tooth surface by projecting a grating and receiving the reflected light. This point cloud data contains the three-dimensional coordinate information of the tooth surface, representing the three-dimensional shape of the teeth.

[0057] In a specific embodiment, a 3Shape TRIOS 3 intraoral scanner is used to scan the child's teeth in the standard scanning mode. The scanning head is kept at a distance of 5-10 mm from the tooth surface. According to the prompts of the scanning software, starting from the first molar, the maxillary and mandibular dental arches are scanned in turn, and reciprocating scanning is performed in a zigzag path until the scanning of the entire dental arch is completed.

[0058] It should be noted that before the scanning starts, tools such as cotton balls and mouthwash are needed to clean the child's oral cavity, remove saliva and food residues that may affect the scanning, and provide a clear oral environment for subsequent scanning.

[0059] The method for constructing the three-dimensional oral model includes: after the scanning is completed, the obtained original scanning data is processed, the random error points in the scanning data and the non-real structures caused by object movement or reflection are removed, the processed data is subjected to surface reconstruction, the holes in the data are filled, a complete three-dimensional surface is obtained, and the three-dimensional surface is converted into a three-dimensional mesh model.

[0060] In a specific embodiment, in the original point cloud data, for each point, the average distance between it and the 10 nearest points in the neighborhood is calculated. The distance threshold is set to 0.2 mm. If the neighborhood average distance of a certain point exceeds 0.2 mm, then this point is marked as a noise point and removed. For the remaining point cloud data, the normal vector of each point is calculated. The moving least squares method is used for surface reconstruction to generate a smooth surface model. During this process, the holes on the surface are filled using the adjacent point information, and the reconstructed three-dimensional surface model is converted into a three-dimensional mesh model.

[0061] In step S2, analyzing the tooth features includes calculating the Gaussian curvature of the tooth surface, extracting the texture features of the tooth surface, and analyzing the optical properties of the tooth surface.

[0062] The Gaussian curvature is used to describe the degree of curvature of the tooth surface, and abnormal changes often occur in the carious region. By calculating the degree of curvature of each point on the tooth surface and its surrounding points, the concave and convex changes of the tooth surface are reflected to assist in identifying the carious region. Specifically, the three-dimensional tooth model is converted into grid data to obtain the coordinates of each vertex. For each vertex on the grid, its 6 adjacent vertices are selected, and by calculating the difference in function values of the adjacent points, the derivative value on the surface is approximated, and the Gaussian curvature is calculated using the formula:

[0063] ; where, (xi,j , y i,j ) represents the coordinates of the current vertex, (x i+1,j , y i+1,j ) and (x i-1,j , y i-1,j ) represent the coordinates of two adjacent vertices, (x i,j+1 , y i,j+1 ) and (x i,j+1 , y i,j+1 ) represent the coordinates of another two adjacent vertices, and Δx and Δy represent the distances between adjacent points.

[0064] Extract the texture features of the tooth surface. By analyzing the local texture information of the tooth surface, quantify the roughness of the enamel, and extract the features that can distinguish healthy enamel from carious enamel. The texture features of the enamel can reflect its microscopic structure, and caries will cause changes in the texture. The texture feature map can assist in judging the carious area. Specifically, convert the three-dimensional tooth model into a two-dimensional depth map, and use the Z coordinate of each vertex as the depth value. For each pixel point in the depth map, select 8 pixels within a neighborhood with a radius of 1, compare the gray value of the neighborhood pixels with the gray value of the central pixel. If the gray value of the neighborhood pixel is greater than the gray value of the central pixel, set this bit to 1, otherwise set it to 0, thus generating an 8-bit binary code to represent the texture feature of this pixel point.

[0065] Analyze the optical properties of the tooth surface. By analyzing the reflection intensity of light with different wavelengths on the tooth surface, obtain the spectral information of the tooth surface. Due to demineralization in the carious area, the reflectivity of specific wavelengths will change. The reflectivities of different wavelengths can reflect the compositional and structural changes on the tooth surface. Specifically, obtain the reflectivity data of the tooth surface at three wavelengths of 405nm, 525nm, and 635nm respectively. The 405nm wavelength is used to detect the subtle changes on the tooth surface, which can effectively penetrate the enamel and reflect the demineralization situation; the 525nm wavelength is used to analyze the health status of the tooth and can better reflect the properties of the enamel; the 635nm wavelength is used to observe the surface reflection characteristics.

[0066] Step S3 converts the information of the carious area into numerical data that can be used for subsequent analysis and integrates it to form structured data, that is, the dental caries dataset. The specific methods include:

[0067] S31. Segment the carious area and determine the quantification range.

[0068] The method for segmenting the carious area is to identify and segment the carious area on the tooth surface according to the Gaussian curvature, texture features, and optical properties extracted in step S2.

[0069] In a specific embodiment, the curvature feature map is converted into a grayscale image, and the gradient of the grayscale image is calculated using a 3×3 Sobel operator to obtain a gradient map. The two convolution kernels of the Sobel operator are as follows: Gx = [[-1, 0, 1], [-2, 0, 2], [-1, 0, 1]], Gy = [[-1, -2, -1], [0, 0, 0], [1, 2, 1]]. The image is convolved with Gx and Gy respectively to obtain the gradient values of the image in the x and y directions. Calculate the gradient magnitude g = sqrt(Gx 2 + Gy^2). Set the gradient threshold to 1.5 times the average value of all gradient magnitudes in the gradient map, and mark the pixel points with gradient magnitudes greater than this threshold as edge points. Starting from an edge point, traverse its 8 neighboring pixels. If the neighboring pixel is also an edge point, connect these two points, and repeat this step until all edge points are connected. Define the energy function E = ∫(α × E d + β × E 0 )ds, where E d is the data term, which describes the similarity between the segmentation contour and the boundary of the actual carious region and is constructed based on curvature, texture, and reflectivity data. E 0 is the smooth term, which is used to constrain the shape of the segmentation contour to keep it smooth. α and β are weight coefficients, which are set to 0.5 and 0.5 respectively, the evolution speed is set to 0.1, the maximum number of iterations is set to 100 times, and the iteration stops when .

[0070] S32. Quantify the volume and depth of the carious region.

[0071] The carious region is discretized into small volume units. The volume of the caries is calculated by counting the number of volume units within the carious region; the depth of the caries is calculated by calculating the distance from each volume unit to the tooth surface.

[0072] In a specific embodiment: The segmented carious region is converted into voxel data, and the voxel size is set to 0.1mm × 0.1mm × 0.1mm. Calculate the total number of voxels within the carious region, multiply it by the volume of each voxel to obtain the total volume of the caries; calculate the shortest distance from each voxel to the tooth surface mesh as the depth of the voxel, and calculate the average value of the depths of all voxels as the average depth of the caries.

[0073] S33. Integrate the results of steps S31 and S32 to generate a dental caries dataset containing the following information: the three-dimensional position information of the carious region, the volume of the caries, and the depth of the caries.

[0074] Step S4 obtains various non-dental factors related to an individual's oral health status and organizes them into a structured individual dataset. This information will be combined with the dental caries dataset to provide a more comprehensive basis for subsequent oral health assessment and the formulation of personalized care plans, enabling the plans to fully consider individual differences and thus improve the effectiveness of care. Specifically, it includes extracting personal information and preprocessing personal information.

[0075] Specifically, personal information is obtained from a database or questionnaire survey, including general demographic information, oral hygiene habits, dietary habits, medical history, family history, etc. This information reflects an individual's lifestyle, health status, and genetic background, and is closely related to the occurrence and development of dental caries. Among them, general demographic information includes age, gender, place of residence, and educational level; oral hygiene habits include the number of times of brushing teeth per day, whether to use fluoride toothpaste, whether to use dental floss, and the frequency of toothbrush replacement; dietary habits include the number of times of consuming sugary foods / drinks per day, whether to like acidic foods, and whether to often consume refined carbohydrates; medical history includes previous dental caries history and oral treatment history; family history includes whether parents or siblings have a high incidence of dental caries.

[0076] The extracted personal information is cleaned, transformed, and encoded so that it can be processed by a machine learning model, including handling missing values, transforming data types, normalizing numerical features, and encoding categorical features.

[0077] Specifically, for missing values, for example, if the number of times of brushing teeth per day of a certain patient is missing, it is filled with the average value; text data is converted into numerical data; for numerical features, such as age and the number of times of brushing teeth per day, the Z-score normalization method is used to make its mean 0 and variance 1. The normalization formula is as follows: where x is the original data, μ is the mean of the data, and σ is the standard deviation of the data; for categorical features, such as place of residence and previous dental caries history, one-hot encoding is used to convert them into numerical features, that is, a binary vector, in which only one element is 1 and the rest are 0.

[0078] Integrate the results of the above Steps S41 and S42 to generate an individual dataset. This dataset contains preprocessed personal information, which is convenient for subsequent oral health assessment models to use.

[0079] Step S5 constructs a model that can accurately evaluate the oral health level of children by integrating the information of the dental caries dataset and the individual dataset. This model combines the quantitative features of dental caries with the risk factors of individuals, so as to more comprehensively and objectively evaluate the oral health status of patients and provide a scientific basis for the formulation of subsequent personalized care plans.

[0080] Define the gradient boosting machine model with the following configuration:

[0081] The caries dataset and the individual dataset are merged into a single dataset according to the unique individual identifier (ID) as the input of the model. Among them, the caries dataset contains three-dimensional position information of carious areas, carious volume, carious depth and other caries quantification features; the individual dataset contains individual risk factors such as general demographic information, oral hygiene habits, eating habits, past medical history, family history, etc.

[0082] The objective function is a binary logistic regression function, which outputs a probability value ranging from 0 to 1, representing the oral health level and directly interpreting the caries risk. The learning rate is 0.1; the maximum depth of the tree is 3; the subsampling ratio is 0.8; the column sampling ratio is 0.8; regularization parameters add L1 and L2 regularization according to the actual situation; the number of trees is 100.

[0083] The model is optimized using cross-validation, specifically: the dataset is divided into K (5 or 10) subsets. Each time, K - 1 subsets are used as the training set, and the remaining one subset is used as the validation set. Repeat K times, and each time a different subset is used as the validation set. The average value of the K validation results is used as the performance metric of the model.

[0084] The value between 0 and 1 output by the model represents the probability of caries risk, that is, the oral health level. The higher the value, the higher the risk. The risk level is divided into three levels: 0 - 0.3 is low risk; 0.3 - 0.7 is medium risk; 0.7 - 1 is high risk.

[0085] Step S6 provides more personalized care recommendations by considering individual differences, improves patient acceptance and compliance, thereby improving the care effect, and ultimately reducing the caries risk.

[0086] The personalized care plan is divided into three levels:

[0087] Low risk, routine oral hygiene maintenance;

[0088] Medium risk, enhanced oral hygiene maintenance;

[0089] High risk, active intervention, strictly restrict the intake of sugary foods, and apply fluoride varnish regularly.

[0090] In a specific embodiment, the individual characteristics are as follows: 6 years old, irregular toothbrushing, not using dental floss, often eating candies, having the habit of night milk, and a family history of severe dental caries. The overall strategy of the personalized care plan is comprehensive and active intervention, controlling risk factors, and closely monitoring. Specifically, it includes brushing teeth carefully three times a day, in the morning, at noon, and in the evening, with fluoride toothpaste, and providing a video tutorial on the Bass brushing method; strictly prohibiting candies and other sugary snacks, resolutely putting an end to the habit of night milk, and encouraging eating more vegetables, fruits, and whole grains; recommending an oral examination every 3 months to detect and treat dental caries at an early stage; recommending fluoride varnish treatment every 3 months to enhance the anti-caries ability of teeth; considering pit and fissure sealing to protect the occlusal surfaces of molars; parents must actively cooperate to help children develop good oral hygiene habits and eating habits.

[0091] Exemplary system:

[0092] As Figure 2 shown, a children's oral health management system based on three-dimensional modeling and digital restoration, based on the above exemplary method, includes:

[0093] A three-dimensional information acquisition module, used to acquire the three-dimensional information of children's teeth and construct an oral three-dimensional model;

[0094] A tooth feature analysis module, connected to the three-dimensional information acquisition module, used to analyze tooth features based on the oral three-dimensional model and identify carious regions;

[0095] A dental caries data quantification module, connected to the tooth feature analysis module, used to quantify the features of carious regions and generate a dental caries data set;

[0096] An individual information collection module, used to collect children's individual information and generate an individual data set;

[0097] A health risk assessment module, respectively connected to the dental caries data quantification module and the individual information collection module, used to establish an oral health model and input the dental caries data set and the individual data set into the oral health model to evaluate the oral health level of children;

[0098] A personalized plan generation module, connected to the health risk assessment module, used to generate a personalized care plan based on the oral health level assessment result.

[0099] Next, each module will be introduced in detail.

[0100] The three-dimensional information acquisition module includes:

[0101] A scanning unit, used to scan children's teeth with an intraoral scanner to obtain point cloud data on the tooth surface;

[0102] The reconstruction unit, connected to the scanning unit, is used to process the point cloud data and perform surface reconstruction to obtain a three-dimensional oral model.

[0103] The tooth feature analysis module includes:

[0104] The curvature calculation unit is used to calculate the Gaussian curvature of the tooth surface, reflecting the concave and convex changes of the tooth surface;

[0105] The texture extraction unit is used to extract the texture features of the tooth surface and quantify the roughness of the enamel;

[0106] The optical analysis unit is used to analyze the optical properties of the tooth surface and obtain the spectral information of the tooth surface.

[0107] The dental caries data quantification module includes:

[0108] The region segmentation unit is used to identify and segment the carious regions on the tooth surface according to the analysis results of the tooth feature analysis module;

[0109] The volume and depth calculation unit, connected to the region segmentation unit, is used to quantify the volume and depth of the carious regions;

[0110] The data integration unit, connected to the volume and depth calculation unit, is used to integrate the three-dimensional position information, carious volume, and carious depth of the carious regions to generate a dental caries dataset.

[0111] The individual information collection module includes:

[0112] The information extraction unit is used to obtain individual information related to the oral health status of children from the database or questionnaire survey;

[0113] The information preprocessing unit, connected to the information extraction unit, is used to clean, transform, and encode the individual information to generate an individual dataset.

[0114] The oral health risk assessment module includes:

[0115] The data merging unit is used to merge the dental caries dataset and the individual dataset into a single dataset according to the unique individual identifier;

[0116] The model construction unit, connected to the data merging unit, is used to establish an oral health model. The oral health model is a gradient boosting machine model, which is used to evaluate the oral health level of children.

[0117] The oral health model outputs a numerical value, which represents the probability of dental caries risk.

[0118] The personalized solution generation module includes:

[0119] A risk level classification unit, configured to classify oral health risks into different levels based on the output result of an oral health model;

[0120] A solution formulation unit, connected to the risk level classification unit, configured to generate a personalized care solution according to the risk level.

[0121] The personalized care solution includes suggestions for oral hygiene maintenance, diet, regular review, and fluoride application.

[0122] Based on the ideal embodiments of the present invention as an inspiration, through the above description, relevant personnel can completely make various changes and modifications without departing from the technical idea of this invention. The technical scope of this invention is not limited to the content in the specification, and the technical scope must be determined according to the scope of the claims.

Claims

1. A children's oral health management system based on 3D modeling and digital restoration, characterized in that, it includes: A 3D information acquisition module, which is used to acquire the 3D information of children's teeth and construct an oral 3D model; A tooth feature analysis module, connected to the 3D information acquisition module, which is used to analyze tooth features based on the oral 3D model and identify carious areas; A caries data quantification module, connected to the tooth feature analysis module, which is used to quantify the features of the carious areas and generate a caries data set; An individual information collection module, which is used to collect children's individual information and generate an individual data set; A health risk assessment module, respectively connected to the caries data quantification module and the individual information collection module, which is used to establish an oral health model and input the caries data set and the individual data set into the oral health model to evaluate the oral health level of children; A personalized plan generation module, connected to the health risk assessment module, which is used to generate a personalized care plan based on the evaluation result of the oral health level.

2. The system according to claim 1, characterized in that, the 3D information acquisition module includes: A scanning unit, which is used to scan children's teeth with an intraoral scanner to obtain the point cloud data on the tooth surface; A reconstruction unit, connected to the scanning unit, which is used to process the point cloud data and perform surface reconstruction to obtain an oral 3D model.

3. The system according to claim 1, characterized in that, the tooth feature analysis module includes: A curvature calculation unit, which is used to calculate the Gaussian curvature of the tooth surface to reflect the concave and convex changes of the tooth surface; A texture extraction unit, which is used to extract the texture features of the tooth surface and quantify the roughness of the enamel; an optical analysis unit, which is used to analyze the optical properties of the tooth surface to obtain the spectral information of the tooth surface.

4. The system according to any one of claim 1, characterized in that, the caries data quantification module includes: A region segmentation unit, which is used to identify and segment the carious areas on the tooth surface according to the analysis result of the tooth feature analysis module; A volume depth calculation unit, connected to the region segmentation unit, which is used to quantify the volume and depth of the carious areas; A data integration unit, connected to the volume depth calculation unit, which is used to integrate the 3D position information, carious volume and carious depth of the carious areas to generate a caries data set.

5. The system according to any one of claim 4, characterized in that, the individual information collection module includes: An information extraction unit, which is used to obtain individual information related to children's oral health status from a database or a questionnaire survey; An information preprocessing unit, connected to the information extraction unit, which is used to clean, transform and encode the individual information to generate an individual data set.

6. The system according to any one of claim 5, characterized in that, the health risk assessment module includes: A data merging unit, which is used to merge the caries data set and the individual data set into a single data set according to the unique individual identifier. A model construction unit, connected to the data merging unit, for building an oral health model, where the oral health model is a gradient boosting machine model for evaluating the oral health level of children.

7. The system according to any one of claim 6, characterized in that the oral health model outputs a value, which represents the probability of caries risk.

8. The system according to any one of claim 1, characterized in that the personalized plan generation module includes: a risk level division unit for dividing the oral health risk into different levels based on the output result of the oral health model; a plan formulation unit, connected to the risk level division unit, for generating a personalized care plan according to the risk level.

9. The system according to any one of claim 8, characterized in that the personalized care plan includes suggestions for oral hygiene maintenance, diet, regular reexamination, and fluoride application.

Images