Oral treatment planning system driven by big data

Abstract

The invention relates to the technical field of medical data processing, and comprises a big data driven oral treatment planning system, which comprises a tooth form data acquisition module, a microcrack identification module, an occlusion stress data processing module, a restoration form optimization module and a customized treatment recommendation module. According to the method, the reliability of micro-crack identification is improved by acquiring the tooth surface morphology point cloud data, accurately depicting micro details of the tooth surface morphology and screening areas with violent curvature change and continuous space, the areas with large local stress are identified by analyzing the stress conditions of tooth tip staggered contact points in different occlusion states, and the accuracy of micro-crack identification is improved. The contact point form of the local abnormal stress area is adjusted, the long-term stability of the restoration is optimized, the adaptability of a restoration material and tooth tissue under different stress conditions is analyzed, whether the restoration form meets the long-term stress balance requirement or not is comprehensively judged, and the long-term stability and occlusion adaptability of the restoration are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a big data driven oral treatment planning system. Background Art

[0002] The field of medical data processing technology involves the use of computer technology to collect, store, analyze, manage, and apply medical data to support medical diagnosis, treatment, health monitoring, and related medical research. Core areas include electronic medical record management, medical image processing, disease prediction modeling, treatment plan optimization, and remote medical data exchange. Overall, this field involves multiple data processing methods, including the analysis of structured and unstructured medical data. This method uses data mining, statistical analysis, and medical knowledge base matching to assist in medical decision-making. Furthermore, it integrates patient historical data to enable personalized treatment recommendations, improving the accuracy and efficiency of medical services.

[0003] Among them, the big data-driven oral treatment planning system refers to a system that develops personalized treatment plans for patients based on their medical data through computer-assisted analysis. The system mainly covers technical matters such as data information extraction on patients' oral health status, classification of treatment needs, matching of treatment methods, and plan optimization. Specific methods include using data analysis methods to analyze patients' dental imaging data and medical history records, identifying the type of dental lesions through pattern matching, and combining statistical methods to select appropriate treatment strategies from the existing treatment plan library. At the same time, based on factors such as the patient's age and oral health level, the treatment plan is adjusted and optimized to form a treatment plan that meets individual needs.

[0004] In existing oral treatment processes, the acquisition and processing of tooth morphological data rely on two-dimensional imaging or low-precision scanning methods, which have limited ability to depict morphological details, resulting in large errors in the identification of microscopic features on the tooth surface. The detection of microcracks lacks high-precision calculation methods, which can easily miss early subtle lesions and affect the accurate assessment of dental health. The acquisition of occlusal force data mainly relies on discrete measurement methods, which makes it difficult to achieve real-time monitoring of force changes, resulting in a lack of accurate basis for occlusal adjustment strategies and affecting the personalized optimization of restoration plans. The restoration morphology adjustment method is mainly based on standardized model matching, ignoring the differences in individual tooth morphology and force characteristics, which can easily cause the restoration morphology to be mismatched with the occlusal state, affecting the long-term use effect. The selection of restoration materials is usually based on experience or conventional statistical methods, and fails to fully consider the adaptability under different force environments, resulting in stress concentration, material fatigue and other problems in the actual use of the restoration, reducing the durability and stability of the restoration. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the existing technology and propose a big data driven oral treatment planning system.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solutions: A big data driven oral treatment planning system includes:

[0007] The tooth morphology data acquisition module acquires tooth surface morphology point cloud data, converts the point cloud data into a mesh model using triangulation, calculates the normal vector, principal curvature, Gaussian curvature, and mean square curvature of the mesh nodes, analyzes the curvature distribution of the mesh model, determines the morphology change area based on the curvature change gradient, and generates tooth surface morphology feature data;

[0008] The microcrack identification module calculates the local curvature gradient of the grid node based on the tooth surface morphological feature data, calculates the curvature deviation rate in adjacent grid areas, determines the gradient change trend of abnormal curvature points, and screens out potential microcrack areas;

[0009] The occlusal force data processing module obtains the force data of the tooth occlusal contact points, records the force conditions of the tooth cusp interdigitation contact points under different occlusal states, calculates the contact area and pressure distribution, analyzes the force balance of the contact points, and identifies and outputs the high-stress occlusal areas;

[0010] The restoration morphology optimization module calculates the contact point morphology deviation of the local area with relatively large force based on the high occlusal stress area, adjusts the contact point morphology of the corresponding area, calculates the degree of matching between the adjusted dental restoration and the original tooth morphology, and obtains optimized restoration morphology data.

[0011] As a further solution of the present invention, the tooth surface morphological feature data includes grid node normal vectors, principal curvatures, Gaussian curvatures, mean square curvatures, and morphological change areas; the potential microcrack areas include areas with drastic curvature changes, areas with spatially continuous abnormal curvature points, and areas with local curvature gradient mutations; the occlusal high stress areas include contact points with excessive force, areas with abnormal contact areas, and areas with uneven pressure distribution; the optimized restoration morphological data includes the adjusted contact point morphology, data matching the restoration with the original tooth morphology, and local force balance optimization data.

[0012] As a further solution of the present invention, the tooth morphology data acquisition module includes:

[0013] The point cloud data acquisition submodule uses an optical coherence tomography device to scan and obtain point cloud data of the tooth surface morphology, extracts the three-dimensional coordinate points of the tooth surface, removes redundant data and performs point cloud denoising, and uses spatial segmentation to divide the point cloud data into regions to generate tooth surface point cloud data;

[0014] The mesh model construction submodule uses triangulation to construct a mesh model based on the tooth surface point cloud data, calculates the adjacency relationship of mesh vertices, sets boundary constraints, optimizes the quality of triangular facets, removes abnormal meshes, obtains the normal vector of each mesh node, and calculates the principal curvature, Gaussian curvature, and mean square curvature using the formula:

[0015]

[0016] Calculate the mesh node curvature gradient K, adjust the mesh smoothness according to the curvature distribution, and generate the tooth mesh model, where: represents the mean square curvature gradient, κ i represents the principal curvature in the i-th direction, and n represents the number of nodes in the mesh model;

[0017] The morphological feature analysis submodule analyzes the curvature distribution of each node based on the tooth mesh model, calculates the curvature change gradient, compares the mesh node curvature gradient value with the set threshold, screens the area with significant morphological changes, and generates tooth surface morphological feature data.

[0018] As a further solution of the present invention, the microcrack identification module includes:

[0019] The local curvature calculation submodule calculates the local curvature gradient of the grid node based on the tooth surface morphological feature data, selects the adjacent grid area of each node, calculates the gradient values of the principal curvature and Gaussian curvature, and calculates the local curvature change rate of each grid node to generate grid local curvature gradient data;

[0020] The curvature gradient analysis submodule calculates the curvature offset rate in adjacent grid areas based on the local curvature gradient data of the grid, and calculates the curvature offset direction and gradient change rate of each grid node using the formula:

[0021]

[0022] Calculate the abnormal curvature gradient distribution value G, compare the gradient change threshold to screen the local area with drastic changes, and generate abnormal curvature distribution data, where κ i represents the principal curvature of the i-th grid node, κ i-1 represents the principal curvature of the i-1th grid node, Δs i represents the Euclidean distance between adjacent grids, represents the local curvature gradient of the jth grid node, N represents the number of grid nodes, and M represents the number of adjacent grids;

[0023] The microcrack area screening submodule determines the gradient change trend of abnormal curvature points based on the abnormal curvature distribution data, analyzes the continuity of the gradient direction, screens areas with drastic curvature changes and spatial continuity, removes isolated abnormal points, extracts the boundaries of microcrack areas, and generates potential microcrack areas.

[0024] As a further solution of the present invention, the occlusal force data processing module includes:

[0025] The force data acquisition submodule obtains the force data of the tooth occlusal contact points collected by the micromechanical sensor, monitors the force conditions of each point based on the interdigitated contact points of the tooth cusps in different occlusal states, records the changes of the occlusal force over time, and stores all the measured values to form an occlusal force matrix;

[0026] The force distribution calculation submodule calculates the contact area of each occlusal contact point based on the occlusal force matrix using the formula:

[0027]

[0028] Calculate the pressure value P at contact point i i , calculate the pressure distribution of each contact point and construct the occlusal contact pressure distribution matrix, where F i Represents the force value at contact point i, A i represents the contact area of contact point i, U represents the total number of contact points, and F j and A j Represent the force value and contact area of contact point j respectively, and ∑ represents the sum of calculations of all contact points;

[0029] The local force analysis submodule calculates the force balance of each contact point based on the occlusal contact pressure distribution matrix, compares the pressure value of each point with the set local force threshold, identifies the local force-excessive area, and obtains the occlusal high stress area.

[0030] As a further solution of the present invention, the restoration morphology optimization module includes:

[0031] The contact point morphology deviation calculation submodule extracts the contact point morphology data of the local area with relatively large stress based on the high occlusal stress area, compares the contact point morphology with the reference tooth morphology, calculates the morphology deviation value of each contact point, and establishes a contact point morphology deviation matrix;

[0032] The morphology adjustment submodule adjusts the morphology of the contact points in the area with relatively large local forces based on the contact point morphology deviation matrix, using the formula:

[0033]

[0034] Calculate the morphological adjustment amount of each contact point after restoration adjustment, obtain the restoration morphological adjustment data, and establish the restoration morphological matrix after adjustment, where T i Represents the shape value of the contact point i after adjustment, Z i Represents the contact point morphology value of the original restoration, L i Represents the morphological deviation value of contact point i, L j represents the morphological deviation of contact point j, W j represents the force weight of contact point j, and U represents the total number of contact points;

[0035] The matching degree calculation submodule calculates the matching degree between the adjusted restoration and the original tooth shape based on the adjusted restoration shape matrix, and obtains optimized restoration shape data.

[0036] As a further aspect of the present invention, the system further includes a customized treatment recommendation module;

[0037] The customized treatment recommendation module analyzes the compatibility of the dental restoration material and the patient's tooth tissue under different stress conditions based on the potential microcrack area and the optimized restoration morphology data, determines whether the restoration morphology meets the long-term stress equilibrium condition, and reselects the dental restoration material if not, and generates a customized dental restoration recommendation treatment plan;

[0038] The customized tooth restoration recommended treatment plan includes the restoration material compatibility analysis results, long-term force balance assessment results, and the adjusted restoration material selection plan.

[0039] As a further embodiment of the present invention, the customized treatment recommendation module includes:

[0040] The adaptability analysis submodule calculates the adaptability of the dental restoration material under different stress conditions based on the potential microcrack area and the optimized restoration morphology data, analyzes the contact stability and force balance between the restoration material and the patient's tooth tissue, and obtains the restoration adaptation parameter matrix;

[0041] The long-term stress judgment submodule calculates the balance of the restoration morphology under long-term stress conditions based on the restoration adaptation parameter matrix, judges the stress stability of the restoration morphology under different stress environments, identifies the long-term stress concentration area, and obtains the long-term stress balance index of the restoration;

[0042] The restoration plan generation submodule determines whether the restoration shape meets the long-term force balance condition based on the restoration long-term force balance index. If not, the dental restoration material is reselected, the restoration shape is adjusted, and a customized dental restoration recommended treatment plan is obtained.

[0043] Compared with the prior art, the advantages and positive effects of the present invention are:

[0044] In the present invention, an optical coherence tomography device is used to obtain tooth surface morphology point cloud data, and a triangulation technique is used to construct a mesh model to accurately depict the minute details of the tooth surface morphology, calculate the normal vector, principal curvature, Gaussian curvature and mean square curvature of the mesh nodes, and determine the morphological change area based on the curvature change gradient, thereby ensuring the accurate extraction of morphological features and improving the refinement of tooth morphological analysis. The gradient change trend of abnormal curvature points is combined to screen areas with drastic curvature changes and spatial continuity, making the positioning of potential microcracks more accurate and improving the reliability of microcrack identification. By analyzing the stress conditions of the interdigitated contact points of tooth cusps under different occlusal states, Combined with the calculation of contact area and pressure distribution, the local areas with excessive stress are identified to ensure the accuracy of occlusal mechanics analysis. The contact point morphology deviation is analyzed based on the high-stress area of the occlusion. The contact point morphology of the local abnormal stress area is adjusted to make the restoration more suitable for the individual oral condition and optimize the long-term stability of the restoration. Combined with the potential microcrack area and the optimized restoration morphology data, the adaptability of the restoration material and the tooth tissue under different stress conditions is analyzed. It is comprehensively judged whether the restoration morphology meets the long-term force balance requirements. If not, the material is reselected to make the customized restoration plan more accurate and ensure the long-term stability and occlusal adaptability of the restoration. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a system flow chart of the present invention;

[0046] Figure 2 This is a flow chart of the tooth morphology data acquisition module of the present invention;

[0047] Figure 3 This is a flow chart of the microcrack identification module of the present invention;

[0048] Figure 4 This is a flow chart of the occlusal force data processing module of the present invention;

[0049] Figure 5 This is a flow chart of the restoration morphology optimization module of the present invention;

[0050] Figure 6 This is a flow chart of the customized treatment recommendation module of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0052] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0053] See also Figure 1 , a big data driven oral treatment planning system includes:

[0054] The tooth morphology data acquisition module acquires tooth surface morphology point cloud data through an optical coherence tomography device, converts the point cloud data into a mesh model using triangulation, calculates the normal vector, principal curvature, Gaussian curvature, and mean square curvature of the mesh nodes, analyzes the curvature distribution of the mesh model, determines the morphology change area based on the curvature change gradient, and generates tooth surface morphology feature data;

[0055] The microcrack identification module calculates the local curvature gradient of the grid nodes based on the tooth surface morphological feature data, calculates the curvature deviation rate in adjacent grid areas, determines the gradient change trend of abnormal curvature points, and screens areas with drastic curvature changes and spatial continuity to obtain potential microcrack areas.

[0056] The occlusal force data processing module uses micromechanical sensors to obtain force data on the tooth occlusal contact points, records the force conditions of the interdigital contact points under different occlusal states, calculates the contact area and pressure distribution, analyzes the force balance of the contact points, identifies areas with excessive force, and outputs areas of high occlusal stress.

[0057] The restoration morphology optimization module calculates the contact point morphology deviation of the local area with relatively large stress based on the high occlusal stress area, adjusts the contact point morphology of the corresponding area, calculates the degree of matching between the adjusted tooth restoration and the original tooth morphology, and obtains the optimized restoration morphology data;

[0058] The customized treatment recommendation module analyzes the compatibility of dental restoration materials and patient tooth tissues under different stress conditions based on potential microcrack areas and optimized restoration morphology data, and determines whether the restoration morphology meets the long-term stress balance conditions. If not, the dental restoration material is reselected to generate a customized dental restoration recommendation treatment plan.

[0059] The tooth surface morphological feature data include grid node normal vector, principal curvature, Gaussian curvature, mean square curvature, and morphological change area; potential microcrack areas include areas with drastic curvature changes, areas with spatially continuous abnormal curvature points, and areas with local curvature gradient mutations; occlusal high stress areas include contact points with excessive force, areas with abnormal contact area, and areas with uneven pressure distribution; optimized restoration morphological data include adjusted contact point morphology, restoration and original tooth morphology matching data, and local force balance optimization data; customized tooth restoration recommended treatment plans include restoration material adaptability analysis results, long-term force balance assessment results, and adjusted restoration material selection plans.

[0060] See also Figure 2 , the tooth morphology data acquisition module includes:

[0061] The point cloud data acquisition submodule uses an optical coherence tomography device to scan and obtain point cloud data of the tooth surface morphology, extracts the three-dimensional coordinate points of the tooth surface, removes redundant data and performs point cloud denoising, and uses spatial segmentation to divide the point cloud data into regions to generate tooth surface point cloud data;

[0062] To obtain point cloud data of tooth surface morphology, an optical coherence tomography device was first used to perform multi-angle scanning of the target tooth area. During the scanning process, the wavelength of the light source was set to 1310 nm, and the scanning depth range was controlled within 2 mm to ensure the integrity and stability of data acquisition. The position of the acquisition point was recorded using a three-dimensional coordinate conversion method, and the coordinate system was converted so that the spatial position of the data point was aligned with the standard tooth coordinate system. A large amount of original point cloud data was obtained through data acquisition. These data points contained noise and redundant information and needed to be preprocessed. A statistical filtering method was used to reduce the noise of the point cloud data. The neighborhood radius was set to 0.5 mm, and abnormal points with a standard deviation of more than 1.5 times were filtered out to reduce the impact of measurement errors. At the same time, after the noise reduction process, a spatial segmentation operation was performed on the point cloud data, and the point cloud was gridded at intervals of 0.1 mm for subsequent grid model construction, and finally the tooth surface point cloud data was generated.

[0063] Table 1 Point cloud data acquisition parameters

[0064] Parameter name Numerical unit Light source wavelength 1310 nm Scanning depth range 2 mm Sampling interval 0.1 mm Neighborhood radius 0.5 mm Standard Deviation Threshold 1.5 none

[0065] As shown in Table 1, during the point cloud data acquisition process, the settings of the light source wavelength and scanning depth range ensure high data accuracy, while the adjustment of the neighborhood radius and standard deviation threshold helps to reduce noise interference and improve data quality.

[0066] The mesh model construction submodule uses triangulation to construct a mesh model based on the tooth surface point cloud data, calculates the adjacency relationship of mesh vertices, sets boundary constraints, optimizes the quality of triangular facets, removes abnormal meshes, obtains the normal vector of each mesh node, and calculates the principal curvature, Gaussian curvature, and mean square curvature using the formula:

[0067]

[0068] Calculate the mesh node curvature gradient K, adjust the mesh smoothness according to the curvature distribution, and generate the tooth mesh model, where: represents the mean square curvature gradient, κ i represents the principal curvature in the i-th direction, and n represents the number of nodes in the mesh model;

[0069] Based on the tooth surface point cloud data, the Delaunay triangulation method is used to construct a mesh model. First, the topological structure is established by calculating the distance between adjacent points, and the mesh surface is ensured to meet the triangle quality standard. The minimum angle threshold of the triangle is set to 15°, and the maximum side length threshold is set to 0.2mm. The specific settings are based on the local curvature variation range of the tooth surface. Experimental measurements show that the optimal angle range of the tooth surface mesh unit is usually between 10° and 20°. If the angle is lower than 10°, the mesh quality decreases, resulting in an increase in the curvature calculation error. When it is greater than 20°, the mesh surface quality tends to be uniform, but The fitting accuracy of complex morphological areas is reduced, so 15° is selected as the threshold, and the maximum side length threshold of 0.2mm refers to the optimal distance distribution between tooth surface points. If the side length exceeds 0.2mm, the grid density is insufficient, resulting in loss of details. If it is less than 0.1mm, the computational complexity increases exponentially. Considering the computational efficiency and accuracy, 0.2mm is selected to optimize the uniformity of the grid subdivision. Then, the normal vector of each grid node is calculated, and the discrete differential geometry method is used to calculate the principal curvature and Gaussian curvature of the grid. The principal curvature is calculated based on the curvature tensor of the node, and the principal curvature direction is solved by matrix eigenvalue decomposition.

[0070] The curvature gradient threshold is set to 0.1, and is adjusted according to the curvature variation range of different parts of the teeth. The curvature gradient of the anterior teeth is usually lower than 0.05, while the gradient of the occlusal surface of the molar may reach above 0.15 due to its complex morphology. Therefore, 0.1 is selected as the dividing value of the medium curvature gradient. Areas exceeding 0.1 usually show large curvature changes, such as occlusal grooves or wedge-shaped defects, while areas below 0.1 are usually smooth surfaces, which are suitable for smooth mesh processing. Gaussian curvature is further calculated to analyze the local change trend of the tooth surface. Finally, the formula is used to obtain the curvature gradient of the mesh node, and the mesh smoothness is adjusted according to the curvature distribution to generate the tooth mesh model.

[0071] Assume that the principal curvatures of a point cloud data are 0.05, 0.08, and 0.12 respectively, and the mean square curvature gradient If is 0.06, then calculate the curvature gradient:

[0072]

[0073] The calculated result of 0.0097 is lower than the set threshold of 0.1, indicating that the curvature change in this area is small and is not treated as a high curvature change area.

[0074] The morphological feature analysis submodule analyzes the curvature distribution of each node based on the tooth mesh model, calculates the curvature change gradient, compares the mesh node curvature gradient value with the set threshold, screens the areas with significant morphological changes, and generates tooth surface morphological feature data;

[0075] Based on the tooth mesh model, the curvature distribution of each node is analyzed, and the mesh gradient analysis method is used to calculate the local curvature change rate of each mesh. First, the Gaussian curvature and mean square curvature of each mesh node are obtained, and the curvature change threshold is set to 0.05. This value comes from the curvature change range of the smooth area and the high curvature change area of the tooth surface. Experimental data show that the curvature change of most normal enamel surfaces is between 0.02-0.05, while the curvature change of areas with damage or wear usually exceeds 0.1. Therefore, 0.05 is selected as the threshold to define the normal curvature change area and the abnormal curvature change area. When the curvature change of a certain area exceeds the threshold, it is determined to be a morphological change area, and the curvature distribution density in the area is further calculated. The rate of change is defined as the amount of change in curvature gradient per unit area. The calculation uses a combination of Gaussian curvature and principal curvature parameters. Experimental data show that areas with a curvature change rate between 0.05 and 0.2 are mostly concentrated in tooth edges, pits and fissures, while areas with a rate of change greater than 0.2 usually appear in abnormal morphological locations such as defects and wedge-shaped defects. Therefore, 0.2 is selected as the threshold for significant change areas, and areas with a curvature change rate between 0.05 and 0.2 are marked as medium change areas, and areas with a rate of change greater than 0.2 are marked as significant change areas. At the same time, the Gaussian curvature value is extracted, and the morphological feature distribution matrix is calculated. The coordinates of the curvature change feature points are used as key morphological feature points. Finally, the areas with significant morphological changes are screened, and the tooth surface morphological feature data is generated.

[0076] Table 2 Curvature change interval setting table

[0077] Variation range Level of change 0.05-0.2 Moderate changes >0.2 Significant changes

[0078] As shown in Table 2, by distinguishing the levels of the curvature change areas, the distribution range of the morphological change areas can be clarified and feature point data can be extracted.

[0079] See also Figure 3 , the microcrack identification module includes:

[0080] The local curvature calculation submodule calculates the local curvature gradient of the mesh nodes based on the tooth surface morphological feature data, selects the adjacent mesh area of each node, calculates the gradient values of the principal curvature and Gaussian curvature, and calculates the local curvature change rate of each mesh node to generate the mesh local curvature gradient data;

[0081] Based on the tooth surface morphological feature data, the mesh model of the tooth surface needs to be parsed first. Each mesh node is surrounded by multiple triangular facets, and the curvature calculation is based on the change in the normal vector of each facet. In a typical triangular mesh of a tooth surface, the neighborhood of each mesh node usually includes 6 to 10 adjacent nodes, which form a local area for evaluating curvature changes. In this step, the adjacent mesh area of each node, that is, the 1st or 2nd order neighborhood centered on the node (to control the calculation range), is selected to calculate the gradient values of the principal curvature and Gaussian curvature. The principal curvatures κ1 and κ2 represent the maximum and minimum curvatures of the grid point in the main direction, respectively, and the Gaussian curvature K G =κ1·κ2 reflects the overall curvature characteristics of the point. The local curvature change rate of each grid node is estimated by numerical difference method, that is, the curvature change between adjacent grid nodes is calculated as Δκ=κ i -κ i-1 And divided by the spatial distance Δs between nodes i , the calculation formula is as follows:

[0082]

[0083] Among them, g i represents the local curvature gradient of the node, κ i represents the principal curvature of the current node, κ i-1 represents the principal curvature of adjacent nodes, Δs i Represents the Euclidean distance between adjacent mesh nodes. To give a practical example, assume that the principal curvature of a mesh node is 0.02, the principal curvature of its adjacent node is 0.015, and the Euclidean distance between the two is 0.1 mm, then

[0084]

[0085] The calculation shows that the curvature change rate of this node is 0.05. If the curvature gradient of a region exceeds the set threshold, it is considered that there is a large curvature fluctuation in that region, requiring further screening and analysis. Then, a spatial segmentation method is used to divide the curvature change value into regions. This means comparing the gradient values of different grid regions and classifying them according to gradient continuity to generate local curvature gradient data for the grid.

[0086] The curvature gradient analysis submodule calculates the curvature offset rate in adjacent grid areas based on the local curvature gradient data of the grid, and calculates the curvature offset direction and gradient change rate of each grid node using the formula:

[0087]

[0088] Calculate the abnormal curvature gradient distribution value G, compare the gradient change threshold to screen the local area with drastic changes, and generate abnormal curvature distribution data, where κ i represents the principal curvature of the i-th grid node, κ i-1 represents the principal curvature of the i-1th grid node, Δs i represents the Euclidean distance between adjacent grids, represents the local curvature gradient of the jth grid node, N represents the number of grid nodes, and M represents the number of adjacent grids;

[0089] Based on the local curvature gradient data of the grid, the curvature deviation rate in adjacent grid areas is statistically analyzed. The curvature deviation rate is defined as:

[0090]

[0091] Among them, κ i represents the principal curvature of the node, Represents the average curvature of its neighborhood. If the principal curvature of a grid node is 0.02 and the average curvature of its neighborhood is 0.018, then:

[0092]

[0093] That is, the curvature offset rate of this node is 11.1%. Next, the curvature offset direction and gradient change rate of each grid node are calculated and substituted into the formula to calculate the abnormal curvature gradient distribution value.

[0094] A certain grid area contains N=5 nodes, and the principal curvatures of each node are:

[0095] 0.02, 0.015, 0.018, 0.017, 0.019;

[0096] The average Euclidean distance between adjacent grid nodes is 0.1 mm, and the local curvature gradient The values are:

[0097] 0.04, 0.03, 0.05, 0.045, 0.035;

[0098] Substitute into the formula and calculate:

[0099]

[0100] The abnormal curvature change threshold is set at 0.01. This value is based on the curvature variation characteristics of microcrack areas on the tooth surface. Experimental analysis shows that the curvature gradient of microcrack areas in enamel is typically between 0.005 and 0.015, while in healthy enamel areas, this value is generally below 0.008. Therefore, if the calculated value G > 0.01, abnormal curvature variation is determined in that area, and abnormal curvature distribution data is generated.

[0101] The microcrack area screening submodule determines the gradient change trend of abnormal curvature points based on abnormal curvature distribution data, analyzes the continuity of gradient direction, screens areas with drastic curvature changes and spatial continuity, removes isolated abnormal points, extracts microcrack area boundaries, and generates potential microcrack areas;

[0102] Based on the abnormal curvature distribution data, the gradient change trend of the abnormal curvature points is determined, the relative gradient difference between the abnormal points is calculated, and the continuous abnormal gradient area is detected using a window sliding method. Assume that the four identified abnormal points in a certain area are located at the (x, y) coordinates:

[0103] (2.1, 3.5), (2.2, 3.6), (2.3, 3.7), (2.5, 3.8);

[0104] Then calculate the distance between points:

[0105]

[0106] The spatial continuity threshold was set at 0.2. This value is based on the spatial distribution characteristics of microcrack formation on the tooth surface, primarily referring to the critical crack propagation distance and the distribution of microscopic defects in the surface material structure. Experimental data show that microcracks in tooth enamel typically extend between 0.1mm and 0.3mm, and in the early stages of crack propagation, when the crack spacing exceeds 0.2mm, their continuity is significantly affected. Therefore, 0.2 is set as the criterion for determining the spatial continuity of the microcrack area.

[0107] If the calculated value D of a certain adjacent point pair i,i+1 >0.2, the continuity of the crack area is destroyed and it may be a different crack area. 3,4 =0.223>0.2, indicating that the crack in this area tends to break, and this point needs to be removed. After eliminating isolated abnormal points, the potential microcrack area is generated.

[0108] Table 3 Detection data of potential microcrack area

[0109] Abnormal point number X coordinate (mm) Y coordinate (mm) Distance between adjacent points (mm) 1 2.1 3.5 0.141 2 2.2 3.6 0.141 3 2.3 3.7 0.223 4 2.5 3.8 0.100

[0110] As shown in Table 3, the calculated abnormal point spacing values indicate the spatial continuity of the crack area and are further used for microcrack identification and screening.

[0111] See also Figure 4 , the occlusal force data processing module includes:

[0112] The force data acquisition submodule obtains the force data of the tooth occlusal contact points collected by the micromechanical sensor, monitors the force conditions of each point based on the interdigitated contact points of the tooth cusps in different occlusal states, records the changes of the occlusal force over time, and stores all the measured values to form an occlusal force matrix;

[0113] During the tooth occlusion process, micro mechanical sensors are used to detect the force conditions at each tooth contact point. The mechanical sensors are placed in the key contact area between the upper and lower teeth to monitor the force changes at multiple contact points under different occlusion states. The data is collected and normalized, and invalid signals are eliminated to ensure the accuracy of the force data. For example, during the test of a subject, the force data at different contact points were measured as follows:

[0114] Table 4 Initial pressure gauge of monitoring points

[0115]

[0116]

[0117] After data collection is completed, the force data is normalized and outliers are removed. For example, if the force data at a certain point deviates significantly from the mean, such as exceeding two standard deviations, the data is considered abnormal and removed. In the above data, the force at point A3 is 9.8N, which is two standard deviations (1.98N) lower than the mean of other data points (12.58N). In this case, outlier removal and data compensation are required to finally form the occlusal force matrix.

[0118] The force distribution calculation submodule calculates the contact area of each occlusal contact point based on the occlusal force matrix using the formula:

[0119]

[0120] Calculate the pressure value P at contact point i i , calculate the pressure distribution of each contact point and construct the occlusal contact pressure distribution matrix, where F i Represents the force value at contact point i, A i represents the contact area of contact point i, U represents the total number of contact points, and F j and A j Represent the force value and contact area of contact point j respectively, and ∑ represents the sum of calculations of all contact points;

[0121] Based on the occlusal force matrix, the contact area of each contact point is calculated and measured using a contact pressure sensing system. Assume that the area data of a tooth occlusal contact point is as follows:

[0122] Table 5 Contact area of monitoring points

[0123] Monitoring point number <![CDATA[Contact area (mm 2 )]]> A1 2.5 A2 3.2 A3 1.9 A4 2.8 A5 2.3

[0124] Use the formula to calculate the pressure value of each contact point. Take the A1 monitoring point as an example and input the data:

[0125]

[0126] Calculated:

[0127]

[0128] P A1 ≈5.0+0.31=5.31MPa;

[0129] Similarly, other monitoring points are calculated to finally obtain the occlusal contact pressure distribution matrix.

[0130] The local force analysis submodule calculates the force balance of each contact point based on the occlusal contact pressure distribution matrix, compares the pressure value of each point with the set local force threshold, identifies the local force-excessive area, and obtains the occlusal high stress area;

[0131] Based on the occlusal contact pressure distribution matrix, the force balance degree of each contact point is calculated to determine whether there is a situation of local excessive force. The local force threshold is defined as 1.5 times the average occlusal contact pressure, that is:

[0132]

[0133] Assuming the calculated average pressure is 5.1 MPa, then:

[0134] Local stress threshold = 1.5 × 5.1 = 7.65 MPa;

[0135] If the pressure at a certain point exceeds this value, it is determined to be a high-stress occlusal area. For example, if the pressure at point A2 is calculated to be 8.12 MPa, which is higher than the threshold of 7.65 MPa, the A2 area is determined to be a high-stress occlusal area.

[0136] See also Figure 5 , the restoration morphology optimization module includes:

[0137] The contact point morphology deviation calculation submodule extracts the contact point morphology data of the local area with relatively large stress based on the high stress area of the occlusion, compares the contact point morphology with the reference tooth morphology, calculates the morphology deviation value of each contact point, and establishes the contact point morphology deviation matrix;

[0138] Based on the high-stress occlusal areas, tooth contact points with abnormal stress are first identified. Contact point morphological data for areas with locally elevated stress are obtained. Representative monitoring points, such as those in the anterior and molar regions, are selected. The contact area, force, and pressure distribution are measured at each point, and morphological characteristics, such as cusp height and groove depth, are recorded. High-precision measurement equipment, such as a 3D scanner or digital model, is used to obtain 3D coordinate data for each contact point, and the morphological characteristics of each point are recorded. Based on this data, the deviation of the contact point from a baseline tooth morphology is calculated. This baseline tooth morphology can be a standard crown model of a healthy individual of the same age, or the morphology of the contralateral side of the same tooth. For example, if the actual cusp height of a contact point is 1.2 mm, while the baseline value is 1.5 mm, the morphological deviation is -0.3 mm. Furthermore, local slope changes are calculated to reflect the smoothness of the tooth morphology, based on changes in the curvature of the occlusal surface. The morphological deviation values of all contact points are compared to create a contact point morphological deviation matrix. This matrix contains the morphological deviation data for each contact point and serves as a basis for subsequent morphological adjustments.

[0139]

[0140] As shown in Table 6, the morphological deviation values of the monitoring points show the deviation of different contact points, providing data support for subsequent adjustments. Finally, the contact point morphological deviation matrix is obtained.

[0141] The morphology adjustment submodule adjusts the morphology of the contact points in the area with relatively large local forces based on the contact point morphology deviation matrix, using the formula:

[0142]

[0143] Calculate the morphological adjustment amount of each contact point after restoration adjustment, obtain the restoration morphological adjustment data, and establish the restoration morphological matrix after adjustment, where T i Represents the shape value of the contact point i after adjustment, Z i Represents the contact point morphology value of the original restoration, L i Represents the morphological deviation value of contact point i, L j represents the morphological deviation of contact point j, W j represents the force weight of contact point j, and U represents the total number of contact points;

[0144] Based on the contact point morphology deviation matrix, contact points with locally high stress are selected and their morphology adjusted to reduce local stress. Key parameters requiring adjustment are first determined, such as tooth tip height, groove depth, and contact point area. Local contact points are fine-tuned using CNC equipment or manual grinding to reduce morphology deviation. For example, if the deviation value of a contact point is -0.3mm, the tooth tip should be raised by 0.3mm to restore it to the standard shape. A formula is then used to calculate the morphology value representing the adjusted contact point.

[0145] The force weight is set based on the pressure value of the contact point. For example, the contact point with a higher pressure value has a larger weight. Assume that the original shape value Z of a contact point i is i is 1.2mm, and its shape deviation L i is -0.3mm, and the force weights of the three surrounding contact points are W j are 0.5, 0.3 and 0.2 respectively, and the corresponding morphological deviation L j If they are -0.2mm, -0.1mm and 0.05mm respectively, then we can calculate:

[0146]

[0147]

[0148] The calculation shows that the restoration contact point should be adjusted to 1.36 mm to achieve the optimized shape. Finally, the adjusted restoration shape matrix is obtained.

[0149] The matching degree calculation submodule calculates the matching degree between the adjusted restoration and the original tooth shape based on the adjusted restoration shape matrix, and obtains the optimized restoration shape data;

[0150] Based on the adjusted restoration morphology matrix, the matching degree between the restored restoration and the original tooth morphology is calculated. The Euclidean distance is used to calculate the morphological changes of each point and quantify the overall matching degree. For the three-dimensional coordinate data before and after the restoration morphology adjustment, the morphological error between each contact point is calculated and normalized to the matching degree value. The matching degree is calculated using the formula:

[0151]

[0152] Among them, Z max Represents the maximum shape value, U is the total number of contact points. Assume that the adjusted shape value T i They are 1.36mm, 1.55mm and 1.41mm respectively, and the original shape value Z i They are 1.2mm, 1.6mm and 1.4mm respectively, and the maximum morphological value Z max If it is set to 2.0mm, the matching degree is calculated as follows:

[0153]

[0154] The calculation shows that the matching degree of the adjusted restoration is 96.33%, indicating that the adjusted restoration morphology is closer to the original tooth morphology. Finally, the optimized restoration morphology data is obtained.

[0155] See also Figure 6 , the customized treatment recommendation module includes:

[0156] The adaptability analysis submodule calculates the adaptability of dental restoration materials under different stress conditions based on the potential microcrack area and optimized restoration morphology data, analyzes the contact stability and force balance between the restoration materials and the patient's tooth tissue, and obtains the restoration adaptation parameter matrix;

[0157] Based on the potential microcrack area and the optimized restoration morphology data, the material parameters of the restoration contact points, including elastic modulus, yield strength, fracture toughness, etc., are extracted, and different stress conditions are set, such as uniform stress, single-point stress, and multi-point stress distribution. The contact stability between the restoration material and the tooth tissue is compared, and the stress change trend of each contact point is determined. In practical applications, it is assumed that the restoration material is zirconia, its elastic modulus is set to 200GPa, and its yield strength is 900MPa, while the elastic modulus of the patient's natural teeth is 80GPa and its yield strength is 350MPa. Based on this, the deformation variables of different materials under the same stress conditions are compared and calculated, where the deformation variable calculation of the material can use the stress-strain formula. Furthermore, the contact stress of the restoration in a uniform stress environment is calculated. For example, under the action of a 50N bite force, the stress distribution of the restoration contact point can be determined by finite element simulation or experimental measurement to determine the degree of stress matching between the restoration and the natural tooth. The maximum stresses in different regions of the restoration were compared with the tolerance of the tooth tissue. If the maximum stress exceeded the safe stress threshold of natural teeth (approximately 60 MPa), the material selection or morphology optimization was adjusted. Ultimately, the restoration adaptation parameter matrix was obtained, which included data such as material properties, deformation, and stress distribution at each contact point, as shown in Table 7.

[0158] Table 7 Restoration adaptation parameter matrix

[0159] Contact point number Elastic modulus (GPa) Yield strength (MPa) Maximum stress (MPa) Deformation (μm) 1 200 900 50 5 2 200 900 55 6 3 80 350 45 7

[0160] As shown in Table 7, the adaptability parameters of each contact point can be used to further determine the long-term stress conditions of the restoration.

[0161] The long-term stress judgment submodule calculates the balance of the restoration morphology under long-term stress conditions based on the restoration adaptation parameter matrix, determines the stress stability of the restoration morphology under different stress environments, identifies the long-term stress concentration area, and obtains the long-term stress balance index of the restoration;

[0162] Based on the restoration's adaptation parameter matrix, the restoration's balance under long-term stress conditions is calculated. First, common stress environments for dental restorations are set, such as chewing hard objects, normal occlusion, and bruxism. Each stress condition is different, and the maximum stress difference of the restoration under each condition is calculated separately. For example, under a 50N bite force, the maximum stress of a zirconia restoration can reach 55MPa. However, during bruxism, the stress can reach up to 70N, causing the stress in the restoration to rise to 70MPa, exceeding the safe stress range of natural teeth. Next, the stress gradients at each contact point of the restoration are compared to determine if there are areas of stress concentration. For example, if the stress at a contact point is more than 20% higher than that of the surrounding area, it is considered a stress concentration area, and its long-term stress balance index is calculated. To ensure accuracy, the stress values at different contact points are weighted averaged, with weights assigned to different areas. For example, the area near the tooth edge is weighted 0.6, while the central area is weighted 0.4. The overall stress balance is calculated to determine whether it meets the long-term stress requirements. Finally, the long-term stress balance index of the restoration is obtained to further evaluate the durability of the restoration material.

[0163] The restoration plan generation submodule determines whether the restoration shape meets the long-term force balance condition based on the restoration long-term force balance index. If not, the dental restoration material is reselected, the restoration shape is adjusted, and a customized dental restoration treatment plan is obtained;

[0164] According to the long-term force balance index of the restoration, it is judged whether the restoration morphology meets the long-term force balance conditions. If it is found that the restoration material or morphology does not meet the expected standards, the dental restoration material is reselected. For example, if the stress in a specific area of the original zirconia restoration exceeds the tolerance range of natural teeth, it can be considered to use a glass-ceramic material with higher fracture toughness. Its lower elastic modulus can reduce the local stress concentration phenomenon. At the same time, adjust the restoration morphological parameters, such as appropriately increasing the contact point area to reduce the unit force intensity, and adjust the surface microstructure of the restoration to optimize the occlusal pressure distribution. The basis for setting the long-term force balance index is the stress fluctuation of the restoration under different occlusal environments. Under normal circumstances, the maximum stress fluctuation of the restoration should not exceed 10% of the occlusal balance reference value, which can be determined by the force fluctuation range of normal tooth tissue. For example, under normal occlusion, the force fluctuation of natural teeth is usually within the range of ±6MPa. If the force fluctuation range of a restoration exceeds 10% of ±6MPa (i.e. 0.6MPa), it is judged that its long-term force balance is poor, so the threshold of the long-term force balance index is set to no more than 10%. In practical applications, assuming that the force fluctuation of the restoration material is ±5.5MPa, it meets the long-term force balance requirements. If its force fluctuation reaches ±7MPa, the material or morphology needs to be optimized. This value fluctuates with the changes in the material properties, contact point distribution and force direction of the restoration. If the elastic modulus of the material is high, the overall stress fluctuation is small. If the surface morphology of the restoration is uneven, local stress concentration is likely to occur, resulting in an expansion of the stress fluctuation range. If the long-term force balance index of the restoration meets the set threshold after adjustment (such as not exceeding 10% of the stress fluctuation range, i.e., below the fluctuation standard of 0.6MPa), the restoration plan is finally determined, and a customized tooth restoration recommended treatment plan is generated.

[0165] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A big data driven oral treatment planning system, characterized in that: The system comprises: The tooth morphology data acquisition module acquires tooth surface morphology point cloud data, converts the point cloud data into a mesh model using triangulation, calculates the normal vector, principal curvature, Gaussian curvature, and mean square curvature of the mesh nodes, analyzes the curvature distribution of the mesh model, determines the morphology change area based on the curvature change gradient, and generates tooth surface morphology feature data; The microcrack identification module calculates the local curvature gradient of the grid node based on the tooth surface morphological feature data, calculates the curvature deviation rate in adjacent grid areas, determines the gradient change trend of abnormal curvature points, and screens out potential microcrack areas; The occlusal force data processing module obtains the force data of the tooth occlusal contact points, records the force conditions of the tooth cusp interdigitation contact points under different occlusal states, calculates the contact area and pressure distribution, analyzes the force balance of the contact points, and identifies and outputs the high-stress occlusal areas; The restoration morphology optimization module calculates the contact point morphology deviation of the local area with relatively large force based on the high occlusal stress area, adjusts the contact point morphology of the corresponding area, calculates the degree of matching between the adjusted dental restoration and the original tooth morphology, and obtains optimized restoration morphology data.

2. The big data driven oral treatment planning system according to claim 1, characterized in that: The tooth surface morphological feature data includes the grid node normal vector, principal curvature, Gaussian curvature, mean square curvature, and morphological change area; the potential microcrack area includes the area with drastic curvature change, the area with spatially continuous abnormal curvature point, and the area with local curvature gradient mutation; the occlusal high stress area includes the contact point with excessive force, the area with abnormal contact area, and the area with uneven pressure distribution; the optimized restoration morphological data includes the contact point morphology after adjustment, the matching data between the restoration and the original tooth morphology, and the local force balance optimization data.

3. The big data driven oral treatment planning system according to claim 1, characterized in that: The tooth morphology data acquisition module includes: The point cloud data acquisition submodule uses an optical coherence tomography device to scan, obtain point cloud data of the tooth surface morphology, extract the three-dimensional coordinate points of the tooth surface, divide the point cloud data into regions, and generate tooth surface point cloud data; The mesh model construction submodule uses triangulation to construct a mesh model based on the tooth surface point cloud data, calculates the adjacency relationship of mesh vertices, sets boundary constraints, obtains the normal vector of each mesh node, calculates the principal curvature, Gaussian curvature and mean square curvature, and uses the formula: Calculate the mesh node curvature gradient K, adjust the mesh smoothness according to the curvature distribution, and generate the tooth mesh model, where: represents the mean square curvature gradient, κ i represents the principal curvature in the i-th direction, and n represents the number of nodes in the mesh model; The morphological feature analysis submodule analyzes the curvature distribution of each node based on the tooth mesh model, calculates the curvature change gradient, compares the mesh node curvature gradient value with the set threshold, screens the area with significant morphological changes, and generates tooth surface morphological feature data.

4. The big data driven oral treatment planning system according to claim 1, characterized in that: The microcrack identification module includes: The local curvature calculation submodule calculates the local curvature gradient of the grid node based on the tooth surface morphological feature data, selects the adjacent grid area of each node, calculates the gradient values of the principal curvature and Gaussian curvature, and calculates the local curvature change rate of each grid node to generate grid local curvature gradient data; The curvature gradient analysis submodule calculates the curvature offset rate in adjacent grid areas based on the local curvature gradient data of the grid, and calculates the curvature offset direction and gradient change rate of each grid node using the formula: Calculate the abnormal curvature gradient distribution value G, compare the gradient change threshold to screen the local area with drastic changes, and generate abnormal curvature distribution data, where κ i represents the principal curvature of the i-th grid node, κ i-1 represents the principal curvature of the i-1th grid node, Δs i represents the Euclidean distance between adjacent grids, represents the local curvature gradient of the jth grid node, N represents the number of grid nodes, and M represents the number of adjacent grids; The microcrack area screening submodule determines the gradient change trend of abnormal curvature points based on the abnormal curvature distribution data, analyzes the continuity of the gradient direction, screens areas with drastic curvature changes and spatial continuity, removes isolated abnormal points, extracts the boundaries of microcrack areas, and generates potential microcrack areas.

5. The big data driven oral treatment planning system according to claim 1, characterized in that: The occlusal force data processing module includes: The force data acquisition submodule obtains the force data of the tooth occlusal contact points collected by the micromechanical sensor, monitors the force conditions of each point based on the interdigitated contact points of the tooth cusps in different occlusal states, records the changes of the occlusal force over time, and stores all the measured values to form an occlusal force matrix; The force distribution calculation submodule calculates the contact area of each occlusal contact point based on the occlusal force matrix using the formula: Calculate the pressure value P at contact point i i , calculate the pressure distribution of each contact point and construct the occlusal contact pressure distribution matrix, where F i Represents the force value at contact point i, A i represents the contact area of contact point i, U represents the total number of contact points, and F j and A j Represent the force value and contact area of contact point j respectively, and ∑ represents the sum of calculations of all contact points; The local force analysis submodule calculates the force balance of each contact point based on the occlusal contact pressure distribution matrix, compares the pressure value of each point with the set local force threshold, identifies the local force-excessive area, and obtains the occlusal high stress area.

6. The big data driven oral treatment planning system according to claim 1, characterized in that: The restoration morphology optimization module includes: The contact point morphology deviation calculation submodule extracts the contact point morphology data of the local area with relatively large stress based on the high occlusal stress area, compares the contact point morphology with the reference tooth morphology, calculates the morphology deviation value of each contact point, and establishes a contact point morphology deviation matrix; The morphology adjustment submodule adjusts the morphology of the contact points in the area with relatively large local forces based on the contact point morphology deviation matrix, using the formula: Calculate the morphological adjustment amount of each contact point after restoration adjustment, obtain the restoration morphological adjustment data, and establish the restoration morphological matrix after adjustment, where T i Represents the shape value of the contact point i after adjustment, Z i Represents the contact point morphology value of the original restoration, L i Represents the morphological deviation value of contact point i, L j represents the morphological deviation of contact point j, W j represents the force weight of contact point j, and U represents the total number of contact points; The matching degree calculation submodule calculates the matching degree between the adjusted restoration and the original tooth shape based on the adjusted restoration shape matrix, and obtains optimized restoration shape data.

7. The big data driven oral treatment planning system according to claim 1, characterized in that: The system also includes a customized treatment recommendation module; The customized treatment recommendation module analyzes the compatibility of the dental restoration material and the patient's tooth tissue under different stress conditions based on the potential microcrack area and the optimized restoration morphology data, determines whether the restoration morphology meets the long-term stress equilibrium condition, and reselects the dental restoration material if not, and generates a customized dental restoration recommendation treatment plan; The customized tooth restoration recommended treatment plan includes the restoration material compatibility analysis results, long-term force balance assessment results, and the adjusted restoration material selection plan.

8. The big data driven oral treatment planning system according to claim 7, characterized in that: The customized treatment recommendation module includes: The adaptability analysis submodule calculates the adaptability of the dental restoration material under different stress conditions based on the potential microcrack area and the optimized restoration morphology data, analyzes the contact stability and force balance between the restoration material and the patient's tooth tissue, and obtains the restoration adaptation parameter matrix; The long-term stress judgment submodule calculates the balance of the restoration morphology under long-term stress conditions based on the restoration adaptation parameter matrix, judges the stress stability of the restoration morphology under different stress environments, identifies the long-term stress concentration area, and obtains the long-term stress balance index of the restoration; The restoration plan generation submodule determines whether the restoration shape meets the long-term force balance condition based on the restoration long-term force balance index. If not, the dental restoration material is reselected, the restoration shape is adjusted, and a customized dental restoration recommended treatment plan is obtained.

Images