Dental restoration model construction method based on intraoral scanner

Abstract

The application discloses a method for constructing a dental restoration model based on an intraoral scanner, and applies to the technical field of data processing, and comprises the following steps: a desktop scanner is used to scan a prepared body model to obtain a digital reference model; an intraoral scanner is used to scan the prepared body model to obtain a digital experimental model, and 3D comparison analysis is performed on the model to determine the mean absolute deviation, the maximum positive average deviation and the maximum negative average deviation and obtain a color-coded graph; 3D analysis is repeatedly performed according to preset analysis conditions; all 3D analysis results are stored in a database, data deviation value analysis is performed, and a modeling data deviation adjustment library is determined; user scanning data is obtained, the user scanning data is adjusted by using the modeling data deviation adjustment library to determine modeling correction data, and the modeling correction data is used to construct a restoration model. The technical problem that the intraoral scanner has low modeling precision and poor dental restoration effect when modeling the internal structure of the oral cavity in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of data processing, and more particularly to a method for constructing oral restoration models based on an intraoral scanner. Background Technology

[0002] Intraoral scanners are devices used to create 3D models of images inside the oral cavity. However, due to the limited space inside the oral cavity, the size of the scanning end of the intraoral scanner is restricted, preventing the use of higher-precision scanning equipment. As a result, the oral cavity models constructed by intraoral scanners have lower accuracy and cannot achieve accurate modeling of the internal space of the oral cavity.

[0003] Therefore, in the existing technology, intraoral scanners have technical problems such as low modeling accuracy and poor oral restoration results when modeling the internal structure of the oral cavity. Summary of the Invention

[0004] This application provides a method for constructing oral restoration models based on intraoral scanners, which solves the technical problem that intraoral scanners have low modeling accuracy and poor oral restoration results when modeling the internal structure of the oral cavity in the prior art.

[0005] This application provides a method for constructing an oral restoration model based on an intraoral scanner. The method involves creating a preparatory model; scanning the preparatory model using a desktop scanner to obtain a digital reference model; scanning the preparatory model using an intraoral scanner to obtain a digital experimental model; performing 3D comparative analysis based on the digital reference model and the digital experimental model to determine the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation, and obtaining a color-coded map; repeating the 3D analysis according to preset analysis conditions to obtain the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation corresponding to the preset analysis conditions, and obtaining a color-coded map; storing all 3D analysis results in a database, performing data deviation analysis, and determining a modeling data deviation adjustment library; scanning the user's oral cavity using an intraoral scanner to obtain user scan data, adjusting the user scan data using the modeling data deviation adjustment library to determine modeling correction data, and using the modeling correction data to construct the restoration model.

[0006] This application also provides a dental restoration model construction system based on an intraoral scanner, comprising: a simulation model construction module for creating a preparatory model; a digital reference model acquisition module for scanning the preparatory model using a desktop scanner to obtain a digital reference model; a digital experimental model acquisition module for scanning the preparatory model using an intraoral scanner to obtain a digital experimental model; a comparative analysis module for performing 3D comparative analysis based on the digital reference model and the digital experimental model, determining the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation, and obtaining a color-coded map; a repeat analysis module for repeatedly performing 3D analysis according to preset analysis conditions, obtaining the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation corresponding to the preset analysis conditions, and obtaining a color-coded map; a deviation value analysis module for storing all 3D analysis results in a database, performing data deviation value analysis, and determining a modeling data deviation adjustment library; and a restoration model construction module for scanning the user's oral cavity using an intraoral scanner to obtain user scan data, adjusting the user scan data using the modeling data deviation adjustment library to determine modeling correction data, and using the modeling correction data to construct the restoration model.

[0007] This application also provides an electronic device, including:

[0008] Memory, used to store executable instructions;

[0009] The processor, when executing executable instructions stored in the memory, implements the oral restoration model construction method based on an intraoral scanner provided in the embodiments of this application.

[0010] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the oral restoration model construction method based on an intraoral scanner provided in this application.

[0011] This application proposes a method for constructing oral restoration models based on an intraoral scanner. A desktop scanner is used to scan a preparatory model to obtain a digital reference model. An intraoral scanner is then used to scan the preparatory model to obtain a digital experimental model, and 3D comparative analysis of the models is performed. 3D analysis is repeated according to preset analysis conditions. All 3D analysis results are stored in a database, and data deviation analysis is conducted to determine a modeling data deviation adjustment library. User scan data is obtained, and the modeling data deviation adjustment library is used to adjust the user scan data to determine modeling correction data. The modeling correction data is then used to construct the restoration model. This method solves the technical problem of low modeling accuracy and poor oral restoration results when using intraoral scanners to model the internal oral structure in existing technologies. It achieves accurate construction of a 3D model of the user's oral cavity and obtains more accurate restoration data using the scanned 3D model, improving the accuracy of user oral restoration data acquisition.

[0012] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Obviously, the drawings described below only relate to some embodiments of this disclosure and are not intended to limit this disclosure.

[0014] Figure 1 A flowchart illustrating the method for constructing an oral restoration model based on an intraoral scanner, as provided in an embodiment of this application;

[0015] Figure 2 A schematic diagram illustrating the process of constructing a modeling data deviation adjustment library for the oral restoration model construction method based on an intraoral scanner provided in the embodiments of this application;

[0016] Figure 3 A schematic diagram illustrating the 3D comparative analysis of the oral restoration model construction method based on an intraoral scanner provided in the embodiments of this application;

[0017] Figure 4 A schematic diagram of the system structure for the oral restoration model construction method based on an intraoral scanner provided in the embodiments of this application;

[0018] Figure 5 A schematic diagram of the system electronic device for constructing an oral restoration model based on an intraoral scanner, as provided in an embodiment of the present invention.

[0019] Figure labeling: Simulation model construction module 11, Digital reference model acquisition module 12, Digital experimental model acquisition module 13, Comparison and analysis module 14, Repeatability analysis module 15, Deviation value analysis module 16, Repair model construction module 17, Processor 31, Memory 32, Input device 33, Output device 34. Detailed Implementation

[0020] Example 1

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0023] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0025] While this application makes various references to certain modules of the system according to embodiments of this application, any number of different modules may be used and run on user terminals and / or servers. These modules are merely illustrative, and different aspects of the system and method may use different modules.

[0026] This application uses flowcharts to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, various steps can be processed in reverse order or simultaneously, as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0027] like Figure 1As shown in the embodiments of this application, a method for constructing an oral restoration model based on an intraoral scanner is provided, the method comprising:

[0028] S10: Create a preliminary body model;

[0029] S20: Use a desktop scanner to scan the preliminary model to obtain a digital reference model;

[0030] S30: Use an intraoral scanner to scan the prepared body model to obtain a digital experimental model;

[0031] Specifically, intraoral scanners are devices used for 3D modeling of images inside the oral cavity. However, due to the limited space within the oral cavity, the scanning end of the intraoral scanner is limited in size, preventing the use of higher-precision scanning equipment. This results in lower accuracy of the oral cavity models constructed by intraoral scanners, failing to achieve precise modeling of the oral cavity space. To address these shortcomings, a preparatory model is created. This preparatory model is an oral cavity simulation model with different tooth shape parameters, including simulation models of pulp chamber retention crowns with varying degrees of axial wall defects, as well as a standard undefected simulation model. For example, a preparatory model of a standard pulp chamber retention crown for 36 teeth is fabricated. The facial pulp chamber depth was 2 mm, and the axial wall defect was located mesially. Based on the degree of axial wall defect, the prepared teeth were divided into four groups: 1 mm supragingival, at gingival level, 1 mm subgingival, and 2 mm subgingival, with one tooth prepared from each group. Subsequently, the prepared tooth models were scanned using a desktop scanner to obtain digital reference models. The prepared tooth models were then scanned using an intraoral scanner to obtain digital experimental models.

[0032] S40: Based on the digital reference model and digital experimental model, perform 3D comparative analysis to determine the mean absolute deviation, the maximum positive uniform deviation, the maximum negative mean deviation, and obtain the color coding map;

[0033] S50: Repeat the 3D analysis according to the preset analysis conditions to obtain the mean absolute deviation, maximum positive uniform deviation, maximum negative mean deviation and color-coded map corresponding to the preset analysis conditions.

[0034] S60: Store all 3D analysis results in the database, perform data deviation analysis, and determine the modeling data deviation adjustment library;

[0035] S70: The user's oral cavity is scanned using an intraoral scanner to obtain user scan data. The user scan data is adjusted using the modeling data deviation adjustment library to determine modeling correction data. The repair model is constructed using the modeling correction data.

[0036] Specifically, a 3D comparative analysis is performed on the digital reference model acquired by the desktop scanner and the digital experimental model acquired by the intraoral scanner to determine the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation, and to obtain a color-coded map. The mean absolute deviation is the average deviation of the distance differences between the construction points of each model in the digital reference model and the digital experimental model, used to quantify the 3D differences between the scanned data. The maximum positive uniform deviation is the average deviation where the distance difference between the construction points of each model in the digital reference model and the digital experimental model is positive. The maximum negative uniform deviation is the average deviation where the distance difference between the construction points of each model in the digital reference model and the digital experimental model is negative. The color-coded map reflects the differences between the digital reference model and the digital experimental model. The maximum positive uniform deviation and the maximum negative uniform deviation have different color codes; the larger the absolute value, the darker the color. Data within the mean absolute deviation range uses a different color than the maximum positive uniform deviation and the maximum negative uniform deviation, and the color depth is the same, facilitating a visual evaluation of the scanned modeling data through images. Subsequently, 3D analysis was repeated according to preset analysis conditions to obtain the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation corresponding to the preset analysis conditions, and to obtain a color-coded map. The preset analysis conditions included 3D analysis of different models using the same scanner, 3D analysis of the same model using different scanners, and 3D analysis of the same model using the same scanner. Further, all 3D analysis results were stored in a database for data deviation analysis to determine a modeling data deviation adjustment library. Finally, the user's oral cavity was scanned using an intraoral scanner to obtain user scan data. The modeling data deviation adjustment library was used to adjust the user scan data to determine modeling correction data, and the modeling correction data was used to construct the restoration model. This achieved accurate construction of the user's oral cavity 3D model, and the use of the scanned oral cavity 3D model to obtain more accurate restoration data improved the accuracy of user oral restoration data acquisition.

[0037] like Figure 2 As shown, the method S60 provided in this application embodiment further includes:

[0038] S61: Extract the first difference data from the same scanner for different models from all 3D analysis results;

[0039] S62: Extract second difference data from different scanners for the same model from all 3D analysis results;

[0040] S63: Based on the first difference data and the second difference data, evaluate the accuracy of the model construction data and determine the accuracy of each parameter;

[0041] S64: Extract third difference data from all 3D analysis results for the same model and the same scanner;

[0042] S65: Evaluate the authenticity of the model construction data based on the third difference data, and determine the authenticity of each parameter;

[0043] S66: Analyze the accuracy and authenticity of each parameter to determine the deviation adjustment coefficient;

[0044] S67: Based on the accuracy and authenticity of each parameter, and in conjunction with the deviation adjustment coefficient, construct the modeling data deviation adjustment library.

[0045] Specifically, when storing all 3D analysis results in the database, performing data deviation analysis, and determining the modeling data deviation adjustment library, the first difference data of different models using the same scanner is extracted from the 3D analysis results. The second difference data of the same model using different scanners is extracted from all 3D analysis results. Based on the first and second difference data, the accuracy of the model construction data is evaluated, and the accuracy of each parameter is determined. The first and second difference data are both mean absolute deviation data, and the accuracy of each parameter is the average of the first and second difference data. Subsequently, the third difference data of the same model using the same scanner is extracted from all 3D analysis results, where the third difference data is the mean absolute deviation data. Based on the third difference data, the realism of the model construction data is evaluated, and the realism of each parameter is determined. The realism of the parameter is the mean of the deviation data of each parameter. The accuracy and realism of each parameter are analyzed to determine the deviation adjustment coefficient. Since the accuracy of each parameter represents the data error generated by the same acquisition device during acquisition, the deviation adjustment coefficient is obtained by subtracting the realism of the corresponding parameter from the accuracy of each parameter. Finally, based on the accuracy and accuracy of each parameter, and in conjunction with the deviation adjustment coefficient, the modeling data deviation adjustment library is constructed. This enables targeted compensation for different devices and different oral and dental structures.

[0046] like Figure 3 As shown, the method S40 provided in this application embodiment further includes:

[0047] S41: Overlay the pre-aligned and cropped digital experimental model onto the corresponding digital reference model, perform quantitative comparison between scan data, compare the differences based on the quantized scan data, and obtain the mean absolute deviation.

[0048] S42: Based on the difference comparison results of the quantized scan data, obtain the positive uniform deviation, and determine the maximum positive uniform deviation from the positive uniform deviation;

[0049] S43: Based on the difference comparison results of the quantized scan data, obtain the negative uniform deviation, and determine the maximum negative average deviation from the negative uniform deviation;

[0050] S44: The digital experimental model is superimposed on the corresponding digital reference model and color-coded to obtain the color-coded image, which is used to qualitatively evaluate the deviation of the scan data.

[0051] Specifically, the pre-aligned and cropped digitized experimental model is overlaid onto the corresponding digitized reference model. A quantized comparison is performed between scanned data points, and the mean absolute deviation is obtained by comparing the differences in the quantized scanned data. Based on the difference comparison results of the quantized scanned data, a positive uniform deviation is obtained, and the maximum positive uniform deviation is determined from the positive uniform deviations. Based on the difference comparison results of the quantized scanned data, a negative uniform deviation is obtained, and the maximum negative average deviation is determined from the negative uniform deviations. The digitized experimental model is then overlaid onto the corresponding digitized reference model and color-coded to obtain the color-coded image. This color-coded image is used for qualitative evaluation of scanned data deviation.

[0052] S51: The preset analysis conditions include different models using the same scanner, the same model using different scanners, and the same model using the same scanner, wherein the different models are medullary cavity fixation crowns with different degrees of axial wall defects.

[0053] The method S70 provided in this application embodiment further includes:

[0054] S71: Obtain the scanning parameters of the intraoral scanner;

[0055] S72: Based on the scanning parameters of the intraoral scanner, match them in the modeling data deviation adjustment library to obtain the same scanner correction parameters;

[0056] S73: Extract point cloud features based on the user scan data to determine the degree of user shaft wall damage;

[0057] S74: Based on the degree of user shaft wall damage, match it in the modeling data deviation adjustment library to obtain the correction parameters of the same model;

[0058] S75: Using the same scanner correction parameters and the same model correction parameters, correct the user's scan data and determine the modeling correction data;

[0059] S76: Construct a 3D model of the user's oral cavity using the user's scan data;

[0060] S77: The user's oral cavity 3D model is corrected using the modeling correction data, and the corrected user's oral cavity 3D model is overlaid and analyzed with the corresponding digital reference model to determine the repair data;

[0061] S78: Based on the repair data and the corrected 3D model of the user's oral cavity, construct a user repair model.

[0062] Specifically, the user's scan data is adjusted using the modeling data deviation adjustment library to determine the modeling correction data. When constructing the repair model using the modeling correction data, the scanning parameters of the intraoral scanner are obtained. These parameters include scanning device parameters and the degree of axial wall defects in the pre-scanned model. The scanning parameters of the intraoral scanner are matched in the modeling data deviation adjustment library to obtain correction parameters for the same scanner. Point cloud features are extracted from the user's scan data to determine the degree of axial wall defects. The degree of axial wall defects is then matched in the modeling data deviation adjustment library to obtain correction parameters for the same model. Finally, the correction parameters for the same scanner and the same model are used to correct and locate the user's scan data, determining the modeling correction data. A 3D model of the user's oral cavity is constructed using the user's scan data. The 3D model of the user's oral cavity is corrected using the modeling correction data. The corrected 3D model of the user's oral cavity is then overlaid and analyzed with a standard oral cavity model in the corresponding digital reference model to determine the repair parameters for the repair site, such as the user's axial wall defect repair parameters, thus determining the repair data. Based on the repair data and the corrected 3D model of the user's oral cavity, a user repair model is constructed, which includes specific repair parameters for each location of the user's oral cavity.

[0063] The method S76 provided in this application embodiment further includes:

[0064] S761: Determine the scanning position node based on the user's scanning data, use the scanning position node to determine the coordinates, and construct a 3D coordinate system;

[0065] S762: Based on the scan position nodes, establish a mapping relationship between the 3D coordinate system and the user scan data;

[0066] S763: Perform overlap analysis on node scan data and determine splicing edges based on overlap.

[0067] S764: Use the stitching edges to stitch together user scan data to construct a 3D model of the user's oral cavity.

[0068] Specifically, when constructing a 3D model of a user's oral cavity, scanning position nodes are determined based on the user's scan data. These scanning position nodes serve as the origin of the 3D coordinate system. Coordinates are determined using these scanning position nodes, and the 3D coordinate system is constructed. A mapping relationship between the 3D coordinate system and the user's scan data is established based on these scanning position nodes. Furthermore, overlap analysis is performed on the node scan data to identify overlapping points. The stitching edges are determined based on this overlap; that is, the overlapping points are used as the stitching edges of the scan points. Finally, the user's scan data is stitched together using these stitching edges to construct the 3D model of the user's oral cavity.

[0069] The method S73 provided in this application embodiment further includes:

[0070] S731: The user scanning data is input into the semantic segmentation model. The user scanning data enters the first channel to obtain a first recognition result. The user scanning data enters the second channel to obtain a second recognition result. The first channel has a first step length for data extraction, the second channel has a second step length for data extraction, and the first step length is greater than the second step length.

[0071] S732: The image features in the first recognition result and the second recognition result are fused by feature point fusion to obtain a point cloud feature set;

[0072] S733: Perform shaft wall defect degree feature matching on the point cloud feature set to determine the degree of shaft wall defect of the user.

[0073] Specifically, the user scan data is input into an image semantic segmentation model to separate the axial wall defect region. The user scan data enters a first channel, i.e., the scanned image is input into the first channel to obtain a first recognition result. The user scan data then enters a second channel, i.e., the scanned image is input into the second channel to obtain a second recognition result. The first channel has a first step length for data extraction, and the second channel has a second step length for data extraction. The first step length is greater than the second step length, and both the first and second step lengths are the step lengths for the axial wall defect region. Finally, the image features from the first and second recognition results are fused to obtain a point cloud feature set. Axial wall defect degree feature matching is performed on the point cloud feature set to determine the degree of axial wall defect of the user. This achieves the acquisition of the user's axial wall defect degree, thereby matching the corresponding correction parameters.

[0074] The technical solution provided in this invention involves creating a preparatory model, scanning the preparatory model with a desktop scanner to obtain a digital reference model, and then scanning the preparatory model with an intraoral scanner to obtain a digital experimental model. Based on the digital reference model and the digital experimental model, a 3D comparative analysis is performed to determine the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation, and a color-coded map is obtained. The 3D analysis is repeated according to preset analysis conditions to obtain the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation corresponding to the preset analysis conditions, and a color-coded map is obtained. All 3D analysis results are stored in a database, and data deviation value analysis is performed to determine a modeling data deviation adjustment library. The user's oral cavity is scanned using an intraoral scanner to obtain user scan data. The user scan data is adjusted using the modeling data deviation adjustment library to determine modeling correction data, and the repair model is constructed using the modeling correction data. This achieves accurate construction of a 3D model of the user's oral cavity and obtains more accurate repair data using the scanned 3D model, improving the accuracy of user oral repair data acquisition. This technology solves the technical problem of low modeling accuracy and poor oral restoration results when using intraoral scanners to model the internal structure of the oral cavity.

[0075] Example 2

[0076] Based on the same inventive concept as the oral prosthetic model construction method based on an intraoral scanner in the foregoing embodiments, this invention also provides a system for constructing an oral prosthetic model based on an intraoral scanner. The system can be implemented in hardware and / or software, and is generally integrated into an electronic device to execute the methods provided in any embodiment of this invention. For example... Figure 4 As shown, the system includes:

[0077] Simulation model building module 11 is used to create a preliminary body model;

[0078] The digital reference model acquisition module 12 is used to scan the preparatory model with a desktop scanner to obtain a digital reference model.

[0079] The digital experimental model acquisition module 13 is used to scan the preparatory body model using an intraoral scanner to obtain a digital experimental model.

[0080] The comparison analysis module 14 is used to perform 3D comparison analysis based on the digital reference model and the digital experimental model, determine the mean absolute deviation, the maximum positive uniform deviation, the maximum negative mean deviation, and obtain the color coding map.

[0081] The repeat analysis module 15 is used to repeatedly perform 3D analysis according to preset analysis conditions, obtain the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation corresponding to the preset analysis conditions, and obtain a color-coded map.

[0082] The deviation value analysis module 16 is used to store all 3D analysis results in the database, perform data deviation value analysis, and determine the modeling data deviation adjustment library.

[0083] The repair model construction module 17 is used to perform oral cavity scanning of the user through an intraoral scanner to obtain user scan data, adjust the user scan data using the modeling data deviation adjustment library to determine modeling correction data, and use the modeling correction data to construct a repair model.

[0084] Furthermore, the deviation analysis module 16 is also used for:

[0085] Extract the first difference data from the same scanner for different models from all 3D analysis results;

[0086] Extract the second difference data of the same model from different scanners from all 3D analysis results;

[0087] Based on the first and second difference data, the accuracy of the model construction data is evaluated, and the accuracy of each parameter is determined.

[0088] Extract third difference data from the same model and the same scanner from all 3D analysis results;

[0089] The authenticity of the model construction data is evaluated based on the third difference data, and the authenticity of each parameter is determined.

[0090] The accuracy and authenticity of each parameter are analyzed to determine the deviation adjustment coefficient.

[0091] Based on the accuracy and authenticity of each parameter, and in conjunction with the deviation adjustment coefficient, the modeling data deviation adjustment library is constructed.

[0092] Furthermore, the comparison and analysis module 14 is also used for:

[0093] The pre-aligned and cropped digital experimental model is superimposed on the corresponding digital reference model, and a quantitative comparison is performed between the scan data. The difference is compared based on the quantized scan data to obtain the mean absolute deviation.

[0094] Based on the difference comparison results of the quantized scan data, the positive uniform deviation is obtained, and the maximum positive uniform deviation is determined from the positive uniform deviation.

[0095] Based on the difference comparison results of the quantized scan data, the negative uniform deviation is obtained, and the maximum negative average deviation is determined from the negative uniform deviation.

[0096] The digital experimental model is superimposed on the corresponding digital reference model and color-coded to obtain the color-coded image, which is used to qualitatively evaluate the deviation of the scan data.

[0097] Furthermore, the repair model construction module 17 is also used for:

[0098] Obtain the scanning parameters of the intraoral scanner;

[0099] Based on the scanning parameters of the intraoral scanner, the same scanner correction parameters are obtained by matching them in the modeling data deviation adjustment library.

[0100] Point cloud features are extracted based on the user's scan data to determine the degree of damage to the user's shaft wall;

[0101] Based on the degree of user shaft wall defects, the modeling data deviation adjustment library is matched to obtain the correction parameters of the same model;

[0102] Using the same scanner correction parameters and the same model correction parameters, the user's scan data is corrected to determine the modeling correction data;

[0103] Using the user's scan data, a 3D model of the user's oral cavity is constructed;

[0104] The user's oral cavity 3D model is corrected using the modeling correction data. The corrected user's oral cavity 3D model is then overlaid and analyzed with the corresponding digital reference model to determine the repair data.

[0105] Based on the repair data, a user repair model is constructed on the basis of the corrected 3D model of the user's oral cavity.

[0106] Furthermore, the repair model construction module 17 is also used for:

[0107] The scanning location nodes are determined based on the user's scanning data, and the coordinates are determined using the scanning location nodes to construct a 3D coordinate system.

[0108] Based on the scan location nodes, establish a mapping relationship between the 3D coordinate system and the user scan data;

[0109] Perform overlap analysis on the node scan data and determine the splicing edges based on the overlap.

[0110] The user's oral cavity 3D model is constructed by stitching together user scan data using the stitching edges.

[0111] Furthermore, the repair model construction module 17 is also used for:

[0112] The user scanning data is input into the semantic segmentation model. The user scanning data enters the first channel to obtain a first recognition result. The user scanning data enters the second channel to obtain a second recognition result. The first channel has a first step length for data extraction, and the second channel has a second step length for data extraction. The first step length is greater than the second step length.

[0113] The image features in the first and second recognition results are fused by feature point fusion to obtain a point cloud feature set;

[0114] The degree of shaft wall damage is determined by performing shaft wall damage feature matching on the point cloud feature set.

[0115] The various units and modules included are divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0116] Example 3

[0117] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present invention. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. Figure 5 As shown, the electronic device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the electronic device can be one or more. Figure 5 Taking a processor 31 as an example, the processor 31, memory 32, input device 33, and output device 34 in an electronic device can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0118] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the oral prosthetic model construction method based on an intraoral scanner in this embodiment of the invention. The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 32, thereby realizing the above-mentioned oral prosthetic model construction method based on an intraoral scanner.

[0119] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for constructing oral restoration models based on intraoral scanners, characterized in that, include: Create a preparatory body model, which is an oral cavity simulation model with different tooth shape parameters; A desktop scanner was used to scan the preliminary model to obtain a digital reference model; The prepared body model was scanned using an intraoral scanner to obtain a digital experimental model. Based on the digital reference model and digital experimental model, a 3D comparative analysis is performed to determine the mean absolute deviation, the maximum positive uniform deviation, the maximum negative mean deviation, and to obtain a color coding map. Repeat the 3D analysis according to the preset analysis conditions to obtain the mean absolute deviation, maximum positive uniform deviation, maximum negative mean deviation and color-coded map corresponding to the preset analysis conditions. All 3D analysis results are stored in a database, and data deviation values ​​are analyzed to determine the modeling data deviation adjustment library. The user's oral cavity is scanned using an intraoral scanner to obtain user scan data. The user scan data is then adjusted using the modeling data deviation adjustment library to determine modeling correction data. The repair model is then constructed using the modeling correction data.

2. The method as described in claim 1, characterized in that, The process of storing all 3D analysis results in a database, performing data deviation analysis, and determining a modeling data deviation adjustment library includes: Extract the first difference data from the same scanner for different models from all 3D analysis results; Extract the second difference data of the same model from different scanners from all 3D analysis results; Based on the first and second difference data, the accuracy of the model construction data is evaluated, and the accuracy of each parameter is determined. Extract third difference data from the same model and the same scanner from all 3D analysis results; The authenticity of the model construction data is evaluated based on the third difference data, and the authenticity of each parameter is determined. The accuracy and authenticity of each parameter are analyzed to determine the deviation adjustment coefficient. Based on the accuracy and authenticity of each parameter, and in conjunction with the deviation adjustment coefficient, the modeling data deviation adjustment library is constructed.

3. The method as described in claim 1, characterized in that, Based on the aforementioned digital reference model and digital experimental model, a 3D comparative analysis is performed to determine the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation, and to obtain a color-coded map, including: The pre-aligned and cropped digital experimental model is superimposed on the corresponding digital reference model, and a quantitative comparison is performed between the scan data. The difference is compared based on the quantized scan data to obtain the mean absolute deviation. Based on the difference comparison results of the quantized scan data, the positive uniform deviation is obtained, and the maximum positive uniform deviation is determined from the positive uniform deviation. Based on the difference comparison results of the quantized scan data, the negative uniform deviation is obtained, and the maximum negative average deviation is determined from the negative uniform deviation. The digital experimental model is superimposed on the corresponding digital reference model and color-coded to obtain the color-coded map, which is used to qualitatively evaluate the deviation of the scan data.

4. The method as described in claim 1, characterized in that, The preset analysis conditions include different models using the same scanner, the same model using different scanners, and the same model using the same scanner. Among these, the different models are canal fixation crowns with different degrees of axial wall defects.

5. The method as described in claim 2, characterized in that, The modeling data deviation adjustment library is used to adjust the user's scan data to determine the modeling correction data, and the modeling correction data is used to build a repair model, including: Obtain the scanning parameters of the intraoral scanner; Based on the scanning parameters of the intraoral scanner, the same scanner correction parameters are obtained by matching them in the modeling data deviation adjustment library. Point cloud features are extracted based on the user's scan data to determine the degree of damage to the user's shaft wall; Based on the degree of user shaft wall defects, the modeling data deviation adjustment library is matched to obtain the correction parameters of the same model; Using the same scanner correction parameters and the same model correction parameters, the user's scan data is corrected to determine the modeling correction data; Using the user's scan data, a 3D model of the user's oral cavity is constructed; The user's oral cavity 3D model is corrected using the modeling correction data. The corrected user's oral cavity 3D model is then overlaid and analyzed with the corresponding digital reference model to determine the repair data. Based on the repair data, a user repair model is constructed on the basis of the corrected 3D model of the user's oral cavity.

6. The method as described in claim 5, characterized in that, The step of constructing a 3D model of the user's oral cavity using the user's scan data includes: The scanning location nodes are determined based on the user's scanning data, and the coordinates are determined using the scanning location nodes to construct a 3D coordinate system. Based on the scan location nodes, establish a mapping relationship between the 3D coordinate system and the user scan data; Perform overlap analysis on the node scan data and determine the splicing edges based on the overlap. The user's oral cavity 3D model is constructed by stitching together user scan data using the stitching edges.

7. The method as described in claim 5, characterized in that, Point cloud features are extracted based on the user scan data to determine the degree of user shaft wall damage, including: The user scanning data is input into the semantic segmentation model. The user scanning data enters the first channel to obtain a first recognition result. The user scanning data enters the second channel to obtain a second recognition result. The first channel has a first step length for data extraction, and the second channel has a second step length for data extraction. The first step length is greater than the second step length. The image features in the first and second recognition results are fused by feature point fusion to obtain a point cloud feature set; The degree of shaft wall damage is determined by performing shaft wall damage feature matching on the point cloud feature set.

8. A system for constructing oral restoration models based on an intraoral scanner, characterized in that, include: The simulation model construction module is used to create a preparatory body model, which is an oral simulation model with different tooth shape parameters; The digital reference model acquisition module is used to scan the preparatory model with a desktop scanner to obtain a digital reference model. The digital experimental model acquisition module is used to scan the preparatory body model using an intraoral scanner to obtain a digital experimental model. The comparative analysis module is used to perform 3D comparative analysis based on the digital reference model and the digital experimental model, determine the mean absolute deviation, the maximum positive uniform deviation, the maximum negative mean deviation, and obtain the color-coded map. The repeat analysis module is used to repeatedly perform 3D analysis according to preset analysis conditions, obtain the mean absolute deviation, maximum positive uniform deviation, and maximum negative mean deviation corresponding to the preset analysis conditions, and obtain a color-coded map. The deviation analysis module is used to store all 3D analysis results in the database, perform data deviation analysis, and determine the modeling data deviation adjustment library. The repair model construction module is used to perform oral cavity scanning on the user using an intraoral scanner to obtain user scan data, adjust the user scan data using the modeling data deviation adjustment library to determine modeling correction data, and use the modeling correction data to construct a repair model.

9. An electronic device, characterized in that, The electronic device includes: Memory, used to store executable instructions; The processor, when executing executable instructions stored in the memory, implements the oral restoration model construction method based on an intraoral scanner as described in any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the oral restoration model construction method based on an intraoral scanner as described in any one of claims 1-7.

Images