Denture margin line determination method and apparatus, electronic device, and storage medium

Abstract

The present application relates to the technical field of denture restoration, and provides a denture margin line determination method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring three-dimensional oral-cavity mesh data; and using an AI model to perform denture margin line identification with respect to the three-dimensional oral-cavity mesh data, so as to obtain a denture margin line. In the denture margin line determination method of the present application, an AI model is used to perform automatic denture margin line identification with respect to the three-dimensional oral-cavity mesh data, thereby achieving a high degree of intelligence and improving the accuracy and robustness of denture margin line identification.

Description

A method, apparatus, electronic device and storage medium for determining the edge line of a denture. Cross-reference to related applications

[0001] This application claims priority to Chinese Patent Application No. 202411888172.7, filed on December 19, 2024, entitled "A method, apparatus, electronic device and storage medium for determining the edge line of a denture", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the technical field of denture restoration, and in particular to a method, apparatus, electronic device and storage medium for determining the edge line of a denture. Background Technology

[0003] In dentistry, especially when fabricating complete dentures or removable partial dentures, identifying the myostatic line is crucial for ensuring denture retention and function.

[0004] Currently, in clinical dentistry, when fabricating complete dentures or removable partial dentures, the dentist typically uses manual impression taking to shape the prosthesis's margins. However, this manual impression taking method has some drawbacks. For example, it may cause discomfort to the patient, and the efficiency of taking impressions is relatively low. Furthermore, it requires a high level of skill from the dentist, who needs to manually draw lines based on the impression, leading to significant uncertainty in the prosthesis margins obtained by different dentists and being greatly influenced by subjective human factors. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a method, apparatus, electronic device and storage medium for determining the edge line of a denture, so as to alleviate the technical problems of poor accuracy and low intelligence of the determination process of the denture edge line determined by traditional technology.

[0006] In a first aspect, embodiments of this application provide a method for determining the edge line of a denture, comprising: acquiring three-dimensional mesh data of the oral cavity obtained by scanning the oral cavity with an oral scanning device; and using an AI model to identify the edge line of the denture from the three-dimensional mesh data of the oral cavity to obtain the edge line of the denture.

[0007] Optionally, an AI model is used to identify the denture edge line of the oral cavity three-dimensional mesh data, including: segmenting the oral cavity three-dimensional mesh data using a region segmentation model to obtain the denture coverage area; and determining the denture edge line based on the denture coverage area.

[0008] Optionally, the denture coverage area includes a myostatic region, and determining the denture edge line based on the denture coverage area includes: determining a target three-dimensional myostatic line based on the myostatic region, and determining the denture edge line based on the target three-dimensional myostatic line.

[0009] Optionally, after acquiring the oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral scanning device, the method further includes: preprocessing the oral cavity three-dimensional mesh data to obtain preprocessed oral cavity three-dimensional mesh data; and using an AI model to identify the denture edge line of the preprocessed oral cavity three-dimensional mesh data to obtain the denture edge line.

[0010] Optionally, after acquiring the oral cavity three-dimensional mesh data obtained by the oral cavity scanning device and before preprocessing the oral cavity three-dimensional mesh data, the method further includes: determining whether the oral cavity three-dimensional mesh data completely contains the specified region; if it does not completely contain it, issuing a prompt message and reacquiring the oral cavity three-dimensional mesh data obtained by the oral cavity scanning device until the oral cavity three-dimensional mesh data completely contains the specified region.

[0011] Optionally, the method further includes: determining the degree of alveolar ridge resorption based on oral cavity three-dimensional mesh data; determining the accuracy of the denture margin line based on the degree of alveolar ridge resorption; and outputting the accuracy to a display screen or voice broadcast.

[0012] Optionally, determining the target three-dimensional myostatic line based on the myostatic region includes: smoothing the edges of the myostatic region to obtain a smooth-contoured myostatic region; drawing a three-dimensional myostatic line based on the edges of the smooth-contoured myostatic region; and smoothing the three-dimensional myostatic line to obtain the target three-dimensional myostatic line.

[0013] Optionally, the edges of the myostatic region are smoothed and optimized, including: using a graph cut algorithm to smooth and optimize the edges of the myostatic region to obtain a myostatic region with a smooth contour; or, the three-dimensional myostatic lines are smoothed, including: determining a target smoothing algorithm based on the morphological characteristics and processing technology of the denture, wherein the target smoothing algorithm includes any of the following: Laplace smoothing algorithm, least squares smoothing algorithm, and curvature-based feature smoothing algorithm; and using the target smoothing algorithm to smooth the three-dimensional myostatic lines to obtain the target three-dimensional myostatic lines.

[0014] Optionally, the training process of the region segmentation model includes: acquiring oral cavity three-dimensional mesh data samples, wherein the oral cavity three-dimensional mesh data samples are marked with denture coverage areas; preprocessing the oral cavity three-dimensional mesh data samples to obtain preprocessed oral cavity three-dimensional mesh data samples; and using the preprocessed oral cavity three-dimensional mesh data samples to train the original region segmentation model to obtain the region segmentation model.

[0015] Optionally, the oral cavity 3D mesh data samples are preprocessed, including: performing data processing on the oral cavity 3D mesh data samples to obtain data-processed oral cavity 3D mesh data samples; performing vertex optimization on the data-processed oral cavity 3D mesh data samples to obtain vertex-optimized oral cavity 3D mesh data samples; performing feature calculation on the vertex-optimized oral cavity 3D mesh data samples to obtain feature-calculated oral cavity 3D mesh data samples; and using the feature-calculated oral cavity 3D mesh data samples as preprocessed oral cavity 3D mesh data samples.

[0016] Optionally, data processing is performed on the oral cavity 3D mesh data samples, including: denoising the oral cavity 3D mesh data samples to obtain denoised oral cavity 3D mesh data samples; projecting the denoised oral cavity 3D mesh data samples in the same direction to obtain a two-dimensional depth image; fitting the dental arch curve based on the depth values ​​in the two-dimensional depth image; aligning the corresponding denoised oral cavity 3D mesh data samples with reference to the dental arch curve to obtain aligned oral cavity 3D mesh data samples; and using the aligned oral cavity 3D mesh data samples as the processed oral cavity 3D mesh data samples.

[0017] Optionally, feature calculation is performed on the vertex-optimized oral 3D mesh data samples, including: extracting features in different frequency domains of the vertex-optimized oral 3D mesh data samples using the Laplacian operator of the mesh to obtain oral 3D mesh data samples with Laplacian features; performing multi-scale enhancement processing on the oral 3D mesh data samples with Laplacian features to obtain multi-scale oral 3D mesh data samples; representing the multi-scale oral 3D mesh data samples using sparse coding to obtain sparsely coded oral 3D mesh data samples; calculating the geometric features of the sparsely coded oral 3D mesh data samples to obtain oral 3D mesh data samples with geometric features, wherein the geometric features include: surface curvature and normal vector; and using the oral 3D mesh data samples with geometric features as the oral 3D mesh data samples after feature calculation.

[0018] Optionally, after using an AI model to identify the denture edge line from the three-dimensional mesh data of the oral cavity and obtaining the denture edge line, the method further includes: when a first command is detected, determining the first pose change of the denture edge line relative to its initial position, wherein the first command is a command from the user to adjust the pose of the denture edge line in the three-dimensional mesh data of the oral cavity; based on the first pose change and preset reference conditions, determining the first adjusted pose of the denture edge line, and updating and displaying the pose of the denture edge line based on the first adjusted pose of the denture edge line, wherein the preset reference conditions include: the denture edge line conforming to the outer surface of the three-dimensional mesh data of the oral cavity, and the denture edge line conforming to simulated physiological movement or The denture edge line is located within one or more of the denture coverage area; wherein, when a first pose change is detected that causes the denture edge line to not conform to the preset reference conditions, the pose of the denture edge line is adaptively updated according to the preset reference conditions, or, the pose of the denture edge line is not updated and the result of user reconfirmation is obtained and the pose of the denture edge line is adjusted according to the result of user reconfirmation; and / or when a first adjusted pose is detected that causes the denture edge line to not conform to the preset reference conditions, the pose of the denture edge line is adaptively updated according to the preset reference conditions, or, the pose of the denture edge line is not updated and the result of user reconfirmation is obtained and the pose of the denture edge line is adjusted according to the result of user reconfirmation.

[0019] Optionally, the method further includes: generating a three-dimensional denture model based on the denture edge line and oral cavity three-dimensional mesh data, and sending the three-dimensional denture model to a 3D printing device configured for printing; receiving user requests for modifying the three-dimensional denture model in real time; and outputting revised denture edge lines and / or a revised three-dimensional denture model based on the user requests, denture edge lines, and oral cavity three-dimensional mesh data.

[0020] Optionally, the oral cavity may contain some teeth or not.

[0021]

[0021] Furthermore, the oral cavity is an edentulous jaw.

[0022] Optionally, the denture coverage area includes: a myostatic region.

[0023] Optionally, the designated area includes: the labial frenulum, the buccal frenulum, the vestibular mucosa fold, the lower border of the zygomatic bone, and the buccal side of the maxillary tuberosity; or the designated area includes: the labial frenulum, the buccal frenulum, the maxillary tuberosity, the pterygomaxillary notch, and the area 2 mm behind the lesser maxillary fossa.

[0024] Optionally, the method further includes: if the oral cavity three-dimensional mesh data contains the specified region, then preprocessing the oral cavity three-dimensional mesh data to obtain preprocessed oral cavity three-dimensional mesh data.

[0025] Secondly, embodiments of this application also provide a denture edge line determination device, including: an acquisition unit configured to acquire oral cavity three-dimensional mesh data obtained by an oral scanning device scanning the oral cavity; and a denture edge line recognition unit configured to use an AI model to recognize the denture edge line from the oral cavity three-dimensional mesh data to obtain the denture edge line.

[0026] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in any of the first aspects above.

[0027] Fourthly, embodiments of this application also provide a computer-readable storage medium storing machine-executable instructions, which, when invoked and executed by a processor, cause the processor to perform the method described in any of the first aspects above.

[0028] This application provides a method for determining the edge line of a denture, comprising: acquiring three-dimensional mesh data of the oral cavity obtained by scanning the oral cavity with an oral scanning device; and using an AI model to identify the denture edge line from the three-dimensional mesh data of the oral cavity to obtain the denture edge line. As can be seen from the above description, the method for determining the denture edge line of this application uses an AI model to automatically identify the denture edge line from the three-dimensional mesh data of the oral cavity. This method is highly intelligent, improves the accuracy and robustness of denture edge line identification, and alleviates the technical problems of poor accuracy and low intelligence in the determination process of traditional techniques. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0030] Figure 1 is a flowchart of a method for determining the edge line of a denture according to an embodiment of this application;

[0031] Figure 2 is a schematic diagram of the target three-dimensional myostatic line provided in an embodiment of this application;

[0032] Figure 3 is a schematic diagram of a three-dimensional mesh data sample of an oral cavity provided in an embodiment of this application;

[0033] Figure 4 is a schematic diagram of another oral cavity three-dimensional mesh data sample provided in an embodiment of this application;

[0034] Figure 5 is a schematic diagram of a denture edge line determination device provided in an embodiment of this application;

[0035] Figure 6 is a schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0036] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0037] Traditional techniques have poor accuracy in determining the edge line of dentures and lack intelligence in the determination process.

[0038] Based on this, the method for determining the denture edge line in this application uses an AI model to automatically identify the denture edge line from the three-dimensional mesh data of the oral cavity. This method is highly intelligent and improves the accuracy and robustness of the denture edge line identification.

[0039] To facilitate understanding of this embodiment, a method for determining the edge line of a denture disclosed in this application will first be described in detail.

[0040] Example 1:

[0041] According to an embodiment of this application, an embodiment of a method for determining the edge line of a denture is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0042] Figure 1 is a flowchart of a method for determining the edge line of a denture according to an embodiment of this application. As shown in Figure 1, the method includes the following steps:

[0043] Step S102: Obtain oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral cavity scanning device;

[0044] Specifically, the aforementioned three-dimensional oral mesh data is an intraoral digital impression, which includes the structure of teeth, gums, and surrounding soft tissues. The oral cavity can be the patient's mouth, which may or may not contain teeth. In this application, when acquiring the three-dimensional oral mesh data, scanning the oral cavity (i.e., intraoral scanning) does not require scanning a static oral cavity while it is being stretched. That is, the obtained three-dimensional oral network data is obtained by scanning the patient's oral cavity without stretching, and each point in the oral cavity has only static data in one positional state. The aforementioned oral scanning equipment can specifically be an intraoral scanner and an extraoral scanner.

[0045] Step S104: Use an AI model to identify the denture edge line from the three-dimensional mesh data of the oral cavity to obtain the denture edge line;

[0046] Specifically, the aforementioned AI model can be trained using oral 3D mesh data samples labeled with denture edges, and it has the ability to recognize denture edges; the aforementioned AI model can also be trained using oral 3D mesh data samples labeled with anatomical points, and it has the ability to recognize anatomical points; the aforementioned AI model can also be other models, such as region segmentation models, anatomical point recognition models, etc.; the process will be described in detail below, and will not be repeated here.

[0047] This application provides a method for determining the edge line of a denture, comprising: acquiring three-dimensional mesh data of the oral cavity obtained by scanning the oral cavity with an oral scanning device; and using an AI model to identify the denture edge line from the three-dimensional mesh data of the oral cavity to obtain the denture edge line. As can be seen from the above description, the method for determining the denture edge line of this application uses an AI model to automatically identify the denture edge line from the three-dimensional mesh data of the oral cavity. This method is highly intelligent, improves the accuracy and robustness of denture edge line identification, and alleviates the technical problems of poor accuracy and low intelligence in the determination process of traditional techniques.

[0048] The above provides a brief overview of the method for determining the edge line of the denture in this application. The specific details involved are described in detail below.

[0049] In one optional embodiment of this application, an AI model is used to identify the denture edge lines from the three-dimensional mesh data of the oral cavity, specifically including the following steps:

[0050] (1) The three-dimensional mesh data of the oral cavity is segmented using a region segmentation model to obtain the denture coverage area;

[0051] Specifically, the aforementioned region segmentation model is a deep learning network capable of processing three-dimensional mesh data. In this application, the aforementioned region segmentation model is a deep learning network capable of segmenting oral three-dimensional mesh data into regions. Furthermore, the aforementioned region segmentation model can specifically be a denture overlay region segmentation model or a myostatic region segmentation model. When the region segmentation model is a myostatic region segmentation model, the obtained denture overlay region can specifically be a myostatic region.

[0052] (2) Determine the edge line of the denture based on the denture coverage area.

[0053] Specifically, the denture coverage area includes the myostatic region. Determining the denture edge line based on the denture coverage area involves the following steps:

[0054] The target three-dimensional myostatic line is determined based on the myostatic region, and the denture edge line is determined based on the target three-dimensional myostatic line.

[0055] Specifically, after obtaining the target three-dimensional myostatic line, the equidistant line about 2mm-5mm away from the target three-dimensional myostatic line is determined as the denture edge line.

[0056] The myostatic region can be divided into upper and lower parts by the denture margin. Therefore, the denture coverage area can refer to the entire myostatic region, or specifically the upper part of the myostatic region divided by the denture margin. This upper part includes rigid areas such as the gingiva or teeth. When wearing a complete denture or a removable partial denture, this upper part is exactly covered by the denture. It should be noted that when the denture coverage area refers to the entire myostatic region, the myostatic region can be determined first, then the target three-dimensional myostatic line can be determined, and finally the denture margin can be obtained. When the denture coverage area refers to the upper part of the myostatic region divided by the denture margin, the denture margin can be directly determined through the denture coverage area.

[0057] The target myostatic line refers to the boundary between the myostatic and myodynamic regions; that is, the boundary line of the myostatic region. In prosthetic restoration, this refers to the area related to masticatory muscle activity, which needs to be considered. The myostatic region's mucosa does not move during physiological activities such as chewing and speaking. Correctly identifying these areas helps in designing more stable and comfortable prostheses.

[0058] In this application, no traction is required; default static 3D oral cavity data is used, meaning each point in the oral cavity has only a single data point (static data at one location). A region segmentation model is then used to segment the preprocessed 3D oral cavity mesh data, resulting in the denture coverage area. The final denture edge line is determined based on this coverage area. Specifically, the denture coverage area includes a myostatic region. A target 3D myostatic line is determined based on this region, and then the denture edge line is determined based on this target 3D myostatic line. In this application, the use of a region segmentation model to segment the preprocessed 3D oral cavity mesh data to obtain the myostatic region eliminates the need for patient chewing movements.

[0059] In one optional embodiment of this application, an AI model is used to identify the denture edge line from the oral cavity 3D mesh data. Specifically, this includes the following steps: using an anatomical point recognition model to identify the oral cavity 3D mesh data to obtain anatomical points; and determining the denture edge line based on the anatomical points. Therefore, the AI ​​model automatically generates the denture edge line based on the anatomical points, thus eliminating the need for a region segmentation model.

[0060] In an optional embodiment of this application, after acquiring the three-dimensional mesh data of the oral cavity obtained by the oral cavity scanning device, the method further includes the following steps:

[0061] (1) Preprocess the oral cavity three-dimensional mesh data to obtain the preprocessed oral cavity three-dimensional mesh data;

[0062] Specifically, the preprocessing here can include: data processing (including data denoising and data alignment), mesh simplification, feature calculation (including Laplacian feature calculation and geometric feature calculation), and sparse coding representation. The implementation process is the same as the relevant content below, and will not be repeated here.

[0063] (2) The AI ​​model is used to identify the denture edge line of the preprocessed oral three-dimensional mesh data.

[0064] In an optional embodiment of this application, after acquiring the three-dimensional mesh data of the oral cavity obtained by the oral cavity scanning device and before preprocessing the three-dimensional mesh data of the oral cavity, the method further includes the following steps:

[0065] (1) Determine whether the specified region is completely contained in the three-dimensional mesh data of the oral cavity;

[0066] Specifically, AI can be used to automatically determine whether the oral cavity 3D mesh data contains the entire specified area, and then display a prompt indicating whether the scan is complete. Alternatively, manual methods can be used to determine whether the oral cavity 3D mesh data contains the entire specified area to ensure that the oral cavity 3D mesh data contains the complete myostatic lines.

[0067] The designated areas include: the labial frenulum, the buccal frenulum, the vestibular mucosal fold, the lower border of the zygomatic bone, and the buccal side of the maxillary tuberosity; or, the designated areas include: the labial frenulum, the buccal frenulum, the maxillary tuberosity, the pterygomaxillary notch, and the area 2 mm behind the lesser maxillary fossa.

[0068] (2) If not all areas are included, a prompt message is issued, and the oral cavity 3D mesh data obtained by the oral cavity scanning device is acquired again until the oral cavity 3D mesh data completely includes the specified area. If all areas are included, the oral cavity 3D mesh data is preprocessed to obtain preprocessed oral cavity 3D mesh data. This embodiment enables the oral cavity 3D mesh data obtained by static scanning to include all denture edge lines, which is a point that needs to be specially guaranteed by static scanning. It can ensure that the denture edge lines exist in the oral cavity 3D mesh data, which is the key to subsequent denture edge line recognition.

[0069] In an optional embodiment of this application, the method further includes the following steps:

[0070] (1) Determine the degree of alveolar ridge resorption based on oral cavity three-dimensional mesh data;

[0071] Determining the degree of alveolar ridge resorption allows dentists to accurately assess the precision of the prosthesis margins, aiding in treatment. Specifically, the degree of alveolar ridge prominence can be determined first using three-dimensional oral grid data, and then the degree of resorption can be determined based on this prominence. Alternatively, dentists can manually input the degree of alveolar ridge resorption. During implementation, it's important to consider that gingival recession is often accompanied by alveolar bone resorption, which can affect the myostatic area and occlusal relationship. To accurately assess these changes, dentists will use a mouth mirror and probes for a thorough examination to determine the gingival recession and alveolar bone condition. The degree of alveolar ridge resorption is then determined according to Atwood's grading system.

[0072] When the degree of alveolar ridge resorption is mild (e.g., when the degree of alveolar ridge resorption is at level one or two), it helps to achieve more accurate identification of the myostatic region, the target three-dimensional myostatic line, and the denture margin line.

[0073] (2) Determine the accuracy of the denture edge line based on the degree of alveolar ridge resorption, and output the accuracy to the display screen or voice broadcast.

[0074] Specifically, if the alveolar ridge resorption is at level one or two, the accuracy of the obtained target three-dimensional myostatic line and denture edge line is considered accurate; if the alveolar ridge resorption is greater than level two, the accuracy of the obtained target three-dimensional myostatic line and denture edge line is considered inaccurate. Of course, the accuracy value can also be displayed or announced verbally, such as 90%, 80%, etc.

[0075] In an optional embodiment of this application, determining the target three-dimensional myostatic line based on the myostatic region specifically includes the following steps:

[0076] (1) The edges of the myostatic region are smoothed to obtain a smooth-contoured myostatic region;

[0077] Specifically, the GraphCut algorithm is used to smooth the edges of the myostatic region, resulting in a smooth-contoured myostatic region.

[0078] In implementation, graph cut algorithms such as GraphCut are applied to perform fine smoothing and optimization correction on the edges of the myostatic region to ensure the smoothness and accuracy of the contour, resulting in a smooth myostatic region.

[0079] (2) Draw three-dimensional myostatic lines based on the edges of the smooth myostatic region;

[0080] Specifically, in a smooth-contoured myostatic region, the lower edge contour is the three-dimensional myostatic line.

[0081] (3) Smooth the three-dimensional myostatic lines to obtain the target three-dimensional myostatic lines.

[0082] Specifically, the target smoothing algorithm is first determined based on the morphological characteristics and processing technology of the denture. The target smoothing algorithm includes any of the following: Laplace smoothing algorithm, least squares smoothing algorithm, and curvature-based feature smoothing algorithm. Then, the target smoothing algorithm is used to smooth the three-dimensional myostatic lines to obtain the target three-dimensional myostatic lines, as shown in Figure 2. The green curve is the target three-dimensional myostatic line, which shows two visualized oral cavity three-dimensional mesh data and the corresponding target three-dimensional myostatic lines.

[0083] When determining the target smoothing algorithm, the design requirements and material properties of the restoration (e.g., denture) must be considered. The Laplace smoothing algorithm performs well in global smoothing and is suitable for handling complex surfaces, thus improving the efficiency of toolpath generation. The least squares smoothing algorithm, by reducing data point oscillations, is suitable for denture fabrication scenarios with high precision and fit requirements. Curvature-based feature smoothing algorithms, through fine control of curvature distribution, are suitable for scenarios requiring a close fit between the restoration and oral tissues.

[0084] In one optional embodiment of this application, the training process of the region segmentation model includes the following steps:

[0085] (1) Obtain oral cavity three-dimensional mesh data samples, in which the denture coverage area is marked in the oral cavity three-dimensional mesh data samples;

[0086] Specifically, if the region segmentation model is a myostatic region segmentation model, then the obtained oral cavity 3D mesh data samples are marked with myostatic regions, as shown in Figures 3 and 4. The left image is the original oral cavity 3D mesh data sample (the alveolar ridge resorption degree of the original oral cavity 3D mesh data sample in the left image of Figure 3 is less than that of the original oral cavity 3D mesh data sample in the left image of Figure 4), and the right image is the oral cavity 3D mesh data sample, in which the myostatic regions are marked (the white area in the right image is the myostatic region).

[0087] (2) Preprocess the oral cavity three-dimensional mesh data sample to obtain the preprocessed oral cavity three-dimensional mesh data sample;

[0088] Specifically, the steps include the following:

[0089] 21) Perform data processing on the oral cavity 3D mesh data sample to obtain the processed oral cavity 3D mesh data sample;

[0090] Specifically, the steps include the following:

[0091] 211) Denoise the oral cavity 3D mesh data samples to obtain denoised oral cavity 3D mesh data samples;

[0092] Specifically, this can involve denoising and smoothing some data floating around the oral cavity 3D mesh data samples, small patches on the buccal side (i.e., buccal-lingual data), and other unwanted data to improve the robustness of the model.

[0093] 212) Project the denoised oral cavity 3D mesh data samples in the same direction to obtain a 2D depth image;

[0094] 213) The dental arch curve is obtained by fitting the depth values ​​in the two-dimensional depth image.

[0095] In practice, after projecting in the same direction, a strip-shaped region with a depth value different from other regions is obtained. This strip-shaped region is the alveolar ridge. Fitting these depth data to obtain the dental arch curve is then performed. This fitting of the dental arch curve is for better data alignment, adapting to more types of patient oral structures, improving the generalization ability of the AI ​​model, and solving the model generalization problem caused by differences in oral morphology among different patients. It significantly improves the accuracy of the region segmentation model, enabling accurate identification of denture edges subsequently. Data alignment reduces overfitting by using a unified coordinate system. Without this data processing, the subsequent AI model would be unable to identify denture edges; this step creates a synergistic effect with the subsequent AI model.

[0096] 214) Align the corresponding denoised oral cavity 3D mesh data samples with reference to the dental arch curve to obtain aligned oral cavity 3D mesh data samples;

[0097] Specifically, data alignment reduces overfitting to training data, making it easier to improve the network's generalization ability.

[0098] 215) The aligned oral cavity 3D mesh data sample is used as the oral cavity 3D mesh data sample after data processing.

[0099] 22) Perform vertex optimization on the processed oral cavity 3D mesh data sample to obtain vertex-optimized oral cavity 3D mesh data sample;

[0100] Specifically, by optimizing the algorithm to reduce the number of vertices in the mesh while preserving its geometric features as much as possible, processing efficiency can be improved and computational complexity reduced.

[0101] In implementation, this application focuses on the myostatic region, which is a convex position. The curvature of the convex position becomes faster and more prominent, without reducing the number of vertices in this area. The lower extension is flat, and the curvature in this area is smaller. Vertices in this area can be optimized and deleted to ensure that the shape of the entire tooth model does not change significantly, but the number of vertices decreases.

[0102] 23) Perform feature calculation on the vertex-optimized oral cavity 3D mesh data sample to obtain the feature-calculated oral cavity 3D mesh data sample.

[0103] Specifically, the steps include the following:

[0104] 231) The Laplacian operator of the mesh is used to extract the features of different frequency domains of the oral cavity three-dimensional mesh data samples after vertex optimization, so as to obtain oral cavity three-dimensional mesh data samples with Laplacian features.

[0105] Specifically, the Laplacian operator of the mesh is used to capture and extract the characteristics of the vertex-optimized oral cavity 3D mesh data samples in different domains, providing key information for further analysis.

[0106] 232) Perform multi-scale enhancement processing on oral cavity 3D mesh data samples with Laplacian features to obtain multi-scale oral cavity 3D mesh data samples;

[0107] Specifically, enhancing oral cavity 3D mesh data samples with Laplacian features at different scale levels helps the model learn different levels of detail and enhances its generalization ability.

[0108] 233) Sparse coding is used to represent multi-scale oral three-dimensional mesh data samples to obtain sparsely coded oral three-dimensional mesh data samples;

[0109] Specifically, sparse coding techniques are used to represent multi-scale oral 3D mesh data samples to eliminate redundant features, highlight important information, and improve the interpretability of the model.

[0110] 234) Calculate the geometric features of the sparsely encoded oral 3D mesh data sample to obtain an oral 3D mesh data sample with geometric features, wherein the geometric features include: surface curvature and normal vector;

[0111] Specifically, geometric features can enrich the model's input information and enhance its understanding of complex structures.

[0112] 235) Use the oral cavity 3D mesh data sample with geometric features as the oral cavity 3D mesh data sample after feature calculation.

[0113] 24) Use the oral cavity 3D mesh data sample after feature calculation as the preprocessed oral cavity 3D mesh data sample.

[0114] (3) The original region segmentation model was trained using the preprocessed oral cavity three-dimensional mesh data samples to obtain the region segmentation model.

[0115] Specifically, the aforementioned original region segmentation model focuses on a series of deep learning models specifically designed for processing 3D mesh data. These models include: PointNet, which directly manipulates point cloud data; Graph CNNs and MeshCNN, which utilize graph convolutional networks to process mesh topology; multi-view models that analyze 3D information from multiple perspectives; Spectral CNN, based on spectral theory; and DiffusionNet, designed for geometric data. The selection and decision-making process can be comprehensively considered based on the needs of actual application scenarios, such as computational resource consumption and real-time requirements.

[0116] In one optional embodiment of this application, after obtaining the denture edge line through the AI ​​model, the denture edge line is displayed on the interactive interface. The user can adjust the denture edge line on the interactive interface. During the adjustment process, since the user is adjusting the movement of the denture edge line on a two-dimensional display interface, if the denture edge line is adjusted directly according to the user's two-dimensional instructions, it is easy for the denture edge line to move too much, deviating from the myostatic zone or getting too close to the myodynamic zone. Furthermore, if the complete denture or removable partial denture is designed based on a denture edge line that is deviated from the myostatic zone or too close to the myodynamic zone, the denture is prone to displacement during wear, or may collide during chewing and other physiological movements, causing discomfort to the patient. Simultaneously, since the patient's oral environment is not a regular cylinder, if the denture edge line is simply translated or enlarged / reduced according to the user's two-dimensional instructions, the denture edge line may deviate from the model surface, resulting in a discrepancy between the denture edge line and the patient's actual oral condition, making subsequent denture design impossible.

[0117] To address the aforementioned issues, after obtaining the denture edge line, the method further includes the following steps: (1) when a first instruction is detected, determining the first pose change of the denture edge line relative to its initial position, wherein the first instruction is an instruction from the user to adjust the pose of the denture edge line in the oral cavity three-dimensional mesh data; (2) based on the first pose change and preset reference conditions, determining the first adjusted pose of the denture edge line, and updating and displaying the pose of the denture edge line based on the first adjusted pose of the denture edge line; wherein, when a first pose change is detected that causes the denture edge line to not conform to the preset reference conditions, the pose of the denture edge line is adaptively updated according to the preset reference conditions, or, the pose of the denture edge line is not updated and the result of user reconfirmation is obtained and the pose of the denture edge line is adjusted according to the result of user reconfirmation; and / or when a first adjusted pose is detected that causes the denture edge line to not conform to the preset reference conditions, the pose of the denture edge line is adaptively updated according to the preset reference conditions, or, the pose of the denture edge line is not updated and the result of user reconfirmation is obtained and the pose of the denture edge line is adjusted according to the result of user reconfirmation.

[0118] It's understandable that not updating the denture edge pose means not moving or shifting the denture edge, and not updating the displayed pose after any movement or shift. Updating the denture edge pose can be understood as continuing to move or shift the denture edge, and updating the displayed pose after any movement or shift. Adjusting the denture edge pose based on user confirmation means either not updating the denture edge pose or updating it based on the user's choice. When not updating the denture edge pose, a prompt or other notification can be displayed to provide feedback to the user.

[0119] Therefore, in this embodiment, the first adjustment pose can be recalculated based on the first pose change, including the movement distance of the denture edge line relative to its initial placement pose and / or the offset angle of the denture edge line relative to its initial placement pose, in the user's first instruction. Combined with the outer surface of the oral cavity three-dimensional mesh data, the preset reference conditions (medical reference requirements) for the denture coverage area or simulated physiological movements are determined. Some adjustment instructions in the first pose change are ignored and some adjustment instructions in the first pose change are executed. That is, instructions in the first pose change that do not meet the medical reference requirements are ignored, and instructions in the first pose change that meet the medical reference requirements are executed. This ensures that the denture edge line pose (first adjustment pose) on the display interface always meets the preset reference conditions, that is, meets the basic medical requirements, such as the denture edge line should be within the denture coverage area, or conforms to simulated physiological movements, such as the denture edge line not moving or the denture edge line moving within the range during physiological movements such as chewing or mandibular movement.

[0120] Specifically, the first pose change can be decomposed according to preset reference conditions. Some or all of the instructions in the first pose change that meet the preset reference conditions are determined as the first adjustment pose of the denture edge line, while some or all of the instructions in the first pose change that do not meet the preset reference conditions are ignored. For example, the preset reference conditions may include: the denture edge line should conform to the outer surface of the oral cavity three-dimensional mesh data, the denture edge line should be within the denture coverage area, or the denture edge line should conform to one or more of the simulated physiological movements.

[0121] For example, in the first instruction, if the user clicks the mouse to move the denture edge line horizontally or diagonally by an X distance, and this X distance causes the denture edge line to not conform to the outer surface of the 3D oral cavity mesh data, not be within the denture coverage area, or not conform to the simulated physiological movement, then the instruction to move the denture edge line horizontally or diagonally by an X distance will be ignored and not executed. This indicates that the first pose change does not meet the preset reference conditions. In this case, there are two operating methods: First, the computer automatically enlarges or reduces the first pose change according to a preset ratio to make it conform to the simulated physiological movement or be within the denture coverage area, and determines it as the first adjustment pose, displaying the updated denture edge line; Second, the adjusted denture edge line is not displayed initially, and a prompt box is issued, indicating that this adjustment may have problems, asking the user to confirm again. Based on the user's confirmation, the first adjustment pose is determined; if the user indicates "confirm," this adjustment method is adopted as the first adjustment pose, and the denture edge line pose is updated according to the user's instruction; if the user indicates "abandon modification," the first adjustment pose is 0, and the denture edge line pose is not updated according to the user's instruction.

[0122] For example, in the first instruction, the user clicks the mouse to move the denture edge line diagonally by a distance X. This distance X is decomposed into a vertical movement (as shown in the Z direction in Figure 2, vertical movement refers to moving up and down along the gingival surface) distance B and a horizontal movement (as shown in the X direction in Figure 2, horizontal movement refers to moving forward and backward along the normal surface of the oral cavity 3D mesh data) distance C. The horizontal movement distance C is ignored and not executed, while the vertical movement distance B is executed, which is equivalent to projecting onto the vertical plane (as shown in the XZ plane in Figure 2). Therefore, the first adjustment pose of the denture edge line is to move the denture edge line up and down by a distance B along the gingival surface. Based on the denture edge line after the vertical movement distance B and the outer surface of the oral cavity 3D mesh data, the latest denture edge line is automatically calculated and generated, so that the denture edge line fits the outer surface of the model.

[0123] For example, after determining the first adjustment posture, it can be re-evaluated to determine whether it conforms to simulated physiological movement or is located within the denture coverage area. If so, it means the first adjustment posture meets medical reference conditions, and adjustments can be made according to the first adjustment posture, with the adjusted denture edge line displayed on the interactive interface. If not, it means the first adjustment posture does not meet medical reference conditions, and there are two possible operation methods: First, the computer automatically enlarges or reduces the first adjustment posture according to a preset ratio to make it conform to simulated physiological movement or be located within the denture coverage area; Second, the adjusted denture edge line is not displayed initially, and a prompt box is issued, indicating to the user that such adjustment may have problems, and asking the user to confirm again "whether to use this adjustment method to modify". If the user indicates "confirm", this adjustment method will be used to modify, and the denture edge line posture will be updated according to the user's instructions. If the user indicates "abandon modification", the denture edge line posture will not be updated according to the user's instructions.

[0124] In one embodiment, based on a first instruction, the denture edge line can be controlled to rotate relative to the current mouse coordinates to the pose indicated by the first instruction. At this time, the interactive interface displays the denture edge line at the mouse click position. Simultaneously, the angle or distance of rotation of the denture edge line around the denture edge line is determined by projecting the mouse movement distance onto a vertical plane (the XZ plane in Figure 2).

[0125] It should be noted that simulated physiological motion refers to the simulated physiological motion automatically generated by inputting oral cavity 3D mesh data into a motion simulation deep learning model. This simulated physiological motion can be selectively displayed on the interactive interface based on user commands. When the user chooses to display the simulated physiological motion, the oral cavity 3D mesh data on the interface will change in accordance with the simulated physiological motion, allowing the user to visually observe whether the denture edge line is appropriate and to move or adjust the denture edge line. When the user chooses not to display the simulated physiological motion on the interactive interface, the interface will directly output the computer's judgment on whether the denture edge line conforms to the simulated physiological motion result.

[0126] The simulated physiological movements automatically generated by the deep learning model for motion simulation can be generated based on the average movement of multiple patient training samples, or based on mandibular movement trajectories and chewing movement trajectories obtained by CBCT (Cone Beam Computed Tomography) equipment, facial scanners, extraoral scanners, or intraoral scanners.

[0127] In an optional embodiment of this application, the method further includes the following steps:

[0128] (1) Generate a three-dimensional denture model based on the denture edge line and oral cavity three-dimensional mesh data, and send the three-dimensional denture model to the 3D printing device configured for printing;

[0129] (2) Receive user requests for modifying the three-dimensional denture model in real time;

[0130] (3) Based on the user request, the denture edge line and the oral cavity 3D mesh data, output the revised denture edge line and / or output the revised 3D denture model.

[0131] Therefore, this application can quickly generate a three-dimensional denture model and 3D print a solid denture after obtaining the denture edge line through an AI model. The user can try on the solid denture, and the denture edge line or three-dimensional denture model can be directly adjusted according to the user's trial results to obtain a denture that better meets the user's needs.

[0132] In summary, the method for determining the edge line of dentures in this application uses an AI model to segment the three-dimensional mesh data of the oral cavity. It is highly robust and will not be affected by the diversity of dental and jaw morphology or the quality of the mesh surface. This provides solid technical support for the subsequent design and manufacturing process of dentures and improves the efficiency of doctors' clinical diagnosis and treatment.

[0133] This application has the following advantages:

[0134] The denture edge line is determined through static scanning and AI modeling. A neural network is used for the identification of complete denture edge lines, and deep learning technology is used to learn complex patterns from a large amount of data, which ensures better robustness for different dentition shapes, improves the accuracy of myostatic line identification, and reduces human error.

[0135] The fully automated recognition process can significantly reduce the time dental technicians spend recognizing myostatic lines, thus improving overall work efficiency.

[0136] It can be processed directly on the digital impression, avoiding complicated steps such as plaster mold taking.

[0137] The process for determining the denture edge line described in this application is simpler. It does not require the doctor to pull the patient's mouth, requires no operation, and omits the pulling step, yet achieves the same effect. It fully demonstrates how to intelligently and comfortably determine the accurate denture edge line, confirm the accuracy of the denture edge line obtained by the AI ​​model, and quickly manufacture and adjust the three-dimensional denture model based on the accurate denture edge line.

[0138] Example 2:

[0139] This application also provides a denture edge line determination device, which is mainly configured to perform the denture edge line determination method provided in Embodiment 1 of this application. The denture edge line determination device provided in this application will be described in detail below.

[0140] Figure 5 is a schematic diagram of a denture edge line determination device according to an embodiment of this application. As shown in Figure 5, the device mainly includes: an acquisition unit 10 and a denture edge line recognition unit 20, wherein:

[0141] The acquisition unit is configured to acquire oral cavity three-dimensional mesh data obtained by an oral cavity scanning device scanning the oral cavity;

[0142] The denture edge line recognition unit is configured to use an AI model to recognize the denture edge line from the three-dimensional mesh data of the oral cavity, thereby obtaining the denture edge line.

[0143] In this application embodiment, a denture edge line determination device is provided, comprising: acquiring three-dimensional mesh data of the oral cavity obtained by scanning the oral cavity with an oral scanning device; and using an AI model to identify the denture edge line from the three-dimensional mesh data of the oral cavity to obtain the denture edge line. As can be seen from the above description, the denture edge line determination device of this application uses an AI model to automatically identify the denture edge line from the three-dimensional mesh data of the oral cavity, which is highly intelligent, improves the accuracy and robustness of denture edge line identification, and alleviates the technical problems of poor accuracy and low intelligence in the determination process of traditional technologies.

[0144] Optionally, the denture edge line recognition unit is further configured to: segment the oral cavity three-dimensional mesh data using a region segmentation model to obtain the denture coverage area; and determine the denture edge line based on the denture coverage area.

[0145] Optionally, the denture coverage area includes a myostatic region, and the denture edge line recognition unit is further configured to: determine a target three-dimensional myostatic line based on the myostatic region, and determine the denture edge line based on the target three-dimensional myostatic line.

[0146] Optionally, the device is also configured to: preprocess the oral cavity three-dimensional mesh data to obtain preprocessed oral cavity three-dimensional mesh data; and use an AI model to identify the denture edge line of the preprocessed oral cavity three-dimensional mesh data to obtain the denture edge line.

[0147] Optionally, the device is further configured to: determine whether the oral cavity three-dimensional mesh data contains the specified area; if not, issue a prompt message and reacquire the oral cavity three-dimensional mesh data obtained by the oral cavity scanning device until the oral cavity three-dimensional mesh data contains the specified area.

[0148] Optionally, the device is also configured to: determine the degree of alveolar ridge resorption based on oral cavity three-dimensional mesh data; determine the accuracy of the denture margin line based on the degree of alveolar ridge resorption; and output the accuracy to a display screen or voice broadcast.

[0149] Optionally, the denture edge line recognition unit is further configured to: perform smoothing optimization processing on the edge of the myostatic region to obtain a smooth contour myostatic region; draw a three-dimensional myostatic line based on the edge of the smooth contour myostatic region; and perform smoothing processing on the three-dimensional myostatic line to obtain the target three-dimensional myostatic line.

[0150] Optionally, the denture edge line recognition unit is also configured to: use a graph cut algorithm to perform smoothing optimization on the edge of the myostatic region to obtain a myostatic region with a smooth contour.

[0151] Optionally, the denture edge line recognition unit is further configured to: determine a target smoothing algorithm based on the morphological characteristics and processing technology of the denture, wherein the target smoothing algorithm includes any of the following: Laplace smoothing algorithm, least squares smoothing algorithm, and curvature-based feature smoothing algorithm; and use the target smoothing algorithm to smooth the three-dimensional myostatic line to obtain the target three-dimensional myostatic line.

[0152] Optionally, the device is further configured to: acquire oral cavity three-dimensional mesh data samples, wherein the oral cavity three-dimensional mesh data samples are marked with denture coverage areas; preprocess the oral cavity three-dimensional mesh data samples to obtain preprocessed oral cavity three-dimensional mesh data samples; and use the preprocessed oral cavity three-dimensional mesh data samples to train the original region segmentation model to obtain a region segmentation model.

[0153] Optionally, the device is further configured to: process oral cavity three-dimensional mesh data samples to obtain processed oral cavity three-dimensional mesh data samples; optimize the vertex of the processed oral cavity three-dimensional mesh data samples to obtain vertex-optimized oral cavity three-dimensional mesh data samples; perform feature calculation on the vertex-optimized oral cavity three-dimensional mesh data samples to obtain feature-calculated oral cavity three-dimensional mesh data samples; and use the feature-calculated oral cavity three-dimensional mesh data samples as preprocessed oral cavity three-dimensional mesh data samples.

[0154] Optionally, the device is further configured to: denoise the oral cavity three-dimensional mesh data samples to obtain denoised oral cavity three-dimensional mesh data samples; project the denoised oral cavity three-dimensional mesh data samples in the same direction to obtain a two-dimensional depth image; fit the dental arch curve based on the depth values ​​in the two-dimensional depth image; align the corresponding denoised oral cavity three-dimensional mesh data samples with reference to the dental arch curve to obtain aligned oral cavity three-dimensional mesh data samples; and use the aligned oral cavity three-dimensional mesh data samples as the processed oral cavity three-dimensional mesh data samples.

[0155] Optionally, the device is further configured to: extract features in different frequency domains of the vertex-optimized oral 3D mesh data samples using the Laplacian operator of the mesh, to obtain oral 3D mesh data samples with Laplacian features; perform multi-scale enhancement processing on the oral 3D mesh data samples with Laplacian features to obtain multi-scale oral 3D mesh data samples; represent the multi-scale oral 3D mesh data samples using sparse coding to obtain sparsely coded oral 3D mesh data samples; calculate the geometric features of the sparsely coded oral 3D mesh data samples to obtain oral 3D mesh data samples with geometric features, wherein the geometric features include: surface curvature and normal vector; and use the oral 3D mesh data samples with geometric features as oral 3D mesh data samples after feature calculation.

[0156] Optionally, the device is further configured to: upon detecting a first instruction, determine a first pose change of the denture edge line relative to its initial position, wherein the first instruction is a user instruction to adjust the pose of the denture edge line in the oral cavity three-dimensional mesh data; based on the first pose change and preset reference conditions, determine a first adjusted pose of the denture edge line, and update and display the pose of the denture edge line based on the first adjusted pose of the denture edge line, wherein the preset reference conditions include: the denture edge line conforming to the outer surface of the oral cavity three-dimensional mesh data, the denture edge line conforming to simulated physiological movement, or the denture edge line being located within the denture coverage area. One or more; wherein, when a first pose change is detected that causes the denture edge line to not conform to the preset reference conditions, the pose of the denture edge line is adaptively updated according to the preset reference conditions, or, the pose of the denture edge line is not updated and the result of user reconfirmation is obtained and the pose of the denture edge line is adjusted according to the result of user reconfirmation; and / or when a first adjusted pose is detected that causes the denture edge line to not conform to the preset reference conditions, the pose of the denture edge line is adaptively updated according to the preset reference conditions, or, the pose of the denture edge line is not updated and the result of user reconfirmation is obtained and the pose of the denture edge line is adjusted according to the result of user reconfirmation.

[0157] Optionally, the device is also configured to: generate a three-dimensional denture model based on the denture edge line and oral cavity three-dimensional mesh data, and send the three-dimensional denture model to a 3D printing device configured for printing; receive user requests for modifying the three-dimensional denture model in real time; and output revised denture edge lines and / or revised three-dimensional denture models based on user requests, denture edge lines, and oral cavity three-dimensional mesh data.

[0158] The device provided in this application embodiment has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0159] As shown in Figure 6, an electronic device 600 provided in this application embodiment includes: a processor 601, a memory 602 and a bus. The memory 602 stores machine-readable instructions that can be executed by the processor 601. When the electronic device is running, the processor 601 and the memory 602 communicate through the bus. The processor 601 executes the machine-readable instructions to perform the steps of the above-described method for determining the edge line of a denture.

[0160] Specifically, the memory 602 and processor 601 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 601 runs the computer program stored in the memory 602, it can execute the above-mentioned method for determining the edge line of the denture.

[0161] Processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 601 or by instructions in software form. The processor 601 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 602, and processor 601 reads the information from memory 602 and, in conjunction with its hardware, completes the steps of the above method.

[0162] Corresponding to the above-described method for determining the edge line of a denture, this application also provides a computer-readable storage medium storing machine-executable instructions. When the machine-executable instructions are called and run by a processor, the machine-executable instructions cause the processor to perform the steps of the above-described method for determining the edge line of a denture.

[0163] The denture edge line determination device provided in this application embodiment can be specific hardware on a device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this application embodiment are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0164] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0165] For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0166] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0167] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0168] If the aforementioned function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the denture edge line determination method described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0169] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0170] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims. Industrial applicability

[0171] This application provides a method for determining the edge line of a denture, comprising: acquiring three-dimensional mesh data of the oral cavity obtained by scanning the oral cavity with an oral scanning device; and using an AI model to identify the denture edge line from the three-dimensional mesh data of the oral cavity to obtain the denture edge line. As can be seen from the above description, the method for determining the denture edge line of this application uses an AI model to automatically identify the denture edge line from the three-dimensional mesh data of the oral cavity. This method is highly intelligent, improves the accuracy and robustness of denture edge line identification, and alleviates the technical problems of poor accuracy and low intelligence in the determination process of traditional techniques.

Claims

1. A method for determining a denture margin line, comprising: obtaining three-dimensional mesh data of a mouth scanned by a mouth scanning device; recognizing a denture margin line from the three-dimensional mesh data of the mouth by using an AI model.

2. The method of claim 1, wherein, The step of recognizing the denture margin line from the three-dimensional mesh data of the mouth by using the AI model comprises: segmenting the three-dimensional mesh data of the mouth by using a region segmentation model to obtain a denture coverage region; determining the denture margin line based on the denture coverage region.

3. The method of claim 2, wherein, The denture coverage region comprises a myostatic region, and the step of determining the denture margin line based on the denture coverage region comprises: determining a target three-dimensional myostatic line based on the myostatic region, and determining the denture margin line based on the target three-dimensional myostatic line.

4. The method according to any one of claims 1 to 3, wherein, After obtaining the three-dimensional mesh data of the mouth scanned by the mouth scanning device, the method further comprises: preprocessing the three-dimensional mesh data of the mouth to obtain preprocessed three-dimensional mesh data of the mouth; recognizing the denture margin line from the preprocessed three-dimensional mesh data of the mouth by using the AI model.

5. The method of claim 4, wherein, After obtaining the three-dimensional mesh data of the mouth scanned by the mouth scanning device, before preprocessing the three-dimensional mesh data of the mouth, the method further comprises: determining whether the three-dimensional mesh data of the mouth contains all specified regions; if not, issuing a prompt message and re-obtaining the three-dimensional mesh data of the mouth scanned by the mouth scanning device until the three-dimensional mesh data of the mouth contains all specified regions.

6. The method according to any one of claims 1 to 5, wherein, The method further comprises: determining a degree of alveolar ridge absorption based on the three-dimensional mesh data of the mouth; determining an accuracy of the denture margin line based on the degree of alveolar ridge absorption, and outputting the accuracy to a display screen or a voice broadcast.

7. The method of claim 3, wherein, The step of determining a target three-dimensional myostatic line based on the myostatic region comprises: smoothing and optimizing an edge of the myostatic region to obtain a myostatic region with smooth contours; drawing a three-dimensional myostatic line based on the edge of the myostatic region with smooth contours; smoothing the three-dimensional myostatic line to obtain the target three-dimensional myostatic line.

8. The method of claim 7, wherein, The step of smoothing and optimizing the edge of the myostatic region comprises: smoothing and optimizing the edge of the myostatic region by using a graph cut algorithm to obtain the myostatic region with smooth contours. Alternatively, the step of smoothing the three-dimensional myostatic line comprises: determining a target smoothing algorithm based on the morphological characteristics and processing technology of the denture, wherein the target smoothing algorithm comprises any one of the following: Laplace smoothing algorithm, least squares smoothing algorithm, and curvature-based feature smoothing algorithm; smoothing the three-dimensional myostatic line by using the target smoothing algorithm to obtain the target three-dimensional myostatic line.

9. The method of claim 2, wherein, The training process of the region segmentation model comprises: obtaining three-dimensional mesh data samples of a mouth, wherein the three-dimensional mesh data samples of the mouth are labeled with a denture coverage region; preprocessing the three-dimensional mesh data samples of the mouth to obtain preprocessed three-dimensional mesh data samples of the mouth; The original region segmentation model is trained by using the pretreated oral cavity three-dimensional mesh data sample, and the region segmentation model is obtained.

10. The method of claim 9, wherein, The pretreatment of the oral cavity three-dimensional mesh data sample comprises: The data processing of the oral cavity three-dimensional mesh data sample comprises: The vertex optimization of the data-processed oral cavity three-dimensional mesh data sample comprises: The feature calculation of the vertex-optimized oral cavity three-dimensional mesh data sample comprises: The feature-calculated oral cavity three-dimensional mesh data sample is taken as the pretreated oral cavity three-dimensional mesh data sample.

11. The method of claim 10, wherein, The data processing of the oral cavity three-dimensional mesh data sample comprises: The data denoising of the oral cavity three-dimensional mesh data sample comprises: The dental arch curve is fitted according to the depth value in the two-dimensional depth image. The data alignment of the corresponding denoised oral cavity three-dimensional mesh data sample is performed with reference to the dental arch curve, and the aligned oral cavity three-dimensional mesh data sample is obtained. The aligned oral cavity three-dimensional mesh data sample is taken as the data-processed oral cavity three-dimensional mesh data sample. The feature calculation of the vertex-optimized oral cavity three-dimensional mesh data sample comprises:

12. The method of claim 10, wherein, The features of different frequency domains of the vertex-optimized oral cavity three-dimensional mesh data sample are extracted by using the Laplacian operator of the mesh, and the oral cavity three-dimensional mesh data sample with Laplacian features is obtained; The multi-scale oral cavity three-dimensional mesh data sample is obtained by performing multi-scale enhancement processing on the oral cavity three-dimensional mesh data sample with Laplacian features; The multi-scale oral cavity three-dimensional mesh data sample is represented by using sparse coding, and the oral cavity three-dimensional mesh data sample represented by sparse coding is obtained; The geometric features of the oral cavity three-dimensional mesh data sample represented by sparse coding are calculated, and the oral cavity three-dimensional mesh data sample with geometric features is obtained, wherein the geometric features comprise surface curvature and normal vector; The oral cavity three-dimensional mesh data sample with geometric features is taken as the feature-calculated oral cavity three-dimensional mesh data sample. After the AI model is used to identify the denture edge line of the oral cavity three-dimensional mesh data, the method further comprises:

13. The method according to any one of claims 1 to 12, wherein, When the first instruction is monitored, the first pose change of the denture edge line relative to the initial position is determined, wherein the first instruction is an instruction for a user to adjust the pose of the denture edge line in the oral cavity three-dimensional mesh data; ​ determine a first adjusted pose of the denture margin line based on the first pose change and a preset reference condition, and update and display the pose of the denture margin line based on the first adjusted pose of the denture margin line, wherein the preset reference condition comprises one or more of that the denture margin line is fitted to an outer surface of the three-dimensional mesh data of the oral cavity, that the denture margin line conforms to a simulated physiological movement, or that the denture margin line is located within a denture coverage area; wherein, when the first pose change is detected to cause the denture margin line to not conform to the preset reference condition, the pose of the denture margin line is adaptively updated according to the preset reference condition, or the pose of the denture margin line is not updated and a result of user reconfirmation is obtained and the pose of the denture margin line is adjusted according to the result of user reconfirmation; and / or when the first adjusted pose is detected to cause the denture margin line to not conform to the preset reference condition, the pose of the denture margin line is adaptively updated according to the preset reference condition, or the pose of the denture margin line is not updated and a result of user reconfirmation is obtained and the pose of the denture margin line is adjusted according to the result of user reconfirmation.

14. The method of any one of claims 1 to 13, wherein, The method further comprises: generating a three-dimensional denture model according to the denture margin line and the three-dimensional mesh data of the oral cavity, and sending the three-dimensional denture model to a 3D printing device configured to print; receiving a user request for modifying the three-dimensional denture model in real time; outputting a revised denture margin line and / or outputting a revised three-dimensional denture model according to the user request, the denture margin line and the three-dimensional mesh data of the oral cavity.

15. The method of claim 1, wherein, The oral cavity contains part of the teeth or does not contain teeth.

16. The method of claim 2, wherein, The denture coverage area comprises a myotatic region.

17. The method of claim 5, wherein, The specified area comprises a labial frenulum, a buccal frenulum, a vestibular mucosa fold, a lower edge line of a zygomatic bone, a buccal side of a maxillary tuberosity, or the specified area comprises a labial frenulum, a buccal frenulum, a maxillary tuberosity, an alar maxillary notch, and a region 2 mm behind a maxillary palatine fossa. The method further comprises: if all of the specified areas are contained in the three-dimensional mesh data of the oral cavity, pre-processing the three-dimensional mesh data of the oral cavity to obtain pre-processed three-dimensional mesh data of the oral cavity. 18.A denture margin line determination apparatus, comprising: an acquisition unit configured to acquire three-dimensional mesh data of an oral cavity obtained by an oral scanning device scanning the oral cavity; a denture margin line identification unit configured to identify a denture margin line from the three-dimensional mesh data of the oral cavity using an AI model. 19.An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1 to 17 when executing the computer program. 20.A computer readable storage medium storing machine executable instructions, wherein the machine executable instructions, when invoked and executed by a processor, cause the processor to perform the method of any one of claims 1 to 17.

Images