False tooth edge line determination method and device, electronic equipment and storage medium

Abstract

The invention provides a false tooth edge line determination method and device, electronic equipment and a storage medium, and belongs to the technical field of false tooth repair, and the method comprises the following steps: obtaining oral cavity three-dimensional grid data; and carrying out false tooth edge line identification on the oral cavity three-dimensional grid data by adopting an AI model to obtain a false tooth edge line. According to the false tooth edge line determination method, the AI model is adopted to carry out false tooth edge line automatic identification on the oral cavity three-dimensional grid data, the intelligence is high, and the accuracy and robustness of false tooth edge line identification are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of denture restoration, and in particular to a method, device, electronic equipment and storage medium for determining a denture edge line. Background Art

[0002] In dentistry, especially when fabricating complete or removable partial dentures, identification of the myostatic line is crucial to ensure retention and function of the denture.

[0003] At present, when making complete dentures or removable partial dentures in oral clinics, doctors usually take manual impressions to perform edge shaping to obtain the edge lines of the dentures. However, this manual impression method has some disadvantages. For example, it may cause discomfort to patients, and the efficiency of impression taking is low. At the same time, it has high technical requirements for doctors, and doctors are required to draw lines manually based on the impressions, resulting in greater uncertainty in the denture edge lines obtained by different doctors, which are greatly affected by human subjective factors. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, electronic device and storage medium for determining a denture edge line, so as to alleviate the technical problems of poor accuracy of the denture edge line determined by traditional technology and low intelligence of the determination process.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining a denture edge line, comprising: Acquire oral three-dimensional mesh data obtained by scanning the oral cavity with an oral scanning device; The AI ​​model is used to identify the denture edge line of the oral three-dimensional grid data to obtain the denture edge line.

[0006] Furthermore, the AI ​​model is used to identify the denture edge line of the oral three-dimensional mesh data, including: Using a regional segmentation model to segment the oral three-dimensional mesh data to obtain a denture coverage area; The denture margin line is determined based on the denture coverage area.

[0007] Further, the denture coverage area includes: a myostatic area, and determining the denture edge line based on the denture coverage area includes: A target three-dimensional myostatic line is determined based on the myostatic area, and a denture edge line is determined based on the target three-dimensional myostatic line.

[0008] Furthermore, after acquiring the three-dimensional mesh data of the oral cavity obtained by scanning the oral cavity with the oral scanning device, the method further includes: Preprocessing the oral cavity three-dimensional mesh data to obtain preprocessed oral cavity three-dimensional mesh data; The AI ​​model is used to identify the denture edge line of the preprocessed oral three-dimensional mesh data to obtain the denture edge line.

[0009] Furthermore, after acquiring the oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral scanning device, and before preprocessing the oral cavity three-dimensional mesh data, the method further includes: Determining whether the oral three-dimensional mesh data completely includes the designated area; If not all of them are included, a prompt message is issued, and the oral three-dimensional mesh data obtained by scanning the oral cavity with an oral scanning device is re-acquired until the designated area is completely included in the oral three-dimensional mesh data.

[0010] Furthermore, the method further comprises: determining the degree of alveolar ridge resorption according to the oral three-dimensional mesh data; The accuracy of the denture edge line is determined according to the degree of alveolar ridge absorption, and the accuracy is output to a display screen or voice broadcast.

[0011] Further, determining a target three-dimensional myostatic line based on the myostatic area includes: Performing a smoothing optimization process on the edge of the myostatic area to obtain a myostatic area with a smooth contour; Drawing a three-dimensional myostatic line according to the edge of the myostatic area with a smooth contour; The three-dimensional muscle static line is smoothed to obtain the target three-dimensional muscle static line.

[0012] Furthermore, the edge of the myostatic area is subjected to a smoothing optimization process, including: A graph cut algorithm is used to perform smoothing optimization processing on the edge of the myostatic region to obtain the myostatic region with a smooth contour; Alternatively, the three-dimensional myostatic lines are smoothed, including: Determine a target smoothing algorithm according to the morphological characteristics and processing technology of the denture, wherein the target smoothing algorithm includes any one of the following: a Laplace smoothing algorithm, a least squares smoothing algorithm, and a curvature-based feature smoothing algorithm; The target smoothing algorithm is used to smooth the three-dimensional muscle static line to obtain the target three-dimensional muscle static line.

[0013] Furthermore, the training process of the region segmentation model includes: Acquire an oral three-dimensional mesh data sample, wherein the oral three-dimensional mesh data sample is marked with a denture coverage area; Preprocessing the oral cavity three-dimensional mesh data sample to obtain a preprocessed oral cavity three-dimensional mesh data sample; The preprocessed oral three-dimensional mesh data samples are used to train the original region segmentation model to obtain the region segmentation model.

[0014] Furthermore, the oral three-dimensional mesh data sample is preprocessed, including: Performing data processing on the oral cavity three-dimensional mesh data sample to obtain a data-processed oral cavity three-dimensional mesh data sample; Performing vertex optimization on the oral three-dimensional mesh data sample after the data processing to obtain the oral three-dimensional mesh data sample after vertex optimization; Performing feature calculation on the oral cavity three-dimensional mesh data sample after vertex optimization to obtain the oral cavity three-dimensional mesh data sample after feature calculation; The oral three-dimensional mesh data sample after the feature calculation is used as the oral three-dimensional mesh data sample after the preprocessing.

[0015] Furthermore, data processing is performed on the oral three-dimensional mesh data sample, including: Performing data denoising on the oral cavity three-dimensional mesh data sample to obtain a denoised oral cavity three-dimensional mesh data sample; Projecting the denoised oral three-dimensional mesh data samples in the same direction to obtain a two-dimensional depth image; Obtaining a dental arch curve by fitting the depth values ​​in the two-dimensional depth image; Performing data alignment on the corresponding denoised oral three-dimensional mesh data samples with reference to the dental arch curve to obtain aligned oral three-dimensional mesh data samples; The aligned oral three-dimensional mesh data samples are used as the oral three-dimensional mesh data samples after data processing.

[0016] Furthermore, feature calculation is performed on the oral cavity three-dimensional mesh data sample after vertex optimization, including: Using the Laplace operator of the grid to extract the features of different frequency domains of the oral three-dimensional grid data sample after the vertex optimization, to obtain the oral three-dimensional grid data sample with Laplace features; Performing multi-scale enhancement processing on the oral three-dimensional mesh data sample with Laplace features to obtain a multi-scale oral three-dimensional mesh data sample; Using sparse coding to represent the multi-scale oral three-dimensional mesh data samples to obtain sparsely coded oral three-dimensional mesh data samples; Calculating the geometric features of the oral three-dimensional mesh data sample represented by the sparse coding to obtain the oral three-dimensional mesh data sample with geometric features, wherein the geometric features include: surface curvature and normal vector; The oral three-dimensional mesh data sample with the geometric features is used as the oral three-dimensional mesh data sample after the feature calculation.

[0017] Furthermore, after the denture edge line is identified by using the AI ​​model to the oral three-dimensional mesh data to obtain the denture edge line, the method further includes: When a first instruction is detected, determining a first posture change of the denture edge line relative to the initial position, wherein the first instruction is an instruction for a user to adjust the posture of the denture edge line in the three-dimensional mesh data of the oral cavity; Based on the first posture change and preset reference conditions, determine a first adjusted posture of the denture edge line, and update and display the posture of the denture edge line based on the first adjusted posture of the denture edge line, wherein the preset reference conditions include: the denture edge line fits the outer surface of the oral three-dimensional mesh data, the denture edge line conforms to simulated physiological movement, or the denture edge line is located in the denture coverage area. One or more; Wherein, when it is detected that the first posture change makes the denture edge line not meet the preset reference condition, the posture of the denture edge line is adaptively updated according to the preset reference condition, or, the posture of the denture edge line is not updated and the result of user reconfirmation is obtained and the posture of the denture edge line is adjusted according to the result of user reconfirmation; and / or When it is detected that the first adjustment posture makes the denture edge line not meet the preset reference condition, the posture of the denture edge line is adaptively updated according to the preset reference condition, or the posture of the denture edge line is not updated and the result of user re-confirmation is obtained and the posture of the denture edge line is adjusted according to the result of user re-confirmation.

[0018] Furthermore, the method further comprises: Generate a three-dimensional denture model according to the denture edge line and the oral three-dimensional mesh data, and send the three-dimensional denture model to a 3D printing device for printing; receiving a user request for modifying the three-dimensional denture model in real time; According to the user request, the denture edge line and the oral three-dimensional mesh data, a revised denture edge line and / or a revised three-dimensional denture model is output.

[0019] In a second aspect, an embodiment of the present invention further provides a device for determining a denture edge line, comprising: An acquisition unit, used for acquiring oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral cavity scanning device; The denture edge line recognition unit is used to use an AI model to perform denture edge line recognition on the oral three-dimensional grid data to obtain the denture edge line.

[0020] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0021] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to execute any method described in the first aspect above.

[0022] In an embodiment of the present invention, a method for determining a denture edge line is provided, comprising: obtaining oral three-dimensional mesh data obtained by scanning an oral cavity with an oral scanning device; and using an AI model to identify a denture edge line on the oral three-dimensional mesh data to obtain a denture edge line. As can be seen from the above description, in the method for determining a denture edge line of the present invention, an AI model is used to automatically identify a denture edge line on the oral three-dimensional mesh data, which is highly intelligent, improves the accuracy and robustness of the denture edge line identification, and alleviates the technical problems of poor accuracy of the denture edge line determined by traditional technologies and low intelligence in the determination process. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 A flowchart of a method for determining a denture edge line provided by an embodiment of the present invention; Figure 2 A schematic diagram of a target three-dimensional muscle static line provided by an embodiment of the present invention; Figure 3 A schematic diagram of an oral three-dimensional mesh data sample provided by an embodiment of the present invention; Figure 4 A schematic diagram of another oral three-dimensional mesh data sample provided by an embodiment of the present invention; Figure 5A schematic diagram of a denture edge line determination device provided by an embodiment of the present invention; Figure 6 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The accuracy of denture edge lines determined by traditional technology is poor and the determination process is not very intelligent.

[0027] Based on this, in the denture edge line determination method of the present invention, an AI model is used to automatically identify the denture edge line of the oral three-dimensional grid data, which is highly intelligent and improves the accuracy and robustness of the denture edge line recognition.

[0028] To facilitate understanding of this embodiment, a method for determining a denture edge line disclosed in an embodiment of the present invention is first introduced in detail.

[0029] Embodiment 1: According to an embodiment of the present invention, an embodiment of a method for determining a denture edge line is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 1 is a flow chart of a method for determining a denture edge line according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps: Step S102, obtaining oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral cavity scanning device; Specifically, the oral cavity three-dimensional mesh data is an intraoral digital impression, which includes the structure of teeth, gums and surrounding soft tissues. The oral cavity can be a patient's oral cavity, which may contain some teeth or no teeth. The oral cavity scanning device can be an intraoral scanner and an extraoral scanner.

[0031] Step S104, using an AI model to identify the denture edge line of the oral three-dimensional mesh data to obtain the denture edge line; Specifically, the above-mentioned AI model can be obtained by training the original AI model using oral three-dimensional mesh data samples marked with denture edge lines, and it has the ability to recognize denture edge lines; the above-mentioned AI model can be obtained by training the original AI model using oral three-dimensional mesh data samples marked with anatomical points, and it has the ability to recognize anatomical points; the above-mentioned AI model can also be other models, for example, regional segmentation models, anatomical point recognition models, etc.; the process will be described in detail below and will not be repeated here.

[0032] In an embodiment of the present invention, a method for determining a denture edge line is provided, comprising: obtaining oral three-dimensional mesh data obtained by scanning an oral cavity with an oral scanning device; and using an AI model to identify a denture edge line on the oral three-dimensional mesh data to obtain a denture edge line. As can be seen from the above description, in the method for determining a denture edge line of the present invention, an AI model is used to automatically identify a denture edge line on the oral three-dimensional mesh data, which is highly intelligent, improves the accuracy and robustness of the denture edge line identification, and alleviates the technical problems of poor accuracy of the denture edge line determined by traditional technologies and low intelligence in the determination process.

[0033] The above content briefly introduces the denture edge line determination method of the present invention, and the specific contents involved are described in detail below.

[0034] In an optional embodiment of the present invention, an AI model is used to identify the denture edge line of the oral three-dimensional mesh data, which specifically includes the following steps: (1) Use the regional segmentation model to segment the oral 3D mesh data to obtain the denture coverage area; Specifically, the above-mentioned region segmentation model is a deep learning network capable of processing three-dimensional mesh data. In the present invention, the above-mentioned region segmentation model is a deep learning network capable of performing region segmentation on oral three-dimensional mesh data. In addition, the above-mentioned region segmentation model can be a denture coverage region segmentation model, or a myostatic region segmentation model. When the region segmentation model is a myostatic region segmentation model, the obtained denture coverage region can be a myostatic region.

[0035] (2) Determine the denture margin line based on the denture coverage area.

[0036] Specifically, the denture coverage area includes: a myostatic area, and determining the denture edge line based on the denture coverage area specifically includes the following steps: A target three-dimensional myostatic line is determined based on the myostatic area, and a denture margin line is determined based on the target three-dimensional myostatic line.

[0037] Specifically, after the target three-dimensional myostatic line is obtained, an equidistant line about 2 mm to 5 mm from the target three-dimensional myostatic line toward the gum is determined as the denture edge line.

[0038] Among them, the myostatic area can be divided into an upper and lower part by the denture edge line, and the denture coverage area can refer to the entire myostatic area, or directly refer to the upper part of the myostatic area divided by the denture edge line, the upper part includes rigid areas such as gums or teeth, and when wearing a total denture (full denture) or a removable partial denture, the upper part is just covered by the denture. It should be noted that when the denture coverage area refers to the entire myostatic area, the myostatic area can be determined first, then the target three-dimensional myostatic line can be determined, and then the denture edge line can be obtained. When the denture coverage area refers to the upper part of the myostatic area divided by the denture edge line, the denture edge line can be directly determined by the denture coverage area.

[0039] The target myostatic line refers to the boundary between the myostatic area and the myodynamic area, that is, the boundary line of the myostatic area. Among them, when performing denture restoration, the area related to the activity of the masticatory muscles needs to be considered. The mucosa in the myostatic area will not move during physiological activities such as chewing and speaking. Correctly identifying these areas will help design more stable and comfortable dentures.

[0040] In an optional embodiment of the present invention, an AI model is used to identify the denture edge line of the oral three-dimensional mesh data, which specifically includes the following steps: using an anatomical point recognition model to identify the oral three-dimensional 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 according to the anatomical points, so that there is no need to use a regional segmentation model.

[0041] In an optional embodiment of the present invention, after acquiring the oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral cavity scanning device, the method further comprises the following steps: (1) Preprocessing the oral cavity three-dimensional mesh data to obtain preprocessed oral cavity three-dimensional mesh data; Specifically, the preprocessing here may include: data processing (including: data denoising, data alignment), grid simplification, feature calculation (including: Laplace feature calculation, geometric feature calculation) and sparse coding representation. The implementation process is the same as the relevant content below, and will not be repeated here.

[0042] (2) The AI ​​model is used to identify the denture edge line of the preprocessed oral three-dimensional mesh data to obtain the denture edge line.

[0043] In an optional embodiment of the present invention, after acquiring the oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral scanning device, and before preprocessing the oral cavity three-dimensional mesh data, the method further includes the following steps: (1) Determine whether the oral three-dimensional mesh data contains all the specified areas; Specifically, it can be through AI to automatically determine whether the oral three-dimensional mesh data contains all the specified areas, and then display a prompt whether the scan is complete. It can also be manually determined whether the oral three-dimensional mesh data contains all the specified areas to ensure that the oral three-dimensional mesh data has contained the complete myostatic line.

[0044] The above-mentioned designated areas include: lip frenulum, cheek frenulum, vestibular mucosal fold, lower zygomatic bone line, buccal side of maxillary tuberosity, or, the above-mentioned designated areas include: lip frenulum, cheek frenulum, maxillary tuberosity, pterygomaxillary notch, and 2 mm area behind the maxillary concavity.

[0045] (2) If not all of the data is included, a prompt message is issued, and the three-dimensional mesh data of the oral cavity obtained by scanning the oral cavity with the oral scanning device is re-acquired until the three-dimensional mesh data of the oral cavity contains all of the specified area.

[0046] In an optional embodiment of the present invention, the method further comprises the following steps: (1) Determine the degree of alveolar ridge resorption based on oral 3D mesh data; Specifically, the degree of alveolar ridge protrusion can be determined based on the oral 3D mesh data, and then the degree of alveolar ridge absorption can be determined by the degree of alveolar ridge protrusion. In addition, the degree of alveolar ridge absorption can be manually input by the doctor. When implementing, it is considered that gingival atrophy is often accompanied by alveolar bone absorption, which will affect the myostatic area and occlusal relationship. In order to accurately evaluate these changes, dentists will use mouth mirrors and probes for detailed examinations to determine gingival atrophy and alveolar bone conditions. Determine the degree of alveolar ridge absorption based on Atwood's grading system.

[0047] When the degree of alveolar ridge resorption is mild (e.g., when the degree of alveolar ridge resorption is level one or two), it helps to achieve more accurate identification of the myostatic area, the target three-dimensional myostatic line, and the denture margin line.

[0048] (2) Determine the accuracy of the denture edge line based on the degree of alveolar ridge absorption, and output the accuracy to the display screen or voice broadcast.

[0049] Specifically, if the alveolar ridge absorption degree is at level one or level two, the accuracy of the target three-dimensional myostatic line and the denture edge line is determined to be accurate; if the alveolar ridge absorption degree is greater than level two, the accuracy of the target three-dimensional myostatic line and the denture edge line is determined to be inaccurate. Of course, the accuracy value can also be specifically displayed or voice broadcast, such as 90%, 80%, etc.

[0050] In an optional embodiment of the present invention, determining a target three-dimensional myostatic line based on the myostatic area specifically includes the following steps: (1) Smoothing and optimizing the edge of the myostatic area to obtain a myostatic area with a smooth contour; Specifically, the GraphCut algorithm is used to perform smoothing optimization on the edge of the myostatic region to obtain a myostatic region with a smooth contour.

[0051] During implementation, graph cutting algorithms such as GraphCut are applied to finely smooth and optimize the edges of the myostatic area to ensure the smoothness and accuracy of the contour and obtain a myostatic area with a smooth contour.

[0052] (2) Draw three-dimensional myostatic lines based on the edges of the myostatic area with smooth contours; Specifically, in the myostatic area with a smooth contour, the lower edge contour is the three-dimensional myostatic line.

[0053] (3) Smoothing the three-dimensional muscle static lines to obtain the target three-dimensional muscle static lines.

[0054] Specifically, the target smoothing algorithm is first determined according to the morphological characteristics and processing technology of the denture, wherein the target smoothing algorithm includes any one 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 muscle static line to obtain the target three-dimensional muscle static line, such as Figure 2 As shown, the green curve is the target three-dimensional myostatic line, which shows two visualized oral three-dimensional mesh data and the corresponding target three-dimensional myostatic line.

[0055] When determining the target smoothing algorithm, the design requirements and material properties of the restoration (such as dentures) need to be considered. The Laplace smoothing algorithm performs well in global smoothing and is suitable for processing complex surfaces, thereby improving the efficiency of tool path generation; the least squares smoothing algorithm is suitable for denture processing scenarios with high requirements for accuracy and adaptability by reducing the oscillation of data points; the curvature-based feature smoothing algorithm is suitable for scenarios where the fit between the restoration and oral tissue needs to be ensured by finely controlling the curvature distribution.

[0056] In an optional embodiment of the present invention, the training process of the region segmentation model includes the following steps: (1) obtaining an oral three-dimensional mesh data sample, wherein the oral three-dimensional mesh data sample is marked with a denture coverage area; Specifically, if the region segmentation model is a myostatic region segmentation model, then the acquired oral 3D mesh data sample is marked with a myostatic region, such as Figure 3 and Figure 4 As shown, the figure on the left is the original oral 3D mesh data sample ( Figure 3 The figure on the left shows the alveolar ridge resorption degree of the original oral 3D mesh data sample compared to Figure 4 The original oral 3D mesh data sample in the left picture has a lighter degree of alveolar ridge absorption). The right picture is the oral 3D mesh data sample, in which the myostatic area is marked (the white area in the right picture is the myostatic area).

[0057] (2) Preprocessing the oral three-dimensional mesh data sample to obtain a preprocessed oral three-dimensional mesh data sample; The specific steps include: 21) Processing the oral cavity three-dimensional mesh data sample to obtain the processed oral cavity three-dimensional mesh data sample; The specific steps include: 211) performing data denoising on the oral cavity three-dimensional mesh data sample to obtain the denoised oral cavity three-dimensional mesh data sample; Specifically, some data floating around the oral three-dimensional grid data samples, some small blocks on the buccal side (i.e., buccal and lingual data), and unnecessary data may be denoised and smoothed to improve the robustness of the model.

[0058] 212) Projecting the denoised oral 3D mesh data samples in the same direction to obtain a 2D depth image; 213) The dental arch curve is obtained by fitting the depth values ​​in the two-dimensional depth image.

[0059] During implementation, after projection in the same direction, a strip-shaped area with a depth value different from that of other areas can be obtained. This strip-shaped area is the alveolar ridge, and these depth data are fitted to obtain the dental arch curve.

[0060] 214) performing data alignment on the corresponding denoised oral three-dimensional mesh data samples with reference to the dental arch curve to obtain aligned oral three-dimensional mesh data samples; Specifically, data alignment reduces overfitting of training data and facilitates improving the generalization ability of the network.

[0061] 215) The aligned oral 3D mesh data samples are used as the oral 3D mesh data samples after data processing.

[0062] 22) Performing vertex optimization on the oral 3D mesh data sample after data processing to obtain the oral 3D mesh data sample after vertex optimization; Specifically, the number of vertices of the mesh is reduced through optimization algorithms while preserving its geometric features as much as possible to improve processing efficiency and reduce computational complexity.

[0063] During implementation, the present invention focuses on the myostatic area, which is a raised position. The curvature of the raised position will become faster and more prominent, and the number of vertices here will not be reduced. The lower extended part is flat, and the curvature here will be relatively small. The vertices here can be optimized and deleted to ensure that the shape of the entire tooth model does not change significantly, but the number of vertices is reduced.

[0064] 23) Perform feature calculation on the oral three-dimensional mesh data sample after vertex optimization to obtain the oral three-dimensional mesh data sample after feature calculation.

[0065] The specific steps include: 231) Using the Laplace operator of the grid to extract the features of different frequency domains of the oral three-dimensional grid data sample after vertex optimization, the oral three-dimensional grid data sample with Laplace features is obtained; Specifically, the Laplacian operator of the mesh is used to capture and extract the features of the oral 3D mesh data samples in different domains after vertex optimization, providing key information for further analysis.

[0066] 232) Perform multi-scale enhancement processing on the oral 3D mesh data samples with Laplace features to obtain multi-scale oral 3D mesh data samples; Specifically, oral 3D mesh data samples with Laplacian features are enhanced at different scale levels, which helps the model learn details at different levels and enhances its generalization ability.

[0067] 233) Using sparse coding to represent multi-scale oral three-dimensional mesh data samples, to obtain sparsely coded oral three-dimensional mesh data samples; Specifically, sparse coding technology is used to represent multi-scale oral three-dimensional mesh data samples to eliminate redundant features, highlight important information, and improve the interpretability of the model.

[0068] 234) Calculate the geometric features of the oral three-dimensional mesh data sample represented by sparse coding to obtain the oral three-dimensional mesh data sample with geometric features, wherein the geometric features include: surface curvature and normal vector; Specifically, geometric features can enrich the input information of the model and enhance its understanding of complex structures.

[0069] 235) The oral three-dimensional mesh data sample with geometric features is used as the oral three-dimensional mesh data sample after feature calculation.

[0070] 24) The oral 3D mesh data samples after feature calculation are used as preprocessed oral 3D mesh data samples.

[0071] (3) The preprocessed oral 3D mesh data samples are used to train the original region segmentation model to obtain a region segmentation model.

[0072] Specifically, the original region segmentation model mentioned above focuses on a series of deep learning models that specifically process 3D mesh data. These models include: PointNet that directly operates on point cloud data, Graph CNNs and MeshCNN that use graph convolutional networks to process mesh topology, multi-view models that parse 3D information from multiple perspectives, SpectralCNN based on spectral theory, and DiffusionNet designed for geometric data. Comprehensive considerations and decisions can be made based on the needs of actual application scenarios, such as computing resource consumption, real-time requirements, and other factors.

[0073] In an optional embodiment of the present invention, after the denture edge line is obtained through the AI ​​model, the denture edge line will be displayed on the interactive interface, and the user can adjust the denture edge line on the interactive interface. During the adjustment process, since the user adjusts the movement of the denture edge line on the two-dimensional display interface, if the denture edge line is directly adjusted according to the user's two-dimensional instructions, the denture edge line is prone to move too much, leaving the muscle static area or being too close to the muscle dynamic area. The total denture (full denture) or removable partial denture designed according to the denture edge line that is separated from the muscle static area or too close to the muscle dynamic area is easy to shift during the patient's wearing process, or it will collide during physiological movements such as chewing, causing the patient to be uncomfortable. At the same time, since the patient's oral environment is not a regular cylinder, if the denture edge line is simply translated or enlarged and reduced according to the user's two-dimensional instructions, the denture edge line will be separated from the model surface, causing the denture edge line to be inconsistent with the patient's actual oral condition, and subsequent denture design operations cannot be performed.

[0074] To solve the above problem, after obtaining the denture edge line, the method further includes the following steps: (1) when a first instruction is detected, determining a first pose change of the denture edge line relative to an initial position, wherein the first instruction is an instruction for a user to adjust the pose of the denture edge line in the three-dimensional mesh data of the oral cavity; (2) based on the first pose change and a preset reference condition, determining a 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 it is detected that the first pose change makes the denture edge line not meet the preset reference condition, the pose of the denture edge line is adaptively updated according to the preset reference condition, or, the pose of the denture edge line is not updated and a result of user confirmation is obtained and the pose of the denture edge line is adjusted according to the result of user confirmation; and / or when it is detected that the first adjusted pose makes the denture edge line not meet the preset reference condition, the pose of the denture edge line is adaptively updated according to the preset reference condition, or, the pose of the denture edge line is not updated and a result of user confirmation is obtained and the pose of the denture edge line is adjusted according to the result of user confirmation.

[0075] It can be understood that not updating the posture of the denture edge line means not moving or offsetting the denture edge line, and not updating the posture of the denture edge line after the movement or offset; updating the posture of the denture edge line can be understood as continuing to move or offset the denture edge line, and updating the posture of the denture edge line after the movement or offset. Adjusting the posture of the denture edge line according to the result of the user's reconfirmation can be based on the user's choice to not update the posture of the denture edge line or to update the posture of the denture edge line. When the posture of the denture edge line is not updated, a prompt box or other prompt information can be issued to give the user certain feedback.

[0076] Therefore, in this embodiment, the first adjustment posture can be recalculated based on the first posture change in the user's first instruction, including the movement distance of the denture edge line relative to its initial placement posture and / or the offset angle of the denture edge line relative to its initial placement posture, combined with the outer surface of the oral three-dimensional mesh data, the preset reference conditions (medical reference requirements) such as the denture coverage area or simulated physiological movement, and some adjustment instructions in the first posture change are ignored and some adjustment instructions in the first posture change are executed, that is, the instructions in the first posture change that do not meet the medical reference requirements are ignored, and the instructions in the first posture change that meet the medical reference requirements are executed, so that the denture edge line posture (first adjustment posture) 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 conform to the simulated physiological movement, and during the chewing process or physiological movements such as mandibular movement, the denture edge line will not move or the movement amplitude of the denture edge line is within the range.

[0077] Among them, the first pose change can be decomposed according to the preset reference conditions, and some or all instructions in the first pose change that meets the preset reference conditions are determined as the first adjustment pose of the denture edge line, and some or all instructions in the first pose change that does not meet the preset reference conditions are ignored; among them, for example: the preset reference conditions may include: the denture edge line should fit the outer surface of the oral 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.

[0078] For example, in the first instruction, the user clicks the mouse to move the denture edge line horizontally or obliquely by an X distance. If the X distance makes the denture edge line not fit the outer surface of the oral three-dimensional mesh data, not within the denture coverage area, or does not conform to the simulated physiological movement, then the instruction of the X distance of the denture edge line horizontally or obliquely moving will be ignored and not executed. This indicates that the first pose change does not meet the preset reference conditions. At this time, there are two operation methods. The first one is that the computer automatically enlarges or reduces the first pose change according to the 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, and displays the updated denture edge line; the second one is that the adjusted denture edge line is not displayed first, and a prompt box is issued to prompt the user that there may be problems with such adjustment, and the user is asked to confirm again. According to the result of the user's reconfirmation, the first adjustment pose is determined; if the user indicates "confirm", this adjustment method is used as the first adjustment pose, and the pose of the denture edge line is updated according to the user's instructions. If the user indicates "abandon modification", the first adjustment pose is 0, and the pose of the denture edge line is not updated according to the user's instructions.

[0079] For example, in the first instruction, the user clicks the mouse to move the denture edge line diagonally. The X distance is decomposed into vertical (such as Figure 2 The Z direction in the vertical direction refers to the up and down movement along the gingival surface) and the horizontal direction (such as Figure 2 In the X direction, the horizontal movement refers to the forward and backward movement along the normal of the outer surface of the oral 3D mesh data) moving the C distance, where the horizontal movement C distance will be ignored and not executed, and the vertical movement B distance will be executed, which is equivalent to projecting onto the vertical plane (such as Figure 2 The first adjustment position of the denture edge line is to move the denture edge line up and down by a distance B along the gingival surface, and automatically calculate and generate the latest denture edge line based on the denture edge line after vertical movement of the distance B and the outer surface of the oral three-dimensional mesh data, so that the denture edge line fits the outer surface of the model.

[0080] For example, after determining the first adjusted posture, it can be determined again whether it conforms to the simulated physiological movement or is located in the denture coverage area. If so, it means that the first adjusted posture conforms to the medical reference conditions, and it can be adjusted according to the first adjusted posture and the adjusted denture edge line can be displayed in the interactive interface; if not, it means that the first adjusted posture does not conform to the medical reference conditions. At this time, there are two operation methods. First, the computer automatically enlarges or reduces the first adjusted posture according to a preset ratio to make it conform to the simulated physiological movement or be located in the denture coverage area; second, the adjusted denture edge line is not displayed first, and a prompt box is issued to prompt the user that there may be problems with such adjustment. Please confirm again whether to use this adjustment method to modify. If the user indicates "confirm", this adjustment method is used to modify, and the posture of the denture edge line is updated according to the user's instructions. If the user indicates "abandon modification", the posture of the denture edge line is not updated according to the user's instructions.

[0081] In one embodiment, based on the first instruction, the denture edge line can be controlled to rotate to the position indicated by the first instruction based on the current coordinate point of the mouse. At this time, the interactive interface shows that the denture edge line falls on the position where the mouse is clicked. At the same time, the angle or distance of the denture edge line rotating around the denture edge line is the projection of the mouse movement distance onto the vertical plane (such as Figure 2 The XZ plane in the image is determined by the

[0082] It should be noted that simulated physiological movement refers to the simulated physiological movement automatically generated by inputting the oral three-dimensional mesh data into the motion simulation deep learning model, and the simulated physiological movement can be selectively displayed on the interactive interface according to the user's instructions. When the user chooses to display the simulated physiological movement on the interactive interface, the oral three-dimensional mesh data on the interactive interface will simulate the physiological movement and change. The user can observe with the naked eye whether the denture edge line is suitable, and can move up and down or adjust the denture edge line. When the user chooses not to display the simulated physiological movement on the interactive interface, the interactive interface can directly output the computer's judgment on whether the denture edge line meets the simulated physiological movement results.

[0083] The simulated physiological motion automatically generated by the motion simulation deep learning model can be generated based on the average motion of multiple patient training samples, or based on the mandibular motion trajectory and chewing motion trajectory obtained by CBCT equipment, facial scanner, extraoral scanner or intraoral scanner.

[0084] In an optional embodiment of the present invention, the method further comprises the following steps: (1) Generate a 3D denture model based on the denture edge line and oral 3D mesh data, and send the 3D denture model to a 3D printing device for printing; (2) receiving user requests for modifying the three-dimensional denture model in real time; (3) Outputting a revised denture edge line and / or a revised three-dimensional denture model according to a user request, the denture edge line and the oral three-dimensional mesh data.

[0085] Therefore, after obtaining the denture edge line through the AI ​​model, the present invention can quickly generate a three-dimensional denture model and perform 3D printing to obtain a physical denture. The user tries on the physical denture and directly adjusts the denture edge line or the three-dimensional denture model according to the user's trial results to obtain a denture that better meets the user's needs.

[0086] In summary, in the denture edge line determination method of the present invention, an AI model is used to segment the oral three-dimensional mesh data, which has high robustness and will not be affected by the diversity of dental and maxillofacial morphology and the quality of mesh surface. It provides solid technical support for the subsequent denture design and manufacturing process and improves the efficiency of doctors' clinical diagnosis and treatment.

[0087] The present invention has the following advantages: Using deep learning technology, complex patterns can be learned from large amounts of data, ensuring better robustness for different forms of jaws, improving the accuracy of myostatic line identification, and reducing human errors.

[0088] The fully automated identification process can significantly reduce the time dental technicians spend identifying myostatic lines and improve overall work efficiency.

[0089] It can be processed directly on the digital impression, avoiding complicated steps such as plaster touching.

[0090] Embodiment 2: An embodiment of the present invention further provides a denture edge line determination device, which is mainly used to execute the denture edge line determination method provided in the first embodiment of the present invention. The denture edge line determination device provided in the embodiment of the present invention is specifically introduced below.

[0091] Figure 5 is a schematic diagram of a denture edge line determination device according to an embodiment of the present invention. Figure 5 As shown, the device mainly includes: an acquisition unit 10, a denture edge line recognition unit 20, wherein: An acquisition unit, used for acquiring oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral cavity scanning device; The denture edge line recognition unit is used to use the AI ​​model to perform denture edge line recognition on the oral three-dimensional grid data to obtain the denture edge line.

[0092] In an embodiment of the present invention, a denture edge line determination device is provided, comprising: obtaining oral three-dimensional mesh data obtained by scanning the oral cavity with an oral scanning device; using an AI model to perform denture edge line recognition on the oral three-dimensional mesh data to obtain the denture edge line. From the above description, it can be seen that in the denture edge line determination device of the present invention, an AI model is used to automatically recognize the denture edge line on the oral three-dimensional mesh data, which is highly intelligent, improves the accuracy and robustness of the denture edge line recognition, and alleviates the technical problems of poor accuracy of the denture edge line determined by traditional technology and low intelligence of the determination process.

[0093] Optionally, the denture edge line recognition unit is further used to: segment the oral three-dimensional grid data using a region segmentation model to obtain a denture coverage area; and determine the denture edge line based on the denture coverage area.

[0094] Optionally, the denture coverage area includes: a myostatic area, and the denture edge line recognition unit is further used to: determine a target three-dimensional myostatic line based on the myostatic area, and determine the denture edge line based on the target three-dimensional myostatic line.

[0095] Optionally, the device is also used to: preprocess the oral three-dimensional mesh data to obtain preprocessed oral three-dimensional mesh data; use an AI model to identify the denture edge line of the preprocessed oral three-dimensional mesh data to obtain the denture edge line.

[0096] Optionally, the device is also used to: determine whether the oral three-dimensional grid data completely contains the specified area; if not, issue a prompt message and re-acquire the oral three-dimensional grid data obtained by scanning the oral cavity with an oral scanning device until the oral three-dimensional grid data completely contains the specified area.

[0097] Optionally, the device is also used to: determine the degree of alveolar ridge absorption based on the oral three-dimensional grid data; determine the accuracy of the denture edge line based on the degree of alveolar ridge absorption, and output the accuracy to a display screen or voice broadcast.

[0098] Optionally, the denture edge line recognition unit is also used to: smooth and optimize the edge of the myostatic area to obtain a myostatic area with a smooth contour; draw a three-dimensional myostatic line based on the edge of the myostatic area with a smooth contour; and smooth the three-dimensional myostatic line to obtain a target three-dimensional myostatic line.

[0099] Optionally, the denture edge line recognition unit is further used to: use a graph cutting algorithm to perform smoothing optimization processing on the edge of the myostatic area to obtain a myostatic area with a smooth contour.

[0100] Optionally, the denture edge line recognition unit is also used to: determine a target smoothing algorithm based on the morphological characteristics and processing technology of the denture, wherein the target smoothing algorithm includes any one of the following: a Laplace smoothing algorithm, a least squares smoothing algorithm, and a curvature-based feature smoothing algorithm; use the target smoothing algorithm to smooth the three-dimensional muscle static line to obtain the target three-dimensional muscle static line.

[0101] Optionally, the device is also used to: obtain an oral three-dimensional mesh data sample, wherein the oral three-dimensional mesh data sample is marked with a denture coverage area; preprocess the oral three-dimensional mesh data sample to obtain a preprocessed oral three-dimensional mesh data sample; and use the preprocessed oral three-dimensional mesh data sample to train an original region segmentation model to obtain a region segmentation model.

[0102] Optionally, the device is also used to: perform data processing on the oral three-dimensional mesh data samples to obtain the data processed oral three-dimensional mesh data samples; perform vertex optimization on the data processed oral three-dimensional mesh data samples to obtain the vertex optimized oral three-dimensional mesh data samples; perform feature calculation on the vertex optimized oral three-dimensional mesh data samples to obtain the feature calculated oral three-dimensional mesh data samples; use the feature calculated oral three-dimensional mesh data samples as the preprocessed oral three-dimensional mesh data samples.

[0103] Optionally, the device is also used to: perform data denoising on the oral three-dimensional mesh data samples to obtain denoised oral three-dimensional mesh data samples; project the denoised oral three-dimensional mesh data samples in the same direction to obtain a two-dimensional depth image; obtain a dental arch curve according to the depth value fitting in the two-dimensional depth image; perform data alignment on the corresponding denoised oral three-dimensional mesh data samples with reference to the dental arch curve to obtain aligned oral three-dimensional mesh data samples; and use the aligned oral three-dimensional mesh data samples as the oral three-dimensional mesh data samples after data processing.

[0104] Optionally, the device is also used to: use the Laplace operator of the grid to extract features in different frequency domains of the oral three-dimensional mesh data samples after vertex optimization, and obtain oral three-dimensional mesh data samples with Laplace features; perform multi-scale enhancement processing on the oral three-dimensional mesh data samples with Laplace features, and obtain multi-scale oral three-dimensional mesh data samples; use sparse coding to represent the multi-scale oral three-dimensional mesh data samples, and obtain oral three-dimensional mesh data samples represented by sparse coding; calculate the geometric features of the oral three-dimensional mesh data samples represented by sparse coding, and obtain oral three-dimensional mesh data samples with geometric features, wherein the geometric features include: surface curvature, normal vector; use the oral three-dimensional mesh data samples with geometric features as the oral three-dimensional mesh data samples after feature calculation.

[0105] Optionally, the device is also used to: when a first instruction is monitored, determine a first posture change of the denture edge line relative to the initial position, wherein the first instruction is an instruction for the user to adjust the posture of the denture edge line in the three-dimensional mesh data of the oral cavity; based on the first posture change and a preset reference condition, determine a first adjusted posture of the denture edge line, and update and display the posture of the denture edge line based on the first adjusted posture of the denture edge line, wherein the preset reference condition includes: the denture edge line fits the outer surface of the three-dimensional mesh data of the oral cavity, the denture edge line conforms to simulated physiological movement, or the denture edge line is located in the denture coverage area. or more; wherein, when it is detected that the first posture change makes the denture edge line not meet the preset reference condition, the posture of the denture edge line is adaptively updated according to the preset reference condition, or, the posture of the denture edge line is not updated and the result of user reconfirmation is obtained and the posture of the denture edge line is adjusted according to the result of user reconfirmation; and / or when it is detected that the first adjusted posture makes the denture edge line not meet the preset reference condition, the posture of the denture edge line is adaptively updated according to the preset reference condition, or, the posture of the denture edge line is not updated and the result of user reconfirmation is obtained and the posture of the denture edge line is adjusted according to the result of user reconfirmation.

[0106] Optionally, the device is also used to: generate a three-dimensional denture model based on the denture edge line and the oral three-dimensional mesh data, and send the three-dimensional denture model to a 3D printing device for printing; receive user requests for modifying the three-dimensional denture model in real time; output revised denture edge lines and / or output a revised three-dimensional denture model based on the user request, the denture edge line and the oral three-dimensional mesh data.

[0107] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0108] like Figure 6 As shown, an electronic device 600 provided in an embodiment of the present application includes: a processor 601, a memory 602 and a bus, wherein the memory 602 stores machine-readable instructions executable by the processor 601, and when the electronic device is running, the processor 601 communicates with the memory 602 through the bus, and the processor 601 executes the machine-readable instructions to perform the steps of the denture edge line determination method as described above.

[0109] Specifically, the above-mentioned memory 602 and processor 601 can be general-purpose memory and processor, which are not specifically limited here. When the processor 601 runs the computer program stored in the memory 602, the above-mentioned denture edge line determination method can be executed.

[0110] The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 601. The above 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 gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the steps of the above method in combination with its hardware.

[0111] Corresponding to the above-mentioned method for determining the denture edge line, an embodiment of the present application also provides a computer-readable storage medium, which stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned method for determining the denture edge line.

[0112] The denture edge line determination device provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in the embodiment of the present application are the same as those of the aforementioned method embodiment. For the sake of brief description, the parts not mentioned in the device embodiment can refer to the corresponding contents in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0113] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0114] For another example, the flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0115] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0117] If the function is implemented in the form of 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 the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable an electronic device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the denture edge line determination method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0118] It should be noted that similar numbers and letters represent similar items in the following figures. 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 only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0119] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solution of the present application, rather than to limit it. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solution recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiment of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for determining a denture edge line, characterized in that: include: Acquire oral three-dimensional mesh data obtained by scanning the oral cavity with an oral scanning device; The AI ​​model is used to identify the denture edge line of the oral three-dimensional grid data to obtain the denture edge line.

2. The method according to claim 1, characterized in that The AI ​​model is used to identify the denture edge line of the oral three-dimensional mesh data, including: Using a regional segmentation model to segment the oral three-dimensional mesh data to obtain a denture coverage area; The denture margin line is determined based on the denture coverage area.

3. The method according to claim 2, characterized in that The denture coverage area includes: a myostatic area, and determining the denture edge line based on the denture coverage area includes: A target three-dimensional myostatic line is determined based on the myostatic area, and a denture edge line is determined based on the target three-dimensional myostatic line.

4. The method according to claim 1, characterized in that: After acquiring the oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral cavity scanning device, the method further includes: Preprocessing the oral cavity three-dimensional mesh data to obtain preprocessed oral cavity three-dimensional mesh data; The AI ​​model is used to identify the denture edge line of the preprocessed oral three-dimensional mesh data to obtain the denture edge line.

5. The method according to claim 4, characterized in that After acquiring the oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral scanning device, and before preprocessing the oral cavity three-dimensional mesh data, the method further includes: Determining whether the oral three-dimensional mesh data completely includes the designated area; If not all of them are included, a prompt message is issued, and the oral three-dimensional mesh data obtained by scanning the oral cavity with an oral scanning device is re-acquired until the designated area is completely included in the oral three-dimensional mesh data.

6. The method according to claim 1, characterized in that The method further comprises: determining the degree of alveolar ridge resorption according to the oral three-dimensional mesh data; The accuracy of the denture edge line is determined according to the degree of alveolar ridge absorption, and the accuracy is output to a display screen or voice broadcast.

7. The method according to claim 3, characterized in that Determining a target three-dimensional myostatic line based on the myostatic area includes: Performing a smoothing optimization process on the edge of the myostatic area to obtain a myostatic area with a smooth contour; Drawing a three-dimensional myostatic line according to the edge of the myostatic area with a smooth contour; The three-dimensional muscle static line is smoothed to obtain the target three-dimensional muscle static line.

8. The method according to claim 7, characterized in that The edge of the myostatic area is smoothed and optimized, including: A graph cut algorithm is used to perform smoothing optimization processing on the edge of the myostatic region to obtain the myostatic region with a smooth contour; Alternatively, the three-dimensional myostatic lines are smoothed, including: Determine a target smoothing algorithm according to the morphological characteristics and processing technology of the denture, wherein the target smoothing algorithm includes any one of the following: a Laplace smoothing algorithm, a least squares smoothing algorithm, and a curvature-based feature smoothing algorithm; The target smoothing algorithm is used to smooth the three-dimensional muscle static line to obtain the target three-dimensional muscle static line.

9. The method according to claim 2, characterized in that: The training process of the region segmentation model includes: Acquire an oral three-dimensional mesh data sample, wherein the oral three-dimensional mesh data sample is marked with a denture coverage area; Preprocessing the oral cavity three-dimensional mesh data sample to obtain a preprocessed oral cavity three-dimensional mesh data sample; The preprocessed oral three-dimensional mesh data samples are used to train the original region segmentation model to obtain the region segmentation model.

10. The method according to claim 9, characterized in that Preprocessing the oral three-dimensional mesh data sample includes: Performing data processing on the oral cavity three-dimensional mesh data sample to obtain a data-processed oral cavity three-dimensional mesh data sample; Performing vertex optimization on the oral three-dimensional mesh data sample after the data processing to obtain the oral three-dimensional mesh data sample after vertex optimization; Performing feature calculation on the oral cavity three-dimensional mesh data sample after vertex optimization to obtain the oral cavity three-dimensional mesh data sample after feature calculation; The oral cavity three-dimensional mesh data sample after the feature calculation is used as the oral cavity three-dimensional mesh data sample after the preprocessing.

11. The method according to claim 10, characterized in that The oral cavity three-dimensional mesh data sample is processed, including: Performing data denoising on the oral cavity three-dimensional mesh data sample to obtain a denoised oral cavity three-dimensional mesh data sample; Projecting the denoised oral three-dimensional mesh data samples in the same direction to obtain a two-dimensional depth image; Obtaining a dental arch curve by fitting the depth values ​​in the two-dimensional depth image; Performing data alignment on the corresponding denoised oral three-dimensional mesh data samples with reference to the dental arch curve to obtain aligned oral three-dimensional mesh data samples; The aligned oral three-dimensional mesh data samples are used as the oral three-dimensional mesh data samples after data processing.

12. The method according to claim 10, characterized in that Performing feature calculation on the oral three-dimensional mesh data sample after vertex optimization, including: Using the Laplace operator of the grid to extract the features of different frequency domains of the oral three-dimensional grid data sample after the vertex optimization, to obtain the oral three-dimensional grid data sample with Laplace features; Performing multi-scale enhancement processing on the oral three-dimensional mesh data sample with Laplace features to obtain a multi-scale oral three-dimensional mesh data sample; Using sparse coding to represent the multi-scale oral three-dimensional mesh data samples to obtain sparsely coded oral three-dimensional mesh data samples; Calculating the geometric features of the oral three-dimensional mesh data sample represented by the sparse coding to obtain the oral three-dimensional mesh data sample with geometric features, wherein the geometric features include: surface curvature and normal vector; The oral three-dimensional mesh data sample with the geometric features is used as the oral three-dimensional mesh data sample after the feature calculation.

13. The method according to claim 1, characterized in that After the AI ​​model is used to identify the denture edge line of the oral three-dimensional mesh data to obtain the denture edge line, the method further includes: When a first instruction is detected, determining a first posture change of the denture edge line relative to the initial position, wherein the first instruction is an instruction for a user to adjust the posture of the denture edge line in the three-dimensional mesh data of the oral cavity; Based on the first posture change and preset reference conditions, determine a first adjusted posture of the denture edge line, and update and display the posture of the denture edge line based on the first adjusted posture of the denture edge line, wherein the preset reference conditions include: the denture edge line fits the outer surface of the oral three-dimensional mesh data, the denture edge line conforms to simulated physiological movement, or the denture edge line is located in the denture coverage area. One or more; Wherein, when it is detected that the first posture change makes the denture edge line not meet the preset reference condition, the posture of the denture edge line is adaptively updated according to the preset reference condition, or, the posture of the denture edge line is not updated and the result of user reconfirmation is obtained and the posture of the denture edge line is adjusted according to the result of user reconfirmation; and / or When it is detected that the first adjustment posture makes the denture edge line not meet the preset reference condition, the posture of the denture edge line is adaptively updated according to the preset reference condition, or the posture of the denture edge line is not updated and the result of user re-confirmation is obtained and the posture of the denture edge line is adjusted according to the result of user re-confirmation.

14. The method according to any one of claims 1 to 13, characterized in that: The method further comprises: Generate a three-dimensional denture model according to the denture edge line and the oral three-dimensional mesh data, and send the three-dimensional denture model to a 3D printing device for printing; receiving a user request for modifying the three-dimensional denture model in real time; According to the user request, the denture edge line and the oral three-dimensional mesh data, a revised denture edge line and / or a revised three-dimensional denture model is output.

15. A denture edge line determination device, characterized in that: include: An acquisition unit, used for acquiring oral cavity three-dimensional mesh data obtained by scanning the oral cavity with an oral cavity scanning device; The denture edge line recognition unit is used to use an AI model to perform denture edge line recognition on the oral three-dimensional grid data to obtain the denture edge line.

16. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 13 are implemented.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to execute the method according to any one of claims 1 to 13.

Images