Denture edge line determination method and apparatus, computer device, and storage medium

Abstract

The present application provides a denture edge line determination method and apparatus, a computer device, and a storage medium, and relates to the technical field of denture design. The method comprises: acquiring first oral cavity data and second oral cavity data which correspond to a target object, wherein the first oral cavity data is used for representing the oral cavity of the target object in a first pressure state, the second oral cavity data is used for representing the oral cavity of the target object in a second pressure state, and the pressure in the second pressure state is less than the pressure in the first pressure state; on the basis of a trained AI model, performing denture reference line recognition on the first oral cavity data to obtain a first denture reference line; and mapping the first denture reference line to the second oral cavity data to obtain a target denture edge line. The present application combines the first oral cavity data and the second oral cavity data in different pressure states to automatically and accurately recognize the highly accurate denture edge line of the second oral cavity data, aiding in subsequent digital storage and design.

Description

Methods, devices, computer equipment, and storage media for determining the edge line of dentures Cross-reference to related applications

[0001] This application claims priority to Chinese Patent Application No. 202411884026.7, filed on December 19, 2024, entitled “Method, Apparatus, Computer Equipment and Storage Medium for Determining the Edge Line of Dentures”, the entire contents of which are incorporated herein by reference. Technical Field

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

[0003] In dentistry, especially in the fabrication of complete dentures or removable partial dentures, identifying the myostatic line is crucial for ensuring denture retention and function. The myostatic zone refers to the area related to masticatory muscle activity that needs to be considered during denture restoration. In these areas, the mucosa does not move during physiological activities such as chewing and speaking. The boundary between the myostatic zone and the muscular zone is the myostatic line. Based on the myostatic line, the denture margin can be determined, allowing for the design of the corresponding denture. Therefore, correctly identifying the myostatic line contributes to designing more stable and comfortable dentures.

[0004] Currently, myostatic lines are usually marked manually. For example, they can be marked directly on the plaster model, or they can be marked on the digital oral impression or the scanned plaster model using digital drawing software. The digital oral impression is obtained by scanning the inside of the mouth with a scanner. The plaster model is a physical model of plaster material obtained by traditional molding methods, and the scanned plaster model is obtained by scanning the plaster model.

[0005] However, the aforementioned methods of manually annotating myostatic lines rely on the clinical experience of designers and other relevant personnel, making them susceptible to subjective human factors, difficult to achieve consistency and standardization, and requiring significant time and effort from relevant personnel, resulting in high labor costs and low efficiency. Specifically, in the method of manually annotating myostatic lines based on plaster models, the plaster models require physical storage, and sharing and transmission are not as convenient as digital dental impressions. Furthermore, shrinkage of the impression material, expansion of the plaster, or other physical factors can cause deviations between the plaster model and the actual oral condition, making the plaster model less accurate than a digital dental impression. The method of manually annotating myostatic lines based on digital drawing software tools requires the support of relevant marking tools and software, incurring a learning cost and being inconvenient to operate. Additionally, digital dental impressions are taken under near-pressure-free conditions; during intraoral scanning, the patient's oral cavity is essentially still, making it impossible to distinguish between myostatic and dynamic zones and obtain accurate denture margin lines. Summary of the Invention

[0006] The purpose of this application is to provide a method, apparatus, computer device, and storage medium for determining the edge line of a denture, so as to automatically and accurately identify the edge line of the denture, while facilitating subsequent digital storage and design.

[0007] In a first aspect, embodiments of this application provide a method for determining the edge line of a denture, comprising: acquiring first oral cavity data and second oral cavity data corresponding to a target object; wherein, the first oral cavity data is used to represent the oral cavity of the target object under a first pressure state, and the second oral cavity data is used to represent the oral cavity of the target object under a second pressure state, wherein the pressure under the second pressure state is less than the pressure under the first pressure state; identifying a denture reference line on the first oral cavity data according to a trained AI model to obtain a first denture reference line; and mapping the first denture reference line onto the second oral cavity data according to the registration information between the first oral cavity data and the second oral cavity data to obtain the edge line of the target denture.

[0008] Optionally, the first denture reference line is obtained by identifying the first oral cavity data using the trained AI model, including: preprocessing the first oral cavity data to obtain preprocessed first oral cavity data; wherein, the preprocessing includes one or more of the following: data denoising, data alignment, mesh simplification, Laplacian feature calculation, sparse coding representation, and surface feature fusion; inputting the preprocessed first oral cavity data into the AI ​​model to obtain the denture reference line identification result output by the AI ​​model; wherein, the AI ​​model is obtained by training a three-dimensional deep learning model based on multiple sample oral cavity data with denture reference line annotation data, and the sample oral cavity data is used to represent the oral cavity of the sample object under the first pressure state; and determining the first denture reference line based on the denture reference line identification result.

[0009] Optionally, the first denture reference line includes a first myostatic line, and the denture reference line annotation data includes myostatic annotation data, which includes myostatic line data or myostatic region data; or, the first denture reference line includes a first denture edge line, and the denture reference line annotation data includes myostatic annotation data or denture edge line annotation data.

[0010] Optionally, based on the registration information between the first oral cavity data and the second oral cavity data, the first denture reference line is mapped onto the second oral cavity data to obtain the target denture edge line, including: registering the first oral cavity data and the second oral cavity data using a preset rigid body region to obtain registration information; wherein, the rigid body region includes the alveolar ridge and / or the maxilla; mapping the first denture reference line onto the second oral cavity data based on the registration information to obtain the second denture reference line; and determining the target denture edge line based on the second denture reference line.

[0011] Optionally, based on the registration information, the first denture reference line is mapped onto the second oral data to obtain the second denture reference line, including: acquiring multiple sampling points from the first denture reference line; determining the matching point of each sampling point on the second oral data based on the registration information; and performing three-dimensional curve fitting on each matching point to obtain the second denture reference line.

[0012] Optionally, determining the edge line of the target denture based on the second denture reference line includes: smoothing the second denture reference line to obtain a smoothed denture reference line; and determining the edge line of the target denture based on the smoothed denture reference line.

[0013] Optionally, the above method further includes: acquiring multiple sample oral cavity data with denture reference line annotation data; training a three-dimensional deep learning model based on each sample oral cavity data to obtain an AI model; wherein the three-dimensional deep learning model includes any of the following: PointNet model, graph convolutional neural network model, MeshCNN model, multi-view model that parses three-dimensional information from multiple perspectives, convolutional neural network model based on graph theory, and diffusion network DiffusionNet model.

[0014] Optionally, multiple sample oral cavity data with denture reference line annotation data are obtained, including: obtaining multiple initial oral cavity data with denture reference line annotation data; wherein the initial oral cavity data is used to represent the oral cavity of the sample object under the first pressure state; preprocessing the multiple initial oral cavity data to obtain multiple sample oral cavity data; wherein the preprocessing includes one or more of the following: data denoising, data alignment, mesh simplification, Laplacian feature calculation, multi-scale data augmentation, sparse coding representation and surface feature fusion.

[0015] Optionally, the first oral cavity data is obtained by three-dimensional scanning of a plaster model of the target subject's oral cavity obtained by impression under the first pressure, or by three-dimensional scanning of the target subject's historical dentures, or by scanning the target subject's oral cavity under air pressure; the second oral cavity data is obtained by directly scanning the target subject's oral cavity without physical pressure or under standard atmospheric pressure.

[0016] Optionally, after obtaining the first oral cavity data and the second oral cavity data corresponding to the target object, the above method further includes: judging the data integrity of the first oral cavity data and the second oral cavity data to obtain the degree of integrity; and determining the accuracy of the edge line of the target denture based on the degree of integrity.

[0017] Optionally, the data integrity of the first oral cavity data and the second oral cavity data is assessed to obtain the degree of integrity, including: determining whether the first oral cavity data and / or the second oral cavity data contain a preset key region, and obtaining a containment assessment result; wherein the key region corresponding to the first oral cavity data includes a first designated region, and the key region corresponding to the second oral cavity data includes a second designated region; the degree of integrity is determined based on the containment assessment result; after assessing the data integrity of the first oral cavity data and the second oral cavity data to obtain the degree of integrity, the above method further includes: determining whether the degree of integrity is less than a preset integrity threshold; if it is less than the integrity threshold, a data incompleteness warning is issued.

[0018] Optionally, after mapping the first denture reference line onto the second oral data based on the registration information between the first and second oral data to obtain the target denture edge line, the method further includes: when a first command is detected, determining the first pose change of the target denture edge line relative to its initial position, wherein the first command is a user command to adjust the pose of the target denture edge line in the second oral data; determining the first adjusted pose of the target denture edge line based on the first pose change and preset reference conditions, and updating and displaying the pose of the target denture edge line based on the first adjusted pose of the target denture edge line, wherein the preset reference conditions include the target denture edge line fitting the outer surface of the second oral data and the target denture edge line conforming to simulated physiology. The movement or target 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 target denture edge line to not conform to the preset reference conditions, the pose of the target denture edge line is adaptively updated according to the preset reference conditions, or, the pose of the target denture edge line is not updated and the result of user reconfirmation is obtained and the pose of the target denture edge line is adjusted according to the result of user reconfirmation; and / or when a first adjusted pose is detected that causes the target denture edge line to not conform to the preset reference conditions, the pose of the target denture edge line is adaptively updated according to the preset reference conditions, or, the pose of the target denture edge line is not updated and the result of user reconfirmation is obtained and the pose of the target denture edge line is adjusted according to the result of user reconfirmation.

[0019] Optionally, after mapping the first denture reference line onto the second oral data based on the registration information between the first and second oral data to obtain the target denture edge line, the method further includes: generating a three-dimensional denture model based on the target denture edge line and the second oral data, and sending the three-dimensional denture model to a 3D printing device configured to print the three-dimensional denture model; when a user request to modify the three-dimensional denture model is received, outputting the revised target denture edge line and / or the revised three-dimensional denture model based on the user request, the target denture edge line, and the second oral data.

[0020] Optionally, the target object's oral cavity may contain some teeth or no teeth.

[0021] Optionally, the target object is an edentulous target object.

[0022] Optionally, the first myostatic line is the boundary line between the myostatic zone and the myodynamic zone.

[0023] Optionally, the second denture reference line includes a second myostatic line corresponding to the first myostatic line, or a second denture edge line corresponding to the first denture edge line.

[0024] Optionally, both the first designated region and the second designated region include at least two of the following: labial frenulum, buccal frenulum, maxillary tuberosity, pterygomaxillary notch, and the region 2 mm behind the maxillary fossa; or, the first designated region includes at least two of the following: alveolar ridge, jaw structure, palate, labial, buccal, and lingual mucosa, frenulum, and salivary gland opening, and the second designated region includes at least two of the following: labial frenulum, buccal frenulum, vestibular mucosal fold, lower zygomatic bone line, and buccal side of maxillary tuberosity.

[0025] Secondly, embodiments of this application also provide a denture edge line determination device, comprising: a data acquisition module configured to acquire first oral cavity data and second oral cavity data corresponding to a target object; wherein the first oral cavity data is used to represent the oral cavity of the target object under a first pressure state, and the second oral cavity data is used to represent the oral cavity of the target object under a second pressure state, wherein the pressure under the second pressure state is less than the pressure under the first pressure state; a denture reference line recognition module configured to perform denture reference line recognition on the first oral cavity data according to a trained AI model to obtain a first denture reference line; and a denture edge line mapping module configured to map the first denture reference line onto the second oral cavity data according to the registration information between the first oral cavity data and the second oral cavity data to obtain the target denture edge line.

[0026] Thirdly, embodiments of this application also provide a computer device, including a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the denture edge line determination method of the first aspect.

[0027] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the denture edge line determination method of the first aspect.

[0028] The method, apparatus, computer equipment, and storage medium for determining the edge line of a denture provided in this application can acquire first oral cavity data and second oral cavity data corresponding to the target object when determining the edge line of the denture. The first oral cavity data represents the oral cavity of the target object under a first pressure state, and the second oral cavity data represents the oral cavity of the target object under a second pressure state, where the pressure under the second pressure state is less than the pressure under the first pressure state. A denture reference line is identified on the first oral cavity data using a trained AI model to obtain a first denture reference line. Based on the registration information between the first and second oral cavity data, the first denture reference line is mapped onto the second oral cavity data to obtain the target denture edge line. Since the impression pressure corresponding to the first oral cavity data is greater than that corresponding to the second oral cavity data, the accuracy of the second oral cavity data is higher than that of the first oral cavity data. The first denture reference line corresponding to the first oral cavity data is less susceptible to interference from the diversity of dental morphology and the quality of the mesh surface. Through artificial intelligence learning, the first denture reference line corresponding to the first oral cavity data can be accurately identified. Mapping the first denture reference line onto the more accurate second oral cavity data facilitates subsequent data storage and design. By combining the first and second oral cavity data under different pressure conditions, the edge trimming effect is achieved. The denture edge line of the second oral cavity data is automatically and accurately identified, which also facilitates subsequent digital storage and design. 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 illustrating 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 appearance of a digital dental impression provided in an embodiment of this application;

[0032] Figure 3 is a schematic diagram of the appearance of a target three-dimensional plaster model provided in an embodiment of this application;

[0033] Figure 4 is a schematic diagram of a target three-dimensional plaster model for marking muscle static lines provided in an embodiment of this application;

[0034] Figure 5 is a schematic diagram of a myostatic line mapping provided in an embodiment of this application;

[0035] Figure 6 is a schematic diagram showing the edge line of a target denture on an interactive interface according to an embodiment of this application;

[0036] Figure 7 is a schematic diagram of a denture edge line determination device provided in an embodiment of this application;

[0037] Figure 8 is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0038] 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.

[0039] Currently, myostatic lines are typically manually marked directly on digital dental impressions or scanned plaster models using digital drawing software tools to obtain the denture margins. However, this method has the following drawbacks: a) It requires clinical experience to ensure that the design allows for flexibility; b) It requires a significant investment of time and effort; c) It requires the support of relevant marking tools and software, incurring a learning curve; d) Compared to the traditional method of marking directly on plaster models, marking and editing on 3D models within digital drawing software tools is a considerable challenge for designers; e) It is susceptible to the influence of subjective human factors, making it difficult to achieve consistency and standardization.

[0040] With the development of image processing technology, artificial intelligence can be used to automatically identify myostatic lines in digital dental impressions (such as intraoral edentulous digital impressions). However, because digital dental impressions are taken under near-pressure-free conditions, directly identifying myostatic lines on these impressions cannot yield accurate myostatic boundaries, resulting in inaccurate denture margins and making them unsuitable for pressure fabrication of the embankment area. Furthermore, material shrinkage, plaster expansion, or other physical factors can cause deviations between traditional impression methods and the actual oral cavity conditions in plaster models, resulting in lower accuracy compared to digital dental impressions.

[0041] Based on this, the present application provides a method, apparatus, computer device, and storage medium for determining the edge line of a denture. Based on the application of deep learning technology in three-dimensional meshes, it can automatically identify the edge line of a denture on a three-dimensional digital oral impression. This method is highly robust and is not affected by the diversity of dentition morphology or the quality of the mesh surface, providing solid technical support for the subsequent design and manufacturing process of dentures. For example, when obtaining the edge line of a denture, a combination of a digital oral impression and a traditional impression-taking method can be used. A scanner is used to scan a plaster model obtained through traditional impression taking (e.g., a plaster model of an edentulous jaw). Through artificial intelligence learning, myostatic lines or denture edge lines are identified on the scanned plaster model, and then these myostatic lines or denture edge lines are mapped onto the digital oral impression obtained by the intraoral scanner.

[0042] In related technologies, the oral cavity of edentulous patients and the oral cavity of dentate patients are different. The environment, the scanned object, and the object being prepared are different. The oral cavity of edentulous patients has a mucosal area without natural teeth, while the oral cavity of dentate patients contains teeth. The oral cavity of dentate patients can scan the hard tissue of teeth (teeth or tooth preparation) with accurate boundaries. The oral cavity of edentulous patients can only scan the mucosal area of ​​the oral cavity without accurate boundaries. The data processing is also different. This application is for complete dentures (adhesive dentures).

[0043] The inventors of this application discovered that first oral data acquired under a certain pressure state, due to the significant functional pressure on the oral soft tissue during the fabrication process, can more accurately reflect the anatomical morphology of the myostatic line, resulting in a more accurate prosthesis edge line. Based on this discovery, a scheme is proposed that uses an AI model to identify the prosthesis reference line from the first oral data acquired under higher pressure, and then maps it onto second oral data acquired under lower pressure to obtain the target prosthesis edge line. The myodynamic area is displaced under stress; therefore, the first oral data in this application can characterize the myodynamic area displaced under stress state acquired under the first pressure state, i.e., the mucosa is under stress, causing the myodynamic area to be displaced. This allows for accurate acquisition of the prosthesis edge line without traction, and avoids inadequate traction and adhesion between the soft tissue and alveolar ridge, resulting in a more accurate extracted myostatic line.

[0044] 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.

[0045] 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.

[0046] This application provides a method for determining the edge line of a denture. This method can be executed by a computer device with data processing capabilities. Referring to Figure 1, a flowchart of a method for determining the edge line of a denture is shown. The method mainly includes the following steps S110 to S140:

[0047] Step S110: Obtain the first oral cavity data and the second oral cavity data corresponding to the target object.

[0048] The first oral cavity data represents the oral cavity of the target object under a first pressure state, and the second oral cavity data represents the oral cavity of the target object under a second pressure state, wherein the pressure under the second pressure state is less than the pressure under the first pressure state.

[0049] Specifically, the target group can be individuals who require dentures, for example, those whose oral cavity contains some teeth or no teeth. In one embodiment, the target group is an edentulous individual.

[0050] Optionally, the first oral cavity data can be obtained by three-dimensional scanning of a physical model of the target subject's oral cavity obtained under a first pressure impression, or by three-dimensional scanning of the target subject's historical dentures (old dentures), or by scanning the target subject's oral cavity under air pressure. The first pressure state can refer to the pressure state of the impression on the oral cavity, the pressure state of the historical denture on the oral cavity, or the pressure state of air pressure on the oral cavity. The second oral cavity data can be obtained by directly scanning the target subject's oral cavity under no physical pressure or standard atmospheric pressure (the second oral cavity data can be called a digital oral impression). The second pressure state can refer to no physical pressure or standard atmospheric pressure.

[0051] There are at least two ways to take a physical model of the oral cavity of the target subject under the first pressure. One is to use a high-precision physical impression material to completely wrap the soft tissues such as the gums and alveolar ridge, and remove the impression after it solidifies to obtain an oral impression (such as a silicone rubber impression, alginate impression, etc.). The other is to pour a mixed plaster material into the oral impression after it is taken, and obtain a plaster model after the plaster solidifies and the impression is separated.

[0052] There are at least two ways to obtain the first oral cavity data through the aforementioned physical model. One is to directly scan the surface of the oral impression to obtain intermediate data, which is then flipped to generate the first oral cavity data. The other is to directly scan the surface of the plaster model to obtain the first oral cavity data. If the first oral cavity data is obtained by scanning the plaster model corresponding to the target object in three dimensions, then the first oral cavity data can be called the target three-dimensional plaster model (i.e., the three-dimensional plaster model corresponding to the target object).

[0053] Optionally, both the first and second oral cavity data can be obtained by scanning the target's oral cavity with an intraoral scanner, the difference being the pressure exerted on the target's oral cavity during the scan.

[0054] The oral cavity of a target object can be scanned using scanning devices such as intraoral scanners and extraoral scanners to obtain a digital oral impression as shown in Figure 2. Similarly, the plaster model shown in Figure 3 can be scanned using extraoral scanners, intraoral scanners, or desktop scanners to obtain a target 3D plaster model. Figures 2 and 3 respectively show the digital oral impression and the target 3D plaster model corresponding to a specific target object. Both the digital oral impression and the target 3D plaster model can be obtained as meshed data through 3D reconstruction, point cloud registration, and meshing processing after 3D scanning.

[0055] Digital dental impressions can be obtained using high-precision optical dental scanning technology. This process does not involve physical pressure, making it difficult to accurately record the myostatic line characteristics under functional conditions (i.e., muscle movement), thus affecting the denture margin. In contrast, traditional plaster models are affected by functional pressure from the oral soft tissues during fabrication, which more accurately reflects the anatomical morphology of the myostatic line, resulting in a more accurate denture margin.

[0056] Step S120: Based on the trained AI model, the first oral cavity data is used to identify the denture reference line to obtain the first denture reference line.

[0057] The aforementioned first denture reference line can be either the first myostatic line on the first oral cavity data or the first denture edge line on the first oral cavity data. For example, three-dimensional deep learning technology can be used to identify the myostatic line / denture edge line in the scanned target three-dimensional plaster model to obtain the first myostatic line / first denture edge line, as shown in Figure 4, where the line indicated by the arrow is the first myostatic line.

[0058] In this embodiment, the denture edge line (myostatic line) refers to the edge of a suction-type denture designed for edentulous patients (the myostatic line is a virtual boundary line of the myostatic zone, which refers to the area related to masticatory muscle activity that needs to be considered during denture restoration; these areas do not experience mucosal movement during physiological activities such as chewing and speaking), and is not an anatomical structure. The denture edge line is an artificially defined virtual line that cannot be directly observed in the patient's mouth. It cannot be directly identified by clearly visible geometric features such as the shoulder area, and it lacks obvious groove or protrusion areas, making static confirmation impossible. Meanwhile, the denture margin is located in soft tissue areas such as the gums and mucosa that are not easily identifiable, and the tissue area is different from that of the cervical margin of the prepared tooth. During the design process, it is necessary to consider that the suction denture may affect the patient's chewing movement. For example, when the patient wears a denture with an unsuitable margin, the patient's chewing movement may collide with the myostatic area in the oral cavity, causing discomfort to the patient. Therefore, during the design process, it is necessary to consider the patient's chewing movement and other dynamic movements before determining the margin of the suction denture. This application also obtained the margin of the denture by speculation before denture processing.

[0059] In some possible embodiments, the denture margin line can be designed based on the myostatic line within the oral cavity. The myostatic line can only be confirmed after dynamic occlusion or stretching, and is not a static feature line visible to the naked eye; it cannot be directly identified by clearly visible geometric features (such as the shoulder). The myostatic line is the boundary between the dynamic and static zones, i.e., a line with zero mobility; it is a theoretical line located in the middle region of the gingival mucosa. It is not a line obtained by simply identifying geometric features (such as the shoulder), nor is it a line clearly visible after tooth preparation or other processing. Currently, the identification of the myostatic line usually relies on the doctor's experience, and different doctors may identify the same myostatic line. This application uses the pressure during impression taking to simulate the patient's chewing movements, thereby inferring the denture margin line (myostatic line). In some possible embodiments of this application, the geometric features of the oral mucosa are identified to infer the denture margin line (myostatic line).

[0060] In some possible embodiments, the AI ​​model can be a denture reference line recognition model. This model is trained on a 3D deep learning model using multiple sample oral cavity data with denture reference line annotations. The sample oral cavity data represents the oral cavity of the sample object under a first pressure state. The training process of the AI ​​model will be described in detail later. Therefore, step S120 may include: using the denture reference line recognition model to identify the first oral cavity data to obtain a first denture reference line.

[0061] In other possible embodiments, considering that specific anatomical points within the oral cavity can be used to locate denture reference lines such as myostatic lines or denture margins, the AI ​​model can be an anatomical point recognition model. This model is trained on a three-dimensional deep learning model using multiple sample oral data with anatomical point annotations. The sample oral data represents the oral cavity of the sample object under a first pressure state. Based on this, step S120 can include: using the anatomical point recognition model to identify the first oral data to obtain the target anatomical point; and determining the first denture reference line based on the target anatomical point. In one possible implementation, the target anatomical point can first be curve-fitted to obtain an anatomical point curve, and then the anatomical point curve can be pre-adjusted to obtain the first denture reference line. In another possible implementation, the reference point corresponding to the target anatomical point can be determined first, and then the reference point can be curve-fitted to obtain the first denture reference line.

[0062] Step S130: Based on the registration information between the first oral cavity data and the second oral cavity data, the first denture reference line is mapped onto the second oral cavity data to obtain the target denture edge line.

[0063] Taking the first oral cavity data as the target three-dimensional plaster model and the second oral cavity data as the oral digital impression as an example, we can first use the common rigid body regions such as the alveolar ridge and / or the maxilla to obtain the registration information between the oral digital impression and the target three-dimensional plaster model. The registered oral digital impression and the target three-dimensional plaster model are in the same coordinate system, so the first denture reference line can be mapped onto the oral digital impression to obtain the edge line of the target denture.

[0064] The method for determining the edge line of a denture provided in this application can acquire first oral cavity data and second oral cavity data corresponding to the target object when determining the edge line of the denture. The first oral cavity data represents the oral cavity of the target object under a first pressure state, and the second oral cavity data represents the oral cavity of the target object under a second pressure state, where the pressure under the second pressure state is less than the pressure under the first pressure state. A denture reference line is identified on the first oral cavity data using a trained AI model to obtain a first denture reference line. Based on the registration information between the first and second oral cavity data, the first denture reference line is mapped onto the second oral cavity data to obtain the target denture edge line. Since the impression pressure corresponding to the first oral cavity data is greater than that corresponding to the second oral cavity data, the accuracy of the second oral cavity data is higher than that of the first oral cavity data. The first denture reference line corresponding to the first oral cavity data is less susceptible to interference from the diversity of dental morphology and the quality of the mesh surface. Through artificial intelligence learning, the first denture reference line corresponding to the first oral cavity data can be accurately identified. Mapping the first denture reference line onto the more accurate second oral cavity data facilitates subsequent data storage and design. By combining the first and second oral cavity data under different pressure conditions, the edge trimming effect is achieved. The denture edge line of the second oral cavity data is automatically and accurately identified, which also facilitates subsequent digital storage and design.

[0065] To facilitate understanding, the specific details involved in the above method for determining the edge line of dentures will be explained in detail below.

[0066] To improve computational efficiency and recognition accuracy, the step S120, which involves identifying the denture reference line from the first oral cavity data using the trained AI model, may include the following sub-steps:

[0067] Sub-step S121 involves preprocessing the first oral cavity data to obtain preprocessed first oral cavity data. The preprocessing includes one or more of the following: data denoising, data alignment, mesh simplification, Laplacian feature calculation, sparse coding representation, and surface feature fusion. These preprocessing procedures will be described in detail later.

[0068] Sub-step S122: Input the preprocessed first oral cavity data into the AI ​​model to obtain the denture reference line recognition result output by the AI ​​model; wherein, the AI ​​model is obtained by training a three-dimensional deep learning model based on multiple sample oral cavity data with denture reference line annotation data, and the sample oral cavity data is used to represent the oral cavity of the sample object under the first pressure state.

[0069] The first denture reference line can be the first myostatic line. At this time, the denture reference line annotation data can be myostatic annotation data, which includes myostatic line data or myostatic region data. The denture reference line recognition result output by the AI ​​model is the myostatic recognition result, which can be the identified myostatic line or the identified myostatic region.

[0070] The first denture reference line can also be the first denture edge line. In this case, the denture reference line annotation data can be myostatic annotation data or denture edge line annotation data. The denture reference line recognition result output by the AI ​​model can be the myostatic recognition result or the denture edge line recognition result.

[0071] Sub-step S123: Determine the first denture reference line based on the denture reference line recognition result.

[0072] When the first denture reference line is the first myostatic line and the denture reference line recognition result is the myostatic recognition result, if the myostatic recognition result is the identified myostatic line, then the identified myostatic line can be directly used as the first myostatic line; if the myostatic recognition result is the identified myostatic area, then the boundary line of the identified myostatic area can be directly determined as the first myostatic line.

[0073] When the reference line for the first denture is the edge line of the first denture, and the denture reference line identification result is the myostatic identification result, if the myostatic identification result is the identified myostatic line, then the identified myostatic line can be used as the first myostatic line, and the edge line of the first denture can be determined based on the first myostatic line; if the myostatic identification result is the identified myostatic area, then the boundary line of the identified myostatic area can be first determined as the first myostatic line, and then the edge line of the first denture can be determined based on the first myostatic line. Optionally, the step of determining the edge line of the first denture based on the first myostatic line may include: determining an equidistant line approximately 2mm-5mm from the boundary of the first myostatic line towards the gum line as the edge line of the first denture.

[0074] When the reference line for the first denture is the edge line of the first denture, and the denture reference line recognition result is the denture edge line recognition result, the denture edge line in the denture edge line recognition result can be directly determined as the edge line of the first denture.

[0075] This will give you the reference line for the first denture.

[0076] To improve the accuracy of the mapping, the step S130, which maps the first denture reference line onto the second oral data based on the registration information between the first and second oral data to obtain the edge line of the target denture, may include the following sub-steps:

[0077] Sub-step S131: Using a preset rigid body region, register the first oral cavity data and the second oral cavity data to obtain registration information; wherein, the rigid body region includes the alveolar ridge and / or the maxilla.

[0078] Sub-step S132: Based on the registration information, the first denture reference line is mapped onto the second oral cavity data to obtain the second denture reference line.

[0079] Sampling points can be obtained from the first denture reference line. Based on the registration information, neighboring points (i.e., matching points) are found on the second oral data. The neighboring points are fitted into a three-dimensional curve, which is the second denture reference line. Based on this, sub-step S132 can be implemented through the following process: obtaining multiple sampling points from the first denture reference line; determining the matching points of each sampling point on the second oral data according to the registration information; and performing three-dimensional curve fitting on each matching point to obtain the second denture reference line.

[0080] When the reference line for the first denture is the first myostatic line, the reference line for the second denture is the second myostatic line; when the reference line for the first denture is the edge line of the first denture, the reference line for the second denture is the edge line of the second denture.

[0081] Sub-step S133: Determine the edge line of the target denture based on the second denture reference line.

[0082] To improve data quality and enhance the precision and accuracy of data processing, the second denture reference line can be smoothed to obtain a smoothed denture reference line; based on the smoothed denture reference line, the edge line of the target denture can be determined.

[0083] Optionally, the above-mentioned smoothing process of the second denture reference line to obtain a smoothed denture reference line may include: smoothing the second denture reference line using a target smoothing algorithm to obtain a smoothed denture reference line; wherein, the target smoothing algorithm is determined according to the preset morphological characteristics and processing requirements of the denture, and the target smoothing algorithm includes one or more of the following: Laplace smoothing algorithm, least squares smoothing algorithm, and curvature-based feature smoothing algorithm.

[0084] Optionally, determining the target denture edge line based on the smoothed denture reference line may include: when the second denture reference line is the second myostatic line, the target denture edge line can be determined based on the smoothed second myostatic line; when the second denture reference line is the second denture edge line, the smoothed second denture edge line can be directly determined as the target denture edge line. Optionally, the step of determining the target denture edge line based on the smoothed second myostatic line may include: determining an equidistant line approximately 2mm-5mm from the boundary of the smoothed second myostatic line towards the gingiva as the target denture edge line.

[0085] In some possible embodiments, the above AI model can be trained through the following two steps:

[0086] A1. Obtain oral data from multiple samples with denture reference line annotations.

[0087] The initial oral data, such as the scanned 3D plaster model, can be manually marked with myostatic lines, myostatic regions, and denture edge lines. Then, preprocessing such as mesh optimization can be performed to reduce the amount of computation while preserving geometric features. Finally, the preprocessed data can be fed into the constructed 3D deep learning model for training.

[0088] In one possible implementation, multiple sample oral cavity data can be obtained by: acquiring multiple initial oral cavity data with denture reference line annotation data; wherein the initial oral cavity data is used to represent the oral cavity of the sample object under the first pressure state; preprocessing the multiple initial oral cavity data to obtain multiple sample oral cavity data; wherein the preprocessing includes one or more of the following: data denoising, data alignment, mesh simplification, Laplacian feature calculation, multi-scale data augmentation, sparse coding representation and surface feature fusion.

[0089] The above preprocessing methods will be described in detail below:

[0090] (a) Data denoising: Data denoising can be performed on the buccal and lingual sides of the data. After denoising, smoothing can be performed to improve the robustness of the algorithm.

[0091] (b) Data Alignment: By referencing oral features such as the dental arch curve, the 3D tooth mesh is initially aligned to reduce overfitting of the training data and facilitate the improvement of the network's generalization ability. Initial oral data, such as the 3D plaster model, can be aligned with pre-defined reference models using oral features such as the dental arch curve. Specifically, the 3D plaster model can be projected from multiple angles to obtain multiple 2D depth images. The dental arch curve is then fitted based on these multiple 2D depth images. This dental arch curve can be a contour line obtained by curve fitting the highest point of the tooth based on the depth data in the multiple 2D depth images, and it will appear as a curved crescent shape.

[0092] (c) Mesh Simplification: The number of vertices in flat regions is reduced by optimizing the algorithm while preserving their geometric features as much as possible, thereby improving processing efficiency and reducing computational complexity. Flat regions refer to areas in an image with relatively uniform visual characteristics, i.e., areas with small curvature variations. These regions may lack obvious color, texture, or shape variations and appear relatively uniform. Flat regions do not contain much visual detail or information and have a relatively small impact on image analysis and understanding; therefore, the number of mesh vertices can be appropriately reduced.

[0093] (d) Laplacian Feature Calculation (Obtaining Data with Laplacian Features): The Laplacian operator of the mesh is used to capture and extract the features of the mesh in different domains, providing crucial information for further analysis. These different domains refer to high frequencies (better mesh details) and low frequencies (better overall shape) in the frequency domain.

[0094] (e) Multi-scale data augmentation: Augmenting data at different scale levels (i.e., data augmentation through scaling) increases the number of samples, which helps the model learn different levels of detail and enhances its generalization ability.

[0095] (f) Sparse coding representation: Sparse coding techniques are used to represent the grid to eliminate redundant features, highlight important information, and may improve the interpretability of the model.

[0096] (g) Surface Feature Fusion: Calculate and fuse geometric features such as surface curvature and normal vectors of the mesh to enrich the model's input information and enhance its understanding of complex structures. Surface feature fusion yields data with geometric features such as surface curvature and normal vectors, facilitating better feature extraction by 3D deep learning networks.

[0097] Optionally, preprocessing can be performed in the order of (a), (b), (c), (d), and (g) to ensure high processing efficiency and good training results. Alternatively, preprocessing can be performed in the order of (a) to (g) to improve the accuracy of the trained recognition model and enhance its robustness and generalization ability. It should be noted that the specific preprocessing method can be selected according to actual needs, and this embodiment does not limit it.

[0098] A2. Train the 3D deep learning model based on the oral cavity data of each sample to obtain the AI ​​model; wherein, the 3D deep learning model includes any of the following: PointNet model, graph convolutional neural network model, MeshCNN model, multi-view model that analyzes 3D information from multiple perspectives, convolutional neural network model based on graph theory, and DiffusionNet model.

[0099] The aforementioned 3D deep learning models can be deep learning models specifically designed for processing 3D mesh data, and may include any of the following: PointNet models that directly manipulate point cloud data; Graph CNNs (i.e., graph convolutional neural network models) and MeshCNN models that utilize graph convolutional networks to process mesh topology; multi-view models that analyze 3D information from multiple perspectives; Spectral CNN models based on spectral theory (i.e., convolutional neural network models based on graph theory); and DiffusionNet models designed for geometric data, etc. The 3D deep learning model can be comprehensively considered and decided upon based on the needs of the actual application scenario, such as computational resource consumption and real-time requirements.

[0100] For both complete dentures and removable partial dentures, multiple sample oral data points for complete dentures and removable partial dentures can be acquired separately. These two types of sample oral data can be used to train an AI model that can be applied to the identification of myostatic lines / myostatic regions / denture edges in both cases. Alternatively, multiple sample oral data points for complete dentures can be used separately to train a first AI model for complete dentures, which can be applied to the identification of myostatic lines / myostatic regions / denture edges in the case of complete dentures. Conversely, multiple sample oral data points for removable partial dentures can be used separately to train a second AI model for removable partial dentures, which can be applied to the identification of myostatic lines / myostatic regions / denture edges in the case of removable partial dentures.

[0101] To facilitate understanding, the following section uses the first oral cavity data as the target 3D plaster model and the second oral cavity data as the oral digital impression as examples to provide a detailed introduction to the methods for determining the denture edge line in two cases: when the first denture reference line is the first myostatic line and when the first denture reference line is the edge line of the first denture.

[0102] I. The reference line for the first denture is the first muscle static line.

[0103] The above method for determining the edge line of dentures may include the following steps:

[0104] Step a1: Obtain the target 3D plaster model and oral digital impression corresponding to the target object.

[0105] Step a2 involves preprocessing the target 3D plaster model to obtain a preprocessed target 3D plaster model. The preprocessing may include one or more of the following: data denoising, data alignment, mesh simplification, Laplacian feature calculation, sparse coding representation, and surface feature fusion.

[0106] Step a3: Input the preprocessed target 3D plaster model into the first recognition model to obtain the myostatic force recognition result output by the first recognition model; wherein, the first recognition model is obtained by training a 3D deep learning model based on multiple first sample 3D plaster models with myostatic force annotation data, and the myostatic force annotation data includes myostatic force line data or myostatic force region data.

[0107] The above myostatic force recognition results correspond to the labeled data used during the training of the first recognition model, and can be the recognized myostatic force lines or the recognized myostatic force regions.

[0108] Step a4: Determine the first myostatic line based on the myostatic identification results.

[0109] In one possible implementation, when the myostatic force identification result is the identified myostatic force line, the identified myostatic force line can be directly used as the first myostatic force line; when the myostatic force identification result is the identified myostatic force region, the boundary line of the identified myostatic force region (i.e., the dividing line between the myostatic force region and the myodynamic force region) can be directly determined as the first myostatic force line.

[0110] In another possible implementation, the myostatic force identification results can be adjusted interactively: the myostatic force identification results are displayed on an interactive interface for users to view and adjust them; in response to the user's adjustment operation, the adjusted myostatic force identification result is determined, and a first myostatic force line is determined based on the adjusted myostatic force identification result. Specifically, when the myostatic force identification result is the identified myostatic force line, the adjusted myostatic force identification result is the adjusted myostatic force line, and this adjusted myostatic force line can be determined as the first myostatic force line; when the myostatic force identification result is the identified myostatic force region, the adjusted myostatic force identification result is the adjusted myostatic force region, and the boundary line of the adjusted myostatic force region can be determined as the first myostatic force line.

[0111] Step a5: Using a preset rigid body region, register the oral digital impression and the target three-dimensional plaster model to obtain registration information; wherein, the rigid body region includes the alveolar ridge and / or the maxilla.

[0112] Step a6: Based on the registration information, map the first myostatic line onto the oral digital impression to obtain the second myostatic line.

[0113] Referring to Figure 5, a schematic diagram of myostatic line mapping is shown. After obtaining the oral digital impression and the first myostatic line on the target three-dimensional plaster model, the oral digital impression and the target three-dimensional plaster model can be registered according to the alveolar ridge region, and the myostatic line (i.e., the first myostatic line) can be mapped onto the digital impression (i.e., the oral digital impression).

[0114] Sampling points can be obtained from the first myostatic line. Based on the registration information, neighboring points (i.e., matching points) are found on the digital oral impression. The neighboring points are fitted into a three-dimensional curve, which is the second myostatic line. Based on this, sub-step S132 can be implemented through the following process: obtaining multiple sampling points from the first myostatic line; determining the matching points of each sampling point on the digital oral impression according to the registration information; and performing three-dimensional curve fitting on each matching point to obtain the second myostatic line.

[0115] This method maps the myostatic lines identified on the 3D plaster model corresponding to the traditional impression method onto the oral digital impression, ensuring a high-precision digital model while obtaining accurate myostatic boundary lines.

[0116] Step a7: Determine the target denture edge line based on the second myostatic line.

[0117] To improve data quality and enhance the precision and accuracy of data processing, the second myostatic line can be smoothed to obtain a smoothed second myostatic line; based on the smoothed second myostatic line, the edge line of the target denture can be determined.

[0118] Optionally, the above-mentioned smoothing process of the second myostatic line to obtain the smoothed second myostatic line may include: smoothing the second myostatic line using a target smoothing algorithm to obtain the smoothed second myostatic line; wherein, the target smoothing algorithm is determined according to the preset morphological characteristics and processing requirements of the denture, and the target smoothing algorithm includes one or more of the Laplace smoothing algorithm, the least squares smoothing algorithm, and the curvature-based feature smoothing algorithm.

[0119] In one possible implementation, the target denture edge line can be directly determined based on the smoothed second myostatic line. For example, an equidistant line approximately 2mm-5mm from the boundary of the smoothed second myostatic line towards the gum line can be defined as the target denture edge line. In another possible implementation, the smoothed second myostatic line can be adjusted interactively: the smoothed second myostatic line is displayed on an interactive interface for user viewing and adjustment; in response to user adjustments, the adjusted target myostatic line is determined, and the target denture edge line is determined based on this adjusted target myostatic line. For example, an equidistant line approximately 2mm-5mm from the boundary of the adjusted target myostatic line towards the gum line can be defined as the target denture edge line.

[0120] II. The reference line for the first denture is the edge line of the first denture.

[0121] The above method for determining the edge line of dentures may include the following steps:

[0122] Step b1: Obtain the target 3D plaster model and oral digital impression corresponding to the target object.

[0123] Step b2 involves preprocessing the target 3D plaster model to obtain a preprocessed target 3D plaster model. The preprocessing may include one or more of the following: data denoising, data alignment, mesh simplification, Laplacian feature calculation, sparse coding representation, and surface feature fusion.

[0124] Step b3: Input the preprocessed target 3D plaster model into the first recognition model to obtain the myostatic recognition result output by the first recognition model, and determine the first denture edge line according to the first myostatic line corresponding to the myostatic recognition result; or, input the preprocessed target 3D plaster model into the second recognition model to obtain the denture edge line recognition result output by the second recognition model, and determine the denture edge line in the denture edge line recognition result as the first denture edge line.

[0125] The first recognition model is obtained by training a three-dimensional deep learning model on multiple first-sample three-dimensional plaster models with myostatic annotation data, including myostatic line data or myostatic region data; the second recognition model is obtained by training a three-dimensional deep learning model on multiple second-sample three-dimensional plaster models with denture edge line annotation data.

[0126] Step b4: Using a preset rigid body region, register the oral digital impression and the target three-dimensional plaster model to obtain registration information; wherein, the rigid body region includes the alveolar ridge and / or the maxilla.

[0127] Step b5: Based on the registration information, map the edge line of the first denture onto the digital dental impression to obtain the edge line of the second denture.

[0128] Step b6: Determine the edge line of the target denture based on the edge line of the second denture.

[0129] The process and mapping method for obtaining the above registration information can be referred to the corresponding content of the foregoing embodiments, and will not be repeated here. The step of determining the target denture edge line based on the edge line of the second denture may include: smoothing the edge line of the second denture to obtain a smoothed edge line of the second denture; and determining the target denture edge line based on the smoothed edge line of the second denture.

[0130] In one possible implementation, the smoothed edge line of the second denture can be obtained as follows: the edge line of the second denture is smoothed using a target smoothing algorithm to obtain the smoothed edge line of the second denture; wherein, the target smoothing algorithm is determined according to the preset morphological characteristics and processing requirements of the denture, and the target smoothing algorithm includes one or more of the following: Laplace smoothing algorithm, least squares smoothing algorithm, and curvature-based feature smoothing algorithm.

[0131] In one possible implementation, the smoothed edge line of the second denture can be directly determined as the target denture edge line; alternatively, the target denture edge line can be determined as follows: display the smoothed edge line of the second denture on the interactive interface; in response to the user's adjustment operation on the smoothed edge line of the second denture, determine the adjusted denture edge line and set the adjusted denture edge line as the target denture edge line.

[0132] In this embodiment, based on the traditional impression method, three-dimensional deep learning technology is used to accurately mark / identify the myostatic line / denture edge line, ensuring better robustness for different dentition shapes; by combining the plaster model obtained by the traditional impression method with the oral digital impression, a high-precision digital model is ensured while obtaining an accurate myostatic boundary line, thereby obtaining an accurate denture edge line.

[0133] In an optional embodiment, after the steps of obtaining the first oral cavity data and the second oral cavity data corresponding to the target object, the method further includes: judging the data integrity of the first oral cavity data and the second oral cavity data to obtain the degree of integrity; and determining the accuracy of the edge line of the target denture based on the degree of integrity.

[0134] Optionally, the degree of completeness can be determined as follows: determine whether the first oral data and / or the second oral data contain a preset key region, and obtain a containment determination result; wherein, the key region corresponding to the first oral data includes a first designated region, and the key region corresponding to the second oral data includes a second designated region; determine the degree of completeness based on the containment determination result.

[0135] In one possible implementation, both the first and second designated regions may include at least two of the following: the labial frenulum, the buccal frenulum, the maxillary tuberosity, the pterygomaxillary notch, and the region 2 mm posterior to the maxillary fossa.

[0136] In another possible implementation, considering that digital oral impressions need to confirm the complete scanning of key areas such as the labial frenulum, buccal frenulum, vestibular mucosal folds, lower zygomatic border, and buccal aspect of the maxillary tuberosity, to ensure that the scan data includes complete myostatic lines; the target 3D plaster model needs to completely cover key areas such as the alveolar ridge, jaw structure, palate, labial, buccal, and lingual mucosa, frenulum, and salivary gland openings, to ensure accurate occlusal relationships and clear edges, reflecting the detailed oral structure of the target subject and ensuring accurate extraction of myostatic lines or denture margins. Based on this, the first designated area may include at least two of the alveolar ridge, jaw structure, palate, labial, buccal, and lingual mucosa, frenulum, and salivary gland openings; the second designated area may include at least two of the labial frenulum, buccal frenulum, vestibular mucosal folds, lower zygomatic border, and buccal aspect of the maxillary tuberosity.

[0137] Therefore, the first designated region may include at least two of the alveolar ridge, jaw structure, palate, labial, buccal and lingual mucosa, frenulum, and salivary gland openings, ensuring that the scan data includes complete myostatic lines. The second designated region may include at least two of the labial frenulum, buccal frenulum, vestibular mucosal fold, lower border of the zygomatic bone, and buccal side of the maxillary tuberosity, ensuring accurate occlusal relationships and clear edges to reflect the detailed oral structure of the target subject and ensure accurate extraction of myostatic lines or denture edge lines. These are all key to the subsequent application of the target denture edge lines. Therefore, this application uses completeness judgment to determine whether the first pressure state is sufficient when acquiring the first oral data, and whether the key areas are scanned with a certain pressure, thereby judging the accuracy of denture edge line identification.

[0138] AI can be used to determine whether a preset key area is included. The inclusion determination result can include the inclusion status of different key areas, such as whether the oral digital impression includes other key areas besides the labial frenulum. Based on the inclusion determination result, the inclusion percentage corresponding to the first oral data and / or the inclusion percentage corresponding to the second oral data can be determined, wherein the inclusion percentage corresponding to the first oral data and the inclusion percentage corresponding to the second oral data are calculated separately. Based on the inclusion percentage corresponding to the first oral data and / or the inclusion percentage corresponding to the second oral data, the degree of completeness can be determined.

[0139] When determining the inclusion percentage of key regions, the percentage of each key region can be preset, and the inclusion percentage can be determined based on the percentage and inclusion status of each key region. The percentages of different key regions can be the same or different; when the percentages of different key regions are the same, the inclusion percentage can be obtained by dividing the number of included key regions by the total number of key regions; when the percentages of different key regions are different, the inclusion percentages of the included key regions can be summed to obtain the inclusion percentage. If only the inclusion percentage corresponding to the first oral cavity data or the inclusion percentage corresponding to the second oral cavity data exists, then the inclusion percentage corresponding to the first oral cavity data or the inclusion percentage corresponding to the second oral cavity data is directly used as the completeness degree; if there are inclusion percentages corresponding to the first oral cavity data and the inclusion percentages corresponding to the second oral cavity data, then the two (i.e., the two inclusion percentages) can be weighted and summed to obtain the completeness degree. The weights of the two can be set according to actual needs and are not limited here.

[0140] It should be noted that the above-mentioned key areas can be selected according to actual needs, and this embodiment does not limit this.

[0141] Optionally, when determining the accuracy of the target denture edge line based on the degree of integrity, the accuracy can be obtained by looking up the corresponding integrity level in a preset correspondence between integrity and accuracy. Accuracy can be divided into multiple levels according to actual needs, such as two levels (accurate and inaccurate), or three levels (high, medium, and low); accuracy can also be expressed as a percentage, for example, the accuracy of the target denture edge line is 80%.

[0142] Optionally, after determining the integrity of the first oral cavity data and the second oral cavity data and obtaining the integrity level, the above method further includes: determining whether the integrity level is less than a preset integrity threshold; if it is less than the integrity threshold, issuing a data incompleteness reminder.

[0143] The integrity threshold can be set according to actual needs and is not limited here. When issuing a data incompleteness alert, it can only indicate which data is incomplete, for example, the first oral cavity data is incomplete; it can also further indicate which part of which data is incomplete, for example, the maxillary tuberosity buccal side of the second oral cavity data is incomplete. This allows users to easily understand the data incompleteness situation and replace the data in a timely manner.

[0144] In one optional embodiment, the target denture edge line is displayed on the interactive interface, where the user can adjust it. However, since the user is adjusting the target denture edge line on a two-dimensional display interface (i.e., the interactive interface), directly adjusting the edge line according to the user's two-dimensional commands can easily lead to excessive movement, causing it to move out of the myostatic zone or become too close to the myodynamic zone. Furthermore, if the complete denture or removable partial denture is designed based on a target denture edge line that is out of the myostatic zone or too close to the myodynamic zone, the denture is prone to shifting during wear or may collide during chewing or other physiological movements, causing discomfort to the patient. Simultaneously, because the patient's oral cavity is not a regular cylinder, simply translating or enlarging / shrinking the target denture edge line according to the user's two-dimensional commands can cause it to detach from the model surface (i.e., the surface of the second oral data), resulting in a discrepancy between the target denture edge line and the patient's actual oral condition, making subsequent denture design impossible.

[0145] To address the aforementioned issues, after the step of mapping the first denture reference line onto the second oral data based on the registration information between the first and second oral data to obtain the target denture edge line, the method further includes: when a first command is detected, determining the first pose change of the target denture edge line relative to its initial position, wherein the first command is a user command to adjust the pose of the target denture edge line in the second oral data; based on the first pose change and preset reference conditions, determining the first adjusted pose of the target denture edge line, and updating and displaying the pose of the target denture edge line based on the first adjusted pose of the target denture edge line, wherein the preset reference conditions include the fit between the target denture edge line and the outer surface of the second oral data, and the target denture edge line conforming to... The method involves simulating physiological movement or the target denture edge line being located within the denture coverage area, or in one or more of the following ways: when a first pose change is detected that causes the target denture edge line to deviate from the preset reference conditions, the pose of the target denture edge line is adaptively updated according to the preset reference conditions; or, the pose of the target denture edge line is not updated, and the user confirms the result again, and the pose of the target denture edge line is adjusted according to the user confirms the result again; and / or when a first adjusted pose is detected that causes the target denture edge line to deviate from the preset reference conditions, the pose of the target denture edge line is adaptively updated according to the preset reference conditions; or, the pose of the target denture edge line is not updated, and the user confirms the result again, and the pose of the target denture edge line is adjusted according to the user confirms the result again.

[0146] It's understandable that not updating the pose of the target denture edge line means not moving or offsetting the target denture edge line, and not updating the displayed pose after any movement or offset. Updating the pose of the target denture edge line can be understood as continuing to move or offset the target denture edge line, and updating the displayed pose after any movement or offset. Adjusting the pose of the target denture edge line based on the user's confirmation can either mean not updating the pose or updating it, depending on the user's choice. When not updating the pose, a prompt or other feedback message can be displayed to provide the user with some feedback.

[0147] Therefore, in this embodiment, the first adjustment pose can be recalculated based on the first pose change, including the movement distance of the target denture edge line relative to its initial pose and / or the offset angle of the target denture edge line relative to its initial pose, combined with the outer surface of the second oral cavity data, and the preset reference conditions (medical reference requirements) such as the determined denture coverage area or simulated physiological movement, etc. The first adjustment pose is 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 pose of the target denture edge line (first adjustment pose) on the two-dimensional display interface always meets the preset reference conditions, that is, meets the basic medical requirements, such as the target denture edge line should be within the denture coverage area, or meets the simulated physiological movement, that is, the target denture edge line will not move or the movement range of the target denture edge line is within a preset range during chewing or mandibular movement, which can be the range corresponding to the denture coverage area.

[0148] Specifically, the first position change can be decomposed according to preset reference conditions. Some or all of the instructions in the first position change that meet the preset reference conditions are determined as the first adjustment position of the target denture edge line, while some or all of the instructions in the first position change that do not meet the preset reference conditions are ignored. The preset reference conditions may include: the target denture edge line should fit the outer surface of the second oral cavity data, the target denture edge line should be within the denture coverage area, or the target denture edge line should conform to one or more of the simulated physiological movements.

[0149] For example, the first instruction includes the user clicking the target denture edge line with the mouse to move it horizontally or diagonally by an X distance. If the X distance causes the target denture edge line to not conform to the outer surface of the second oral data, not be within the denture coverage area, or not conform to the simulated physiological movement, then the instruction to move the target 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. At this time, there are two operation 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, and displays the updated target denture edge line; Second, the adjusted target denture edge line is not displayed first, and a prompt box is issued to inform the user that there may be a problem with this adjustment, and asks the user to confirm again. Based on the result of 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 pose of the target denture edge line is updated according to the user's instruction; if the user indicates "abandon modification", the first adjustment pose is 0, and the pose of the target denture edge line is not updated according to the user's instruction.

[0150] For example, the first instruction includes the user clicking the target denture edge line by an X-distance to move it diagonally. This X-distance is decomposed into a vertical (Z-direction in Figure 6, where vertical movement refers to moving up and down along the gingival surface) movement by a distance B and a horizontal (X-direction in Figure 6, where horizontal movement refers to moving forward and backward along the normal direction of the outer surface of the second oral cavity data) movement by a distance C. The horizontal movement by distance C is ignored and not executed, while the vertical movement by distance B is executed. This is equivalent to projecting the diagonal X-distance movement onto a vertical plane (XZ plane in Figure 6). The first adjustment pose of the target denture edge line is the target denture edge line moving up and down by a distance B along the gingival surface. Based on the target denture edge line after the vertical movement by distance B, the latest target denture edge line is automatically calculated and generated according to the outer surface of the second oral cavity data, so that the target denture edge line fits the outer surface of the model.

[0151] For example, after determining the first adjustment posture, it can be determined again whether the target denture edge line conforms to simulated physiological movement or is located within the denture coverage area. If so, it means that the first adjustment posture meets the medical reference conditions, and it can be adjusted according to the first adjustment posture, with the adjusted target denture edge line displayed on the interactive interface. If not, it means that the first adjustment posture does not meet the medical reference conditions, and there are two 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 target denture edge line is not displayed first, and a prompt box is issued, indicating to the user that there may be problems with this adjustment, 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 posture of the target denture edge line will be updated according to the user's instructions; If the user indicates "abandon modification", the posture of the target denture edge line will not be updated according to the user's instructions.

[0152] In one embodiment, based on a first instruction, the edge line of the target denture can be controlled to rotate to the pose indicated by the first instruction, based on the current coordinates of the mouse. At this time, the interactive interface displays the edge line of the target denture falling at the mouse click position. Simultaneously, the angle or distance of rotation of the target denture edge line around the target denture edge line is determined by projecting the mouse movement distance onto a vertical plane (the XZ plane in Figure 6).

[0153] It should be noted that the myostatic region can be divided into upper and lower parts by the edge line of the target denture. Therefore, the denture coverage area can refer to the entire myostatic region, or specifically the upper part of the myostatic region divided by the edge line of the target denture. 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. Simulated physiological motion refers to simulated physiological motion automatically generated by inputting second oral 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 selects to display the simulated physiological motion on the interactive interface, the second oral data on the interface will change according to the simulated physiological motion. The user can visually observe whether the edge line of the target denture is suitable and can move or adjust the edge line. When the user chooses not to display the simulated physiological motion on the interactive interface, the interface can directly output the computer's judgment on whether the edge line of the target denture conforms to the simulated physiological motion.

[0154] 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 the mandibular movement trajectory and chewing movement trajectory obtained by CBCT (cone beam computed tomography) equipment, facial scanners, extraoral scanners or intraoral scanners.

[0155] In an optional embodiment, a three-dimensional denture model can be obtained based on the edge line of the target denture. After quickly printing the three-dimensional denture model, a solid denture can be obtained and tested by the user. Based on the results of the user's test, the edge line of the target denture or the three-dimensional denture model can be further adjusted to obtain a denture that better meets the user's needs.

[0156] Based on this, after the step of mapping the first denture reference line onto the second denture data according to the registration information between the first and second oral data to obtain the target denture edge line, the method further includes:

[0157] Based on the target denture edge line and second oral cavity data, a three-dimensional denture model is generated and sent to a 3D printing device configured to print the three-dimensional denture model.

[0158] When a user request to modify the 3D denture model is received, the revised target denture edge line and / or the revised 3D denture model are output based on the user request, the target denture edge line, and the second oral cavity data.

[0159] Corresponding to the above-described method for determining the edge line of a denture, this application also provides a device for determining the edge line of a denture. Referring to Figure 7, a schematic diagram of a device for determining the edge line of a denture is shown. The device includes:

[0160] The data acquisition module 701 is configured to acquire first oral cavity data and second oral cavity data corresponding to the target object; wherein, the first oral cavity data is used to represent the oral cavity of the target object under a first pressure state, and the second oral cavity data is used to represent the oral cavity of the target object under a second pressure state, wherein the pressure under the second pressure state is less than the pressure under the first pressure state;

[0161] The denture reference line recognition module 702 is configured to perform denture reference line recognition on the first oral cavity data based on the trained AI model to obtain the first denture reference line.

[0162] The denture edge mapping module 703 is configured to map the first denture reference line onto the second oral data based on the registration information between the first oral data and the second oral data, so as to obtain the target denture edge line.

[0163] The denture edge line determination device provided in this application can acquire first oral cavity data and second oral cavity data corresponding to the target object when determining the denture edge line. The first oral cavity data represents the target object's oral cavity under a first pressure state, and the second oral cavity data represents the target object's oral cavity under a second pressure state, where the pressure under the second pressure state is less than the pressure under the first pressure state. A denture reference line is identified on the first oral cavity data using a trained AI model to obtain a first denture reference line. Based on the registration information between the first and second oral cavity data, the first denture reference line is mapped onto the second oral cavity data to obtain the target denture edge line. Since the impression pressure corresponding to the first oral cavity data is greater than that corresponding to the second oral cavity data, the accuracy of the second oral cavity data is higher than that of the first oral cavity data. The first denture reference line corresponding to the first oral cavity data is less susceptible to interference from the diversity of dental morphology and the quality of the mesh surface. Through artificial intelligence learning, the first denture reference line corresponding to the first oral cavity data can be accurately identified. Mapping the first denture reference line onto the more accurate second oral cavity data facilitates subsequent data storage and design. By combining the first and second oral cavity data under different pressure conditions, the edge trimming effect is achieved. The denture edge line of the second oral cavity data is automatically and accurately identified, which also facilitates subsequent digital storage and design.

[0164] Optionally, the aforementioned denture reference line recognition module 702 is specifically configured to: preprocess the first oral cavity data to obtain preprocessed first oral cavity data; wherein, the preprocessing includes one or more of the following: data denoising, data alignment, mesh simplification, Laplacian feature calculation, sparse coding representation, and surface feature fusion; input the preprocessed first oral cavity data into the AI ​​model to obtain the denture reference line recognition result output by the AI ​​model; wherein, the AI ​​model is obtained by training a three-dimensional deep learning model based on multiple sample oral cavity data with denture reference line annotation data, and the sample oral cavity data is used to represent the oral cavity of the sample object under the first pressure state; and determine the first denture reference line according to the denture reference line recognition result.

[0165] Optionally, the first denture reference line includes the first myostatic line, and the denture reference line annotation data includes myostatic annotation data, which includes myostatic line data or myostatic region data; or...

[0166] The first denture reference line includes the edge line of the first denture, and the denture reference line annotation data includes myostatic annotation data or denture edge line annotation data.

[0167] Optionally, the aforementioned denture edge mapping module 703 is specifically configured to: register the first oral cavity data and the second oral cavity data using a preset rigid body region to obtain registration information; wherein, the rigid body region includes the alveolar ridge and / or the maxilla; map the first denture reference line onto the second oral cavity data according to the registration information to obtain the second denture reference line; and determine the target denture edge line according to the second denture reference line.

[0168] Optionally, the above-mentioned denture edge mapping module 703 is further configured to: acquire multiple sampling points from the first denture reference line; determine the matching point of each sampling point on the second oral data according to the registration information; and perform three-dimensional curve fitting on each matching point to obtain the second denture reference line.

[0169] Optionally, the above-mentioned denture edge mapping module 703 is further configured to: smooth the second denture reference line to obtain a smoothed denture reference line; and determine the target denture edge line based on the smoothed denture reference line.

[0170] Optionally, the above-mentioned device further includes a training module configured to: acquire multiple sample oral cavity data with denture reference line annotation data; train a three-dimensional deep learning model based on each sample oral cavity data to obtain an AI model; wherein the three-dimensional deep learning model includes any of the following: PointNet model, graph convolutional neural network model, MeshCNN model, multi-view model that parses three-dimensional information from multiple perspectives, convolutional neural network model based on graph theory, and diffusion network DiffusionNet model.

[0171] Optionally, the training module is specifically configured to: acquire multiple initial oral cavity data with denture reference line annotation data; wherein the initial oral cavity data is used to represent the oral cavity of the sample object under the first pressure state; preprocess the multiple initial oral cavity data to obtain multiple sample oral cavity data; wherein the preprocessing includes one or more of the following: data denoising, data alignment, mesh simplification, Laplacian feature calculation, multi-scale data augmentation, sparse coding representation and surface feature fusion.

[0172] Optionally, the aforementioned first oral cavity data is obtained by three-dimensional scanning of a plaster model obtained by taking an impression of the target object's oral cavity under the first pressure, or by three-dimensional scanning of the target object's historical dentures, or by scanning the target object's oral cavity under an air-pressurized state.

[0173] The second oral data is obtained by scanning the oral cavity of the target subject directly without physical pressure or standard atmospheric pressure.

[0174] Optionally, the above-mentioned device further includes:

[0175] The first judgment module is configured to judge the integrity of the first oral cavity data and the second oral cavity data to obtain the integrity level.

[0176] The accuracy determination module is configured to determine the accuracy of the target denture edge line based on the degree of integrity.

[0177] Optionally, the first judgment module is specifically configured to: determine whether the first oral data and / or the second oral data contain a preset key region, and obtain a inclusion judgment result; wherein the key region corresponding to the first oral data includes a first designated region, and the key region corresponding to the second oral data includes a second designated region; and determine the degree of completeness based on the inclusion judgment result.

[0178] Optionally, the above-mentioned device further includes:

[0179] The second judgment module is configured to determine whether the integrity level is less than a preset integrity threshold.

[0180] The reminder module is configured to issue a data incompleteness reminder if the data is less than the integrity threshold.

[0181] Optionally, the device further includes a user adjustment module configured to: upon detecting a first instruction, determine a first pose change of the target denture edge line relative to its initial position, wherein the first instruction is a user instruction to adjust the pose of the target denture edge line in the second oral cavity data; based on the first pose change and preset reference conditions, determine a first adjusted pose of the target denture edge line, and update and display the pose of the target denture edge line based on the first adjusted pose of the target denture edge line, wherein the preset reference conditions include one of the following: the target denture edge line conforms to the outer surface of the second oral cavity data; the target denture edge line conforms to simulated physiological movement; or the target denture edge line is located within the denture coverage area. One or more; wherein, when a first pose change is detected that causes the edge line of the target denture to not conform to the preset reference conditions, the pose of the edge line of the target denture is adaptively updated according to the preset reference conditions, or, the pose of the edge line of the target denture is not updated and the result of user reconfirmation is obtained and the pose of the edge line of the target denture is adjusted according to the result of user reconfirmation; and / or, when a first adjusted pose is detected that causes the edge line of the target denture to not conform to the preset reference conditions, the pose of the edge line of the target denture is adaptively updated according to the preset reference conditions, or, the pose of the edge line of the target denture is not updated and the result of user reconfirmation is obtained and the pose of the edge line of the target denture is adjusted according to the result of user reconfirmation.

[0182] Optionally, the above apparatus further includes: a generation module configured to generate a three-dimensional denture model based on the target denture edge line and second oral cavity data, and send the three-dimensional denture model to a 3D printing device configured to print the three-dimensional denture model; and a modification module configured to, when receiving a user request for modifying the three-dimensional denture model, output a revised target denture edge line and / or a revised three-dimensional denture model based on the user request, the target denture edge line, and the second oral cavity data.

[0183] The device provided in this 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.

[0184] As shown in Figure 8, a computer device 800 provided in this application embodiment includes: a processor 801, a memory 802 and a bus. The memory 802 stores machine-readable instructions that can be executed by the processor 801. When the computer device 800 is running, the processor 801 and the memory 802 communicate through the bus. The processor 801 executes the machine-readable instructions to perform the steps of the above-described method for determining the edge line of a denture.

[0185] Specifically, the memory 802 and processor 801 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 801 runs the computer program stored in the memory 802, it can execute the above-mentioned method for determining the edge line of the denture.

[0186] This application also provides a computer-readable storage medium storing a computer program. When a processor runs the computer program, it executes the denture edge line determination method described in the preceding method embodiments. The computer-readable storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), RAM (Random Access Memory), a magnetic disk, or an optical disk.

[0187] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0188] In all examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not as limitations; therefore, other examples of exemplary embodiments may have different values.

[0189] 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 the block diagrams and / or flowcharts, and combinations of blocks in the 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.

[0190] In the several 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 modules is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules 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 modules may be electrical, mechanical, or other forms.

[0191] The modules described as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0192] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0193] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications 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. Industrial applicability

[0194] The method, apparatus, computer equipment, and storage medium for determining the edge line of a denture provided in this application can acquire first oral cavity data and second oral cavity data corresponding to the target object when determining the edge line of the denture. The first oral cavity data represents the oral cavity of the target object under a first pressure state, and the second oral cavity data represents the oral cavity of the target object under a second pressure state, where the pressure under the second pressure state is less than the pressure under the first pressure state. A denture reference line is identified on the first oral cavity data using a trained AI model to obtain a first denture reference line. Based on the registration information between the first and second oral cavity data, the first denture reference line is mapped onto the second oral cavity data to obtain the target denture edge line. Since the impression pressure corresponding to the first oral cavity data is greater than that corresponding to the second oral cavity data, the accuracy of the second oral cavity data is higher than that of the first oral cavity data. The first denture reference line corresponding to the first oral cavity data is less susceptible to interference from the diversity of dental morphology and the quality of the mesh surface. Through artificial intelligence learning, the first denture reference line corresponding to the first oral cavity data can be accurately identified. Mapping the first denture reference line onto the more accurate second oral cavity data facilitates subsequent data storage and design. By combining the first and second oral cavity data under different pressure conditions, the edge trimming effect is achieved. The denture edge line of the second oral cavity data is automatically and accurately identified, which also facilitates subsequent digital storage and design.

Claims

1. A method for determining the edge line of a denture, comprising: Acquire first oral cavity data and second oral cavity data corresponding to the target object; wherein, the first oral cavity data is used to represent the oral cavity of the target object under a first pressure state, and the second oral cavity data is used to represent the oral cavity of the target object under a second pressure state, wherein the pressure under the second pressure state is less than the pressure under the first pressure state; The first denture reference line is obtained by identifying the denture reference line based on the trained AI model of the first oral cavity data. Based on the registration information between the first oral cavity data and the second oral cavity data, the first denture reference line is mapped onto the second oral cavity data to obtain the target denture edge line.

2. The method according to claim 1, wherein, The step of identifying the first denture reference line based on the trained AI model of the first oral data to obtain the first denture reference line includes: The first oral cavity data is preprocessed to obtain preprocessed first oral cavity data; wherein, the preprocessing includes one or more of the following: data denoising, data alignment, mesh simplification, Laplacian feature calculation, sparse coding representation and surface feature fusion; The preprocessed first oral cavity data is input into the AI ​​model to obtain the denture reference line recognition result output by the AI ​​model; wherein, the AI ​​model is obtained by training a three-dimensional deep learning model based on multiple sample oral cavity data with denture reference line annotation data, and the sample oral cavity data is used to represent the oral cavity of the sample object under the first pressure state; Based on the denture reference line identification results, the first denture reference line is determined.

3. The method according to claim 2, wherein, The first denture reference line includes a first myostatic line, and the denture reference line annotation data includes myostatic annotation data, which includes myostatic line data or myostatic region data; or... The first denture reference line includes the edge line of the first denture, and the denture reference line annotation data includes myostatic annotation data or denture edge line annotation data.

4. The method according to any one of claims 1-3, wherein, The step of mapping the first denture reference line onto the second oral data based on the registration information between the first oral data and the second oral data to obtain the target denture edge line includes: Using a preset rigid body region, the first oral cavity data and the second oral cavity data are registered to obtain registration information; wherein, the rigid body region includes the alveolar ridge and / or the maxilla; Based on the registration information, the first denture reference line is mapped onto the second oral data to obtain the second denture reference line; The edge line of the target denture is determined based on the second denture reference line.

5. The method according to claim 4, wherein, The step of mapping the first denture reference line onto the second oral data based on the registration information to obtain the second denture reference line includes: Multiple sampling points were obtained from the first denture reference line; Based on the registration information, the matching points of each sampling point on the second oral cavity data are determined; Three-dimensional curve fitting is performed on each of the matching points to obtain the second denture reference line.

6. The method according to claim 4 or 5, wherein, Determining the edge line of the target denture based on the second denture reference line includes: The second denture reference line is smoothed to obtain a smoothed denture reference line. The edge line of the target denture is determined based on the smoothed denture reference line.

7. The method according to any one of claims 1-6, wherein, The method further includes: Acquire oral cavity data from multiple samples with denture reference line annotations; The AI ​​model is obtained by training a three-dimensional deep learning model based on the oral cavity data of each sample; wherein the three-dimensional deep learning model includes any one of the following: PointNet model, graph convolutional neural network model, MeshCNN model, multi-view model that analyzes three-dimensional information from multiple perspectives, convolutional neural network model based on graph theory, and diffusion network DiffusionNet model.

8. The method according to claim 7, wherein, The acquisition of multiple sample oral data with denture reference line annotations includes: Acquire multiple initial oral cavity data with denture reference line annotation data; wherein, the initial oral cavity data is used to represent the oral cavity of the sample object under a first pressure state; The multiple initial oral cavity data are preprocessed to obtain the multiple sample oral cavity data; wherein, the preprocessing includes one or more of the following: data denoising, data alignment, mesh simplification, Laplacian feature calculation, multi-scale data augmentation, sparse coding representation and surface feature fusion.

9. The method according to any one of claims 1-8, wherein, The first oral cavity data is obtained by three-dimensional scanning of the physical model of the oral cavity of the target object obtained by taking an impression under the first pressure, or by three-dimensional scanning of the historical dentures of the target object, or by scanning the oral cavity of the target object under the condition of air blowing pressure. The second oral cavity data was obtained by directly scanning the oral cavity of the target object without physical pressure or standard atmospheric pressure.

10. The method according to any one of claims 1-9, wherein, After obtaining the first and second oral cavity data corresponding to the target object, the method further includes: The integrity of the first and second oral cavity data is assessed to determine the degree of integrity. The accuracy of the target denture edge line is determined based on the degree of integrity.

11. The method according to claim 10, wherein, The process of determining the integrity of the first and second oral cavity data to obtain the degree of integrity includes: Determine whether the first oral cavity data and / or the second oral cavity data contain a preset key region, and obtain a determination result; wherein, the key region corresponding to the first oral cavity data includes a first designated region, and the key region corresponding to the second oral cavity data includes a second designated region; The degree of completeness is determined based on the inclusion judgment result; After determining the integrity level of the first and second oral cavity data, the method further includes: Determine whether the degree of integrity is less than a preset integrity threshold; If the data is less than the integrity threshold, an incomplete data alert will be issued.

12. The method according to any one of claims 1-11, wherein, After mapping the first denture reference line onto the second oral data based on the registration information between the first oral data and the second oral data to obtain the target denture edge line, the method further includes: When the first instruction is detected, the first pose change of the target denture edge line relative to the initial position is determined, wherein the first instruction is an instruction from the user to adjust the pose of the target denture edge line in the second oral cavity data; Based on the first pose change and preset reference conditions, the first adjusted pose of the target denture edge line is determined, and the pose of the target denture edge line is updated and displayed based on the first adjusted pose of the target denture edge line. The preset reference conditions include one or more of the following: the target denture edge line fits the outer surface of the second oral data, the target denture edge line conforms to simulated physiological movement, or the target denture edge line is located within the denture coverage area. Wherein, when the first pose change is detected to cause the target denture edge line to not conform to the preset reference condition, the pose of the target denture edge line is adaptively updated according to the preset reference condition; or, the pose of the target denture edge line is not updated and the user confirms again, and the pose of the target denture edge line is adjusted according to the user confirms again; and / or When it is detected that the first adjustment pose causes the edge line of the target denture to not conform to the preset reference conditions, the pose of the edge line of the target denture is adaptively updated according to the preset reference conditions, or the pose of the edge line of the target denture is not updated and the result of user reconfirmation is obtained and the pose of the edge line of the target denture is adjusted according to the result of user reconfirmation.

13. The method according to any one of claims 1-12, wherein, After mapping the first denture reference line onto the second oral data based on the registration information between the first oral data and the second oral data to obtain the target denture edge line, the method further includes: Based on the target denture edge line and the second oral cavity data, a three-dimensional denture model is generated, and the three-dimensional denture model is sent to a 3D printing device configured to print the three-dimensional denture model; When a user request to modify the three-dimensional denture model is received, the revised target denture edge line and / or the revised three-dimensional denture model are output based on the user request, the target denture edge line, and the second oral cavity data.

14. The method according to claim 1, wherein, The target object is an edentulous target object.

15. The method according to claim 3, wherein, The first myostatic line is the boundary between the myostatic zone and the myodynamic zone.

16. The method according to claim 4, wherein, The second denture reference line includes a second myostatic line corresponding to the first myostatic line, or a second denture edge line corresponding to the first denture edge line.

17. The method according to claim 11, wherein, Both the first and second designated regions include at least two of the following: the labial frenulum, the buccal frenulum, the maxillary tuberosity, the pterygomaxillary notch, and the region 2 mm behind the maxillary fossa; or, the first designated region includes at least two of the following: the alveolar ridge, jaw structure, palate, labial, buccal, and lingual mucosa, the frenulum, and the salivary gland opening; and the second designated region includes at least two of the following: 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.

18. A device for determining the edge line of a denture, comprising: The data acquisition module is configured to acquire first oral cavity data and second oral cavity data corresponding to the target object; wherein, the first oral cavity data is used to represent the oral cavity of the target object under a first pressure state, and the second oral cavity data is used to represent the oral cavity of the target object under a second pressure state, wherein the pressure under the second pressure state is less than the pressure under the first pressure state; The denture reference line recognition module is configured to perform denture reference line recognition on the first oral data based on the trained AI model to obtain the first denture reference line. The denture edge mapping module is configured to map the first denture reference line onto the second oral data based on the registration information between the first oral data and the second oral data, thereby obtaining the target denture edge line.

19. A computer device, comprising a memory and a processor; the memory storing a computer program executable on the processor, wherein the processor, when executing the computer program, implements the method for determining the denture edge line according to any one of claims 1-17.

20. A computer-readable storage medium storing a computer program thereon, characterized in that, The computer program is executed by the processor to perform the denture edge line determination method according to any one of claims 1-17.

Images