Dentition template selection method and apparatus, electronic device, and storage medium

Abstract

Disclosed in the present invention are a dentition template selection method and apparatus, an electronic device, and a storage medium. The method comprises: determining a three-dimensional oral model and a plurality of candidate dentition templates, wherein the three-dimensional oral model comprises at least one tooth model, and each candidate dentition template comprises at least one tooth template; determining a target feature point set corresponding to the three-dimensional oral model and comprising a first feature point set corresponding to each tooth model, and determining a template feature point set corresponding to each candidate dentition template and comprising a second feature point set corresponding to each tooth template; registering each candidate dentition template to the three-dimensional oral model on the basis of the target feature point set and the template feature point set to obtain a registered dentition template; and determining deformation error data between each registered dentition template and the three-dimensional oral model, and determining a target dentition template on the basis of the deformation error data. The present invention can achieve the effect of selecting, from among a plurality of candidate dentition templates, a target dentition template having the highest degree of matching with a three-dimensional oral model.

Description

Dental template selection methods, devices, electronic equipment and storage media

[0001] This application claims priority to Chinese Patent Application No. 202510361984.4, filed on March 25, 2025, entitled “Method, Apparatus, Electronic Device and Storage Medium for Selecting Tooth Templates”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This invention relates to the field of computing application technology, and in particular to a method, apparatus, electronic device, and storage medium for selecting a dental template. Background Technology

[0003] The morphology and arch shape of teeth vary considerably among different patients. Before dental treatments such as tooth alignment, it is necessary to select a set of dental templates that closely matches the patient's tooth morphology and arch shape from among multiple sets of dental templates to proceed with the treatment.

[0004] Currently, dental templates are usually selected by doctors based on their personal experience. However, this often results in a low degree of matching between the selected template and the patient's teeth, leading to poor treatment outcomes later on. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for selecting dental templates, in order to solve the technical problem of low matching degree between manually selected dental templates and patient teeth.

[0006] According to one aspect of the present invention, a method for selecting a tooth template is provided. The method includes: determining a three-dimensional oral cavity model and multiple sets of candidate tooth templates, wherein the three-dimensional oral cavity model includes multiple tooth models, and each set of candidate tooth templates includes multiple tooth templates; determining a target feature point set corresponding to the three-dimensional oral cavity model, including a first feature point set corresponding to each tooth model; and determining a template feature point set corresponding to each set of candidate tooth templates, including a second feature point set corresponding to each tooth template; for each set of candidate tooth templates, registering the candidate tooth template to the three-dimensional oral cavity model according to the target feature point set and the template feature point set to obtain a registered tooth template; for each set of registered tooth templates, determining deformation error data between the registered tooth template and the three-dimensional oral cavity model; and determining a target tooth template according to the deformation error data.

[0007] According to another aspect of the present invention, a tooth template selection device is provided, the device comprising: a model template determining module configured to determine a three-dimensional oral cavity model and multiple sets of candidate tooth templates, wherein the three-dimensional oral cavity model includes multiple tooth models, and each set of candidate tooth templates includes multiple tooth templates; a feature point determining module configured to determine a target feature point set corresponding to the three-dimensional oral cavity model, including a first feature point set corresponding to each tooth model, and to determine a template feature point set corresponding to each set of candidate tooth templates, including a second feature point set corresponding to each tooth template; a template registration module configured to register the candidate tooth templates to the three-dimensional oral cavity model for each set of candidate tooth templates according to the target feature point set and the template feature point set, to obtain registered tooth templates; and an error calculation module configured to determine deformation error data between the registered tooth templates and the three-dimensional oral cavity model for each set of registered tooth templates, and to determine a target tooth template based on the deformation error data. According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0008] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the tooth template selection method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the tooth template selection method according to any embodiment of the present invention.

[0010] The technical solution of this invention involves determining a three-dimensional oral cavity model and multiple sets of candidate tooth templates. The three-dimensional oral cavity model includes at least one tooth model, and each set of candidate tooth templates includes at least one tooth template. A target feature point set corresponding to the three-dimensional oral cavity model, comprising a first feature point set corresponding to each tooth model, is determined. A template feature point set corresponding to each set of candidate tooth templates, comprising a second feature point set corresponding to each tooth template, is also determined. For each set of candidate tooth templates, the candidate tooth template is registered to the three-dimensional oral cavity model based on the target feature point set and the template feature point set, resulting in a registered tooth template. For each registered tooth template, deformation error data between the registered tooth template and the three-dimensional oral cavity model is determined, and a target tooth template is determined based on the deformation error data. Based on this embodiment of the invention, the target tooth template with the highest matching degree to the three-dimensional oral cavity model can be selected from multiple sets of candidate tooth templates. This minimizes the deformation and error of the target tooth template during subsequent dental treatment, reduces subsequent template processing, preserves more original details of the tooth template, and ensures the effectiveness of dental treatment.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 is a flowchart of a method for selecting a dental template according to Embodiment 1 of the present invention;

[0014] Figure 2 is an example diagram of a second feature point marked on a tooth template according to an embodiment of the present invention;

[0015] Figure 3 is an example diagram of a projection deformation radius provided according to an embodiment of the present invention;

[0016] Figure 4 is a side view schematic diagram of feature point projection according to an embodiment of the present invention;

[0017] Figure 5 is a schematic diagram of deformation error data provided according to an embodiment of the present invention;

[0018] Figure 6 is a flowchart of a tooth template selection method according to Embodiment 2 of the present invention;

[0019] Figure 7 is an example diagram of a tooth midline point partitioning according to an embodiment of the present invention;

[0020] Figure 8 is an overall flowchart of a tooth template selection method provided according to an embodiment of the present invention;

[0021] Figure 9 is a structural schematic diagram of a tooth template selection device provided according to Embodiment 3 of the present invention;

[0022] Figure 10 is a schematic diagram of the structure of an electronic device that implements the tooth template selection method of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Example 1

[0026] Figure 1 is a flowchart of a tooth template selection method provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of template selection based on registration. The method can be executed by a tooth template selection device, which can be implemented in hardware and / or software and can be configured in a computer. As shown in Figure 1, the method includes:

[0027] S110. Determine the three-dimensional oral cavity model and multiple sets of candidate tooth templates.

[0028] The three-dimensional oral model can be understood as a digital model corresponding to the actual teeth of the target patient. The digital model can be a three-dimensional (3D) digital model. In this embodiment of the invention, the three-dimensional oral model includes at least one tooth model. The tooth model can be a 3D digital model of a single tooth. Optionally, the three-dimensional oral model can be a single tooth model or multiple tooth models selected by the doctor based on the patient's treatment needs. The selected multiple tooth models can be a full-mouth model or a half-mouth model of the patient, etc.

[0029] Candidate tooth templates can be candidate tooth templates. Candidate tooth templates can also be 3D digital templates corresponding to actual tooth templates. The actual tooth template can be a crown template, a dental prosthesis template, or a denture template, etc. In this embodiment of the invention, each set of candidate tooth templates includes at least one tooth template. A tooth template can be a 3D digital template of a single tooth. Optionally, for each set of candidate tooth templates, there is a one-to-one correspondence between at least one tooth template included in the candidate tooth template set and at least one tooth model included in the three-dimensional oral cavity model.

[0030] Based on the embodiments of the present invention, a target tooth template with the highest matching degree to the three-dimensional oral model can be selected from multiple candidate tooth templates to carry out dental treatment or dental aesthetic design for the target patient.

[0031] S120. Determine the target feature point set corresponding to the three-dimensional oral cavity model, including the first feature point set corresponding to each tooth model, and determine the template feature point set corresponding to each set of candidate tooth templates, including the second feature point set corresponding to each tooth template.

[0032] The first feature point set can be understood as the set of feature points on each tooth model. It is understood that the first feature point set can be different for different tooth models. For example, the first feature point set can be represented as D = {d1, d2, d3, ...}. The first feature points on the tooth models in the 3D oral cavity model can also be called shape points. These shape points can be determined based on tooth model curvature calculations or manual identification, or they can be determined by coarse matching of feature points on the tooth model; that is, shape points can be automatically identified during the matching process. The coarse matching process can be based on the calculated or manually identified tooth model curvature results to further improve the accuracy of shape point determination. This coarse matching of feature points can refer to the coarse matching of the already labeled feature points on the candidate tooth template to the tooth model.

[0033] The target feature point set can be understood as a set of multiple first feature point sets.

[0034] The second feature point set can be understood as the set of feature points on each tooth template. It is understood that the second feature point set may be different for different tooth templates. Referring to Figure 2, Figure 2 is an example diagram of the second feature points marked on a tooth template according to an embodiment of the present invention. Figure 2 shows the second feature points marked on the tooth template from three sides. Exemplarily, the second feature point set can be represented as S = {s1, s2, s3, ...}.

[0035] The template feature point set can be understood as a set of multiple second feature point sets. In this embodiment of the invention, the template feature point sets corresponding to different candidate tooth templates can be different. The template feature point set can be represented as P = {p1, p2, p3, ...}.

[0036] In this embodiment of the invention, the second feature point can be annotated on the dental template based on the curvature features of the dental template. Optionally, the feature point can be automatically and / or manually annotated. Correspondingly, the first feature point can be obtained by coarsely matching the feature points already annotated on the dental template to the dental model, or it can be annotated on the dental model based on the curvature features of the dental model.

[0037] Optionally, a template feature point set corresponding to each set of candidate tooth templates is determined, including the second feature point set corresponding to each tooth template, comprising:

[0038] For each tooth template in each set of candidate tooth templates, the set of second feature points corresponding to the tooth template is determined based on the curvature characteristics of the tooth template;

[0039] The template feature point set corresponding to the candidate tooth template is determined based on the second feature point set.

[0040] The curvature feature can be understood as the rate of rotation of the tangent direction angle with respect to the arc length at a point on the curve. The curvature feature can be a curvature value. Specifically, points on the tooth template with curvature values ​​greater than a preset curvature threshold are marked as second feature points. The curvature threshold can be preset according to scenario requirements and is not specifically limited here.

[0041] Specifically, the set of multiple sets of second feature points is used as the template feature point set.

[0042] In this embodiment of the invention, the method for determining the first feature point set can be the same as the method for determining the second feature point set described above, and the method for determining the target feature point set can be the same as the method for determining the template feature point set described above, which will not be elaborated here.

[0043] Based on the above technical solution, marking feature points based on curvature features can make the marked feature points more representative of the curve features of the tooth template or tooth model, so as to facilitate further template matching and selection.

[0044] S130. For each set of candidate tooth templates, register the candidate tooth templates onto the three-dimensional oral model according to the target feature point set and the template feature point set to obtain the registered tooth templates.

[0045] The registered tooth template can be understood as the registered tooth template. Optionally, the registered tooth template can be obtained by registering candidate tooth templates based on a target feature point set, a template feature point set, a template center point set, and a target center point set. The template center point set includes the second center point corresponding to each tooth template, and the target center point set includes the first center point corresponding to each tooth model.

[0046] S140. For each set of registered tooth templates, determine the deformation error data between the registered tooth template and the three-dimensional oral model, and determine the target tooth template based on the deformation error data.

[0047] Optionally, the deformation error data between the registered dental template and the three-dimensional oral model can be accurately matched, including:

[0048] Project the template feature points on the registered tooth template onto the three-dimensional oral model to obtain the set of projection deformation radii corresponding to the set of template feature points;

[0049] The deformation error data between the registered dental template and the three-dimensional oral model are determined based on the set of projection deformation radii.

[0050] The projection deformation radius set includes multiple projection deformation radii. The template feature point set includes multiple template feature points. There is a one-to-one correspondence between the projection deformation radius and the template feature points; that is, each template feature point corresponds to one projection deformation radius. The projection deformation radius can be understood as the deformation radius of the tooth template after the feature point is projected. Referring to Figures 3 and 4, Figure 3 is an example diagram of a projection deformation radius provided according to an embodiment of the present invention. Figure 4 is a side view schematic diagram of feature point projection provided according to an embodiment of the present invention. In Figure 3, each black line represents the projection deformation radius corresponding to a feature point, and the black lines are radially distributed. Figure 4 includes three curves of different shades: the lightest curve represents the tooth model; the medium-colored curve represents the tooth template; and the darkest curve represents the deformation result of the tooth template after the feature point is projected.

[0051] Optionally, the template feature points on the registered tooth template are projected onto the three-dimensional oral model to obtain the set of projection deformation radii corresponding to the template feature point set, including:

[0052] For each tooth template on each set of registered tooth templates, each second feature point on the registered tooth template is projected onto the three-dimensional oral model to obtain the projection deformation radius corresponding to each second feature point. Based on the projection deformation radius, the set of sub-deformation radii corresponding to the tooth template is determined.

[0053] The set of projected deformation radii corresponding to the set of template feature points for registering the tooth template is determined based on the set of sub-deformation radii.

[0054] In this embodiment of the invention, each second feature point on the registered tooth template can be projected onto the three-dimensional oral model in a manner similar to the geodesic distance diffusion algorithm.

[0055] The geodesic distance diffusion algorithm can be understood as a geodesic distance calculation algorithm based on thermal diffusion. Optionally, the set of projection deformation radii can be directly obtained by processing the set of template feature points on the input registered dental template using the geodesic distance diffusion algorithm. It is important to understand that for each template feature point, all points (including template feature points and non-feature points (which can be other point cloud data)) within a circle centered on the template feature point and with the corresponding projection deformation radius as the radius are mapped to a target point on the 3D oral cavity model. This target point is considered as a single point.

[0056] It should be noted that the traditional geodesic distance diffusion algorithm is a precise calculation algorithm. In practical applications, it usually involves a large amount of computation. This invention uses a simplified geodesic distance diffusion algorithm to calculate feature point projection and projection deformation radius. The simplified geodesic distance diffusion algorithm used in this invention ignores the calculation process in the traditional geodesic distance diffusion algorithm, which requires creating different windows for different points and edges of the mesh, and each window needs to be locally flattened and projected onto a 2D plane. It only performs local flattening for points to perform relevant calculations, reducing the amount of computation and thus effectively improving the calculation efficiency of deformation error data, enabling doctors to select the target tooth template suitable for the patient more quickly. The sub-deformation radius set can be understood as the deformation radius set corresponding to the second feature point set of each tooth template. In the embodiments of this invention, the sub-deformation radius sets corresponding to the second feature point sets of different tooth templates can be different. The second feature points in the second feature point set and the deformation radii in the sub-deformation radius set can correspond one-to-one.

[0057] Deformation error data can characterize the differences between the registered dental template and the three-dimensional oral cavity model. In this embodiment of the invention, the deformation error data can be preset according to the needs of the scenario, and is not specifically limited here. Optionally, the deformation error data may include deformation data and / or error data.

[0058] Optionally, the deformation error data between the registered dental template and the three-dimensional oral model is determined based on the set of projected deformation radii, including:

[0059] The trigger point data is determined based on the set of projection deformation radii. The trigger point data represents the trigger point corresponding to each template feature point in the set of template feature points. The trigger point is a point within the projection deformation radius corresponding to the template feature point.

[0060] Deformation data is determined based on the set of projected deformation radii and the data of the triggering points. Error data is determined based on the set of deformation radii and the deformation data. The deformation data represents the degree of deformation of the tooth template after mapping the feature points on the tooth template to the tooth model. The error data represents the degree of error between the tooth template and the tooth model after mapping the feature points on the tooth template to the tooth model.

[0061] Specifically, for each template feature point, a target circle is determined with the template feature point as the origin and the deformation radius corresponding to the template feature point as the radius. All points within the target circle other than the template feature point are designated as trigger points corresponding to the template feature point. Optionally, trigger points can be digital point clouds, etc. It should be noted that the trigger points do not include the feature points themselves. Each template feature point can have one or more trigger points.

[0062] Optionally, the set of projected deformation radii and the data of the induced points can be obtained directly by processing the set of template feature points on the input registered tooth template using a geodesic distance diffusion algorithm.

[0063] For example, error data can be an error value that characterizes the degree of error. Deformation data can be a deformation value that characterizes the degree of deformation.

[0064] Figure 5 is a schematic diagram of deformation error data provided according to an embodiment of the present invention. The specific calculation process of deformation error data will be described below with reference to Figure 5. Figure 5 includes two curves of different shades, wherein the darker curve can represent the tooth model (tooth model) and the lighter curve can represent the tooth template (tooth template).

[0065] Specifically, determining the deformation data based on the set of deformation radii can be achieved using the following formula:

[0066] Wherein, g(r, δ) Pi () represents the deformation of surrounding points caused by an approximate single feature point; This represents the deformation amount corresponding to a feature point, which can be a constant; r represents the deformation radius.

[0067] in, This represents the total deformation of each feature point and the other triggering points within the deformation radius corresponding to that feature point. P represents the deformation corresponding to a feature point. i This represents the i-th feature point. For example, the total deformation can be referenced to the green area in Figure 5, where the green area can be referenced to the two light-colored areas in Figure 5 that are marked as deformation amounts.

[0068] Where D represents deformation data, r i This represents the deformation radius corresponding to the i-th feature point.

[0069] Furthermore, error data is determined based on the set of deformation radii and deformation data. The error can be understood as the difference between the deformed tooth template and the actual tooth model, and can be obtained by subtracting the deformation amount from the projected distance of the triggering points around the feature points. The specific calculation method is as follows:

[0070] Where d(r) represents the projected distance of a single point; e(r, δ) Pi ) represents the error amount corresponding to a single point; δ Pi This represents the deformation amount corresponding to a feature point, which can be a constant. It represents the amount of deformation of surrounding points caused by an approximate single feature point.

[0071] Furthermore, the total error for each feature point and the other triggering points within the deformation radius corresponding to the feature point can be referred to in the red area of ​​Figure 5, where the red area can be referred to as the dark area marked as the error amount in Figure 5.

[0072] Where E represents error data.

[0073] Optionally, the target tooth template is determined based on deformation error data, including:

[0074] Based on the deformation error data, determine the template with the smallest deformation and the template with the smallest error among multiple registered tooth templates. If the template with the smallest deformation and the template with the smallest error are the same tooth template, then the template with the smallest deformation or the template with the smallest error is determined as the target tooth template.

[0075] The template with the smallest deformation can be understood as the registration template with the smallest degree of deformation. The template with the smallest error can be understood as the registration template with the smallest degree of error.

[0076] The target tooth template can be understood as the candidate tooth template selected for the target.

[0077] Optionally, the method for selecting a dental template may also include:

[0078] When the minimum deformation template and the minimum error template are different tooth templates, determine the deformation weight and the error weight;

[0079] The target tooth template in the registration tooth template is determined based on the deformation weight, error weight, deformation data, and error data.

[0080] Here, deformation weight can be understood as the weight corresponding to deformation data. Error weight can be understood as the weight corresponding to error data. In this embodiment of the invention, deformation weight and error weight can be preset according to scenario requirements, and are not specifically limited here.

[0081] The technical solution of this invention involves determining a three-dimensional oral cavity model and multiple sets of candidate tooth templates. The three-dimensional oral cavity model includes multiple tooth models, and each set of candidate tooth templates includes multiple tooth templates. A target feature point set corresponding to the three-dimensional oral cavity model, comprising a first feature point set corresponding to each tooth model, is determined. A template feature point set corresponding to each set of candidate tooth templates, comprising a second feature point set corresponding to each tooth template, is also determined. For each set of candidate tooth templates, the candidate tooth template is registered onto the three-dimensional oral cavity model based on the target feature point set and the template feature point set, resulting in a registered tooth template. For each registered tooth template, deformation error data between the registered tooth template and the three-dimensional oral cavity model is determined, and a target tooth template is determined based on the deformation error data. Based on this embodiment of the invention, the target tooth template with the highest matching degree to the three-dimensional oral cavity model can be selected from multiple sets of candidate tooth templates. This minimizes the deformation and error of the target tooth template during subsequent dental treatment, reduces subsequent template processing, preserves more original details of the tooth template, and ensures the effectiveness of dental treatment.

[0082] Example 2

[0083] Figure 6 is a flowchart of a tooth template selection method provided in Embodiment 2 of the present invention. This embodiment focuses on the above embodiment, which involves registering candidate tooth templates onto a three-dimensional oral model based on a target feature point set and a template feature point set. As shown in Figure 6, the method includes:

[0084] S210. Determine the three-dimensional oral cavity model and multiple sets of candidate tooth templates.

[0085] S220. Determine the target feature point set corresponding to the three-dimensional oral cavity model, including the first feature point set corresponding to each tooth model, and determine the template feature point set corresponding to each set of candidate tooth templates, including the second feature point set corresponding to each tooth template.

[0086] S230. For each set of candidate tooth templates, determine the first center point corresponding to each tooth model, determine the target center point set corresponding to the three-dimensional oral cavity model based on the first center point, and determine the second center point corresponding to each tooth template, and determine the template center point set corresponding to each set of candidate tooth templates based on the second center point.

[0087] The first center point can be understood as the center point of the tooth model. The target center point set includes the center point of each tooth model in the 3D oral cavity model.

[0088] The second center point can be understood as the center point corresponding to the tooth template. The set of template center points includes the center point of each tooth template in the candidate tooth templates. A set of template center points corresponds to a set of candidate tooth templates.

[0089] S240. For each set of candidate tooth templates, register the candidate tooth templates onto the three-dimensional oral model according to the target feature point set, template feature point set, template center point set, and target center point set to obtain the registered tooth templates.

[0090] Optionally, the candidate tooth template is registered onto the 3D oral model based on the target feature point set, the template feature point set, the template center point set, and the target center point set to obtain the registered tooth template, including:

[0091] The candidate tooth template is rigidly registered onto the three-dimensional oral model to obtain the rigid registration template;

[0092] The rigid matching template is isotropically scaled to obtain an isotropically scaled template;

[0093] Based on the target feature point set, template feature point set, template center point set, and target center point set, non-rigid registration is performed on the same-sex scaling template to obtain the registered tooth template registered on the three-dimensional oral model.

[0094] Isotropic scaling can be used to change the volume of the template and its position relative to the global coordinate origin.

[0095] Specifically, the registration of the candidate tooth template (i.e., the non-rigid registration mentioned above) can be achieved based on the following formula:

[0096] Where E represents the registration loss of a dental template (the loss between the dental template and the dental model), s c d represents the second center point. c S represents the first center point. i Let d represent the i-th template feature point. i Let j represent the j-th target feature point.

[0097] Furthermore, the construction of the above formula will be explained below with reference to Figure 7, which is an example diagram of tooth midline point partitioning provided by an embodiment of the present invention. Specifically:

[0098] First, for the template feature point set S = {s1, s2, s3, ...} and the target feature point set D = {d1, d2, d3, ...}, find a transformation matrix M such that E = ∑L(Ms i D) should be as small as possible, where L(Ms) i , D) represents the minimum norm of the transformed template feature point set to the target feature point set.

[0099] Second, to improve registration accuracy, a symmetrical transformation can be performed on the above formula to obtain the formula E=∑L(Ms) i ,D)+∑L(d i The formula (MS) estimates the sum of the minimum error from s to D and the minimum error from D to s. To solve this nonlinear problem, the formula can be simplified to...

[0100] Third, to avoid getting trapped in local optima and to achieve the smallest possible deformation, a center point constraint was added to the simplified formula, that is, the teeth were divided into regions. Referring to Figure 7, the points in region A of the tooth template can only be found in region A of the tooth model (the same applies to B, C and D), so as to obtain the non-rigid registration formula of the target.

[0101] Based on the formula constructed above, candidate tooth templates are registered, which improves the registration accuracy of tooth templates while avoiding getting trapped in local optima.

[0102] S250. For each set of registered tooth templates, determine the deformation error data between the registered tooth template and the three-dimensional oral model, and determine the target tooth template based on the deformation error data.

[0103] The technical solution of this invention involves determining a first center point for each tooth model for each set of candidate tooth templates, determining a set of target center points for each candidate tooth template based on the first center point, and determining a second center point for each tooth template based on the second center point. The candidate tooth templates are then registered onto a three-dimensional oral model based on the set of target feature points and the set of template feature points. This includes registering the candidate tooth templates onto the three-dimensional oral model based on the set of target feature points, the set of template feature points, the set of template center points, and the set of target center points. This approach improves the accuracy of registering the tooth templates onto the tooth model while avoiding getting trapped in local optima, thereby enhancing the pose consistency between the registered tooth templates and the tooth model.

[0104] Figure 8 is an overall flowchart of a tooth template selection method according to an embodiment of the present invention. As shown in Figure 8, the overall flow of the tooth template selection method is as follows:

[0105] 1. Mark feature points on the dental template and automatically identify feature points on the oral model. Different feature points can be marked on different sizes of dental templates.

[0106] 2. Perform pose estimation on the tooth template and the tooth model. For each tooth template, first rigidly register the tooth template onto the tooth model; then isotropically scale the tooth template; finally, non-rigidly match the deformed tooth model onto the tooth model.

[0107] 3. Deform the tooth template based on feature points. The tooth template and the tooth model cannot be exactly the same. Project the pre-selected marked feature points onto the tooth model to obtain the deformation radius corresponding to each marked feature point and the trigger point within the deformation radius. This step can be implemented based on geodesic distance diffusion.

[0108] 4. Estimate deformation and overall error. Find a tooth template with the smallest possible deformation and the smallest possible error between the deformed tooth template and the actual tooth model. Minimizing deformation reduces the degree of distortion of the tooth template during later treatment, preserving more of the tooth's details. Minimizing error indicates the degree of similarity between the two.

[0109] The technical solution of this invention employs pose estimation, deformation estimation, and error estimation to select the tooth template. This allows the tooth model to reduce subsequent processing and retain more tooth details during dental treatment, thus assisting the doctor's work.

[0110] Example 3

[0111] Figure 9 is a schematic diagram of a tooth template selection device provided in Embodiment 3 of the present invention. As shown in Figure 9, the device includes: a model template determination module 310, a feature point determination module 320, a template registration module 330, and an error calculation module 340.

[0112] The model template determination module 310 is configured to determine a three-dimensional oral cavity model and multiple sets of candidate tooth templates, wherein the three-dimensional oral cavity model includes multiple tooth models, and each set of candidate tooth templates includes multiple tooth templates; the feature point determination module 320 is configured to determine a target feature point set corresponding to the three-dimensional oral cavity model, including a first feature point set corresponding to each tooth model, and a template feature point set corresponding to each set of candidate tooth templates, including a second feature point set corresponding to each tooth template; the template registration module 330 is configured to register the candidate tooth templates to the three-dimensional oral cavity model for each set of candidate tooth templates based on the target feature point set and the template feature point set, to obtain registered tooth templates; and the error calculation module 340 is configured to determine the deformation error data between the registered tooth templates and the three-dimensional oral cavity model for each set of registered tooth templates, and determine the target tooth template based on the deformation error data.

[0113] The technical solution of this invention involves determining a three-dimensional oral cavity model and multiple sets of candidate tooth templates. The three-dimensional oral cavity model includes multiple tooth models, and each set of candidate tooth templates includes multiple tooth templates. A target feature point set corresponding to the three-dimensional oral cavity model, comprising a first feature point set corresponding to each tooth model, is determined. A template feature point set corresponding to each set of candidate tooth templates, comprising a second feature point set corresponding to each tooth template, is also determined. For each set of candidate tooth templates, the candidate tooth template is registered onto the three-dimensional oral cavity model based on the target feature point set and the template feature point set, resulting in a registered tooth template. For each registered tooth template, deformation error data between the registered tooth template and the three-dimensional oral cavity model is determined, and a target tooth template is determined based on the deformation error data. Based on this embodiment of the invention, the target tooth template with the highest matching degree to the three-dimensional oral cavity model can be selected from multiple sets of candidate tooth templates. This minimizes the deformation and error of the target tooth template during subsequent dental treatment, reduces subsequent template processing, preserves more original details of the tooth template, and ensures the effectiveness of dental treatment.

[0114] Optionally, the error calculation module 340 includes: a feature point projection unit and a deformation error calculation unit;

[0115] Among them, the feature point projection unit is configured to project the template feature points on the registered tooth template onto the three-dimensional oral model to obtain the set of projection deformation radii corresponding to the template feature point set;

[0116] The deformation error calculation unit is configured to determine the deformation error data between the registered tooth template and the three-dimensional oral cavity model based on the set of projected deformation radii.

[0117] Optionally, the deformation error data includes deformation data and / or error data, and the deformation error calculation unit is specifically configured as follows:

[0118] The trigger point data is determined based on the set of projection deformation radii. The trigger point data represents the trigger point corresponding to each template feature point in the set of template feature points. The trigger point is a point within the projection deformation radius corresponding to the template feature point.

[0119] Deformation data is determined based on the set of projected deformation radii and the data of the triggering points. Error data is determined based on the set of deformation radii and the deformation data. The deformation data represents the degree of deformation of the tooth template after mapping the feature points on the tooth template to the tooth model. The error data represents the degree of error between the tooth template and the tooth model after mapping the feature points on the tooth template to the tooth model.

[0120] Optionally, the feature point projection unit is specifically configured as follows:

[0121] For each tooth template on each set of registered tooth templates, each second feature point on the registered tooth template is projected onto the three-dimensional oral model to obtain the projection deformation radius corresponding to each second feature point. Based on the projection deformation radius, the set of sub-deformation radii corresponding to the tooth template is determined.

[0122] The set of projected deformation radii corresponding to the set of template feature points for the registered tooth template is determined based on the set of sub-deformation radii. Optionally, the tooth template selection device further includes:

[0123] The center point determination module is configured to, before registering the candidate tooth templates onto the 3D oral model based on the target feature point set and the template feature point set, determine the first center point corresponding to each tooth model for each set of candidate tooth templates, determine the target center point set corresponding to the 3D oral model based on the first center point, and determine the second center point corresponding to each tooth template, and determine the template center point set corresponding to each set of candidate tooth templates based on the second center point.

[0124] The template registration module 330 is specifically configured to register the candidate tooth template onto the three-dimensional oral model based on the target feature point set, the template feature point set, the template center point set, and the target center point set.

[0125] Optionally, the feature point determination module 320 is specifically configured as follows:

[0126] For each tooth template in each set of candidate tooth templates, the set of second feature points corresponding to the tooth template is determined based on the curvature characteristics of the tooth template;

[0127] The template feature point set corresponding to the candidate tooth template is determined based on the second feature point set.

[0128] Optionally, the error calculation module 340 includes:

[0129] The target template determination unit is configured to determine the minimum deformation template and the minimum error template among multiple registered tooth templates based on deformation error data, and to determine the minimum deformation template or the minimum error template as the target tooth template when the minimum deformation template and the minimum error template are the same tooth template.

[0130] Optionally, the error calculation module 340 further includes: a weight determination unit and a target template selection unit;

[0131] The weight determination unit is configured to determine the deformation weight and error weight when the minimum deformation template and the minimum error template are different tooth templates.

[0132] The target template selection unit is configured to determine the target tooth template in the registered tooth template based on deformation weight, error weight, deformation data, and error data.

[0133] The tooth template selection device provided in the embodiments of the present invention can execute the tooth template selection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0134] Example 4

[0135] Figure 10 illustrates a schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0136] As shown in Figure 10, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0137] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0138] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the tooth template selection method.

[0139] In some embodiments, the dental template selection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the dental template selection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the dental template selection method by any other suitable means (e.g., by means of firmware).

[0140] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0142] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0143] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0144] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0145] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0146] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0147] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention. Industrial applicability

[0148] The tooth template selection method provided by this invention can achieve the effect of selecting a target tooth template with the highest matching degree with the three-dimensional oral model from multiple candidate tooth templates, so as to minimize the deformation and error of the target tooth template during subsequent dental treatment, reduce the subsequent template processing, retain more original details of the tooth template, ensure the dental treatment effect, and has strong industrial applicability.

Claims

1. A method for selecting a dental template, wherein, include: A three-dimensional oral cavity model and multiple sets of candidate tooth templates are determined, wherein the three-dimensional oral cavity model includes at least one tooth model, and each set of candidate tooth templates includes at least one tooth template; Determine the target feature point set corresponding to the three-dimensional oral cavity model, which includes the first feature point set corresponding to each tooth model; and determine the template feature point set corresponding to each set of candidate tooth templates, which includes the second feature point set corresponding to each tooth template. For each set of candidate tooth templates, the candidate tooth templates are registered onto the three-dimensional oral model according to the target feature point set and the template feature point set to obtain the registered tooth templates; For each set of registered tooth templates, the deformation error data between the registered tooth template and the three-dimensional oral model is determined, and the target tooth template is determined based on the deformation error data.

2. The method according to claim 1, wherein, The determination of deformation error data between the registered dental template and the three-dimensional oral model includes: The template feature points on the registered tooth template are projected onto the three-dimensional oral model to obtain the set of projection deformation radii corresponding to the set of template feature points. The deformation error data between the registered dental template and the three-dimensional oral model is determined based on the set of projection deformation radii.

3. The method according to claim 2, wherein, The deformation error data includes deformation data and / or error data. Determining the deformation error data between the registered tooth template and the three-dimensional oral model based on the set of projected deformation radii includes: The trigger point data is determined based on the set of projected deformation radii, wherein the trigger point data represents the trigger point corresponding to each template feature point in the set of template feature points, and the trigger point is a point within the projected deformation radius corresponding to the template feature point; The deformation data is determined based on the set of projected deformation radii and the trigger point data, and the error data is determined based on the set of deformation radii and the deformation data. The deformation data characterizes the degree of deformation of the tooth template after mapping the feature points on the tooth template to the tooth model, and the error data characterizes the degree of error between the tooth template and the tooth model after mapping the feature points on the tooth template to the tooth model.

4. The method according to claim 2, wherein, The step of projecting template feature points on the registered dental template onto the three-dimensional oral model to obtain the set of projection deformation radii corresponding to the set of template feature points includes: For each tooth template on each set of registered tooth templates, each second feature point on the registered tooth template is projected onto the three-dimensional oral model to obtain the projection deformation radius corresponding to each second feature point. The sub-deformation radius set corresponding to the tooth template is determined based on the projection deformation radius. The set of projected deformation radii corresponding to the set of template feature points of the registered tooth template is determined based on the set of sub-deformation radii.

5. The method according to claim 1, wherein, Before registering the candidate tooth template onto the three-dimensional oral model based on the target feature point set and the template feature point set, the method further includes: For each set of candidate tooth templates, a first center point is determined for each tooth model, a set of target center points for the three-dimensional oral cavity model is determined based on the first center point, and a second center point is determined for each tooth template, a set of template center points for each set of candidate tooth templates is determined based on the second center point. The step of registering the candidate tooth template onto the three-dimensional oral model based on the target feature point set and the template feature point set includes: The candidate tooth template is registered onto the three-dimensional oral model based on the target feature point set, the template feature point set, the template center point set, and the target center point set.

6. The method according to claim 1, wherein, The step of determining the template feature point set corresponding to each set of candidate tooth templates, which includes the second feature point set corresponding to each tooth template, includes: For each tooth template in each set of candidate tooth templates, a second set of feature points corresponding to the tooth template is determined based on the curvature characteristics of the tooth template; The template feature point set corresponding to the candidate tooth template is determined based on the second feature point set.

7. The method according to claim 1, wherein, The step of determining the target tooth template based on the deformation error data includes: Based on the deformation error data, the template with the smallest deformation and the template with the smallest error among the multiple registered tooth templates are determined. If the template with the smallest deformation and the template with the smallest error are the same tooth template, the template with the smallest deformation or the template with the smallest error is determined as the target tooth template.

8. The method according to claim 7, wherein, Also includes: When the minimum deformation template and the minimum error template are different tooth templates, the deformation weight and the error weight are determined. The target tooth template in the registered tooth template is determined based on the deformation weight, the error weight, the deformation data, and the error data.

9. A dental template selection device, wherein, include: The model template determination module is configured to determine a three-dimensional oral cavity model and multiple sets of candidate tooth templates, wherein the three-dimensional oral cavity model includes at least one tooth model, and each set of candidate tooth templates includes at least one tooth template; The feature point determination module is configured to determine a target feature point set corresponding to the three-dimensional oral cavity model, including a first feature point set corresponding to each tooth model, and to determine a template feature point set corresponding to each set of candidate tooth templates, including a second feature point set corresponding to each tooth template. The template registration module is configured to register the candidate tooth template onto the three-dimensional oral model for each set of candidate tooth templates according to the target feature point set and the template feature point set, thereby obtaining a registered tooth template. The error calculation module is configured to determine the deformation error data between the registered tooth template and the three-dimensional oral model for each set of registered tooth templates, and determine the target tooth template based on the deformation error data.

10. An electronic device, wherein, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the tooth template selection method according to any one of claims 1-8.

11. A computer-readable storage medium, wherein, The computer-readable storage medium stores computer instructions that cause a processor to execute the tooth template selection method according to any one of claims 1-8.

Images