Method, program, storage medium and system for tooth abutment surface repair
Through a three-dimensional dental data repair method based on AI prediction data of dental point cloud, the problem of loss of tooth abutment surface information and manual repair is solved, and more realistic and accurate dental surface shape restoration is achieved, and the simulation effect of invisible orthodontics is improved.
Patent Information
- Application Number
- CN202411156530.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-11-29
AI Technical Summary
In the three-dimensional oral sweep teeth data, the information about the tooth abutment surface is easily lost, and the manual repair process of traditional doctors is cumbersome and difficult to restore the real tooth morphology.
The three-dimensional tooth data repair method based on AI prediction data of tooth point cloud is used to reconstruct and repair the tooth adjacency surface through point cloud registration and denoising, Poisson reconstruction algorithm, Laplace deformation and Delooney triangulation. Ensure that the restored face shape fits the original crown and the real tooth shape.
It improves the authenticity and accuracy of tooth abutment surface repair, simplifies the operation process, and enhances the simulation ability of invisible orthodontic teeth modeling.
Smart Images

Figure CN119048713A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of oral digital technology, and in particular to a method, program, storage medium and system for repairing tooth proximal surfaces. Background Art
[0002] In dental data from 3D oral scans, a significant amount of information about adjacent tooth surfaces is lost, a major challenge faced by computer-aided dental software. Traditionally, manual restoration of adjacent tooth surfaces by a doctor is complex and difficult to achieve, reproducing the true tooth form. Summary of the Invention
[0003] The technical problem to be solved by the present invention is to design a three-dimensional tooth data proximal surface repair method based on tooth point cloud AI prediction data. On the basis of the crown fitting mouth scan, the proximal surfaces of adjacent teeth are restored as realistically as possible in the proximal surface area according to the point cloud prediction data to solve the existing technical problems.
[0004] To solve the above technical problems, the present invention provides a method for tooth proximal surface restoration based on point cloud prediction data, comprising the following steps: Step S1: perform registration and denoising on the tooth point cloud data and the tooth data with missing adjacent surfaces to obtain point cloud data that predicts the true shape of the tooth.
[0005] Step S2: Use the Poisson reconstruction algorithm to construct a triangular mesh based on the point cloud data, and perform mesh repair and closure on the reconstructed triangular mesh.
[0006] Step S3: deform the triangular mesh reconstructed from the point cloud based on the original crown information so that the reconstructed mesh in the crown area fits the original crown better, which is recorded as MeshA.
[0007] Step S4: Generate a mesh at the proximal surface of the real tooth and deform it to the corresponding position of the proximal surface of MeshA.
[0008] Step S5: On the inner fixed boundary of the proximal mesh, suture it with the original crown, and erase the suture line of the surrounding mesh using the Laplace smoothing algorithm.
[0009] Furthermore, in step S1, registration is performed according to the whole-jaw fusion matching method, and data with a Euclidean distance greater than 2 mm from the real tooth surface is filtered out in the point cloud data of each tooth to remove the influence of noise in the point cloud prediction, and the proximal point cloud data of the real tooth morphology predicted by AI is obtained, and fused with all the mesh vertices of the real tooth surface to form the point cloud data of the real tooth.
[0010] Furthermore, in step S3, the triangular mesh reconstructed from the point cloud is deformed using the Laplace deformation algorithm by taking the boundary points of the real teeth as target points and calculating the nearest points of the boundary points on the point cloud data as control points.
[0011] Furthermore, step S4 specifically includes the following steps: Step S41: Fill the holes in the mesh to repair the black triangles, obtain the lowest point of the crown boundary, and construct the adjacent triangular mesh, which is recorded as MeshB.
[0012] Step S42: In order to make the completed interproximal mesh more consistent with the tooth shape predicted by AI, the interproximal mesh MeshB is reshaped to be more consistent with the point cloud reconstructed mesh MeshA.
[0013] Furthermore, in step S41 , based on the most adjacent regions of adjacent teeth, the tooth crown mesh boundaries are selected and sorted so that the boundaries are connected end to end, thereby obtaining the lowest point of the tooth crown boundary.
[0014] Furthermore, step S42 specifically includes the following steps: Step S421: distinguishing the inner and outer boundaries in the boundary of MeshB, where the inner boundary represents the fixed boundary sutured with the original tooth crown, and the outer boundary represents the free boundary; Step S422: Re-dividing MeshA using Delaunay triangulation, so that there are no overly sharp triangles in the mesh of MeshA. Overly sharp means that the minimum angle is less than 15°, so that the mesh of MeshA appears sufficiently uniform and delicate. Step S423: Find the midpoint of the inner and outer boundaries of MeshB as the control point for deformation, calculate the normal of the midpoint, draw a ray from the midpoint and the midpoint normal to intersect MeshA, use the intersection as the target point for deformation, and deform MeshB to a target position that better matches MeshA using the Laplace deformation algorithm.
[0015] Furthermore, the present invention further comprises the following steps: Step S6: For two adjacent teeth, if there is a collision between the adjacent surfaces of the restored teeth, the collision value is made to approach zero through Laplace deformation, while keeping the intersection area of the original collision unchanged.
[0016] The present invention also provides a computer program product comprising computer instructions, which, when executed by a processor, enable a computer device to perform the above-mentioned method for restoring tooth proximal surfaces.
[0017] The present invention also provides a computer-readable storage medium having computer-executable instructions stored thereon. When a processor executes the computer-executable instructions, the method for repairing tooth proximal surfaces as described above is implemented.
[0018] The present invention also provides a system for repairing tooth proximal surfaces, comprising: at least one processor; and at least one memory in communication with the processor; The memory stores instructions that can be executed by the processor, and the instructions are executed by the processor to enable the system to perform the aforementioned method for repairing tooth proximal surfaces.
[0019] Beneficial effects of the present invention: The method of tooth proximal surface repair of the present invention is based on the point cloud data predicted by AI. Under the premise of keeping the real tooth body of the oral scan unchanged, the method simulates the real proximal surface conditions of the patient's teeth through point cloud reconstruction, proximal surface deformation, suture smoothing, etc., thereby improving the authenticity of the simulated proximal surfaces in the invisible orthodontic tooth modeling stage. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The specific embodiments of the present invention will be further explained below with reference to the accompanying drawings.
[0021] Figure 1 is a flow chart of the tooth proximal surface repair method of the present invention; Figure 2 Schematic diagram of point cloud data obtained in the method of the present invention; Figure 3 This is a schematic diagram of the point cloud after reconstruction and restoration in the method of the present invention; Figure 4 A schematic diagram of deformation reconstruction in the method of the present invention; Figure 5 Schematic diagram of interproximal suturing in the method of the present invention; Figure 6 Schematic diagram of inner and outer boundaries in the method of the present invention; Figure 7 Schematic diagram of adjacent surface deformation in the method of the present invention; Figure 8 This is a schematic diagram of the final effect of tooth proximal surface restoration according to the present invention. DETAILED DESCRIPTION Example 1
[0022] Combine Figure 1 As shown, this embodiment provides a method for tooth proximal surface restoration based on point cloud prediction data, comprising the following steps: Step S1: align and denoise the tooth point cloud data with the tooth data of the missing adjacent surfaces to remove the noise influence and obtain the point cloud data of the predicted true tooth shape.
[0023] In this embodiment, preferably, in step S1, registration is performed according to the whole jaw fusion matching method, and the data with a Euclidean distance greater than 2 mm from the real tooth surface is filtered out in the point cloud data of each tooth to remove the noise effect in the point cloud prediction, and the point cloud data of the proximal surface of the real tooth morphology predicted by AI is obtained, and is fused with all the mesh vertices of the real tooth surface to form the point cloud data of the real tooth, such as Figure 2 shown.
[0024] Step S2: Use the Poisson reconstruction algorithm to construct a triangular mesh based on the point cloud data, and perform mesh repair and closure on the reconstructed triangular mesh.
[0025] Specifically, in this embodiment, in this step, the grid anomaly problem is repaired, the self-intersecting small channel non-manifold edge problem is repaired, and then the small holes that may exist on the grid are repaired, and finally the grid is simplified, such as Figure 3 shown.
[0026] Step S3: deform the triangular mesh reconstructed from the point cloud based on the original crown information so that the reconstructed mesh in the crown area fits the original crown better, which is recorded as MeshA.
[0027] In this embodiment, preferably, in step S3, the triangular mesh reconstructed from the point cloud is deformed using the Laplace deformation algorithm by taking the boundary points of the real teeth as target points and calculating the nearest points of the boundary points on the point cloud data as control points.
[0028] Step S4: Generate a mesh at the proximal surface of the real tooth, and deform it to the corresponding position of the proximal surface of MeshA in order to fit the mesh reconstructed with the point cloud.
[0029] In this embodiment, preferably, step S4 specifically includes the following steps: Step S41: Fill the holes in the mesh to repair the black triangles, obtain the lowest point of the crown boundary, and construct the adjacent triangular mesh, which is recorded as MeshB.
[0030] In this embodiment, preferably, in step S41 , based on the most adjacent regions of adjacent teeth, the tooth crown mesh boundaries are selected and sorted so that they are connected end to end, thereby obtaining the lowest point of the tooth crown boundary.
[0031] Step S42: In order to make the completed interproximal mesh more consistent with the tooth shape predicted by AI, the interproximal mesh MeshB is reshaped to be more consistent with the point cloud reconstructed mesh MeshA.
[0032] In this embodiment, preferably, step S42 specifically includes the following steps: Step S421: Distinguish the inner and outer boundaries in the boundary of MeshB. The inner boundary represents the fixed boundary sutured with the original crown, and the outer boundary represents the free boundary. Figure 5 As shown; Step S422: Re-dividing MeshA using Delaunay triangulation, so that there are no overly sharp triangles in the mesh of MeshA. Overly sharp means that the minimum angle is less than 15°, so that the mesh of MeshA appears sufficiently uniform and delicate. Step S423: Find the midpoint of the inner and outer boundaries of MeshB as the control point of deformation, obtain the normal of the midpoint, draw a ray from the midpoint and the midpoint normal to intersect MeshA, and use the intersection as the target point of deformation, while maintaining the fixed boundary in step S421 (i.e. Figure 5 ) remains unchanged, and MeshB is deformed to a target position that is more in line with MeshA according to the Laplace deformation algorithm, as shown in Figure 6 shown.
[0033] Step S5: On the inner fixed boundary of the adjacent mesh (i.e., MeshB), suture it with the original crown, and erase the suture line of the surrounding mesh using the Laplace smoothing algorithm, as shown in the following example: Figure 7 shown.
[0034] In this embodiment, the present invention preferably further comprises the following steps: Step S6: For two adjacent teeth, if there is a collision between the adjacent surfaces of the restored teeth, the collision value is made to approach zero through Laplace deformation, while keeping the intersection area of the original collision unchanged.
[0035] The tooth proximal surface restoration method of this embodiment can restore the proximal surfaces of adjacent teeth as realistically as possible based on the crown fitting mouth scan in the proximal surface area according to the point cloud prediction data. The final effect is as follows: Figure 8 shown. Example 2
[0036] This embodiment provides a computer program product, comprising computer instructions, which, when executed by a processor, enable a computer device to execute the method for restoring tooth proximal surfaces in embodiment 1. Example 3
[0037] This embodiment provides a computer-readable storage medium having computer-executable instructions stored thereon. When a processor executes the computer-executable instructions, the method for tooth proximal surface repair as in Example 1 is implemented. Example 4
[0038] This embodiment provides a system for repairing tooth proximal surfaces, comprising: at least one processor; and at least one memory in communication with the processor; The memory stores instructions that can be executed by the processor, and the instructions are executed by the processor to enable the system to perform the method for repairing tooth proximal surfaces in Example 1.
[0039] In the above description, many specific details are set forth in order to fully understand the present invention. However, the above description is only a preferred embodiment of the present invention. The present invention can be implemented in many other ways different from those described herein, so the present invention is not limited to the specific implementation disclosed above. At the same time, any person skilled in the art can make many possible changes and modifications to the technical solution of the present invention using the methods and technical contents disclosed above without departing from the scope of the technical solution of the present invention, or modify it into an equivalent embodiment of equivalent changes. Any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of protection of the technical solution of the present invention.
Claims
1. A method for repairing tooth proximal surfaces, characterized in that: Based on the point cloud prediction data, the following steps are included: Step S1: registering and denoising the tooth point cloud data with the tooth data of the missing adjacent surface to obtain point cloud data that predicts the true shape of the tooth; Step S2: Use the Poisson reconstruction algorithm to construct a triangular mesh based on the point cloud data, and perform mesh repair and closure on the reconstructed triangular mesh; Step S3: deforming the triangular mesh reconstructed from the point cloud based on the original crown information so that the reconstructed mesh on the crown area fits the original crown better, denoted as MeshA; Step S4: Generate a mesh at the proximal surface of the real tooth, and deform it to the corresponding position of the proximal surface of MeshA; Step S5: On the inner fixed boundary of the adjacent mesh, suture it with the original crown, and erase the suture line of the surrounding mesh by Laplace smoothing algorithm.
2. The method for repairing tooth proximal surfaces according to claim 1, characterized in that: In step S1, registration is performed according to the whole jaw fusion matching method, and the data with a Euclidean distance greater than 2 mm from the actual tooth surface is filtered out in the point cloud data of each tooth to remove the influence of noise in the point cloud prediction, and the adjacent surface point cloud data of the actual tooth morphology predicted by AI is obtained. It is then fused with all the mesh vertices of the actual tooth surface to form the point cloud data of the actual tooth.
3. The method for repairing tooth proximal surfaces according to claim 1, characterized in that: In step S3, the triangular mesh reconstructed from the point cloud is deformed using the Laplace deformation algorithm by taking the boundary points of the real teeth as target points and calculating the nearest points of the boundary points on the point cloud data as control points.
4. The method for repairing tooth proximal surfaces according to claim 1, characterized in that: Step S4 specifically includes the following steps: Step S41: fill the mesh holes, obtain the lowest point of the crown boundary, and construct the adjacent triangular mesh, denoted as MeshB; Step S42: reshape the adjacent surface mesh MeshB to fit the point cloud reconstructed mesh MeshA more closely.
5. The method for repairing tooth proximal surfaces according to claim 4, characterized in that: In step S41, based on the most adjacent regions of adjacent teeth, the tooth crown mesh boundaries are selected and the boundaries are sorted so that they are connected end to end, thereby obtaining the lowest point of the tooth crown boundary.
6. The method for repairing tooth proximal surfaces according to claim 4, characterized in that: Step S42 specifically includes the following steps: Step S421: distinguishing inner and outer boundaries in the boundary of MeshB, wherein the inner boundary represents a fixed boundary sutured with the original tooth crown, and the outer boundary represents a free boundary; Step S422: Delaunay triangulation is used to re-divide MeshA so that there are no overly sharp triangles in the mesh of MeshA. Overly sharp means that the minimum angle is less than 15°, so that the mesh of MeshA appears sufficiently uniform and delicate. Step S423: Find the midpoint of the inner and outer boundaries on MeshB as the control point of deformation, obtain the normal of the midpoint, make a ray from the midpoint and the midpoint normal to intersect MeshA, use the intersection point as the target point of deformation, and deform MeshB to a target position that better fits MeshA according to the Laplace deformation algorithm.
7. The method for repairing tooth proximal surfaces according to claim 1, characterized in that: The following steps are also included: Step S6: For two adjacent teeth, if there is a collision between the adjacent surfaces of the completed teeth, the collision value is made to approach zero through Laplace deformation, while keeping the intersection area of the original collision unchanged.
8. A computer program product, characterized in that: The invention comprises computer instructions, which, when executed by a processor, cause a computer device to execute the method for tooth proximal surface restoration according to any one of claims 1 to 7.
9. A computer-readable storage medium, characterized in that: Computer-executable instructions are stored thereon, and when a processor executes the computer-executable instructions, a method for tooth proximal surface repair as described in any one of claims 1-7 is implemented.
10. A system for repairing tooth proximal surfaces, characterized in that: include: at least one processor; as well as at least one memory in communication with the processor; The memory stores instructions executable by the processor, and the instructions are executed by the processor to enable the system to perform the method for tooth proximal surface repair according to any one of claims 1 to 7.
Citation Information
Cited By
Method and device for automatically generating triangular mesh model without dental crown, and electronic equipment
CN121437799A
