Generation method and system of gingival model with aesthetic characteristics

Abstract

The invention discloses a method and a system for generating a gingival model with aesthetic features, and relates to the technical field of gingival generation methods, an initial grid model of gingiva is determined according to synthesis of an upper surface area, an upper jaw area, a side area and a bottom area, the area accuracy of the initial grid model is ensured, and the generation efficiency of the gingival model is improved. The accurate construction of the initial grid model is realized, and the initial grid model has no gingival aesthetic form; therefore, aesthetic features of the gingiva are constructed according to the mastoid curved surface, the gingival edge form and the gingival form; constructing a primary gingival model according to the initial grid model of the gingiva, the aesthetic characteristics of the gingiva and the intradental flesh surface area, determining a gingival model with the aesthetic characteristics according to the primary gingival model and the dental model, further constructing the aesthetic characteristics of the gingiva for the initial grid model, further perfecting the primary gingival model, and obtaining a gingival model; accurate control of the aesthetic characteristics of the gingiva is achieved, and the accuracy of the gingiva model with the aesthetic characteristics is guaranteed.

Description

Technical Field

[0001] This invention relates to the technical field of gingival generation methods, and more particularly to a method and system for generating an aesthetically pleasing gingival model. Background Technology

[0002] With the advancement of technology, complete denture treatment plans require the gingiva to support and fix the dentures and distribute occlusal pressure. Digital complete denture design solutions necessitate generating an aesthetically pleasing gingival model based on both the jaw model and the denture model. Current gingival model generation algorithms still have room for improvement in the stability and aesthetics of the resulting model, especially in aesthetic reconstruction, where the control over aesthetic features is not precise enough, affecting the accuracy of the aesthetically pleasing gingival model. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art. This invention provides a method and system for generating a gingival model with aesthetic features.

[0004] This invention provides a method for generating a gingival model with aesthetic features, comprising: The initial mesh model of the gingiva is determined by synthesizing the upper surface region, the maxillary region, the lateral region, and the bottom region. Collect the mastoid surface and gingival margin morphology, and construct the aesthetic features of the gingiva based on the mastoid surface, gingival margin morphology and gingival morphology; The intradental fleshy surface region is determined based on the initial gingival model, and a primary gingival model is constructed based on the aesthetic characteristics of the gingiva and the intradental fleshy surface region. A gingival model with aesthetic characteristics is then determined based on the primary gingival model and the jaw model.

[0005] This invention provides a system for generating a gingival model with aesthetic features. This system is applied to the aforementioned method for generating a gingival model with aesthetic features. The system includes: The initial mesh model module is used to determine the initial mesh model of the gingiva based on the synthesis of the upper surface region, the maxillary region, the lateral region, and the bottom region. The aesthetic features module is used to collect the mastoid surface and gingival margin morphology, and to construct the aesthetic features of the gingiva based on the mastoid surface, gingival margin morphology and gingival morphology. The gingival module is used to determine the intraocular fleshy area based on the initial gingival model, construct a primary gingival model based on the aesthetic features of the gingiva and the intraocular fleshy area, and determine an aesthetically pleasing gingival model based on the primary gingival model and the jaw model.

[0006] Compared with the prior art, the beneficial effects of the present invention are: In this embodiment of the invention, the initial mesh model of the gingiva is determined by synthesizing the upper surface region, the maxillary region, the lateral region, and the bottom region using the method described in this embodiment. This achieves the overall synthesis of the upper surface region, the maxillary region, the lateral region, and the bottom region, and ensures the regional accuracy of the initial mesh model. The initial mesh model does not have the aesthetic morphology of the gingiva. Therefore, the mastoid surface and gingival margin morphology are collected, and the aesthetic features of the gingiva are constructed based on the mastoid surface, gingival margin morphology, and gingival morphology. The intradental fleshy surface region is determined based on the initial gingival model, and a primary gingival model is constructed based on the aesthetic features of the gingiva and the intradental fleshy surface region. A gingival model with aesthetic features is determined based on the primary gingival model and the jaw model. The aesthetic features of the gingiva are further constructed on the initial mesh model, and the primary gingival model is further improved. This achieves precise control of the aesthetic features of the gingiva and ensures the accuracy of the gingival model with aesthetic features. Attached Figure Description

[0007] Figure 1 This is a schematic flowchart of the method for generating a gingival model with aesthetic features according to an embodiment of the present invention. Figure 2 This is a flowchart illustrating step S11 in the method for generating an aesthetically pleasing gingival model according to an embodiment of the present invention. Figure 3 This is a flowchart illustrating step S12 in the method for generating an aesthetically pleasing gingival model according to an embodiment of the present invention. Figure 4 This is a flowchart illustrating step S13 in the method for generating an aesthetically pleasing gingival model according to an embodiment of the present invention. Figure 5 This is a schematic diagram of the structural composition of the system for generating an aesthetically pleasing gingival model according to an embodiment of the present invention. Figure 6 This is a schematic diagram of the cervical margin of the method for generating an aesthetically pleasing gingival model according to an embodiment of the present invention. Figure 7 This is a schematic diagram of the gingival margin outline of the method for generating a gingival model with aesthetic features according to an embodiment of the present invention. Figure 8 This is a schematic diagram of the gingival margin region of the method for generating an aesthetically pleasing gingival model according to an embodiment of the present invention. Detailed Implementation

[0008] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0009] Please see Figures 1 to 8A method for generating an aesthetically pleasing gingival model is applied to gingival model generation scenarios. The method for generating an aesthetically pleasing gingival model includes: Step S11: Determine the initial mesh model of the gingiva based on the synthesis of the upper surface region, maxillary region, lateral region, and bottom region; Step S12: Collect the mastoid surface and gingival margin morphology, and construct the aesthetic features of the gingiva based on the mastoid surface, gingival margin morphology and gingival morphology; Step S13: Determine the intraocular flesh surface area based on the initial gingival model, construct a primary gingival model based on the aesthetic characteristics of the gingiva and the intraocular flesh surface area, and determine a gingival model with aesthetic characteristics based on the primary gingival model and the jaw model. refer to Figure 2 In step S11, the specific steps are as follows: S111: Synthesize the upper surface region, upper palatal region, lateral region, and bottom region to form a complete initial set of gingival vertices, which contains all the key points that constitute the shape of the gingiva; S112: Transform the initial set of gingival vertices into an initial mesh model, which consists of multiple triangles or polygons to represent the geometry of the gingiva.

[0010] In the embodiments of this application, before proceeding to S111, four regions have been constructed respectively through the following steps: Upper surface region: including buccal, central, lingual curves and alveolar bone boundary curves, forming the geometry of the upper surface of the gingiva; Maxillary region: composed of lingual boundary curve segments and alveolar bone boundary curves, generated by UV spline surfaces; Lateral region: constructed based on the transition curves of the lateral contour and multiple lateral vertices; Bottom region: constructed based on the gingival boundary lines identified by the dental model and multiple dental model vertices. Each of these regions contains an independent set of vertices, and there may be overlaps or gaps at the junctions.

[0011] To combine the four regions into a single initial set of gingival vertices, the following method is used: The vertex deduplication and merging method uses a spatial hash table for vertex deduplication. The principle is to map all vertices to the hash table according to their spatial positions. A merging threshold is set (e.g., 0.05mm). If the distance between two vertices is less than this threshold, they are considered the same vertex and merged. The actual operation involves: traversing all vertices and mapping their coordinates to the hash table; comparing the distances of vertices within each hash bucket and merging duplicate vertices; and updating the indexes of adjacent regions to ensure that the merged vertices can be correctly connected.

[0012] Boundary alignment method: At the boundary of adjacent regions (such as the top surface and the side surface), the nearest neighbor search algorithm is used to align the boundary points; Principle: Match the vertices at the boundary to ensure that the boundary points of adjacent regions are consistent in spatial position; If there are gaps, new vertices are generated by interpolation (such as linear interpolation) to fill the gaps; Practical operation: Extract the boundary points of the top surface and the side surface; Calculate the nearest neighbor distance between the boundary points; For point pairs with a distance greater than a threshold, new vertices are generated by interpolation.

[0013] Normal consistency check method: After merging vertices, perform a consistency check on the normal vectors of adjacent triangles; Principle: Ensure that the normal vectors of adjacent triangles are in the same direction to avoid normal flipping; If inconsistency in normal vectors is found, adjust the vertex order or regenerate the triangles; Practical operation: Traverse all triangles and calculate their normal vectors; Check the angle between the normal vectors of adjacent triangles. If the angle is greater than a threshold (such as 90 degrees), adjust the vertex order.

[0014] By deduplicating vertices, aligning boundaries, and checking normal consistency, the four regions are combined into a complete initial set of gingival vertices. This method ensures the geometric accuracy and continuity of the model, laying a solid foundation for subsequent mesh generation. In practical applications, this method can efficiently handle complex gingival morphologies and adapt to individual differences among different patients.

[0015] Furthermore, the initial set of gingival vertices is transformed into an initial mesh model, which consists of multiple triangles or polygons to represent the geometry of the gingiva, referencing the geometry of the gingiva; At this point, the input is: initial set of gingival vertices; file format: initialvertices.obj; number of vertices: 8,312; vertex attributes: 3D coordinates (x, y, z); normal vector (nx, ny, nz); boundary markers (indicating whether a vertex is located on a boundary).

[0016] To transform the initial gingival vertex set into an initial mesh model, the following method is used: The Delaunay triangulation method: An initial mesh is generated using the 3D Delaunay triangulation algorithm. Principle: Delaunay triangulation is a method of connecting point sets into a triangular mesh, ensuring that the circumcircle of all triangles does not contain other vertices. In 3D space, this method can generate tetrahedral meshes, but by projecting onto a 2D plane or restricting the triangulation range, triangular meshes can be generated. Practical operation: Project the vertex set onto a 2D plane (such as the xy-plane); perform Delaunay triangulation on the projected vertices; map the triangulation result back to 3D space to generate the initial triangular mesh.

[0017] Mesh optimization methods: Edge flipping and edge collapsing are used to optimize mesh quality; Principle: Edge flipping: Improves the geometric quality of the mesh by swapping the connection of triangle edges (e.g., reducing narrow triangles); Edge collapsing: Merges short edges into a single vertex, reducing mesh complexity; Practical operation: Traverse all edges, calculate their length and the included angle of adjacent triangles; Collapsing edges with a length less than 0.1mm; Flipping edges of triangles with included angles less than 30° or greater than 150°.

[0018] Boundary handling method: Repair the mesh boundary to ensure the model's closure; Principle: Boundary vertices may have gaps or overlaps due to triangulation or optimization operations; Repair the boundary by detecting boundary edges (edges belonging to only one triangle) and filling in the missing triangles; Actual operation: Traverse all edges and mark the boundary edges; Fill the boundary edges to generate new triangles; Check whether the filled mesh is closed.

[0019] By employing Delaunay triangulation, mesh optimization, and boundary treatment, the initial gingival vertex set is transformed into a high-quality initial mesh model. This method ensures the geometric accuracy and mesh quality of the model, laying a solid foundation for subsequent aesthetic feature addition and model optimization. In practical applications, this method can efficiently handle complex gingival morphologies and adapt to individual differences among different patients. refer to Figure 3 In step S12, the specific steps are as follows: S121: Collect the curves of the buccal and lingual gingival boundaries, construct an aesthetically pleasing cervical margin line based on the curves of the buccal and lingual gingival boundaries, and adjust the mastoid strength and height parameters of the cervical margin line to output a three-dimensional mastoid surface. S122: Multiple feature segments are determined based on the division of the cervical margin. Smooth and continuous peripheral lines of the gingival margin are generated based on these feature segments. The inner and outer boundaries of the gingival margin region are constructed based on these peripheral lines. The gingival margin morphology is generated based on the inner and outer boundaries of the gingival margin region. At the same time, the gingival morphology is collected, the transition area between the mastoid surface and the gingival margin morphology is identified, and the aesthetic features of the gingiva are constructed based on the transition area and the gingival morphology. The aesthetic features of the gingiva are multi-level aesthetic features of the mastoid surface, the gingival margin morphology, and the gingival morphology.

[0020] In the embodiments of this application, curves of the buccal boundary line and the lingual position of the gingiva are collected. The buccal boundary line is extracted from the lateral region and is a cubic B-spline curve containing 38 control points. The lingual position curve is extracted from the maxillary region boundary and is a cubic B-spline curve containing 42 control points. The coordinate system is the oral coordinate system, with the origin located at the center of the central incisor contact point.

[0021] A cervical margin line with aesthetic features was constructed using the following methods: 4th-order B-spline curve interpolation algorithm; Number of control points: 18 control points per tooth; Aesthetic parameters: Curvature continuity: G2 continuity; Curve smoothness: second derivative rate of change <0.02 / mm; Aesthetic proportion: conforms to the golden ratio (1:1.618); Optimization algorithm: least squares method was used to optimize the position of control points.

[0022] For adjusting the mastoid strength parameter, the parameter range is 0.3-1.2 (1.0 is the standard strength); the adjustment algorithm is based on Gaussian function-based local deformation; the influence range is within a 2mm radius of the mastoid center; the intensity distribution decreases from the center to the edge, conforming to a Gaussian distribution. For adjusting the mastoid height parameter, the parameter range is 0.5-1.5mm; the adjustment method is vertical offset superposition; the height distribution decreases from the center to the edge, using a cosine function distribution. The output is a 3D mastoid surface, generated using Coons surface interpolation; the mesh resolution is 0.1mm; the surface continuity is G1 continuous (tangent continuous); the normal vector consistency is such that all normal vectors point outwards; the output format is OBJ format, containing vertex, face, and normal vector information.

[0023] By accurately acquiring boundary lines, constructing aesthetic cervical margins, adjusting mastoid parameters, and generating 3D surfaces, a highly realistic mastoid surface was successfully created. This method not only considers anatomical accuracy but also fully incorporates aesthetic principles, achieving personalized customization of mastoid morphology through parametric adjustments. In particular, when handling the strength and height parameters of the mastoid, the distribution patterns of Gaussian and cosine functions are used to ensure a natural transition and aesthetic effect of the mastoid morphology. The generated mastoid surface meets clinical application standards in terms of geometric accuracy, continuity, and aesthetic features, providing a crucial aesthetic foundation for the subsequent construction of a complete gingival model.

[0024] In the real-time example of this application, the mastoid surface is constructed as follows: a. Calculate the highest points hP1 and hP2 at the near and far ends of each neckline; b. Divide each neckline into two parts, the buccal line and the lingual line, with hP1 and hP2 as endpoints. Take half of the vertices in the middle part of the buccal line as the half buccal line and half of the vertices in the middle part of the lingual line as the half lingual line. c. Translate hP1 and its two adjacent points along the occlusal direction by a distance dist, where dist = (f - 0.5) + h, and f is the mastoid intensity, and h is the height of the vector from hP1 to the center of the tooth in the occlusal direction; process hP2 and its two adjacent points in the same way. d. Fit halfBuccleLine, halfBongueLine, the translated hP1 and its two adjacent points, and the translated hP2 and its two adjacent points together to form a new neckline newNeckLine, so as to gradually construct the corresponding mastoid surface.

[0025] Furthermore, multiple feature segments are determined based on the division of the cervical margin. The cervical margin input is cervical margin data. According to the curvature change of the cervical margin and the anatomical features of the teeth, the cervical margin is divided into several segments, each corresponding to a specific anatomical region, such as the cervical region of the tooth or interdental papilla. The division method is to set a curvature threshold to identify feature points and then divide the feature segments.

[0026] Smooth and continuous gingival margin outlines are generated based on multiple feature segments. B-spline curves are used to fit the point set on the feature segments. By adjusting the number and position of control points, the smoothness and continuity of the curve are ensured, forming the gingival contour around the outer side of the cervical margin. The inner and outer boundaries of the gingival margin region are constructed based on each gingival margin outline. The inner boundary is defined as the side closer to the cervical margin, usually maintaining a certain distance from the cervical margin. The outer boundary is defined as the gingival margin outline itself. The construction method is to generate the inner boundary by offsetting the gingival margin outline, with the offset distance set according to the anatomical structure.

[0027] The gingival margin morphology is generated based on the inner and outer boundaries of the gingival margin region. The generation method involves filling the area between the inner and outer boundaries using a bilinear or NURBS surface. Morphological adjustment involves locally adjusting the surface according to the actual anatomical structure to ensure a natural and realistic morphology. Simultaneously, the data acquisition method uses a 3D scanning device to acquire overall gingival morphological data. The recognition method uses computer vision algorithms to identify the boundary area between the mastoid surface and the gingival margin morphology. The transition area is defined as the smooth and natural transition zone between the mastoid surface and the gingival margin morphology. Combining the data from the mastoid surface, gingival margin morphology, and overall gingival morphology, multi-level modeling techniques are used to construct aesthetic features, including the three-dimensionality of the mastoid, the contour beauty of the gingival margin, and the harmony of the overall gingiva.

[0028] Through meticulous segmentation of features, generation of the gingival margin perimeter, construction of the gingival margin region, identification of transition areas, and construction of aesthetic features, a gingival model with multi-layered aesthetic features was successfully created. Each step closely integrates anatomical structure and aesthetic principles, ensuring a high degree of realism and personalization of the model. In particular, when dealing with the transition area between the gingival margin morphology and the mastoid surface, a natural and smooth transition effect was achieved through precise identification and modeling techniques. The final constructed aesthetic features of the gingiva not only meet the standards for clinical application but also provide patients with aesthetically pleasing and functional gingival restoration solutions.

[0029] In the real-time example of this application, the gingival margin region is constructed as follows: A. Calculate the outer edge of the gingival margin (neckOutterLine): a. Calculate the highest points in the occlusal direction, hP1 and hP2, at the mesial and distal ends of each newNeckLine, as well as the buccal center point (buccleCenterPoint) and lingual center point (bongueCenterPoint); b. Divide each newNeckLine into four segments with hP1, hP2, buccleCenterPoint, and bongueCenterPoint as endpoints; c. Calculate four vectors of length gingivaThickness for each of the four points, dir1, dir2, dir3, and dir4, corresponding to the mesial direction, distal direction, (buccal direction + archNormal), and (lingual direction + archNormal), respectively; d. Traverse the points pi of the above four curve segments in sequence, and calculate the coordinates of the points p = pi + dirStart*(1-t) + dirEndt + archNormal(t*(t-1)), where dirStart is the vector corresponding to the starting endpoint of the line segment, dirEnd is the vector corresponding to the ending endpoint of the line segment, and t = current point index / number of vertices of the current line segment; e. The above p forms the gingival margin outer line neckOutterLine to determine the gingival margin outer line neckOutterLine.

[0030] B. Calculate the target coordinates of the gingival margin region: a. Calculate the intersection line between the tooth model and the gingival model, toothGingLine; b. Calculate the vertices of the gingival model that are outside the tooth model's range within the radius of the above intersection line, marginDist (gingival margin width morphology parameter), and mark them as the gingival margin region. marginDist is the gingival margin width morphology parameter set by the user; c. Calculate the point tempClosestP, which is the closest point to toothGingLine for each vertex in the gingival margin region, at a distance of tempDist; d. Calculate the point p0 on newNeckLine and the point p1 on neckOutterLine corresponding to tempClosestP. e. Calculate the normal vector at p0: dirNeckNormal = tempDir1 ^ tempDir2, where tempDir1 is the tangent of the curve at p0, tempDir2 is the vector from p1 to p0, and ^ represents the cross product of vectors; f. Calculate the new coordinates of each point: p = (1 - tempDist / marginDist)p0 + tempDist / marginDist * p1 + dirNeckNormal * u, where u is the shape control variable, u = marginDist * marginDist * sin(pitempDist / marginDist) / 2, and p is the target coordinate of each vertex in the gingival region.

[0031] refer to Figure 4 In step S13, the specific steps are as follows: S131: Acquire an initial gingival model, identify multiple tooth apex nodes based on the initial gingival model, and construct the intradental flesh surface region based on the multiple tooth apex nodes; S132: Organically integrate the aesthetic features of the gingiva and the intraocular fleshy area, and smoothly connect the aesthetic features of the gingiva and the intraocular fleshy area to further optimize the initial gingival model and output the primary gingival model. S133: Collect a dental model, register the dental model and the primary gingival model, and determine the difference between the dental model and the primary gingival model. If the difference is lower than the preset difference threshold, then determine the gingival model with aesthetic features.

[0032] In the embodiments of this application, an initial gingival model is acquired, and multiple tooth apex nodes are determined based on the identification of the initial gingival model. Simultaneously, based on curvature analysis and local height detection algorithms, principal curvature (k1, k2) and Gaussian curvature (K) analysis are used, with a height threshold of 0.5 mm or more above the gingival surface. Optionally, the principal curvature and Gaussian curvature of each vertex are calculated; vertices with curvature values ​​in the range of 0.1-0.3 mm⁻¹ are selected; height selection: Z-coordinate is 0.5 mm or more above the average gingival plane; the DBSCAN clustering algorithm (ε=0.2 mm, min_samples=5) is used; adjacent candidate vertices are aggregated into clusters; each cluster represents the apex region of a tooth; boundary detection is performed on each cluster; extreme points on the boundary are extracted as apex nodes; node spacing is approximately 0.8-1.2 mm.

[0033] The intraocular surface region was constructed using the following method: 4th-order NURBS surface fitting; number of control points: 25-30 per tooth; surface continuity: G2 continuity (curvature continuity); UV parameterization was performed on the top nodes; U direction: along the tooth circumference; V direction: along the tooth axis; control point positions were calculated using the least squares method; weighting factors: set according to node importance (0.8-1.2); node vectors: uniformly distributed; the surface was generated based on the NURBS equation, with a surface resolution of 0.05 mm and surface normal vectors uniformly facing outwards.

[0034] By accurately identifying the tooth crest nodes and constructing high-quality NURBS surfaces, an anatomically accurate intraocular meat surface region was successfully generated. This method maintains geometric accuracy while ensuring the smoothness and continuity of the surface. Especially when dealing with complex tooth morphologies, curvature analysis and clustering algorithms can accurately identify key nodes, while the application of NURBS surfaces ensures the generation of a high-quality intraocular meat surface region. This method is not only applicable to standard tooth morphologies but also can handle individualized anatomical variations well, laying a solid foundation for subsequent aesthetic feature integration and model optimization.

[0035] Furthermore, the aesthetic features of the gingiva and the intraocular flesh surface area are organically integrated, and a smooth connection is made between the aesthetic features of the gingiva and the intraocular flesh surface area to further optimize the initial gingival model and output a primary gingival model. This process introduces the output primary gingival model.

[0036] At this point, the input sources are: initial gingival model (from S132); intraocular flesh surface area (from S151); aesthetic feature data: color mapping: RGB values ​​(e.g., #D4A373 is the color of healthy gingiva); texture details: including fine vascular texture and surface gloss; surface microstructure: concavity and convexity parameters (0.02-0.05mm).

[0037] The integration of aesthetic features with the intraocular flesh surface region was carried out using a hybrid algorithm based on vertex weights. The weight allocation was as follows: intraocular flesh surface region weight: 0.7; aesthetic feature weight: 0.3.

[0038] Spatially align the vertices of the aesthetic features with the vertices of the inner lining of the tooth, with an alignment accuracy of 0.01 mm; Alignment algorithm: ICP (Iterative Closest Point); Weighted interpolation: perform weighted interpolation on the vertices of each overlapping region; Interpolation result: smooth transition of vertex positions; Normal vector adjustment: recalculate the normal vectors of the blended vertices; ensure lighting consistency; Normal vector deviation: <5°.

[0039] For smooth connection processing, the smoothing algorithm is based on Laplacian smoothing; smoothing parameters: number of iterations: 5; smoothing factor: 0.3; boundary preservation: enabled; simultaneously, boundary detection: identifies the boundary region between the inner surface of the tooth and aesthetic features; boundary width: 2-3 vertex loops; boundary markers: stored as a list of boundary vertices; Laplacian smoothing: applies Laplacian smoothing to non-boundary vertices; boundary preservation: boundary vertices maintain their original positions; ensuring geometric continuity; G1 continuity (tangent continuity): 100% satisfied.

[0040] Optimization: Mesh simplification: Reduce redundant vertices; Simplification rate: 15% (preserving key features); Simplification algorithm: QEM (quadratic error metric); Quality check: Triangle quality: Minimum angle: >30°; Maximum angle: <120°; Aspect ratio: <3:1; Smoothness check: Curvature variation: <0.01mm; Surface continuity: G2 continuity.

[0041] By organically integrating aesthetic features with the intradental gingival surface and combining smooth connection processing, a high-quality primary gingival model was successfully generated. This method significantly improves the aesthetic performance of the model while maintaining anatomical accuracy. In particular, when dealing with boundary transitions, the combination of weighted interpolation and Laplacian smoothing ensures the smoothness and continuity of the model. The final output primary gingival model not only meets clinical requirements in terms of geometric accuracy but also reaches professional standards in terms of visual effect, laying a solid foundation for subsequent model registration and final validation.

[0042] Therefore, a dental model was collected, the dental model and the primary gingival model were registered, and the difference between the dental model and the primary gingival model was determined. If the difference was lower than the preset difference threshold, a gingival model with aesthetic features was determined, and a gingival model with aesthetic features was introduced.

[0043] At this point, a dental model is acquired, and registration is performed between the dental model and the primary gingival model. The registration algorithm used is an improved ICP (Iterative Closest Point) algorithm; registration accuracy is 0.01 mm. Initial alignment: coarse registration based on feature points. Feature point selection: anatomical landmarks such as cusps and sockets. Coarse registration error: <0.5 mm. Fine registration: number of iterations: 50; convergence threshold: 0.001 mm. Each iteration calculates: finding the closest point pair, calculating the transformation matrix, and applying the transformation. Registration time: approximately 2.3 seconds. Registration quality assessment: registration error distribution: 90% of point pairs have an error <0.02 mm; maximum error: 0.05 mm; registration success rate: 99.2%.

[0044] Difference calculation method: The Hausdorff distance algorithm is used to calculate the spatial distance of each corresponding point pair. Specific steps: Point pair matching: Sampling is performed on the dental and gingival models; Sampling density: 4 points per square millimeter; Total number of sampling points: approximately 25,000; Calculation of the Euclidean distance for each point pair; Calculation time: approximately 0.8 seconds; Statistical analysis: Mean distance: 0.018 mm; Standard deviation: 0.008 mm; Maximum distance: 0.045 mm; 95% confidence interval: 0.012-0.024 mm. Preset difference threshold: Clinically required threshold: 0.03 mm; Safety factor: 1.5; Actual usage threshold: 0.02 mm; Judgment result: Maximum distance 0.045 mm > threshold 0.02 mm; Further optimization is needed.

[0045] Treating the internal areas of the teeth: a. Calculate the set of vertices C1 located inside each tooth in the gingival model; b. Calculate the set of vertices C2 contained in the intersecting facet of the gingival model and the tooth model; c. Mark the points in the set C1-C2 as the tooth interior region; d. Perform a first-order Laplacian smoothing on the tooth interior region.

[0046] Please see Figure 5 , Figure 5 This is a schematic diagram of the structural composition of the system for generating an aesthetically pleasing gingival model according to an embodiment of the present invention; the system for generating an aesthetically pleasing gingival model includes: Initial mesh model module 21 is used to determine the initial mesh model of the gingiva based on the synthesis of the upper surface region, the maxillary region, the lateral region, and the bottom region; Aesthetic feature module 22 is used to collect the mastoid surface and gingival margin morphology, and to construct the aesthetic features of the gingiva based on the mastoid surface, gingival margin morphology and gingival morphology; The gingival module 23 is used to determine the intraocular fleshy area based on the initial gingival model, construct a primary gingival model based on the aesthetic features of the gingiva and the intraocular fleshy area, and determine a gingival model with aesthetic features based on the primary gingival model and the jaw model.

[0047] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for generating an aesthetically pleasing gingival model, characterized in that, include: The initial mesh model of the gingiva is determined by synthesizing the upper surface region, the maxillary region, the lateral region, and the bottom region. Collect the mastoid surface and gingival margin morphology, and construct the aesthetic features of the gingiva based on the mastoid surface, gingival margin morphology and gingival morphology; The intraocular flesh surface region is determined based on the initial gingival model, and a primary gingival model is constructed based on the aesthetic characteristics of the gingiva and the intraocular flesh surface region. A gingival model with aesthetic characteristics is then determined based on the primary gingival model and the jaw model.

2. The method for generating an aesthetically pleasing gingival model according to claim 1, characterized in that, The determination of the upper surface region, upper palatal region, lateral region, and underside region based on different gingival boundary areas includes: Multiple curves are constructed based on the division of the gingival boundary region, representing the buccal, central, and lingual positions of the teeth. The boundary curves of the alveolar bone morphology are determined based on the multiple curves related to the alveolar bone. The corresponding upper surface regions are constructed based on the multiple curves representing the buccal, central, and lingual positions of the teeth, the boundary curves of the alveolar bone morphology, and the buccal gingival boundary line.

3. The method for generating an aesthetically pleasing gingival model according to claim 1, characterized in that, The initial mesh model of the gingiva, determined by synthesizing the upper surface region, maxillary region, lateral region, and bottom surface region, includes: The upper surface region, upper palatal region, lateral region, and bottom region are synthesized to form a complete initial set of gingival vertices, which contains all the key points that constitute the shape of the gingiva.

4. The method for generating an aesthetically pleasing gingival model according to claim 3, characterized in that, The initial mesh model of the gingiva determined based on the synthesis of the upper surface region, the maxillary region, the lateral surface region, and the bottom surface region also includes: The initial set of gingival vertices is transformed into an initial mesh model, which consists of multiple triangles or polygons to represent the geometry of the gingiva.

5. The method for generating an aesthetically pleasing gingival model according to claim 1, characterized in that, The process of collecting the mastoid surface and gingival margin morphology, and constructing the aesthetic features of the gingiva based on the mastoid surface, gingival margin morphology, and gingival morphology, includes: The curves of the buccal and lingual gingival boundaries are collected. A cervical margin line with aesthetic features is constructed based on the curves of the buccal and lingual gingival boundaries. The mastoid strength and height parameters of the cervical margin line are adjusted to output a three-dimensional mastoid surface.

6. The method for generating an aesthetically pleasing gingival model according to claim 5, characterized in that, The process of collecting the mastoid surface and gingival margin morphology, and constructing the aesthetic features of the gingiva based on the mastoid surface, gingival margin morphology, and gingival morphology, also includes: Multiple feature segments are determined based on the division of the cervical margin. Smooth and continuous peripheral lines of the gingival margin are generated based on these feature segments. The inner and outer boundaries of the gingival margin region are constructed based on each peripheral line of the gingival margin region. The gingival margin morphology is generated based on the inner and outer boundaries of the gingival margin region.

7. The method for generating an aesthetically pleasing gingival model according to claim 6, characterized in that, The process of collecting the mastoid surface and gingival margin morphology, and constructing the aesthetic features of the gingiva based on the mastoid surface, gingival margin morphology, and gingival morphology, also includes: The gingival morphology was collected to identify the transition area between the mastoid surface and the gingival margin. Based on the transition area and the gingival morphology, the aesthetic features of the gingiva were constructed. These aesthetic features of the gingiva are multi-level aesthetic features of the mastoid surface, the gingival margin, and the gingival morphology.

8. The method for generating an aesthetically pleasing gingival model according to claim 1, characterized in that, The process involves determining the intraocular flesh surface region based on an initial gingival model, constructing a primary gingival model based on the aesthetic characteristics of the gingiva and the intraocular flesh surface region, and determining an aesthetically pleasing gingival model based on the primary gingival model and the jaw model, including: An initial gingival model is acquired, and multiple tooth apical nodes are identified based on the initial gingival model. The intradental flesh surface region is then constructed based on these multiple tooth apical nodes.

9. The method for generating an aesthetically pleasing gingival model according to claim 8, characterized in that, The process of determining the intraocular flesh surface region based on an initial gingival model, constructing a primary gingival model based on the aesthetic characteristics of the gingiva and the intraocular flesh surface region, and determining an aesthetically pleasing gingival model based on the primary gingival model and the jaw model further includes: The aesthetic features of the gingiva and the intraocular flesh surface area are organically integrated, and a smooth connection is made between the aesthetic features of the gingiva and the intraocular flesh surface area to further optimize the initial gingival model and output a primary gingival model. A dental model is collected, and the dental model and the primary gingival model are registered. The difference between the dental model and the primary gingival model is determined. If the difference is lower than the preset difference threshold, the gingival model with aesthetic features is determined.

10. A system for generating an aesthetically pleasing gingival model, characterized in that, The system for generating an aesthetically pleasing gingival model is applied to the method for generating an aesthetically pleasing gingival model as described in any one of claims 1-9, wherein the system for generating an aesthetically pleasing gingival model comprises: The initial mesh model module is used to determine the initial mesh model of the gingiva based on the synthesis of the upper surface region, the maxillary region, the lateral region, and the bottom region. The aesthetic features module is used to collect the mastoid surface and gingival margin morphology, and to construct the aesthetic features of the gingiva based on the mastoid surface, gingival margin morphology and gingival morphology. The gingival module is used to determine the intraocular fleshy area based on the initial gingival model, construct a primary gingival model based on the aesthetic features of the gingiva and the intraocular fleshy area, and determine an aesthetically pleasing gingival model based on the primary gingival model and the jaw model.

Images