A method and system for automatic full-mouth tooth alignment based on occlusal plane feature points
By using a full-mouth automatic tooth alignment method based on occlusal plane feature points, the problem of malocclusion errors in the upper and lower jaws has been solved, achieving efficient, precise, and aesthetically pleasing automatic tooth alignment, thus improving the effectiveness of orthodontic treatment and patient comfort.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHENGZHOU JIANER BUFAN TECH CO LTD
- Filing Date
- 2024-09-18
- Publication Date
- 2026-06-30
AI Technical Summary
Existing automatic tooth alignment methods cannot effectively solve the problem of occlusal errors of the first, second, third and fourth molars in the upper and lower jaws, resulting in poor chewing function, uneven tooth wear, unstable occlusion, and affecting temporomandibular joint function and aesthetics.
The full-mouth automatic tooth alignment method based on occlusal plane feature points obtains dental model information, calculates the centroid coordinates, constraint distances, and feature points of the teeth, performs tooth pairing and iterative registration, constructs an objective function to optimize tooth occlusion and alignment, and optimizes tooth spacing using alveolar ridge crest lines.
It improves the accuracy and aesthetics of tooth alignment, reduces manual operation time, ensures the accuracy and comfort of orthodontic treatment, reduces tooth conflict and mold penetration, and provides personalized treatment plans.
Smart Images
Figure CN119251267B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of oral medicine technology, and in particular to a method and system for automatic full-mouth tooth alignment based on occlusal plane feature points. Background Technology
[0002] In the process of making complete dentures, obtaining an artificial dentition that matches the patient's oral characteristics is one of the key steps to the success of the restoration. A good artificial dentition can effectively restore the patient's chewing function, reshape facial features, and enhance the patient's confidence.
[0003] Currently, the following three methods are mainly used for automatic full-mouth tooth alignment:
[0004] Method 1 specifically involves: 1) establishing a three-dimensional database of standard tooth features; 2) extracting patient oral cavity feature information; and 3) tooth arrangement. This method for fabricating complete dentures establishes a mutual constraint relationship between the oral cavity and artificial teeth, thereby achieving automatic tooth arrangement and obtaining dentition that conforms to the oral cavity features of different patients. The arranged dentition can be appropriately adjusted according to the patient's needs to suit their gender, age, etc., effectively meeting the clinical requirements of complete dentures.
[0005] Method 2 specifically involves: performing virtual completion processing on the original dentition image to obtain a complete dentition image; performing dentition processing on the complete dentition image according to preset dentition rules to obtain an initial dentition result; and adjusting the initial dentition result according to preset adjustment requirements to obtain an adjusted dentition result.
[0006] Method 3 specifically involves: acquiring a 3D model of a triangular mesh of teeth for tooth alignment; inputting the triangular mesh model into a pre-trained deep learning model to obtain the predicted tooth positions for the tooth alignment result. The deep learning model includes a first feature encoder that takes the 3D triangular mesh model as input to obtain tooth shape features, a second feature encoder that takes the dentition point cloud as input to obtain global dentition features, and a feature decoder and mapper that, based on the tooth shape features and the global dentition features, obtains the predicted tooth alignment result.
[0007] Method four involves adjusting the settings based on human experience. However, different people may have different designs for a single dental model. This method of arranging teeth based on human experience is inefficient and prone to large errors.
[0008] None of the four methods described above can resolve the malocclusion issues of the first, second, third, and fourth molars (the four innermost teeth on the left and right sides of the upper and lower jaws, totaling eight pairs). This ultimately leads to inadequate chewing function, uneven tooth wear, unstable occlusion, and impaired temporomandibular joint function. Therefore, the aesthetics and comfort of orthodontic treatment still need further improvement. Summary of the Invention
[0009] This invention aims to solve the problems of occlusal errors and unattractive tooth arrangement in the first, second, third and fourth mandibles. It proposes a full-mouth automatic tooth arrangement method and system based on occlusal plane feature points to achieve automated full-mouth tooth arrangement. While prioritizing perfect occlusion, it also optimizes the tooth arrangement, improving the aesthetics and neatness of the tooth arrangement results.
[0010] To achieve the above objectives, the technical solution adopted is:
[0011] A method for automatic full-mouth tooth alignment based on occlusal plane feature points, comprising:
[0012] Obtain dental model information, scan the upper and lower jaw dental models and automatically align the teeth, further obtain the centroid coordinates of each tooth, the first limiting distance of each tooth, and the coordinates of each tooth's centroid. Feature points of the surface and the allowed directions of movement;
[0013] Pair the upper and lower teeth to obtain tooth pairs; align the z-axis coordinates of the centroid of each tooth pair, and perform coarse registration of the tooth pairs according to the first limit distance and the allowed direction of movement;
[0014] Based on the point cloud data of the two teeth in the tooth pair, an objective function is constructed to perform iterative registration to achieve the highest degree of occlusion and the greatest degree of fit of the tooth pair, thus completing the fine registration of the upper and lower teeth.
[0015] After completing the fine registration of the tooth pairs, an objective function is constructed based on the alveolar ridge crest line and the minimum distance between two adjacent teeth in the same jaw to optimize tooth alignment.
[0016] According to the automatic full-mouth tooth arrangement method based on occlusal plane feature points of the present invention, further, obtaining the centroid coordinates of each tooth includes: firstly, obtaining the centroid of each tooth based on an existing tooth database; then, establishing the position coordinates of each tooth in space based on the arranged upper and lower jaw tooth model.
[0017] According to the automatic full-mouth tooth alignment method based on occlusal plane feature points of the present invention, the calculation process of the first limiting distance of each tooth in the x and y directions is as follows:
[0018] For a tooth in the lower jaw, Face up, The direction of the plane is the z-axis. The point cloud data is projected onto the occlusal plane to obtain a two-dimensional projection. First, the minimum and maximum values of all points on the x-axis and y-axis are calculated. The width in the x-direction and y-direction is calculated. This width is the maximum width of the tooth in the x-direction and y-direction. Half of this width value is taken as the first limiting distance of the tooth in the x-direction and y-direction. The calculation of the first limiting distance of the remaining teeth in the mandible and the teeth in the maxilla is the same as the above calculation process.
[0019] According to the present invention, the automatic full-mouth tooth alignment method based on occlusal plane feature points further obtains the information of each tooth. The process of calculating the feature points of a surface is as follows:
[0020] For the point cloud data of a single tooth in the maxilla, the tooth is first divided into three equal parts along the z-axis. The point cloud data at one-third of the depth is used to obtain the tooth. Point cloud data at one-third of the location;
[0021] Next, the PCA method was used to calculate the value of the tooth. The curvature values of all points at one-third of the distance are used to filter out points whose curvature values are greater than a set curvature threshold, and the distance from the filtered points to the occlusal plane is calculated.
[0022] The point with the maximum distance among all the selected points is taken as the tooth. The lowest point on the surface is the point with the smallest distance, which is taken as the tooth. Peaks on the surface;
[0023] This tooth The troughs and peaks of the surface are used as the teeth Feature points of the face; all teeth in the maxilla The feature points of the surface are obtained by performing the same operation as above;
[0024] For the middle teeth of the mandible The calculation of feature points on the surface involves cutting off points by extending a fixed distance downwards from the occlusal plane. Subsequent steps are the same as those for calculating the maxillary mid-teeth. The feature points of the surfaces are the same.
[0025] According to the automatic full-mouth tooth arrangement method based on occlusal plane feature points of the present invention, the upper and lower jaw teeth are further paired to obtain a tooth pair, which includes: calculating the tooth with the nearest centroid position based on the centroid position of each tooth, and pairing them into a tooth pair, wherein the tooth pair represents two teeth that mate correspondingly in the upper and lower jaws.
[0026] According to the present invention, the method for automatic full-mouth tooth alignment based on occlusal plane feature points further includes the following process for coarse registration of tooth pairs: first, aligning the z-axis of the centroid coordinates of each tooth pair; then, according to the set allowable movement direction in the upper and lower jaws, moving the teeth in the tooth pair in the upper and lower jaws respectively, with the movement distance being less than the set first limit distance.
[0027] According to the automatic full-mouth tooth alignment method based on occlusal plane feature points of the present invention, further, by constructing an objective function and performing iterative registration to achieve the highest degree of occlusion and maximum degree of fit of the tooth pairs, the following is included:
[0028] Based on the obtained teeth Using point cloud data at one-third of the distance, calculate the occlusion degree of the current tooth pair A1: center two teeth in a tooth pair. Point cloud data from one-third of the contact area was reconstructed using a triangular mesh algorithm to convert the point cloud data into a 3D network model. For each triangle, its area was calculated, and the areas of all triangles in the contact area were summed to obtain the contact degree A1. The larger the A1 value, the stronger the contact between the two teeth. The higher the degree of contact between surfaces;
[0029] Based on the obtained teeth A2: Calculate the occlusion degree of the current tooth pair using point cloud data at one-third of the distance; A3: Calculate the occlusion degree of the maxillary teeth in the current tooth pair. Peak feature points in the surface and mandibular teeth The distance between the valley feature points in the feature points of the surface, and the calculation of the mandibular teeth. Peak feature points in the surface feature points and maxillary teeth The distance between the trough feature points in the feature points of the face is used as the sum of the two distances as the degree of occlusion A2 of the current tooth pair. The smaller the value of A2, the stronger the occlusion of the two teeth. The greater the degree of meshing between the surfaces;
[0030] For a pair of teeth, construct the objective function J1:
[0031]
[0032] Where w1 and w2 are the weights of the parameters, respectively; when J1 reaches its maximum value, the degree of occlusion and the degree of fit of the tooth pair are the highest.
[0033] According to the automatic full-mouth tooth arrangement method based on occlusal plane feature points of the present invention, the objective function constructed based on the alveolar ridge crest line and the minimum distance between two adjacent teeth in the same jaw includes:
[0034] First, move the teeth in the upper and lower jaws along the z-axis upwards and downwards respectively, so that the teeth are aligned. The surface contacts the occlusal plane;
[0035] Then, by constructing an objective function J2, the position coordinates of each tooth in space are adjusted by iteratively moving along the alveolar ridge crest of the maxilla / mandible, so as to minimize the deviation of the tooth from the alveolar ridge crest and maximize the consistency of the distance between two adjacent teeth in the same jaw. When the value of the objective function J2 reaches the minimum, the tooth arrangement optimization is completed.
[0036] According to the automatic full-mouth tooth arrangement method based on occlusal plane feature points of the present invention, the deviation degree B1 between the teeth and the alveolar ridge crest line is calculated: the maxillary alveolar ridge crest line is projected onto the occlusal plane, the z-axis coordinate of the centroid point of each tooth in the maxilla is projected onto the occlusal plane, and the sum of the position coordinate of the centroid point of each tooth projected onto the occlusal plane and the shortest distance of the alveolar ridge crest line projected onto the occlusal plane is calculated and denoted as B1. The larger this value is, the more the position coordinate of the centroid point of the teeth in the maxilla deviates from the alveolar ridge crest line of the maxilla.
[0037] Calculate the consistency of the distance between two adjacent teeth in the same jaw: Calculate the distance between two adjacent teeth after the z-axis coordinate of the centroid of each tooth in the maxilla is projected onto the occlusal plane. Further calculate the variance of the distance between the centroids of two adjacent teeth, denoted as B2. The larger this value is, the greater the difference in the distance between two adjacent teeth in the maxilla, and the poorer the consistency of the maxilla teeth arrangement.
[0038] The calculation of the degree of deviation between the teeth and the ridge line in the mandibular teeth and the consistency of the distance between two adjacent teeth is the same as that in the maxillary teeth, and is denoted as B3 and B4 respectively.
[0039] The objective function J2 is constructed as follows:
[0040] J2 = w3(B1+B2) + w4(B3+B4)
[0041] Where w3 and w4 are the weights of the parameters, respectively.
[0042] Furthermore, the present invention also provides a full-mouth automatic tooth alignment system based on occlusal plane feature points, for implementing the above-described full-mouth automatic tooth alignment method based on occlusal plane feature points, the system comprising:
[0043] The automatic tooth alignment module is used to acquire dental model information, scan the upper and lower jaw dental models, and automatically align the teeth. It further acquires the centroid coordinates of each tooth, the first limiting distance for each tooth, and the coordinates of each tooth's center of gravity. Feature points of the surface and the allowed directions of movement;
[0044] The coarse registration module is used to pair the upper and lower teeth to obtain tooth pairs; it aligns the z-axis coordinates of the centroid of each tooth pair and performs coarse registration on the tooth pairs according to the first limit distance and the allowed direction of movement.
[0045] The fine registration module is used to perform iterative registration based on the point cloud data of the two teeth in a tooth pair by constructing an objective function to achieve the highest degree of occlusion and the greatest degree of fit of the tooth pair, thus completing the fine registration of the upper and lower teeth.
[0046] The tooth alignment optimization module is used to construct an objective function based on the alveolar ridge crest line and the minimum distance between two adjacent teeth in the same jaw after the fine registration of the tooth pairs, in order to optimize the tooth alignment.
[0047] The beneficial effects achieved by adopting the above technical solution are:
[0048] 1. Improved Efficiency: This invention reduces manual operation time and improves work efficiency by automating tooth alignment and registration. The automated tooth alignment function uses computer software to process dental model data and automatically generate an ideal tooth arrangement. This allows dentists to handle complex tooth alignment problems with greater precision and efficiency, enabling more patients to receive timely treatment.
[0049] 2. Enhanced accuracy: By calculating the centroid of the tooth, the first limiting distance, and the tooth... The feature points of the surface, etc., ensure the accuracy of tooth alignment and registration, which helps to improve the accuracy of orthodontic results and reduce errors.
[0050] 3. Improve patient comfort: First, coarse registration ensures accurate matching of the upper and lower teeth; then, fine registration optimizes the occlusal relationship of the upper and lower teeth through iterative adjustments. Precise tooth registration can improve the comfort of occlusion and reduce discomfort that may occur during orthodontic treatment.
[0051] 4. Data-driven decision-making: Utilizing information from existing dental databases for analysis and decision-making makes the process of tooth alignment and registration more scientific and data-driven, thereby providing personalized treatment plans.
[0052] 5. Reduce errors and conflicts: During the fine registration process, by constructing an objective function and making iterative adjustments, the fit between the upper and lower teeth is maximized, reducing conflicts between teeth and the phenomenon of tooth penetration.
[0053] 6. Improve the aesthetics of the upper and lower jaw tooth arrangement models: Further optimize the tooth arrangement after fine registration to ensure the aesthetics of the tooth model, so that the final tooth arrangement meets both functional requirements and aesthetics. Attached Figure Description
[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. The drawings are merely illustrative of some embodiments of the present invention and are not intended to limit the scope of the present invention to all embodiments.
[0055] Figure 1 This is a flowchart illustrating the automatic full-mouth tooth alignment method based on occlusal plane feature points according to an embodiment of the present invention.
[0056] Figure 2 This is a schematic diagram of the maxillary and mandibular dental models according to an embodiment of the present invention;
[0057] Figure 3 This is a schematic diagram of a single tooth according to an embodiment of the present invention;
[0058] Figure 4 This is a schematic diagram of the arranged upper and lower jaw teeth according to an embodiment of the present invention;
[0059] Figure 5 This is a spatial coordinate diagram of the centroid of each tooth in an embodiment of the present invention.
[0060] Figure 6 This is the embodiment of the present invention. A schematic diagram of the point cloud data at one-third of the distance;
[0061] Figure 7 This is a diagram showing the positional relationship between a tooth in the maxilla and the occlusal plane in an embodiment of the present invention;
[0062] Figure 8 This is a schematic diagram of the alveolar crest line according to an embodiment of the present invention; Detailed Implementation
[0063] The exemplary solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art.
[0064] like Figure 1 As shown, this embodiment discloses a method for automatic full-mouth tooth alignment based on occlusal plane feature points, including the following:
[0065] Step S1: Obtain dental model information. Scan the upper and lower jaw dental models and automatically arrange the teeth. Further obtain the centroid coordinates of each tooth, the first limiting distance of each tooth, and the coordinates of each tooth's centroid. Feature points of the surface and the allowed directions of movement.
[0066] (1) Automatic tooth alignment of the upper and lower jaws: Dental models of the upper and lower jaws are obtained by the dentist using oral scan data (e.g., CT scan, oral impressions, etc.). Figure 2 As shown), the dental model data is imported into the computer software. The software uses an existing dental database (a dental database refers to a pre-built database of individual finished teeth, such as...) Figure 3 As shown), further import dental model data, automatically identify and analyze the position, size, and shape of each tooth, and then automatically arrange them according to the ideal position of each tooth in the dentition, thereby automatically obtaining the arranged upper and lower jaw teeth. The arranged upper and lower jaw teeth are as follows: Figure 4 As shown.
[0067] (2) Based on the existing tooth database, calculate the spatial coordinates of the centroid of each tooth, and calculate the first limiting distance, limiting direction of movement, and the position coordinates of each tooth. Feature points of the surface.
[0068] ① Define the positional relationship between each tooth and the spatial coordinate system.
[0069] The method for obtaining the spatial coordinates of the centroid of each tooth is as follows: First, the centroid of each tooth is obtained directly from the existing tooth database. Then, the upper and lower jaw tooth models arranged in step (1) of step S1 are obtained. Finally, the spatial coordinates of each tooth are established. Figure 5 In the diagram, blue represents the z-axis pointing upwards, red represents the x-axis, and green represents the y-axis, both of which lie on a horizontal plane. It should be noted that... Figure 5 This is 3D triangular mesh data, not point cloud data; it is only used here to understand the coordinates of the teeth.
[0070] ② Obtain the first limiting distance
[0071] The calculation process for the first limiting distance of each tooth in the x and y directions is as follows:
[0072] Let's take the y-direction as an example (the calculation process for the x-direction can be referenced from that for the y-direction); for a single tooth in the lower jaw, Face up, The direction of the plane is the z-axis, i.e., the positive z-axis direction. The point cloud data is projected onto the occlusal plane. The z-axis coordinates are ignored, and only the x and y-axis coordinates are retained. This yields a two-dimensional projection of the tooth's three-dimensional point cloud data onto the horizontal plane. In the projected two-dimensional point cloud, the minimum and maximum values of all points on the y-axis are first calculated. The width in the y-direction is then calculated; this width is the maximum width of the tooth in the y-direction. Half of this width is taken as the first limiting distance of the tooth in the y-direction. The calculation of the first limiting distance for the remaining teeth in the mandible and the teeth in the maxilla is performed in the same way.
[0073] ③ Obtain the permitted direction of movement
[0074] By accessing an existing dental database, one can directly obtain information about each tooth, including the minimum distance between teeth and the allowed direction of movement.
[0075] ④ Obtain each tooth Feature points of a surface
[0076] For a tooth in the upper jaw The calculation process for the feature points of a surface is as follows:
[0077] For the point cloud data of a single tooth in the maxilla, the tooth is first divided into three equal parts along the z-axis. The point cloud data at one-third of the depth is used to obtain the tooth. Point cloud data at one-third of the location.
[0078] Next, the PCA method was used to calculate the value of the tooth. The curvature values of all points at one-third of the distance are used to filter out points with curvature values greater than a set curvature threshold. The distance from these filtered points to the occlusal plane is then calculated. Figure 7 As shown.
[0079] The point with the maximum distance among all the selected points is taken as the tooth. The lowest point on the surface is the point with the smallest distance, which is taken as the tooth. Peaks on the surface.
[0080] This tooth The troughs and peaks of the surface are used as the teeth Feature points of the face, in all teeth of the maxilla The same operation is performed on the feature points of the surface to obtain them.
[0081] Of course, the settings can be adjusted according to the actual situation on site, dividing a tooth into several equal parts. For example, if a tooth is divided into four parts, it can be cut... Point cloud at one-quarter of the distance, while ensuring the selection The point cloud at one-quarter of the way needs to include the teeth. All feature points on the surface are included.
[0082] For the middle teeth of the mandible The calculation of feature points on the surface involves cutting off points by extending a fixed distance downwards from the occlusal plane. Subsequent steps are the same as those for calculating the maxillary mid-teeth. The feature points of the surfaces are the same.
[0083] Among them, the setting of the fixed distance for the extension of the upper and lower jaws can be adjusted by experience; the setting of the mid-curvature threshold of the upper and lower jaws can also be adjusted by experience.
[0084] At this point, we have obtained the aligned teeth of the upper and lower jaws, the coordinates of the centroid of each tooth, the first limiting distance for each tooth, the limiting direction of movement, and the coordinates of each tooth. Feature points of the surface.
[0085] Step S2: Pair the upper and lower teeth to obtain tooth pairs; align the z-axis coordinates of the centroid of each tooth pair, and perform coarse registration of the tooth pairs according to the first limit distance and the allowed direction of movement.
[0086] (1) Pair the upper and lower teeth into tooth pairs.
[0087] Since the three-dimensional models of the upper and lower jaws have been registered when the oral cavity model is scanned using a three-dimensional imaging device, that is, the alignment of the upper and lower jaw models has been completed, the scanned upper and lower jaw models have restored the real oral cavity state, and the teeth of the upper and lower jaws have been arranged in step (1) of step S1. The individual teeth of the upper and lower jaws can be directly obtained. Then, the teeth of the upper and lower jaws that have been arranged need to be paired into tooth pairs. Each tooth pair represents two teeth of the upper and lower jaws that are corresponding to each other.
[0088] The pairing process for a tooth pair is as follows: calculate the tooth with the nearest centroid position based on the centroid position of each tooth, and pair them as a tooth pair.
[0089] For example, firstly, the distance between the centroid of one tooth in the maxilla and the centroids of all teeth in the mandible is calculated. The tooth with the smallest distance to the mandibular teeth is then considered as a tooth pair, thus completing the tooth pairing.
[0090] (2) Coarse registration of teeth
[0091] After the teeth in the upper and lower jaws are paired into a tooth pair, the following coarse alignment process is performed for a tooth pair: First, the centroids of the teeth in the upper and lower jaws are moved to the same z-axis. Then, according to the allowed movement direction set for the teeth in the upper and lower jaws, the teeth in the tooth pair are moved respectively, and the movement distance must be less than the set first limit distance.
[0092] For example, if the maxillary teeth in a tooth pair are allowed to move inward toward the inside of the mouth, and the mandibular teeth are allowed to move outward toward the outside of the mouth, then the tooth pair on the same z-axis is moved in the xy-plane according to the allowed directions of movement.
[0093] At this point, the coarse registration of the upper and lower jaw teeth was completed, and the coarsely registered upper and lower jaw tooth models were obtained.
[0094] Step S3: Based on the point cloud data of the two teeth in the tooth pair, an objective function is constructed to perform iterative registration to achieve the highest degree of occlusion and the greatest degree of fit of the tooth pair, thus completing the fine registration of the upper and lower jaw teeth.
[0095] (1) Calculate the characteristic parameters of the tooth pair
[0096] Based on the coarsely aligned teeth, fine alignment is performed by continuously moving one tooth to align with the other two teeth in the x, y, and z directions, until the teeth are aligned with the maxillary teeth. Peak feature points in the surface and mandibular teeth Among the feature points of a surface, the trough feature point is the closest, and the mandibular teeth are the closest. Peak feature points in the surface feature points and maxillary teeth Among the feature points of a face, the trough feature point is the closest, and the teeth of the upper and lower jaws are the closest. At this point, the facial apex is at its maximum, and the two teeth in the upper and lower jaws aligned are most closely connected, completing the fine registration. The fine registration process is as follows:
[0097] ① According to step (2) ④ in step S1, the alignment of the two teeth can be obtained. Point cloud data at one-third of the location.
[0098] ②Based on the obtained teeth Point cloud data at one-third of the depth is used to calculate the current degree of fit of the teeth. The calculation process is as follows:
[0099] For two teeth in a tooth pair Point cloud data at one-third of the depth was analyzed using the KD-tree algorithm (nearest neighbor search) for maxillary teeth. For each point in one-third of the point cloud, find its location on the lower jaw teeth. The closest point in the point cloud at one-third of its distance. By setting a point cloud distance threshold, when two teeth... Point pairs in the point cloud data at one-third of the distance that are closer than this distance threshold are considered to be in contact. The point cloud distance threshold can be set empirically.
[0100] Align one tooth with two other teeth. Point cloud data from one-third of the contact area was converted into a 3D network model using a triangular mesh reconstruction algorithm (such as Poisson reconstruction or moving cubes algorithm). The purpose of meshing is to transform the point cloud data into a set of connected triangles that form the surface. For each triangle, its area is calculated, and the areas of all triangles in the contact area are summed to obtain the contact degree A1. The magnitude of A1 reflects the degree of contact; a larger value indicates a stronger contact between the two teeth. The higher the degree of contact between the surfaces, the better. The expression for the degree of contact A1 is as follows:
[0101]
[0102] in, They are the two side vectors of the triangle. Let represent the area of a triangle, i represent the area of the i-th triangle, and n represent the total number of triangles in the contact area.
[0103] ③Based on the obtained teeth The point cloud data at one-third of the distance is used to calculate the degree of occlusion A2 of the current tooth pair. The calculation process is as follows:
[0104] Calculate the current tooth alignment of the maxillary teeth Peak feature points in the surface and mandibular teeth The distance between the valley feature points in the feature points of the surface, and the calculation of the mandibular teeth. Peak feature points in the surface feature points and maxillary teeth The distance between the trough feature points in the feature points of the face is used as the sum of the two distances as the degree of occlusion A2 of the current tooth pair. The value of A2 reflects the degree of occlusion; the smaller the value, the more pronounced the occlusion between the two teeth. The greater the degree of meshing between the surfaces.
[0105] (2) Construct the objective function and iteratively adjust to complete the fine registration.
[0106] For a pair of teeth, an objective function J1 is constructed. Based on the first constraint distance, the constraint movement direction, and the position coordinates of the centroids of the upper and lower teeth, the relative positions of the upper and lower teeth in the x, y, and z directions are continuously moved and adjusted. The occlusal effect of the tooth pair is continuously calculated and adjusted. When the objective function reaches its maximum value, the degree of occlusion and the degree of fit of the tooth pair are at their highest, at which point the fine registration of the tooth pair is completed. Furthermore, during the movement in the x, y, and z directions, collision detection is continuously performed on the teeth in the tooth pair to avoid erroneous contact after fine registration. The objective function J1 is constructed as follows:
[0107]
[0108] Where w1 and w2 are the weights of the parameters, respectively.
[0109] For example, for a tooth pair after coarse registration, based on the set constraint direction, the first constraint distance, and the coordinates of the centroids of the two teeth in the current tooth pair, for maxillary teeth, the maxillary teeth are moved by randomly selecting one direction and one distance in the x, y, and z directions with a certain step size. The value of the objective function J1 is calculated. Then, the same direction and distance are randomly selected again with a certain step size, and the value of the objective function J1 is calculated again. If the J1 value after the current movement is less than the J1 value after the previous movement, the tooth is moved backward by a certain step size in the currently selected direction or by randomly selecting one of the other two directions. During the movement, collision detection is performed in real time. When a collision is detected, the current movement is not executed. Instead, the tooth is moved backward by a certain step size in the currently selected direction or by randomly selecting one of the other two directions. When the value of the objective function J1 reaches its maximum value or exceeds a certain set threshold, the iterative movement is completed. At this point, the occlusion degree and fit of the tooth pair are the highest, and the fine registration of the tooth pair is completed.
[0110] Step S4: After completing the fine registration of the tooth pairs, construct the objective function based on the alveolar ridge crest line and the minimum distance between two adjacent teeth in the same jaw to optimize the tooth arrangement.
[0111] This method utilizes an objective function to optimize the spacing between upper and lower jaw teeth, maximizing alignment consistency and achieving a neat and aesthetically pleasing tooth arrangement. The main goal is to improve consistency and reduce inefficiencies that may occur during artificial tooth alignment by iteratively adjusting the distance between teeth.
[0112] (1) First, move the teeth of the upper and lower jaws along the z-axis upwards and downwards respectively, so that the teeth are aligned. The surface contacts the occlusal plane.
[0113] For example, for the maxilla, the distance between the occlusal plane and the centroid of each tooth in the maxilla is detected, and the distance between the centroid of each tooth and... The distance from the farthest point on the facial surface moves the maxillary teeth upwards in the oral cavity, thus making the maxillary teeth... The furthest point of the facial surface contacts the occlusal plane, and the teeth in the lower jaw move downwards in the oral cavity as described above.
[0114] (2) Optimize tooth alignment
[0115] Then, by constructing an objective function J2, the spatial coordinates of each tooth are adjusted iteratively along the alveolar ridge crest of the maxilla (or mandible) to minimize the deviation of the teeth from the alveolar ridge crest and maximize the consistency of the distance between adjacent teeth in the same jaw. When the value of the objective function J2 reaches its minimum, the tooth alignment optimization is complete. It is important to note that during the tooth alignment optimization process, the relative distance between each pair of teeth remains constant. Figure 8 This is a schematic diagram of the alveolar ridge crest line. The curve formed by the brown line and the small blue ball in the diagram is the alveolar ridge crest line, also known as the dental ridge line. Figure 8 This is 3D triangular mesh data, provided only for understanding alveolar ridge crests, and is not point cloud data.
[0116] ① Calculate the degree of deviation between the tooth and the alveolar ridge crest line.
[0117] Project the maxillary alveolar ridge crest line onto the occlusal plane. Project the z-axis coordinates (xy-axis values remain unchanged) of the centroid of each maxillary tooth onto the occlusal plane. Calculate the sum of the position coordinates of the centroid of each tooth projected onto the occlusal plane and the shortest distance from the alveolar ridge crest line projected onto the occlusal plane, denoted as B1. The larger this value, the more the position coordinates of the centroid of the maxillary teeth deviate from the maxillary alveolar ridge crest line. This further indicates a poorer alignment of the maxillary teeth. The expression for B1 is as follows:
[0118]
[0119] In the formula, d k represents the shortest distance between the position coordinates of the centroid of the kth tooth projected onto the occlusal plane and the alveolar ridge crest line projected onto the occlusal plane; m represents the total number of m teeth in the oral cavity.
[0120] ② Calculate the consistency of the distance between two adjacent teeth in the same jaw.
[0121] Calculate the distance between two adjacent centroids after projecting the z-axis coordinate of each tooth's centroid onto the occlusal plane. Further calculate the variance of the distance between adjacent centroids, denoted as B2. The larger this value, the greater the difference in distance between adjacent teeth in the maxilla, and the poorer the consistency of the maxilla's tooth arrangement.
[0122] Based on the spacing between the teeth, the formula for B2 can be obtained as follows:
[0123]
[0124] In the formula, X j This represents the distance between the centroids of two adjacent teeth of the j-th generation; The distance represents the mean of all distances; N represents the total number of N pairs of adjacent teeth.
[0125] The calculation of the degree of deviation between the teeth and the ridge line in the mandibular teeth and the consistency of the distance between two adjacent teeth is the same as that in the maxillary teeth, and is denoted as B3 and B4 respectively.
[0126] The objective function J2 is constructed as follows:
[0127] J2 = w3(B1+B2) + w4(B3+B4)
[0128] Where w3 and w4 are the weights of the parameters, respectively.
[0129] For example, for the obtained oral cavity and tooth model after fine registration, while keeping the relative positions of the two teeth in the upper and lower jaws unchanged, firstly, a tooth in the upper jaw is randomly selected, and a direction is randomly chosen on the x and y axes of that tooth, and it is moved with a certain step size. The value of the objective function J2 is calculated. Then, another tooth in the upper jaw is randomly selected, and a direction is randomly chosen on the x and y axes of that tooth, and it is moved with a certain step size. The value of the objective function J2 is calculated again. If the value of J2 in the current step is larger than the value of J2 in the previous step, then the tooth is moved in the opposite direction of the currently selected direction, or another tooth is randomly selected and a direction is randomly chosen for a certain step size. When the value of the objective function J2 reaches the minimum value or is less than a certain set threshold, the iterative movement is completed. At this point, the deviation between the tooth and the ridge line is minimized, and the consistency of the distance between two adjacent teeth in the same jaw is maximized. The tooth alignment optimization is completed.
[0130] The upper teeth are arranged according to standard rules so that, in the full mouth tooth arrangement, priority is given to satisfying the occlusal condition of each pair of teeth, while also satisfying the aesthetics of the upper and lower jaw tooth arrangement model.
[0131] At this point, the automatic tooth alignment is complete.
[0132] Corresponding to the above method, this embodiment also discloses a full-mouth automatic tooth alignment system based on occlusal plane feature points, comprising:
[0133] The automatic tooth alignment module is used to acquire dental model information, scan the upper and lower jaw dental models, and automatically align the teeth. It further acquires the centroid coordinates of each tooth, the first limiting distance for each tooth, and the coordinates of each tooth's center of gravity. Feature points of the surface and the allowed directions of movement.
[0134] The coarse registration module is used to pair the upper and lower jaw teeth to obtain tooth pairs; it aligns the z-axis coordinates of the centroid of each tooth pair and performs coarse registration of the tooth pairs according to the first limit distance and the allowed direction of movement.
[0135] The fine registration module is used to perform iterative registration based on the point cloud data of the two teeth in a tooth pair by constructing an objective function to achieve the highest degree of occlusion and the greatest degree of fit between the teeth, thus completing the fine registration of the upper and lower jaw teeth.
[0136] The tooth alignment optimization module is used to construct an objective function based on the alveolar ridge crest line and the minimum distance between two adjacent teeth in the same jaw after the fine registration of the tooth pairs, in order to optimize the tooth alignment.
[0137] Unless otherwise specifically stated, the relative steps, numerical expressions, and values of the components and steps described in these embodiments do not limit the scope of the invention.
[0138] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.
[0139] The units and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations are not considered to be beyond the scope of this invention.
[0140] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiments can be implemented in hardware or as a software functional module. This invention is not limited to any particular combination of hardware and software.
[0141] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A method for automatic full-mouth tooth alignment based on occlusal plane feature points, characterized in that, Include: S1: Obtain dental model information, scan the upper and lower jaw dental models and automatically arrange the teeth, and further obtain the centroid coordinates of each tooth, the first limit distance of each tooth, the feature points of each tooth's lip surface and the set allowed movement direction; S2: Pair the upper and lower teeth to obtain tooth pairs; align the z-axis coordinates of the centroid of each tooth pair, and perform coarse registration of the tooth pairs according to the first limit distance and the allowed direction of movement; S3: Based on the point cloud data of the two teeth in a tooth pair, an iterative registration is performed by constructing an objective function to achieve the highest degree of occlusion and fit of the tooth pair, completing the fine registration of the upper and lower jaw teeth. Specifically, this includes: Based on the point cloud data obtained at one-third of the tooth's apex, the degree of fit of the current tooth pair is calculated. The point cloud data of the contact area at one-third of the distance between two teeth is reconstructed using a triangular mesh algorithm, converting the point cloud data into a 3D network model. For each triangle, its area is calculated, and the areas of all triangles in the contact area are summed to obtain the degree of contact. , The higher the value, the greater the contact between the two tooth surfaces; Based on the point cloud data obtained at one-third of the tooth's apex, the degree of occlusion of the current tooth pair is calculated. Calculate the distance between the peak feature point on the ulnar surface of the maxillary teeth and the trough feature point on the ulnar surface of the mandibular teeth in the current tooth pair; calculate the distance between the peak feature point on the ulnar surface of the mandibular teeth and the trough feature point on the ulnar surface of the maxillary teeth; sum the two distances as the degree of occlusion of the current tooth pair. , The smaller the value, the greater the degree of meshing between the two tooth surfaces; For a pair of teeth, construct the objective function. : ,in, , These are the weights of the parameters; when When the maximum value is reached, the degree of occlusion and the degree of fit of the tooth pair are the highest; S4: After completing the fine registration of the tooth pairs, construct the objective function based on the alveolar ridge crest line and the minimum distance between two adjacent teeth in the same jaw to optimize the tooth alignment.
2. The automatic full-mouth tooth alignment method based on occlusal plane feature points according to claim 1, characterized in that, Obtaining the centroid coordinates of each tooth involves: first, obtaining the centroid of each tooth based on the existing tooth database; then, establishing the spatial coordinates of each tooth based on the arranged upper and lower jaw tooth models.
3. The automatic full-mouth tooth alignment method based on occlusal plane feature points according to claim 2, characterized in that, The calculation process for the first limiting distance of each tooth in the x and y directions is as follows: For a mandibular tooth with its umbilicus facing upwards and the direction of the umbilicus along the z-axis, the point cloud data is projected onto the occlusal plane to obtain a two-dimensional projection. First, the minimum and maximum values of all points along the x-axis and y-axis are calculated, and the width in the x-direction and y-direction is calculated. This width is the maximum width of the tooth in the x-direction and y-direction. Half of this width value is taken as the first limiting distance of the tooth in the x-direction and y-direction. The calculation of the first limiting distance of the remaining teeth in the mandible and the teeth in the maxilla is carried out in the same way.
4. The automatic full-mouth tooth alignment method based on occlusal plane feature points according to claim 2, characterized in that, The calculation process for obtaining the feature points of the lip surface of each tooth is as follows: For the point cloud data of a tooth in the maxilla, the tooth is first divided into three equal parts along the z-axis, and the point cloud data at the first third is taken to obtain the point cloud data at the first third of the tooth. Next, the PCA method is used to calculate the curvature values of all points at one-third of the tooth, and points with curvature values greater than the set curvature threshold are filtered out. The distance from the filtered points to the occlusal plane is then calculated. The point with the maximum distance among all the selected points is taken as the trough point on the tooth's lip surface, and the point with the minimum distance is taken as the peak point on the tooth's lip surface. The troughs and peaks of the tooth's uvular surface are used as characteristic points of that tooth's uvular surface; the same operation is performed on the characteristic points of the uvular surfaces of all teeth in the maxilla. For calculating the feature points of the occlusal surfaces of the mandibular midteeth, the points are extracted by extending a fixed distance downwards from the occlusal plane. The subsequent steps are the same as those for calculating the feature points of the occlusal surfaces of the maxillary midteeth.
5. The automatic full-mouth tooth alignment method based on occlusal plane feature points according to claim 1, characterized in that, Pairing the upper and lower jaw teeth to obtain a tooth pair includes: calculating the position of the nearest centroid of each tooth based on the position of its centroid, and pairing them together to form a tooth pair, which represents the two teeth of the upper and lower jaws that mate accordingly.
6. The automatic full-mouth tooth alignment method based on occlusal plane feature points according to claim 1, characterized in that, The process of coarse registration of the tooth pairs is as follows: First, align the z-axis of the centroid coordinates of each tooth pair. Then, according to the allowed movement direction set in the upper and lower jaws, move the teeth in the tooth pairs in the upper and lower jaws respectively. The movement distance is less than the set first limit distance.
7. The automatic full-mouth tooth alignment method based on occlusal plane feature points according to claim 2, characterized in that, The objective function is constructed based on the alveolar ridge crest line and the minimum distance between two adjacent teeth in the same jaw, including: First, move the teeth of the upper and lower jaws along the z-axis upwards and downwards respectively, so that the tooth surface is in contact with the occlusal plane; Then, by constructing the objective function Iterative adjustments to the spatial coordinates of each tooth along the maxillary / mandibular alveolar ridge crest line minimize the deviation of the tooth from the alveolar ridge crest line and maximize the consistency of distances between adjacent teeth in the same jaw. When the objective function... The value is minimized, thus optimizing tooth alignment.
8. The automatic full-mouth tooth alignment method based on occlusal plane feature points according to claim 7, characterized in that, Calculate the degree of deviation between the tooth and the alveolar ridge crest line. Project the maxillary alveolar ridge crest line onto the occlusal plane. Project the z-axis coordinates of the centroid of each maxillary tooth onto the occlusal plane. Calculate the sum of the position coordinates of the centroid of each tooth projected onto the occlusal plane and the shortest distance from the projected alveolar ridge crest line onto the occlusal plane. This sum is denoted as: The larger this value, the more the position coordinates of the centroid of the maxillary teeth deviate from the alveolar ridge crest line of the maxilla. Calculate the consistency of the distance between two adjacent teeth in the same jaw. Calculate the distance between two adjacent centroids of each maxillary tooth after projecting the z-axis coordinates of the centroid onto the occlusal plane. Further calculate the variance of the distance between adjacent centroids, denoted as . The larger this value, the greater the difference in distance between two adjacent teeth in the maxilla, and the poorer the consistency of the maxilla's tooth arrangement. The calculation methods for the deviation of teeth from the ridge line and the consistency of distances between adjacent teeth in the mandibular region are the same as those for the maxillary region, and are denoted as follows: ; objective function The structure is as follows: ,in, , These are the weights of the parameters.
9. A fully automatic tooth alignment system based on occlusal plane feature points, characterized in that, For implementing the full-mouth automatic tooth alignment method based on occlusal plane feature points as described in any one of claims 1-8, the system comprises: The automatic tooth alignment module is used to acquire dental model information, scan the upper and lower jaw dental models and automatically align the teeth, and further acquire the centroid coordinates of each tooth, the first limit distance of each tooth, the feature points of the tooth surface and the set allowed movement direction; The coarse registration module is used to pair the upper and lower teeth to obtain tooth pairs; it aligns the z-axis coordinates of the centroid of each tooth pair and performs coarse registration on the tooth pairs according to the first limit distance and the allowed direction of movement. The fine registration module is used to perform iterative registration based on the point cloud data of the two teeth in a tooth pair by constructing an objective function to achieve the highest degree of occlusion and the greatest degree of fit of the tooth pair, thus completing the fine registration of the upper and lower teeth. The tooth alignment optimization module is used to construct an objective function based on the alveolar ridge crest line and the minimum distance between two adjacent teeth in the same jaw after the fine registration of the tooth pairs, in order to optimize the tooth alignment.