Tooth orthodontic path generation method and device, electronic equipment and medium

Abstract

The invention provides a tooth orthodontic path generation method and device, electronic equipment and a medium. The method comprises the following steps: acquiring three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system; calculating a target six-dimensional pose of each tooth based on the target dental arch curve and orthodontic medical constraints; and by taking the target six-dimensional pose corresponding to each tooth as a search space, generating an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose by using an improved particle swarm optimization algorithm. Therefore, automatic, high-precision and interactive tooth orthodontic path generation is realized, and the clinical efficiency and personalized level of tooth orthodontic treatment are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of orthodontics, and in particular to a tooth orthodontic path generation method and device, electronic equipment and a medium. BACKGROUND

[0002] Oral diseases are common diseases worldwide, among which malocclusion (including occlusal relationship misplacement, misalignment, etc.) is listed as one of the three major oral diseases by the World Health Organization with a very high incidence. This problem not only affects facial appearance, but also poses a threat to oral health and even other parts of the human body. The bracket-free invisible orthodontic technology formally combines computer and electronic information technology with the field of oral medicine. With the rapid development of computer graphics and image technology, computer three-dimensional visualization technology, artificial intelligence and other related technologies, they have been increasingly widely applied in the field of oral medicine. Digital automatic generation of tooth paths is imperative. It is very important to develop a digital orthodontic tooth path generation method, research and implement how to automatically generate an orthodontic path through computer-aided technology, and enable doctors to interactively adjust the generated path, which has significant practical significance and good development prospects.

[0003] The existing tooth orthodontic path planning relies on manual setting by doctors, has strong subjectivity and low efficiency, and the path precision estimated by artificial is insufficient, which can easily cause treatment deviation and problems such as tooth crossing and interference in the process of multi-tooth movement. SUMMARY

[0004] The present application provides a tooth orthodontic path generation method, device, electronic equipment and medium to solve the defects of relying on artificial experience, low efficiency, large error and lack of collision detection in the prior art, and to realize automatic, high-precision and interactive tooth orthodontic path generation, thereby improving the clinical efficiency and individualization level of tooth orthodontic treatment. The present application provides a tooth orthodontic path generation method, comprising: obtaining three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system; calculating a target six-dimensional pose of each tooth based on a target dental arch curve and orthodontic medical constraints; using an improved particle swarm optimization algorithm to generate an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose, taking the corresponding target six-dimensional pose of each tooth as a search space.

[0005] In one possible implementation, the method further comprises: performing farthest point sampling on the three-dimensional point cloud data to obtain target three-dimensional point cloud data with reduced data volume; determining an alignment matrix, a centroid, an axis and a face axis point of each tooth based on the target three-dimensional point cloud data; establishing an initial pose of each tooth in a global coordinate system based on the alignment matrix, the centroid, the axis, and the face axis point of each tooth.

[0006] In one possible implementation, the method further comprises: constructing a directional bounding box of each tooth using a bounding box algorithm, the directional bounding box being a smallest cuboid containing the tooth and arbitrary with respect to the direction of the coordinate axes.

[0007] In one possible implementation, the method further comprises: introducing a collision penalty function in the fitness function of the particle swarm optimization algorithm to optimize the translational path and the rotation angle of the teeth, with the target six-dimensional pose of each tooth as the search space, the collision penalty function being based on the directional bounding box and the separation axis theory to calculate the minimum distance between the teeth; based on the preset medical constraints, setting a maximum step constraint condition for the movement amplitude and the rotation angle of each tooth, respectively; based on the fitness function of the particle swarm optimization algorithm and the maximum step constraint condition set for the movement amplitude and the rotation angle of each tooth, respectively, iteratively calculating the orthodontic path until a preset iteration number or a fitness threshold is met, to generate an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose.

[0008] In one possible implementation, the method further comprises: for any two teeth, calculating a separation axis using eight vertices of the directional bounding box corresponding to each tooth; based on the separation axis theory, determining whether the orthodontic paths corresponding to the any two teeth respectively exist overlap; if there is overlap, calculating a minimum penetration depth and adding it to the fitness function after weighting.

[0009] In one possible implementation, the method further comprises: based on all orthodontic stages of the teeth, generating an optimal orthodontic path corresponding to each orthodontic stage; replacing the optimal orthodontic path corresponding to each orthodontic stage with point cloud data of a corresponding color; performing three-dimensional visual display of the point cloud data corresponding to all orthodontic stages in a color gradient manner, and synchronously rendering the directional bounding box corresponding to each tooth.

[0010] In one possible implementation, the method further comprises: the improved particle swarm optimization algorithm adopts a simplified mean particle swarm strategy with normal distribution to accelerate the convergence speed and avoid falling into local optimum.

[0011] The application further provides a tooth orthodontic path generation device, comprising the following modules. An acquisition module is configured to acquire three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system; A calculation module is configured to calculate a target six-dimensional pose of each tooth based on a target dental arch curve and orthodontic medical constraints; A generation module is configured to generate an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose by using an improved particle swarm optimization algorithm with the target six-dimensional pose corresponding to each tooth as a search space.

[0012] The application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the tooth orthodontic path generation method according to any one of the above when executing the computer program.

[0013] The application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the tooth orthodontic path generation method according to any one of the above.

[0014] The application further provides a computer program product comprising a computer program, wherein the computer program is executable by a processor to implement the tooth orthodontic path generation method according to any one of the above.

[0015] The tooth orthodontic path generation method, device, electronic device, and medium provided by the application acquire three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system, calculate a target six-dimensional pose of each tooth based on a target dental arch curve and orthodontic medical constraints, and generate an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose by using an improved particle swarm optimization algorithm with the target six-dimensional pose corresponding to each tooth as a search space. Compared with the prior art, the application realizes automatic, high-precision, and interactive tooth orthodontic path generation, and improves the clinical efficiency and individualization level of tooth orthodontic treatment. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort.

[0017] Figure 1 is one of the flowcharts of the tooth orthodontic path generation method provided by the application.

[0018] Figure 2 is a flowchart of a second method for generating a tooth orthodontic path according to the present application.

[0019] Figure 3 is a schematic diagram of classification and representation of upper and lower teeth according to the present application.

[0020] Figure 4 is a schematic diagram of feature point selection of four types of teeth according to the present application.

[0021] Figure 5 is a schematic diagram of local coordinate system establishment of teeth and feature point selection of teeth according to the present application.

[0022] Figure 6 is a schematic diagram of bounding box algorithm and bounding box of three scenarios according to the present application.

[0023] Figure 7 is a schematic diagram of particle swarm algorithm flow according to the present application.

[0024] Figure 8 is a schematic diagram of movement position and direction of each tooth from an initial position to an ideal position at different orthodontic stages according to the present application.

[0025] Figure 9 is a schematic diagram of final generated tooth path visualization result according to the present application.

[0026] Figure 10 is a schematic diagram of tooth bounding box point cloud information according to the present application.

[0027] Figure 11 is a schematic diagram of stage visualization result of an algorithm generated tooth orthodontic path according to the present application.

[0028] Figure 12 is a schematic diagram of a tooth orthodontic path generation device according to the present application.

[0029] Figure 13 is a schematic diagram of an electronic device according to the present application. DETAILED DESCRIPTION

[0030] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0031] The application is described below Figures 1-11 The application provides a tooth orthodontic path generation method.

[0032] Figure 1 is one of the flowcharts of the tooth orthodontic path generation method provided by the application, as Figure 1 shown, the method comprises the following: S11, acquiring three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system.

[0033] In the embodiment of the application, to plan a tooth orthodontic moving path, first, three-dimensional point cloud data of an initial dentition of a target patient is acquired, which can be acquired by an intraoral scanner on the upper and lower jaw dentition of the target patient. An STL (Standard Tessellation Language) file is a standard file format for representing the surface geometry of a three-dimensional object. The file is used to store a 3D scanning model (point cloud data) of a single tooth, and an oriented bounding box (OBB) is constructed by reading the coordinate information thereof for collision detection.

[0034] Further, the three-dimensional point cloud data is sampled by the farthest point to obtain target three-dimensional point cloud data with reduced data volume; based on the target three-dimensional point cloud data, an alignment matrix, a centroid, an axis and a face axis point of each tooth are determined; and based on the alignment matrix, the centroid, the axis and the face axis point of each tooth, an initial pose of each tooth in the global coordinate system is established. The scanner itself coordinate system is taken as the global coordinate system.

[0035] S12, calculating a target six-dimensional pose of each tooth based on a target dental arch curve and orthodontic medical constraints.

[0036] Considering problems that the teeth may encounter during movement, the problems are taken as movement constraints, and finally connected together by a mathematical structure expression to form an optimization problem with constraints.

[0037] First, the initial and final positions of a single tooth during the correction process are determined. Then, the final ideal position is obtained by tooth arrangement processing. The tooth arrangement algorithm can determine the final position and attitude of each tooth. Tooth movement is divided into two types: tooth translation and tooth rotation. According to the characteristics of tooth movement path planning and the requirements of orthodontic medicine, a corresponding mathematical model is established.

[0038] The ideal position of each tooth is calculated: the rotation vector is converted into a rotation matrix to generate a six-dimensional vector of the ideal pose, wherein the first three vectors are regarded as translation, and the last three vectors are regarded as rotation. By giving the rotation and translation parameters, the point cloud is transformed to obtain the ideal point cloud pose. In actual movement, the tooth is first rotated and then displaced.

[0039] S13, using the target six-dimensional pose corresponding to each tooth as a search space, generating an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose by using an improved particle swarm optimization algorithm.

[0040] Using the target six-dimensional pose corresponding to each tooth as a search space, introducing a collision penalty function into the fitness function of the particle swarm optimization algorithm to optimize the translation path and rotation angle of the teeth, wherein the collision penalty function is used to calculate the minimum distance between the teeth based on the directional bounding box and the separation axis theory; based on the preset medical constraints, the maximum step constraint condition is set for the movement amplitude and the rotation angle of each tooth; based on the fitness function of the particle swarm optimization algorithm and the maximum step constraint condition set for the movement amplitude and the rotation angle of each tooth, the orthodontic path is iteratively calculated until the preset iteration number or the fitness threshold is met, and the optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose is generated.

[0041] The tooth orthodontic path generation method provided by the application comprises the following steps: obtaining the three-dimensional point cloud data of the initial dentition of a target patient and the initial pose of each tooth in a global coordinate system; calculating the target six-dimensional pose of each tooth based on the target dental arch curve and the orthodontic medical constraints; using the target six-dimensional pose corresponding to each tooth as a search space, and using an improved particle swarm optimization algorithm to generate an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose. Compared with the defects of the prior art, such as relying on artificial experience, low efficiency, large error and lack of collision detection, the method can realize automatic, high-precision and interactive tooth orthodontic path generation, and improve the clinical efficiency and individualization level of tooth orthodontic treatment.

[0042] Figure 2 is a flowchart of the tooth orthodontic path generation method provided by the application, as shown in Figure 2 The method comprises the following steps: S21, performing farthest point sampling on the three-dimensional point cloud data to obtain target three-dimensional point cloud data with reduced data quantity.

[0043] The classification representation of teeth is an important theoretical prerequisite for studying and designing tooth arrangement algorithms, arranging and displaying tooth models. A normal adult has 32 teeth, which are divided into 16 teeth in the upper and lower jaws, and the 16 teeth in the single jaw are symmetrical about the left and right sides, that is, there are 8 teeth on one side. According to the position and function, from the front side to the back side, they are named as central incisor, lateral incisor, canine, first premolar, second premolar, first molar, second molar and third molar. Figure 3 is a classification diagrammatic representation of upper and lower teeth.

[0044] Dental arch feature representation: In orthodontics, the description of dental arch features is crucial. The concepts of feature points and feature axes are introduced for representation. Feature points and feature axes are commonly used concepts in this field and are important anatomical features of teeth. When studying orthodontic problems, the representation of tooth features should be clearly defined. Feature points can help determine the specific position and orientation of the teeth; while feature axes can be used to describe the rotation angle and inclination of the teeth. By determining the feature points and feature axes of the teeth, the position and posture of the teeth can be quantitatively evaluated. Figure 4 The feature points of the four types of teeth, namely incisors, canines, premolars and molars, are sequentially shown.

[0045] In the embodiments of the present application, to plan the movement path of orthodontic teeth, first, the three-dimensional point cloud data of the initial dental arch of the target patient is obtained, which can be obtained by an intraoral scanner. The STL file is a standard file format for representing the surface geometry of a three-dimensional object. This file is used to store the 3D scan model (point cloud data) of a single tooth, and the OBB bounding box is constructed by reading its coordinate information for collision detection.

[0046] During the acquisition of three-dimensional point cloud data, farthest point sampling is performed to reduce the amount of data, and the edentulous condition is handled. Then the tooth point cloud is projected onto three feature vector directions, and then projected onto the z-axis to determine the boundary end points, and the center point is calculated, and finally the eight vertices of the OBB bounding box are constructed, providing a geometric basis for subsequent collision detection.

[0047] S22, based on the target three-dimensional point cloud data, determining the alignment matrix, centroid, axis and face axis point of each tooth.

[0048] S23, based on the alignment matrix, centroid, axis and face axis point of each tooth, establishing the initial pose of each tooth in the global coordinate system.

[0049] To generate an orthodontic path, the ideal pose of the teeth needs to be determined. The spatial state of the teeth is described by the alignment matrix, centroid, axis and face axis point of the teeth. Among them, the alignment matrix represents the position and direction of the teeth; the centroid is used to evaluate the occlusion relationship; the axis reflects the rotation and inclination; and the face axis point is used to analyze the occlusion between the upper and lower teeth.

[0050] According to these parameters, a local tooth coordinate system is established, and a fitting ideal dental arch line and a collision detection algorithm are combined to realize the stable arrangement of the teeth from the initial to the target position, meeting the functional and orthodontic aesthetic needs. According to the above information, a local tooth coordinate system can be established Figure 5 as shown in the figure.

[0051] S24, an OBB algorithm is used to construct a directional bounding box for each tooth, which is a minimum cuboid containing the tooth and arbitrary relative to the coordinate axis direction.

[0052] In the path planning problem, the movement of multiple teeth on the orthodontic path can intersect, that is, collide, and the teeth themselves can be regarded as rigid bodies that cannot penetrate each other. Therefore, it is necessary to design a corresponding collision detection algorithm. However, since the shape of the tooth itself is irregular, it is not realistic to directly use the tooth model to simulate collision detection. Therefore, an OBB algorithm is used to simulate the collision detection result of the tooth.

[0053] An OBB algorithm is used to replace the tooth collision detection result, wherein the OBB is a minimum cuboid that contains the object and is arbitrary relative to the coordinate axis direction, and is suitable for orthodontic situations. At the same time, through a collision penalty function, the final generated tooth movement path satisfies the collision constraint. The collision penalty function is based on the directional bounding box and the separation axis theory to calculate the minimum distance between the teeth. Figure 6 OBB, AABB and OBB are three common types of bounding box algorithms.

[0054] S25, the target six-dimensional pose corresponding to each tooth is used as a search space, and a collision penalty function is introduced into the fitness function of the particle swarm optimization algorithm to optimize the translation path and rotation angle of the tooth.

[0055] Particle swarm optimization is a heuristic global search algorithm based on swarm intelligence developed by simulating the foraging behavior of bird flocks. It is also a new heuristic algorithm that finds the global optimal point in a complex search space through competition and cooperation between particles and information sharing. Particle swarm optimization has the characteristics of easy understanding, easy implementation, strong global search ability, etc.

[0056] The orthodontic path generation method based on particle swarm optimization adopted by the embodiment improves from three aspects: first, the translation path and rotation angle of the tooth are optimized through the fitness function, making the trajectory more smooth and efficient; second, the collision detection mechanism is introduced to avoid the intersection or interference of the teeth during movement; third, the movement amplitude and angle of the tooth are considered as constraint conditions to ensure that the path result meets the medical constraints. The above optimization makes the generated path more secure, accurate and implementable.

[0057] S26, based on the preset medical constraints, the maximum step constraint condition of the movement amplitude and rotation angle of each tooth is set.

[0058] According to the orthodontic guidelines, such as the number of correction stages, the moving amount, the rotation amount, etc., a target function is established; secondly, problems encountered in the movement of the teeth are considered as movement constraints, and finally, a mathematical structure expression is used to connect them together to form an optimization problem with constraints. First of all, in order to plan the tooth movement path, the initial and final positions of the single tooth during the orthodontic process must be determined first. The initial position can be obtained through the tooth model data, and then the final ideal position is obtained through the tooth arrangement processing. The tooth arrangement algorithm can determine the final position and attitude of each tooth. Next, the tooth movement is divided into two types: tooth translation and tooth rotation, and according to the characteristics of the tooth movement path planning and the medical requirements, the corresponding mathematical model is established.

[0059] S27, based on the fitness function of the particle swarm optimization algorithm and the constraint condition of setting the maximum step length for the movement amplitude and the rotation angle of each tooth respectively, the orthodontic path is iteratively calculated until the preset iteration number or the fitness threshold is met, and the optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose is generated.

[0060] The main flow of the particle swarm algorithm of the embodiment of the application is as shown in Figure 7 The particle swarm is first initialized, and the speed and position of each particle are determined. Then the fitness value of each particle is calculated, and for each particle, the fitness value and the individual extreme value are compared. If the current fitness value is smaller (better), the pbest (individual extreme value, i.e. the best position searched by the individual so far) is updated to the current fitness value. Then the fitness value and the global extreme value gbest are compared in the same way, and gbest is updated. Then, the speed and position of the particles are updated according to the speed and position update formula of the particles in the particle swarm. This updating process is iteratively repeated. After each update, boundary condition processing is performed, that is, it is judged whether the maximum iteration number is reached or the global optimal position meets the minimum limit. If the termination condition is met, the algorithm is ended and the optimization result is output; otherwise, the fitness value is recalculated and the process is repeated.

[0061] S28, for any two teeth, the eight vertices of the corresponding directional bounding box of each tooth are used to calculate the separation axis.

[0062] S29, based on the separation axis theory, it is judged whether the orthodontic paths corresponding to the two teeth respectively exist overlap.

[0063] S210, if there is overlap, the minimum penetration depth is calculated and weighted and added to the fitness function.

[0064] The following uniformly describes S28-S210: To ensure the rationality of tooth arrangement, the system integrates an OBB-based collision detection algorithm. This method uses tooth point clouds to construct bounding boxes and determines whether a collision occurs through the theory of separating axes. In actual implementation, the system calculates the distance between tooth point clouds. If the distance is too small, it is considered a collision and the position needs to be adjusted. If the distance is too large, it also needs to be optimized to maintain functionality and aesthetics. This detection mechanism combines geometric features and spatial judgments to effectively improve the clinical applicability of path generation.

[0065] During path generation, the system first sets particle swarm parameters and optimization stages, then generates initial particles for each tooth, calculates its six-dimensional pose (position + rotation), and performs iterative optimization to output the best path at each stage. Finally, the motion trajectory of each tooth is converted to OBB format for collision detection, and output as a point cloud text file containing position and color information, providing a basis for visual display.

[0066] The generated orthodontic path is visualized in point cloud form at each stage: the initial state is marked in red, the final state is purple, and the intermediate stages are colored in order. The system synchronously draws OBB bounding boxes to clearly reflect the motion trajectory and spatial position relationship at each stage. The visualization results intuitively show the morphological changes of teeth, movement trends, and ideal pose comparisons, providing intuitive support for path effect evaluation and optimization. Figure 9 The final generated tooth path visualization results are displayed in stages.

[0067] In the algorithm, the system calculates the OBB bounding box of each stage tooth by calling the Tooth_obb_box and Orthodontic functions, where the center coordinates (orth_x) can approximately represent the tooth position. The three-dimensional coordinate information in the point cloud data is extracted and grouped by the 14 teeth at each stage to facilitate analysis of the arrangement of teeth at different stages.

[0068] Experimental results show that the optimized particle swarm algorithm converges stably within a limited number of iterations, converges faster and more accurately than traditional PSO, and has stronger global search ability. Combined with OBB collision detection, it effectively avoids tooth interference, and the final generated orthodontic path meets clinical requirements in terms of occlusion and arrangement specification, and the visualization results clearly show the path effect and tooth change trend.

[0069] Orthodontic treatment is divided into multiple stages, and based on all orthodontic stages, the optimal orthodontic path corresponding to each orthodontic stage is generated; the optimal orthodontic path corresponding to each orthodontic stage is replaced by point cloud data of the corresponding color; the point cloud data corresponding to all orthodontic stages is visualized in three dimensions with color gradient, and the direction bounding box corresponding to each tooth is synchronously rendered. Figure 7The movement position and direction of each tooth from the initial position to the ideal position at different orthodontic stages are shown in different colors. Figure 10 The bounding box point cloud information is shown, and the first to the sixth stages are sequentially corresponded from front to back and from left to right.

[0070] The tooth orthodontic path stage visualization result generated by the algorithm is shown in the figure. Figure 11 The first to the sixth stages are sequentially corresponded from top to bottom and from left to right.

[0071] From the above experimental results, it can be found that through the orthodontic algorithm, the originally discrete point cloud data converges within a limited number of steps and has a good convergence speed, and will not fall into a local optimum, proving that the algorithm has convergence. The original tooth center point cloud data gradually fits the ideal dental arch curve, achieving good orthodontic effect. In this process, the movement between adjacent teeth is prevented from colliding; and the movement distance of each step is limited to avoid the occurrence of detour, proving that the algorithm has effectiveness.

[0072] The embodiment of the application takes the segmented teeth as the data source, first analyzes the characteristics of the movement path planning and converts it into a mathematical model; then according to the characteristics of the teeth, analyzes various collision detection algorithms and selects a suitable collision detection algorithm for the teeth, and combines the ideal dental arch curve fitted by the function to determine the ideal position of the patient's teeth; then a simplified mean particle swarm algorithm based on normal distribution is proposed to solve the optimal path, and experiments prove that whether the convergence or the effectiveness, the convergence accuracy and speed of the algorithm are better, and at the same time meet the orthodontic standard.

[0073] The tooth orthodontic path generation device provided by the application is described below, and the tooth orthodontic path generation device described below can be correspondingly referred to the tooth orthodontic path generation method described above.

[0074] Figure 12 is a structural schematic diagram of the tooth orthodontic path generation device provided by the application, and specifically comprises: The acquisition module 1201 is configured to acquire three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system. For details, refer to the related description of the corresponding method embodiment described above, which will not be repeated here.

[0075] The calculation module 1202 is configured to calculate a target six-dimensional pose of each tooth based on a target dental arch curve and orthodontic medical constraints. For details, refer to the related description of the corresponding method embodiment described above, which will not be repeated here.

[0076] The generating module 1203 is configured to generate an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose by using an improved particle swarm optimization algorithm with the target six-dimensional pose of each tooth as a search space. For details, refer to the related description of the method embodiments described above, which will not be repeated here.

[0077] Figure 13 An example of a schematic diagram of a physical structure of an electronic device is shown in Figure 13 The electronic device can include a processor 1310, a communications interface 1320, a memory 1330, and a communications bus 1340, wherein the processor 1310, the communications interface 1320, and the memory 1330 can communicate with each other through the communications bus 1340. The processor 1310 can invoke a logical instruction in the memory 1330 to execute a tooth orthodontic path generation method, which includes: obtaining three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system; calculating a target six-dimensional pose of each tooth based on a target dental arch curve and orthodontic medical constraints; and generating an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose by using an improved particle swarm optimization algorithm with the target six-dimensional pose of each tooth as a search space.

[0078] In addition, the logical instruction in the memory 1330 described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application or the part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0079] In another aspect, the present application also provides a computer program product comprising a computer program, the computer program being stored in a non-transitory computer-readable storage medium, and the computer program being executable by a processor to enable a computer to perform the tooth orthodontic path generation method provided by any of the above methods, the method comprising: obtaining three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system; calculating a target six-dimensional pose of each tooth based on a target dental arch curve and orthodontic medical constraints; and generating an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose using an improved particle swarm optimization algorithm with the target six-dimensional pose corresponding to each tooth as a search space.

[0080] In yet another aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement a tooth orthodontic path generation method provided by any of the above methods, the method comprising: obtaining three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system; calculating a target six-dimensional pose of each tooth based on a target dental arch curve and orthodontic medical constraints; and generating an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose using an improved particle swarm optimization algorithm with the target six-dimensional pose corresponding to each tooth as a search space.

[0081] The device embodiments described above are merely illustrative, wherein the units illustrated as separate components can or can not be physically separate, and the components illustrated as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0082] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary universal hardware platforms, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in terms of the contribution to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a plurality of instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to perform the methods described in each embodiment or some parts of the embodiments.

[0083] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; and although the present application has been described in detail with reference to the foregoing embodiments, it should be appreciated by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features thereof can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A tooth orthodontic path generation method, characterized by, The method comprises the following steps: obtaining three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system; calculating a target six-dimensional pose of each tooth based on a target dental arch curve and orthodontic medical constraints; generating an optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose by using an improved particle swarm optimization algorithm with the target six-dimensional pose of each tooth as a search space.

2. The method of claim 1, wherein, The method further comprises the following steps: performing farthest point sampling on the three-dimensional point cloud data to obtain target three-dimensional point cloud data with reduced data volume; determining an alignment matrix, a centroid, an axis and a face axis point of each tooth based on the target three-dimensional point cloud data; establishing the initial pose of each tooth in the global coordinate system based on the alignment matrix, the centroid, the axis and the face axis point of each tooth.

3. The method of claim 2, wherein, The method further comprises the following steps: constructing a directional bounding box of each tooth by using a bounding box algorithm, wherein the directional bounding box is a minimum cuboid containing the tooth and arbitrary relative to the direction of the coordinate axis.

4. The method of claim 3, wherein, The method further comprises the following steps: introducing a collision penalty function into a fitness function of the particle swarm optimization algorithm to optimize the translation path and the rotation angle of the tooth with the target six-dimensional pose of each tooth as the search space, wherein the collision penalty function is calculated based on the directional bounding box and the minimum distance between teeth according to the theory of separation axis; setting a maximum step constraint condition for the movement amplitude and the rotation angle of each tooth based on preset medical constraints; iteratively calculating the orthodontic path based on the fitness function of the particle swarm optimization algorithm and the maximum step constraint condition for the movement amplitude and the rotation angle of each tooth until a preset iteration number or a fitness threshold is met, to generate the optimal orthodontic path of each tooth from the initial pose to the target six-dimensional pose.

5. The method of claim 4, wherein, The method further comprises the following steps: calculating a separation axis for any two teeth by using eight vertices of the directional bounding box corresponding to each tooth; judging whether the orthodontic paths corresponding to the any two teeth respectively exist overlap based on the theory of separation axis; if there is overlap, calculating a minimum penetration depth and adding it to the fitness function after weighting.

6. The method of claim 4, wherein, The method further comprises the following steps: generating an optimal orthodontic path corresponding to each orthodontic stage based on all orthodontic stages of the tooth; replacing the optimal orthodontic path corresponding to each orthodontic stage with point cloud data of a corresponding color; performing three-dimensional visual display of the point cloud data corresponding to all orthodontic stages in a color gradient manner, and synchronously rendering the directional bounding box corresponding to each tooth.

7. The method of claim 1, wherein, The improved particle swarm optimization algorithm adopts a simplified mean particle swarm strategy with normal distribution to accelerate the convergence speed and avoid falling into local optimum.

8. An orthodontic path generation apparatus, characterized by, The method comprises the following steps: an obtaining module, configured to obtain three-dimensional point cloud data of an initial dentition of a target patient and an initial pose of each tooth in a global coordinate system; a calculating module, configured to calculate a target six-dimensional pose of each tooth based on a target dental arch curve and orthodontic medical constraints; a generating module, configured to generate an optimal orthodontic path of each tooth from an initial pose to the target six-dimensional pose by using an improved particle swarm optimization algorithm with the target six-dimensional pose of each tooth as a search space.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the tooth orthodontic path generation method in any one of claims 1 to 7 when executing the computer program.

10. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the tooth orthodontic path generation method in any one of claims 1 to 7 when executed by the processor.

Images