Orthodontic treatment planning method, device and storage medium

Abstract

This invention relates to the field of orthodontics, and discloses a method, device, and storage medium for designing a combined orthognathic and orthodontic treatment plan. The method involves obtaining an initial head model of the user; the position of the jawbone in the initial head model is the initial position of the jawbone; obtaining the target position of the user's jawbone; based on the initial head model, calculating several intermediate positions of the jawbone from the initial position to the target position, arranging teeth at each jawbone position, and obtaining a head model corresponding to each jawbone position after tooth arrangement; the jawbone position is either the intermediate position or the target position; selecting a head model that meets preset conditions from the head models corresponding to each jawbone position; and designing a treatment plan based on the head model that meets the preset conditions. This invention combines the orthognathic treatment effect at different stages with the orthodontic effect to obtain a comprehensive treatment effect, reducing communication time between orthodontists and orthognathic surgeons, and quickly providing a treatment plan that meets the needs of combined treatment.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of orthodontics, and particularly to a method, device and storage medium for designing a combined orthognathic and orthodontic treatment plan. Background Technology

[0002] Combined orthognathic and orthodontic treatment is a necessary method for correcting skeletal dentofacial deformities. Patients receive orthodontic treatment to correct tooth position and orthognathic treatment at the appropriate time to change the position of the jawbone, so as to achieve a result that coordinates facial aesthetics and occlusal function.

[0003] However, existing combined orthognathic and orthodontic treatment methods have the following problems: the orthodontic treatment plan is designed separately from the orthognathic treatment plan. When dealing with orthognathic and orthodontic issues simultaneously, especially in cases where orthognathic orthodontic surgery has been performed first, the orthognathic surgeon cannot determine the overall movement of the upper and lower jaws due to the uncertainty of the final occlusion, and therefore cannot obtain the ideal jawbone position. The orthodontist needs to provide the ideal tooth position first. Conversely, because the relative positions of the upper and lower jaws are not yet determined, the orthodontist cannot arrange the teeth to ensure occlusal coordination between the upper and lower teeth, and therefore cannot obtain the ideal tooth position. The orthognathic surgeon also needs to provide the ideal jawbone position first. This leads to a vicious cycle where the two doctors need each other. The interaction with the technician becomes: "Orthodontist determines direction - technician arranges teeth - surgeon determines occlusion - technician moves jawbone - orthodontic surgeon re-determines direction based on values ​​- technician arranges teeth again - surgeon re-determines occlusion - technician moves jawbone again - orthodontic surgeon re-determines direction based on values..." Because the orthodontic plan is not understood, the direction of bone adjustment in orthognathic surgery cannot be clearly defined, and the jawbone position cannot be understood, resulting in an unclear tooth arrangement plan in orthodontics. In this cycle, the corresponding treatment plan can only be designed by predicting or "guessing" the conditions step by step. After each step of the design, communication between the orthodontist and the orthognathic surgeon is needed to adjust the treatment plan. The process of obtaining a feasible treatment plan is cumbersome and inefficient. Summary of the Invention

[0004] The purpose of this invention is to provide a method, device, and storage medium for designing a combined orthognathic and orthodontic treatment plan, so that when performing combined orthognathic and orthodontic treatment, the design of the treatment plan can take into account the effects of orthognathic and orthodontic treatment at the same time, and can efficiently obtain a feasible combined orthognathic and orthodontic treatment plan.

[0005] To achieve the above objectives, embodiments of the present invention provide a method for designing a combined orthognathic and orthodontic treatment plan, comprising: obtaining an initial head model of the user; the position of the jawbone in the initial head model is the initial position of the jawbone; obtaining the target position of the user's jawbone; based on the initial head model, calculating several intermediate positions of the jawbone from the initial position to the target position, and arranging teeth at each jawbone position to obtain a head model corresponding to each jawbone position after tooth arrangement; wherein, the jawbone position is either an intermediate position or a target position; selecting a head model that meets preset conditions from the head models corresponding to the jawbone positions; and designing a treatment plan based on the head models that meet the preset conditions.

[0006] Embodiments of the present invention also provide an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the above-described orthognathic-orthodontic combined treatment scheme design method.

[0007] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method for designing a combined orthognathic and orthodontic treatment scheme.

[0008] In this embodiment of the invention, the target position of the jawbone and several intermediate positions of the jawbone are obtained from the user's initial head model. This allows for the treatment effect of bone blocks at different positions in the orthodontic treatment plan for the jawbone. Then, teeth are arranged at each jawbone position. This allows for the combination of the treatment effect of the jawbone at different stages with the treatment effect of orthodontic treatment to obtain the comprehensive orthodontic treatment effect after orthodontic treatment at different orthognathic stages. Finally, the comprehensive orthodontic treatment effect is judged to select the optimal solution of the orthodontic treatment plan when orthognathic and orthodontic treatment are combined.

[0009] In another example, selecting a head model that meets preset conditions from the head models corresponding to the jawbone position includes: projecting the 3D mesh data of the head model using a preset transformation matrix to form a projected lateral view of the head model; and selecting a head model whose projected lateral view meets the first preset condition based on the projected lateral view of the head model. In existing technologies, most comprehensive analysis of the user's jawbone and tooth positions is performed using the user's projected lateral view. By converting the 3D model onto the projected lateral view for analysis, it is possible to analyze whether the head model meets the standard more quickly and accurately.

[0010] In another example, the preset transformation matrix is ​​obtained through the following steps: marking the marker points in the 3D mesh data and the projection side view data respectively; projecting the marker points in the 3D mesh data onto the plane of the projection side view using the initial transformation matrix to obtain projection points; registering the projection points with the corresponding marker points in the projection side view data to obtain the transformation matrix; and iterating through the transformation matrix to obtain the preset transformation matrix. By establishing the correspondence between the marker points on the 3D model and the projection side view, the 3D model data can be transformed into a 2D projection side view.

[0011] In another example, marking marker points in the 3D mesh data and the projected lateral view data includes: manually marking marker points in the 3D mesh data and the projected lateral view data; or using a graph convolutional neural network or a classical convolutional neural network to mark marker points in the 3D mesh data and the projected lateral view data. Marking marker points manually or using a neural network model allows the method to be applied to a wider range of scenarios.

[0012] In another example, selecting a head model from the head model whose corresponding projection lateral view meets the first preset condition includes: obtaining preset intervals corresponding to various parameters of the projection lateral view; calculating the degree of matching between each parameter and its corresponding preset interval; and determining whether each parameter meets the first preset condition based on the degree of matching. By checking the matching of all relevant parameters when determining the first preset condition, the judgment result can be more accurate.

[0013] In another example, selecting a head model that meets preset conditions includes: acquiring the 3D mesh data of the head model, and selecting a head model whose 3D mesh data meets a second preset condition. Directly judging the various parameters of the head model can improve the judgment efficiency.

[0014] In another example, the calculation involves determining several intermediate jaw positions as the user's jawbone moves progressively from its initial position to its target position. This includes identifying these intermediate jaw positions based on the initial jaw position, the target jaw position, the type of jawbone segment being adjusted, and / or the type of facial parameters being adjusted. This allows for the design of different intermediate jaw positions for various jawbone and facial parameter adjustments, resulting in more diverse and precise orthognathic treatment plans.

[0015] In another example, the orthognathic-orthodontic combined treatment plan design method also includes a screening step. This screening step involves selecting jawbone positions that meet the first boundary condition of orthognathic movement after obtaining the target jawbone position and the intermediate jawbone position; and / or selecting tooth arrangement plans that meet the second boundary condition after tooth arrangement. By screening the orthognathic and tooth arrangement plans, treatment results that clearly do not meet the standards can be initially identified, reducing the workload for subsequent steps and improving the efficiency of treatment plan design.

[0016] In another example, the orthognathic-orthodontic combined treatment plan design method, after designing a treatment plan based on a head model that meets preset conditions, further includes: selecting candidate treatment plans from the treatment plans and visualizing the three-dimensional soft tissue changes corresponding to the candidate treatment plans. Visualization includes predicting and displaying the user's facial image after treatment using the selected treatment plan; or predicting and displaying an image of the head model after treatment using the candidate treatment plan. By visualizing the selected treatment plans in different ways, users or doctors can easily select their preferred treatment plan from different perspectives, facilitating the determination of a treatment plan that meets preset conditions and satisfies the user, thus improving the user experience. Attached Figure Description

[0017] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0018] Figure 1 This is a flowchart of a treatment plan design method combining orthognathic and orthodontic treatment according to an embodiment of the present invention;

[0019] Figure 2 It is a three-dimensional virtual model of jawbone and teeth fusion data according to an embodiment of the present invention;

[0020] Figure 3 It is a virtual model of the fusion data of the three-dimensional jawbone and teeth when the jawbone is in the target position according to an embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram of some marker points in three-dimensional mesh data according to an embodiment of the present invention;

[0022] Figure 5 This is a schematic diagram of some marker points in a projection side view film according to an embodiment of the present invention;

[0023] Figure 6This is a schematic diagram of an electronic device structure according to another embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details are presented in the various embodiments of the present invention to facilitate a better understanding of this application. However, the technical solutions claimed in this application can be implemented even without these technical details and various changes and modifications based on the following embodiments. The division of the various embodiments below is for ease of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with and referenced by each other without contradiction.

[0025] One embodiment of the present invention relates to a method for designing a combined orthognathic and orthodontic treatment plan, which can be applied to an electronic device with the function of designing a combined orthognathic and orthodontic treatment plan. In this embodiment, an initial head model of the user is obtained; the position of the jawbone in the initial head model is the initial position of the jawbone; the target position of the user's jawbone is obtained; based on the initial head model, several intermediate positions of the jawbone are calculated to move the user's jawbone from the initial position to the target position, and teeth are arranged at each jawbone position to obtain a head model corresponding to each jawbone position after tooth arrangement; wherein, the jawbone position is either the intermediate position of the jawbone or the target position of the jawbone; a head model that meets preset conditions is selected from the head models corresponding to the jawbone positions; and a treatment plan is designed based on the head model that meets the preset conditions. By obtaining the target jawbone position and several intermediate jawbone positions from the user's initial head model, the treatment effects at different stages of the orthodontic treatment plan targeting the jawbone can be obtained. Then, tooth alignment is performed at each jawbone position. The treatment effects of the jawbone at different stages can be combined with the treatment effects of orthodontic treatment to obtain the comprehensive treatment effect after orthodontic treatment at different orthognathic stages. Finally, the comprehensive treatment effect is evaluated to select the optimal solution for the combined orthognathic and orthodontic treatment. The following details the implementation of the orthognathic and orthodontic combined treatment plan design method of this embodiment. The following content is only for ease of understanding and is not essential for implementing this solution.

[0026] like Figure 1 As shown, in step 101, the user's initial head model is obtained; the position of the jawbone in the initial head model is the initial position of the jawbone.

[0027] In one example, 3D skull data (including jawbone data), alveolar bone data, and data on tooth roots and crowns can be obtained from the user's CBCT head data. The specific data extraction method can be to extract data from the CBCT image by setting an appropriate Hu value range; however, this implementation does not limit the specific extraction method. Then, the Marching Cube method is used to generate the user's initial head surface mesh data as the user's initial head model based on the extracted data. Additionally, the user's oral scan data is also obtained. Common instance segmentation models such as Mask R-CNN or 3DUnetR++ are used to extract the corresponding data for tooth crowns and roots from the user's CBCT data. Then, the Iterative Closest Point (ICP) algorithm or the Coherent Point Drift (CPD) algorithm is used to register the tooth crown data extracted from the CBCT with the tooth crown data in the oral scan data. This establishes a one-to-one correspondence between the oral scan tooth crown data and the CBCT tooth root data. (Refer to...) Figure 2 The 3D virtual model of the jawbone and teeth shown uses intraoral scan crown data instead of CBCT crown data because the crown data in intraoral scans is generally more accurate than that in CBCTs. This method allows for the creation of a more accurate initial head model of the user.

[0028] In step 102, the target location of the user's jawbone is obtained.

[0029] In one example, after obtaining the user's initial head model and the location of the jawbone within it, deep learning methods are used to learn from historical cases how doctors use the six-element method to formulate orthognathic surgery plans. This allows for the prediction of a reasonable surgical plan and corresponding quantitative target positions for the user. In this implementation, it is assumed that the user's jawbone requires orthognathic surgery. After obtaining the predicted reasonable surgical plan and corresponding quantitative target positions, the target position of the jawbone can be obtained from the head model established in step 101. (Refer to...) Figure 3 The description above is a virtual model of the target location of the jawbone.

[0030] In step 103, based on the initial head model, the user's jawbone is calculated to move from the initial position to the target position of the jawbone at several intermediate positions of the jawbone, and teeth are arranged at each jawbone position to obtain the head model corresponding to each jawbone position after tooth arrangement; wherein, the jawbone position is the intermediate position of the jawbone or the target position of the jawbone.

[0031] In one example, after obtaining the initial head model and the target positions of all free jawbones, to simultaneously consider the combined effect of orthognathic surgery and orthodontics, instead of moving a jawbone from its initial position to its target position in one step, the parameters between the initial and target positions are adjusted step by step with small increments. These parameters include the coordinates of the initial and target positions of the jawbones and the distance between them, as well as the type of jawbone block being adjusted and / or the type of facial parameters being adjusted. For example, when the distance between the initial and target positions of both the maxillary and mandibular bone blocks is 20mm, each unit movement of the maxillary bone block may have a greater impact on the final result, while each unit movement of the mandibular bone block may have a smaller impact. Therefore, the step size for each movement of the maxillary bone block could be designed to be 1mm, and the step size for each movement of the mandibular bone block could be 2mm. Furthermore, the type of facial parameters being adjusted also affects the step size. For example, when adjusting the parameter "angle between the upper central incisors and the anterior skull base plane," since this parameter has a significant impact on the final orthognathic effect of the user's head model, the step size is designed to be as small as possible to obtain the optimal position. This allows for more precise orthodontic results at different stages. Conversely, when adjusting parameters that have a smaller impact on the final orthognathic effect, such as "maxillary convexity," the step size can be larger. This ensures that the optimal solution is obtained while minimizing the computational load of the method, thus improving efficiency.

[0032] In addition, after obtaining several intermediate positions of the jawbone based on the step length designed considering different factors, teeth will be arranged at each intermediate position of the jawbone. This teeth arrangement can be done automatically using algorithms or existing network models, or manually by orthodontists.

[0033] This embodiment also includes a screening step. The screening step involves, after obtaining the target position and intermediate position of the jawbone, screening jawbone positions that meet the first boundary condition for orthognathic movement. Jawbone positions that clearly do not meet the first boundary condition, such as the boundary conditions of individual jawbone segments, are eliminated. In one embodiment, the boundary condition for each jawbone segment is a preset maximum movement amount. When the movement amount of a jawbone segment in an intermediate position exceeds the maximum movement amount, these positions can be directly eliminated. For example, in the current case, the boundary condition for each jawbone segment might be that the maxilla can only move outward a maximum of 20mm within the user's skull. However, if the maxilla moves outward more than 20mm in the intermediate or target position, the jawbone position is clearly unattainable. Therefore, directly eliminating these positions during the design of the treatment plan can initially screen out treatment results that clearly do not meet the standards, reducing the workload for subsequent steps and improving the efficiency of the treatment plan design. Similarly, after tooth arrangement, the treatment plan is screened based on the second boundary condition. This second boundary condition can include whether the tooth root is located within the alveolar bone. For example, if excessive tooth movement is performed in a certain position to achieve the preset standard, causing the tooth root to be exposed outside the alveolar bone, the treatment plan is clearly unreasonable and needs to be eliminated. Directly eliminating these positions during the design of the orthodontic plan can initially screen out treatment results that clearly do not meet the standard, reducing the workload for subsequent steps and improving the efficiency of the orthodontic plan design.

[0034] In step 104, a head model that meets the preset conditions is selected from the head models corresponding to the jawbone position.

[0035] In one example, determining whether a head model meets preset conditions can be achieved by projecting the 3D mesh data of the head model using a preset transformation matrix to generate a lateral projection view of the head model. Then, based on the lateral projection view, head models whose lateral projection views meet the first preset condition are selected. Specifically, the preset transformation matrix is ​​obtained through the following steps: First, some marker points in the 3D mesh data can be manually marked. These marker points mainly correspond to points on the bones from the nasal bridge to the chin in the lateral projection view, such as marker points N', ANS', U1', L1', B', Pog', Gn', Me', Tpl', and Go'. These correspond to points N, ANS, U1, L1, B, Pog, Gn, Me, Tpl, and Go on the lateral projection view of the skull, respectively. Figure 4As shown. Besides manually marking some marker points in the 3D mesh data, automatic marking can also be achieved by using convolutional neural networks to determine marker points on the 3D mesh. After obtaining the marker points in the 3D mesh data, deep learning algorithms can be used to predict the marker points and contour lines on the user's head projection lateral view. Specifically, we can also extract a contour line at the chin on the projection lateral view, which can be a curve from marker point Go to point B. The contour obtained from this projection lateral view is represented as a set of contour line points {p} in the pixel coordinate system. i}, can be seen Figure 5 After acquiring the 3D mesh data and the marker points on the lateral projection image, based on existing multimodal image projection experience, an initial projection matrix is ​​first obtained. The marker points on the 3D mesh data are projected onto the 2D plane where the lateral projection image is located. Then, through optimization methods including but not limited to Constrained Optimization by Linear Approximation (COBYLA), truncated Newton's method, and Powell's method, the projected values ​​of the marker points in the 3D skull are registered with the marker points in the 2D lateral projection image. The intrinsic and extrinsic parameters of the camera are obtained to obtain the preset transformation matrix.

[0036] Specifically, based on existing experience with multimodal image projection, an initial projection matrix is ​​first obtained. The marker points on the 3D mesh data are projected onto the 2D plane of the lateral projection image. Then, optimization methods, including but not limited to Constrained Optimization by Linear Approximation (COBYLA), truncated Newton's method, and Powell's method, are used to register the projected values ​​of the marker points in the 3D skull with the marker points in the 2D lateral projection image. The camera's intrinsic and extrinsic parameters are obtained to acquire the preset transformation matrix. This also includes rotating and translating the point cloud of the 3D mesh data using the mouse in the software, so that the imaginary boundary contour lines projected onto the computer screen are basically coincident with the skull contour of the lateral projection image by the naked eye. Due to the complexity of the data (e.g., the upper half of the skull in the lateral projection image or CBCT data is not fully captured), we only need to align the more obvious contour lines. In this way, the initial camera intrinsic and extrinsic parameters can be obtained in the software based on mouse operations. Considering that the patient's mandible can be captured completely in both CBCT and lateral radiographs, we manually selected two marker points, Go and B, on the 3D mesh data and their corresponding points on the lateral radiographs of the mandible and mandible, i.e., marker points Go' and B'. Simultaneously, we obtained the set of boundary points between Go' and B' from the skull projection lines. Then we use the EM algorithm to perform a fine search for the camera's intrinsic and extrinsic parameters. The EM algorithm consists of two steps. In the E-step: the boundary point set and the point set {p} on the projected side view are used... i Registration is performed, which specifically involves searching for every point on the projected contour line. Which point p on the outline of a 2D lateral skull projection radiograph? i Closest in distance and closest in direction:

[0037]

[0038] Where n i For point p i The normal vector at the outline of the projected side view; For point The normal vector at the projected contour line. σ is a constant. The purpose of this step is to establish the correspondence between the points on the projected contour line and the points on the two-dimensional contour line of the projected side view, and to calculate the error corresponding to this established correspondence. and their sum:

[0039]

[0040] In the M-step, we first determine the set of camera intrinsic and extrinsic parameters χ. During the initial computation of this step, its initial value is given by the manually obtained coarse search result; in subsequent iterations, its initial value is given by the result of the E-step. The loss function to be optimized in this step consists of two parts: the relative positional deviation (Loss) between points on the projected contour line and the corresponding contour line points on the 2D lateral skull projection. p Its definition is:

[0041]

[0042] Loss of the normal deviation of the contour line containing the corresponding point n Its definition is:

[0043]

[0044] Where N is the number of corresponding points. The total loss function to be optimized is Loss. tot =w p *loss p +w n *loss n Among them, w p and w n The weights for these two types of losses are respectively assigned.

[0045] Our goal in this step is to obtain the optimal parameter estimate. Where χ represents the initial camera parameters and initial relative pose. The optimization methods we employ include, but are not limited to, Constrained Optimization by Linear Approximation (COBYLA), truncated Newton's method, and Powell's method. In subsequent optimization processes, χ... * As the initial parameters for the E-step, the E-step and M-step are iterated several times. The iteration termination condition can be set to the point where the loss given by the E-step no longer decreases after 5 consecutive iterations. Once the camera parameters and pose are determined, i.e., the camera transformation matrix is ​​determined, the corresponding positions of other landmarks on the lateral projection image can also be found on the 3D mesh data. Furthermore, due to symmetry, each landmark on the non-bone boundary of the lateral projection image corresponds to two points on the 3D mesh data. The search method for these two points is as follows: Based on the transformation matrix, the projection of each mesh of the 3D mesh onto the 2D lateral projection image plane is calculated. All meshes containing the skull landmark are selected. Then, the two triangular meshes closest to and farthest from the camera plane in the camera coordinate system are selected as the corresponding two landmarks on the 3D mesh data. In existing technologies, most comprehensive analysis of the user's jawbone and tooth position is performed using the user's lateral projection radiographs. By converting the three-dimensional model onto the lateral projection radiographs for analysis, it is possible to analyze whether the head model meets the first preset conditions more quickly and accurately. Specific methods for analyzing lateral projection radiographs can include the Ninth People's Hospital analysis method or other analysis methods.

[0046] Furthermore, when analyzing landmarks on projected lateral radiographs using any facial jawbone analysis method, the corresponding parameters can be calculated from the coordinates on the lateral radiographs. For each parameter value, the analysis method provides a normal value range, and then calculates the degree of matching between each parameter and its corresponding normal value. Based on the degree of matching, it is determined whether each parameter meets a first preset condition. The degree of matching here can include: if the parameter value is within a preset normal value range, the parameter value is considered matched and meets the first preset condition; or if the distance between the parameter value and the normal value range is within a preset numerical range, the parameter value is considered matched and also meets the first preset condition. In this embodiment, the first preset condition is set as the range of the sum of the differences between each parameter value and the normal value range. When judging the degree of matching for each parameter, it is determined that the distance between the parameter value and the normal value range is within the preset numerical range. Ideally, a head model corresponding to the jawbone state and tooth arrangement state where the sum of the differences is minimal or all parameter values ​​are within the normal value range can be selected. When judging the preset condition, judging whether all relevant parameters match can make the judgment results more accurate. It should be noted that this implementation method does not impose specific limitations on the specific analysis standards and preset conditions, as long as the parameters in the head model match the preset standards.Specifically, setting the normal value range for each parameter can include: SNA (82.4°±4.1), FH-NA (91.0°±7.5), NA-Apo (6°±4.4), SNB (80.1°±3.9), FH-NPO (85.4°±3.7), NA-APO (6.0°±4.4), MP-SN (30.4°±5.6), Co-Go (59.0mm±3.2), S... Vert-Co(20.2mm±2.6), SN(71.0mm±3.0), SN / GoMe(%)(100.0%±10.0), Y-Axis(64.0°±2.3), Pog-NB(4.0mm±2.0), A NB(2.7°±2.0), Wits(0.0mm±2.0), ANS-Me / Na-Me(55.0%±2.5), ALFH / PLFH(1.5±0.0), S-Go / N-Me(63.5%±1.5), STN vert-Pog(0.0mm±2.0)、ULL(20.0mm±2.0)、Sn to G Vert(6.0mm±3.0), UL-EP(-1.4mm±0.9), LL-EP(0.6mm±0.9), U1-SN(105.7°±6.3), UD-SN(106. 0°±6.0), U1-NA(deg)(22.8°±5.2), U1-NA(5.1mm±2.4), U1-PP(UADH)(28.0mm±2.1), IMPA(L1- The parameters are: MP (96.7°±6.4), L1-MP (mm) (42.0mm±4.0), L1-NB (deg) (30.3°±5.8), L1-NB (6.7mm±2.1), U1-L1 (124.0°±8.2), Overjet (2.0mm±1.0), Overbite (3.0mm±2.0), FMIA (L1-FH) (55.0°±2.0), and Mx Occ planeto FH (9.3°±1.0). Among these, the parameters STN vert-Pog, Sn to G Vert, and U1-SN have a significant impact on the overall facial appearance and should be prioritized during adjustments. Following these are IMPA (L1-MP), SNA or SNB, Wits, and MP-SN.

[0047] In one example, determining whether a head model meets preset conditions can also involve obtaining the head model's 3D mesh data, and selecting head models whose 3D mesh data meets the second preset condition. Specifically, in the 3D mesh data, the aforementioned parameters are obtained through 3D coordinates: SNA (82.4°±4.1), FH-NA (91.0°±7.5), NA-Apo (6°±4.4), SNB (80.1°±3.9), FH-NPO (85.4°±3.7), NA-APO (6.0°±4.4), MP-SN (30.4°±5.6), Co-Go (59.0mm±3.2), S... Vert-Co(20.2mm±2.6), SN(71.0mm±3.0), SN / GoMe(%)(100.0%±10.0), Y-Axis(64.0°±2.3), Pog-NB(4.0mm±2.0), A NB(2.7°±2.0), Wits(0.0mm±2.0), ANS-Me / Na-Me(55.0%±2.5), ALFH / PLFH(1.5±0.0), S-Go / N-Me(63.5%±1.5), STN vert-Pog(0.0mm±2.0)、ULL(20.0mm±2.0)、Sn to G Vert(6.0mm±3.0), UL-EP(-1.4mm±0.9), LL-EP(0.6mm±0.9), U1-SN(105.7°±6.3), UD-SN(106. 0°±6.0), U1-NA(deg)(22.8°±5.2), U1-NA(5.1mm±2.4), U1-PP(UADH)(28.0mm±2.1), IMPA(L1- The following parameters are used for evaluation: L1-MP (96.7°±6.4), L1-MP (42.0mm±4.0), L1-NB (deg) (30.3°±5.8), L1-NB (6.7mm±2.1), U1-L1 (124.0°±8.2), Overjet (2.0mm±1.0), Overbite (3.0mm±2.0), FMIA (L1-FH) (55.0°±2.0), and Mx Occ plane to FH (9.3°±1.0). Then, it is determined whether each parameter matches the corresponding normal value. In this embodiment, in addition to converting the three-dimensional mesh data of the head model into a projected lateral view for evaluation, the three-dimensional mesh data can also be directly evaluated. For example, the relative position (distance) between the maxilla and mandible can be obtained from the three-dimensional mesh data to determine whether it is within the normal range. Directly evaluating the parameters of the head model can improve the evaluation efficiency.

[0048] In step 105, a treatment plan is designed based on a head model that meets preset conditions.

[0049] In one example, after obtaining a head model that meets preset conditions, a combined orthognathic and orthodontic treatment plan can be designed based on the jawbone position and tooth arrangement plan within the head model. Furthermore, after designing the combined orthognathic and orthodontic treatment plan, candidate treatment plans can be selected from the existing plans, and the corresponding three-dimensional soft tissue changes can be visualized. This visualization includes predicting and displaying the user's facial image after treatment using the selected plans, allowing the user to choose their preferred treatment plan based on the predicted facial image. Alternatively, it can predict and display the head model image after treatment using the candidate plans. Although the selected treatment plans all meet the preset conditions, orthodontists, based on practical experience and the actual situation, can select a more practically feasible plan based on the head model image. By visualizing the selected treatment plans in different ways, users or doctors can easily choose their preferred treatment plan from different perspectives, facilitating the determination of a plan that meets the preset conditions and satisfies the user, thus improving the user experience.

[0050] Specifically, facial shape prediction can be achieved through the following steps: First, obtain a 3D mesh model of the associated dentition, teeth, and soft tissue portions from CBCT images taken of the user's head. Then, fuse the user's lateral facial projection and profile photos to form a composite image. Register and fuse the composite image with the 3D mesh model to form a composite facial model. Next, identify pre-selected feature points, including the tip of the nose and protrusions of the upper and lower lips, on the teeth and jawbone portions of the composite facial model. Then, based on the treatment plan, obtain the second position of the feature points in the composite facial model after the user's orthodontic treatment. Based on the initial and second positions of the feature points, use a deformation method to calculate the relationship between the movement of the feature points and the changes in each mesh vertex in the composite facial model. Based on this relationship, obtain the new positions of the mesh vertices in the soft tissue portion of the composite facial model. After obtaining the new positions of the mesh vertices in the soft tissue portion of the composite facial model, a clear image of the post-treatment composite facial model can be obtained and displayed to the user or doctor.

[0051] In this embodiment, the target position of the jawbone and several intermediate positions of the jawbone are obtained from the user's initial head model. This allows for the acquisition of treatment effects at different stages of the orthodontic treatment plan targeting the jawbone. Then, teeth are arranged at each jawbone position. This allows for the combination of the treatment effects of the jawbone at different stages with the treatment effects of orthodontic treatment to obtain the comprehensive orthodontic treatment effect after orthodontic treatment at different orthognathic stages. Finally, the comprehensive orthodontic treatment effect is evaluated to select the optimal solution for the treatment plan when orthognathic and orthodontic treatment are combined.

[0052] The steps described above are for clarity only. In practice, they can be combined into one step or some steps can be broken down into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this patent.

[0053] Another embodiment of the present invention relates to an electronic device, such as Figure 6 As shown, it includes at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the orthognathic-orthodontic combined treatment plan design method as described above.

[0054] The memory and processor are connected via a bus, which can include any number of interconnecting buses and bridges, connecting various circuits of one or more processors and memories. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and will not be described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over the wireless medium via an antenna, which further receives data and transmits it to the processor.

[0055] The processor manages the bus and general processing, and also provides various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory is used to store data used by the processor during operation.

[0056] Another embodiment of the present invention relates to a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the above-described method embodiments.

[0057] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0058] Those skilled in the art will understand that the above embodiments are specific examples of implementing the present invention, and in practical applications, various changes in form and detail may be made without departing from the spirit and scope of the present invention.

Claims

1. A method for designing a combined orthognathic and orthodontic treatment plan, characterized in that, include: Obtain the user's initial header model; The position of the jawbone in the initial head model is the initial position of the jawbone. Obtain the target location of the user's jawbone; Based on the initial head model, the user's jawbone is calculated to move gradually from the initial position to the target position of the jawbone at several intermediate positions, and teeth are arranged at each jawbone position to obtain the head model corresponding to each jawbone position after tooth arrangement; wherein, the jawbone position is either the intermediate position of the jawbone or the target position of the jawbone. Select a head model that meets the preset conditions from the head models corresponding to each of the jawbone positions; A treatment plan is designed based on the head model that meets the preset conditions.

2. The method for designing a combined orthognathic and orthodontic treatment plan according to claim 1, characterized in that, The step of selecting a head model that meets preset conditions from the head models corresponding to the jawbone position includes: The three-dimensional mesh data of the head model is projected and transformed using a preset transformation matrix to form a projected side view of the head model. Based on the lateral projection image of the head model, select a head model whose lateral projection image meets the first preset condition.

3. The method for designing a combined orthognathic and orthodontic treatment plan according to claim 2, characterized in that, The preset transformation matrix is ​​obtained through the following steps: Mark the marker points in the three-dimensional mesh data and the projected side view data respectively; The initial transformation matrix is ​​used to project the marker points in the three-dimensional mesh data onto the plane where the projection side view is located to obtain the projection points; The transformation matrix is ​​obtained by registering the projection points with the corresponding marker points in the projection side view data. The transformation matrix is ​​iterated to obtain a preset transformation matrix.

4. The method for designing a combined orthognathic and orthodontic treatment plan according to claim 3, characterized in that, The step of marking the marker points in the three-dimensional mesh data and the projected side view data includes: Manually mark the marker points in the three-dimensional mesh data and the projected side view data; Alternatively, a convolutional neural network can be used to label the marker points in the 3D mesh data and the projected side view data.

5. The method for designing a combined orthognathic and orthodontic treatment plan according to claim 2, characterized in that, The step of selecting a head model from the head models whose corresponding projection lateral view meets the first preset condition includes: Obtain the preset range corresponding to each parameter of the projected side view; Calculate the degree of matching between each parameter and the corresponding preset interval; Based on the degree of matching, it is determined whether each parameter meets the first preset condition.

6. The method for designing a combined orthognathic and orthodontic treatment plan according to claim 1, characterized in that, The selection of head models that meet preset conditions includes: Obtain the three-dimensional mesh data of the head model, and select a head model whose three-dimensional mesh data meets the second preset condition from the head models.

7. The method for designing a combined orthognathic and orthodontic treatment plan according to claim 1, characterized in that, The calculation of the user's jawbone moving gradually from its initial position to its target position across several intermediate jawbone positions includes: The intermediate positions of the jawbones are determined based on the initial position of the jawbone, the target position of the jawbone, the type of jawbone fragments, and / or the type of currently adjusted facial parameters.

8. The method for designing a combined orthognathic and orthodontic treatment plan according to claim 1, characterized in that, It also includes a screening step; The screening step includes, after obtaining the target position and the intermediate position of the jawbone, screening jawbone positions that meet the first boundary condition according to the first boundary condition of orthognathic movement; And / or, after the tooth arrangement, select a tooth arrangement scheme that meets the second boundary condition according to the second boundary condition of the tooth arrangement.

9. The method for designing a combined orthognathic and orthodontic treatment plan according to claim 8, characterized in that, The first boundary condition includes the boundary conditions of each jawbone block and whether the upper and lower jaws collide. The second boundary condition includes whether the position of the tooth root is within the alveolar bone.

10. The method for designing a combined orthognathic and orthodontic treatment plan according to claim 1, characterized in that, After designing the correction plan based on the head model that meets the preset conditions, the method further includes: Candidate treatment plans are selected from the treatment plans, and the three-dimensional soft tissue changes corresponding to the candidate treatment plans are visualized.

11. The method for designing a combined orthognathic and orthodontic treatment plan according to claim 10, characterized in that, The visualization includes: Predict and display the user's facial image after treatment using the candidate treatment plan; Alternatively, predict and display an image of the head model after correction using the candidate correction scheme.

12. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the orthognathic-orthodontic combined treatment scheme design method as described in any one of claims 1 to 11.

13. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the orthognathic and orthodontic treatment scheme design method as described in any one of claims 1 to 11.

Images