Method for generating oral correction scheme, electronic equipment and storage medium

Abstract

The invention relates to the field of oral clinical orthodontics, and discloses a method for generating an oral correction scheme, comprising: acquiring a face composite model of an initial state of a patient, the face composite model comprising a dental jaw portion and a soft tissue portion; respectively obtaining P correction schemes of the patient, wherein each correction scheme corresponds to a target state of tooth jaw movement; correspondingly obtaining face prediction models of P target states according to the tooth jaw movement and deformation face composite models of the P correction schemes; and in the P correction schemes, selecting an optimal correction scheme as a target correction scheme according to evaluation of the face prediction model in the target state. The invention further discloses electronic equipment and a storage medium, the orthodontic scheme is determined by predicting the appearance, the predicted result is closer to the real effect after orthodontic treatment, more bases are provided for the patient to select the orthodontic scheme, the patient can conveniently determine the ideal orthodontic scheme from the face expression, and a more preferable orthodontic scheme is generated.

Description

Technical Field

[0001] This application relates to the field of clinical orthodontics in dentistry, and particularly to a method, an electronic device, and a storage medium for generating an oral treatment plan. Background Art

[0002] Orthodontics in dentistry is a comprehensive treatment method for tooth and oral and maxillofacial deformities, mainly aiming at the correction of tooth and oral and maxillofacial deformities. Its main purpose is to treat abnormal conditions such as irregular teeth, tooth gaps, protruding teeth, and jaw development. Through orthodontic treatment in dentistry, teeth can become complete and beautiful, achieving the purpose of coordinated balance of the dentognathic system. In theory, the effect of orthodontics in dentistry is remarkable. It can not only restore chewing function, improve oral hygiene, restore facial beauty, but also correct problems such as unclear pronunciation caused by abnormal development, and improve learning and work efficiency. Due to the long cycle, high cost, and high medical professionalism requirements of orthodontics in dentistry, it is very difficult for patients to judge whether the treatment plan is suitable in the early stage, or whether the treatment effect meets their expectations. As a result, it is very difficult to design an oral treatment plan that fits the user's needs. After some users spend time and money, they cannot obtain the treatment effect they are satisfied with, and there is a large sense of difference in expectations.

[0003] Among the above factors affecting the patient's expectations, the aesthetics after orthodontics is a highly subjective consideration parameter. At present, the prediction of the dental and maxillofacial part in this factor has been carried out through technologies such as three-dimensional model reconstruction and digital design of treatment plans, and can be visually displayed through models, providing reliable reference bases for patients, doctors, or professionals. However, the appearance aesthetics is mainly based on soft tissues, and users cannot perceive the appearance changes only through dental and maxillofacial models. Therefore, we need a method that can accurately predict the changes in the human facial shape, so as to provide richer reference bases for patients, doctors, or other professionals, and thus generate a more optimal oral treatment plan.

[0004] In this application, "jaw" in "malocclusion", "open bite", "overbite", "occlusal plane", etc. is "occlusion" (hé). This character is a rare character, and since it is not in the general input method character library, it is often written as "jaw" in daily life and on the Internet. For the convenience of reading in this article, it is also written as "jaw". Summary of the Invention

[0005] The purpose of this application is to provide a method, an electronic device, and a storage medium for generating an oral treatment plan, which can accurately predict the changes in the human facial shape and generate a more optimal oral treatment plan according to the prediction results.

[0006] To address the aforementioned technical problems, embodiments of this application provide a method for generating orthodontic treatment plans. The method includes: acquiring a composite facial model of the patient in an initial state, the composite facial model comprising a dental and jaw portion and a soft tissue portion; acquiring P orthodontic plans for the patient, each orthodontic plan corresponding to a target state of dental and jaw movement, where P is a natural number greater than 1; deforming the composite facial model according to the dental and jaw movement of the P orthodontic plans, corresponding to the obtained P target state facial prediction models; and selecting the optimal orthodontic plan as the target orthodontic plan based on the evaluation of the target state facial prediction models among the P orthodontic plans.

[0007] This application provides a method for generating an orthodontic treatment plan, the method comprising: acquiring a composite facial model of a patient in an initial state, the composite facial model comprising a dentition and jaw portion and a soft tissue portion; acquiring an orthodontic treatment plan for the patient, the orthodontic treatment plan comprising N sequentially executed orthodontic steps for achieving dentition and jaw movement from an initial state to a target state, wherein each orthodontic step corresponds to a stage state; deforming the composite facial model of the initial state based on the initial state and the stage state of an orthodontic step to obtain a facial prediction model for that orthodontic step; obtaining M facial prediction models corresponding to the stage states of M orthodontic steps; wherein the M orthodontic steps are selected from the kth to the Nth orthodontic steps, where k, N, and M are natural numbers greater than or equal to 1, and k and M are less than or equal to N; selecting the optimal stage state as the orthodontic target based on the evaluation of each facial prediction model among the M stage states; and updating the orthodontic treatment plan based on the orthodontic target.

[0008] Embodiments of this application also provide an electronic device, including: 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 method for generating an orthodontic treatment plan.

[0009] Embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for generating an orthodontic treatment plan.

[0010] The method for generating orthodontic treatment plans in this application provides users with a reference for selecting treatment plans by predicting changes in facial features under target states within the treatment plan. Specifically, it predicts changes in facial features under target states for multiple treatment plans, and then evaluates the obtained facial prediction models to select the best treatment plan. This avoids the problem of current orthodontic plan design relying on a single medical standard without considering the user's personalized needs, resulting in a treatment plan that better meets the user's expectations and improves the user experience. Furthermore, this application can not only optimize among multiple treatment plans but also optimize the target state at multiple stages of a single treatment plan, allowing users to comprehensively consider treatment cycle, cost, and final treatment effect. Its flexible application scenarios facilitate the widespread adoption of the solutions described in this application.

[0011] In some embodiments, the orthodontic plan further includes multiple stages through which the teeth and jaws move from an initial state to a target state; the method further includes: obtaining different face prediction models corresponding to different stage states; and selecting the optimal orthodontic plan as the target orthodontic plan based on the evaluation of the face prediction model for the target state among the P orthodontic plans, including: selecting the optimal orthodontic plan as the target orthodontic plan based on the evaluation of the face prediction model for the target state and the evaluation of the face prediction models for each stage state among the P orthodontic plans. Since orthodontic treatment is lengthy, and considering that patients not only need a better final target state but also better intermediate stage states, evaluating the target state and stage states separately and selecting the overall optimal orthodontic plan can improve user satisfaction with intermediate stage states and better meet the actual needs of users.

[0012] In some embodiments, selecting the optimal treatment plan as the target treatment plan based on the evaluation of the face prediction model for the target state and the evaluation of the face prediction models for each stage state includes: selecting the optimal treatment plan as the target treatment plan based on the evaluation of the face prediction model for the target state and the evaluation of the face prediction models for some stage states. Since the invisible orthodontic process involves multiple steps and numerous intermediate stages, only some stages can be evaluated to reduce the amount of data processing required to obtain accurate evaluation results.

[0013] In some embodiments, the evaluation of the face prediction model for the target state is based on the following parameter: face shape state.

[0014] In some embodiments, the evaluation of the face prediction model is determined based on user instructions. Since the resulting treatment plan needs to closely align with user needs, user instructions determine the evaluation level, increasing user participation and decision-making power, so that the subsequently generated treatment plan better meets the user's requirements.

[0015] In some embodiments, the evaluation of the face prediction model for the target state is further combined with the following parameters: the number of orthodontic steps required to achieve the target state and / or the degree of tooth alignment. Since both the number of orthodontic steps and / or the degree of tooth alignment affect the treatment outcome, combining these parameters increases the objectivity of the evaluation, facilitates automated evaluation, and provides supplementary information for the user.

[0016] In some embodiments, if the number of parameters involved in evaluating the face prediction model is greater than one, different weights are assigned to different parameters. Since the impact of multiple parameters on the treatment outcome varies, and different patients pay different attention to different parameters, setting weights can adjust the importance of the parameters involved in the evaluation in order to obtain evaluation results that better meet the user's needs.

[0017] In some embodiments, if facial shape state is included among the multiple parameters involved in evaluating the face prediction model, then the facial shape state has a higher weight. The goal is to achieve the best possible outcome in terms of shape state, with a focus on the evaluation results of the shape state, in order to obtain a better corrective treatment plan and achieve more ideal treatment results for the patient.

[0018] In some embodiments, the evaluation of tooth alignment is based on a comprehensive evaluation of multiple objectives, where each objective is a medical element of orthodontics. Since tooth alignment can be evaluated using various medical elements, multiple objectives can be selected as needed to participate in the evaluation of tooth alignment in order to obtain a comprehensive and optimal orthodontic treatment plan.

[0019] In some embodiments, the medical elements of orthodontics include: dental arch curve, dental crowding, overbite, overjet, dental arch protrusion, Spee curve curvature, Bolton index, dental arch width, dental arch symmetry, tooth rotation, tooth axial tilt, or tooth torque.

[0020] In some embodiments, any one of the P orthodontic treatment plans is obtained based on one or any combination of the following tooth arrangement methods: direct step-by-step method, spatial search method, and intermediate interpolation method. This embodiment uses different tooth arrangement methods to obtain orthodontic plans. Each tooth arrangement method has its own characteristics, resulting in different orthodontic plans, thus providing users with a wider range of treatment options and increasing their choice.

[0021] In some embodiments, any two of the P orthodontic schemes are obtained using different tooth alignment methods. Since the target state and stage state are different depending on the method used to determine the orthodontic scheme, the method of comprehensive evaluation using multiple models in weight 2 aims to ensure a good final orthodontic effect while maintaining a good intermediate process, thereby increasing the user's willingness to wear the treatment.

[0022] In some embodiments, at least two of the P orthodontic schemes are arranged according to the intermediate interpolation method.

[0023] In some embodiments, the step of deforming a composite face model in the initial state according to an initial state and a stage state of a treatment step to obtain a face prediction model for that treatment step includes: identifying pre-selected dental and jaw feature points on the dental and jaw portion of the composite face model, denoted as the first position of the dental and jaw feature points; obtaining the second position of the dental and jaw feature points in the composite face model based on dental and jaw movement between the initial state and the stage state; calculating the relationship between the movement of the dental and jaw feature points and the change of mesh vertices in the composite face model using a deformation method based on the first and second positions of the dental and jaw feature points; and deforming the composite face model based on the dental and jaw movement and the change relationship to obtain a face prediction model corresponding to that treatment step. In this embodiment, a composite facial model including the dental and soft tissue parts of the associated face is obtained. The relationship between the dental and soft tissue parts is determined. Then, by using the known changes in the dental parts in the orthodontic plan, the relationship of facial shape changes is determined. Thus, the positional changes of other parts are predicted based on this relationship. Since the prediction can be made using only the patient's own data, without the need to combine a large amount of historical data to infer the relationship of changes, the facial shape prediction method in this application involves a small amount of data in the prediction calculation and has high accuracy.

[0024] In some embodiments, obtaining the composite face model in the patient's initial state includes: obtaining a registration image; wherein the registration image is a composite image formed by fusing a lateral view of the patient's face and a profile photograph, or a lateral view of the patient's face; obtaining a face mesh model and a dental model respectively; and registering and fusing the face mesh model and the dental model based on the registration image to form the composite face model. This embodiment forms a composite face model by registering and fusing a face mesh model and a dental model, resulting in a composite face model that possesses associated dental and jaw components and soft tissue components representing appearance. Since the methods for obtaining the face mesh model and the dental model are relatively simple, the generation of the composite face model in this embodiment is reliable and easily promoted, while also reducing the difficulty of data collection at the terminal. This embodiment further uses a lateral view of the face that simultaneously possesses dental and jaw features and some facial contour features, and a profile photograph that possesses facial contour features, for registration and fusing to form a composite image including rich dental and jaw features and facial contour features. This composite image is used as a registration reference for the three-dimensional model, allowing for a wide range of selectable parameters during registration, resulting in more accurate registration results. In addition, this embodiment can directly use lateral facial images for model registration, which is simple and fast.

[0025] In some embodiments, fusing a patient's lateral facial radiograph and profile view photograph to form a composite image includes: identifying pre-selected facial contour feature points on the acquired lateral facial radiograph and profile view photograph; and performing registration and fusion based on the positions of the facial contour feature points to form the composite image. In this embodiment, registration is performed by acquiring facial contour feature points from various types of images. Since the lateral facial radiograph simultaneously contains the jawbone and part of the facial contour, the fusion is highly operable, and the resulting composite image has rich feature information and more selectable feature points, facilitating subsequent 3D model registration.

[0026] In some embodiments, the pre-selected facial contour feature points include: the tip of the nose and the protrusions of the upper and lower lips. In this embodiment, the tip of the nose and the protrusions of the upper and lower lips are used as facial contour feature points for registration. These points have obvious features and are more accurately identified during acquisition, so as to ensure the accuracy of registration in subsequent registration.

[0027] In some embodiments, the registration and fusion of the face mesh model and the dental model based on the registration image to form the face composite model includes: identifying pre-selected facial contour feature points on the face mesh model; identifying dental feature points on the dental model; and registering and fusing the face mesh model and the dental model according to the relationship between the pre-selected dental feature points, the facial contour feature points, and the registration image to form the face composite model.

[0028] In some embodiments, the dental and jaw feature points include: the occlusal contact points of the maxillary first molar and the mandibular first molar, and the occlusal contact points of the maxillary central incisor and the mandibular central incisor.

[0029] In some embodiments, the face mesh model is obtained by: stitching and fusing multi-angle facial photos of the patient; or by scanning the patient's face. This embodiment clarifies multiple methods for obtaining the face mesh model, allowing for the selection of different methods to meet varying needs and expanding the application scenarios of this application.

[0030] In some embodiments, the step of obtaining the face model by stitching and fusing multi-angle facial photos of the patient includes: removing the background from the multi-angle facial photos; performing checkerboard pattern processing on the multi-angle facial photos to achieve calibration and stereo correction, and obtaining camera intrinsic parameters; using the parallax information of the multi-angle facial photos and the camera intrinsic parameters to calculate the depth and three-dimensional coordinates of the face in each facial photo; selecting two facial photos taken from different angles as a group for registration, registering at least two different groups of facial photos; fusing the registered groups of facial photos to form a three-dimensional point cloud model; and processing the three-dimensional point cloud model into the facial mesh model. This embodiment clarifies the specific method of obtaining a facial mesh model by stitching and fusing multi-angle facial photos, using checkerboard pattern processing for positioning and correction, making the positioning and correction accurate and feasible, so as to obtain an accurate three-dimensional mesh model through registration.

[0031] In some embodiments, the step of deforming the facial composite model in the initial state according to the initial state and the stage state of a treatment step to obtain the facial prediction model for that treatment step includes: identifying pre-selected dental and jaw feature points on the dental and jaw portion of the facial composite model, denoted as the first position of the dental and jaw feature points; obtaining the second position of the dental and jaw feature points in the facial composite model based on the dental and jaw movement between the initial state and the stage state; calculating the relationship between the movement of the dental and jaw feature points and the change of mesh vertices in the facial composite model using a deformation method based on the first and second positions of the dental and jaw feature points; and deforming the facial composite model based on the dental and jaw movement in the stage state and the change relationship to obtain the facial prediction model corresponding to that treatment step. This embodiment obtains a composite facial model including the associated dental and soft tissue parts of the face, determines the relationship between the dental and soft tissue parts, and then determines the facial shape change relationship based on the known changes in the dental and soft tissue parts in the orthodontic plan. This change relationship is then used to predict the positional changes of other parts. Since prediction can be made using only the patient's own data, without needing to combine a large amount of historical data to infer the change relationship, the facial shape prediction method in this application involves a small amount of data in the prediction calculation and has high accuracy. Furthermore, the target positions of multiple orthodontic steps can be predicted separately, allowing for the establishment of multiple facial prediction models. This facilitates comparison of intermediate changes when providing the model to the user. Additionally, this embodiment limits the prediction of a single facial prediction model to using known changes in the position of dental and soft tissue feature points. The movement of these feature points and the positional changes of network vertices in the model are calculated through deformation to obtain a facial prediction model that more closely matches the actual post-treatment state.

[0032] In some embodiments, the deformation method includes: using interpolation deformation functions, polynomial interpolation, radial basis function interpolation, Kriging interpolation, local interpolation methods, or calculations based on machine learning methods.

[0033] In some embodiments, the interpolation deformation function is a thin-plate spline interpolation function. This embodiment specifies a thin-plate spline interpolation function and introduces a Gaussian kernel function to participate in the calculation, so that the deformation changes conform to the deformation law of soft tissue, with greater changes closer to the moving tooth and smaller changes further away, making the prediction results more accurate.

[0034] In some embodiments, obtaining a face prediction model specifically includes: adding texture to the established face prediction model based on the texture features of the composite face model. In this embodiment, adding texture to the prediction model makes the model's appearance closer to a real face. Furthermore, the model can be updated based on the original texture to make the model more realistic. Attached Figure Description

[0035] 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.

[0036] Figure 1 This is a flowchart of a method for generating an orthodontic treatment plan according to one embodiment of this application;

[0037] Figure 2 This is a flowchart of a method for forming a composite face model in a method for generating an orthodontic treatment plan according to one embodiment of this application;

[0038] Figure 3 This is a flowchart of a method for obtaining a face mesh model in a method for generating an orthodontic treatment plan according to an embodiment of this application;

[0039] Figure 4 This is a flowchart of a deformed human face composite model in a method for generating an orthodontic treatment plan according to one embodiment of this application;

[0040] Figure 5 This is a flowchart of a method for generating an orthodontic treatment plan according to another embodiment of this application;

[0041] Figure 6 This is a flowchart of a deformed human face composite model in a method for generating an orthodontic treatment plan according to another embodiment of this application;

[0042] Figure 7a This is a schematic diagram of the dental portion of a composite face model in a method for generating an orthodontic treatment plan according to one embodiment of this application;

[0043] Figure 7b This is a schematic diagram of the soft tissue portion of a composite face model in a method for generating an orthodontic treatment plan according to one embodiment of this application;

[0044] Figure 8a This is a rendering of a lateral facial radiograph used in a method for generating an orthodontic treatment plan according to one embodiment of this application;

[0045] Figure 8b yes Figure 8a The black and white version;

[0046] Figure 9 This is a rendering of a composite face model in a method for generating an orthodontic treatment plan according to one embodiment of this application;

[0047] Figure 10 This is a diagram showing the alignment of a lateral view with the midline of a composite face model in a method for generating an orthodontic treatment plan according to one embodiment of this application.

[0048] Figure 11a This is a schematic diagram of a composite face model before deformation in a method for generating an orthodontic treatment plan according to one embodiment of this application;

[0049] Figure 11b This is a schematic diagram of a deformed composite face model in a method for generating an orthodontic treatment plan according to one embodiment of this application;

[0050] Figure 12 This is a schematic diagram of a composite face model with added texture features after deformation in a method for generating an orthodontic treatment plan according to one embodiment of this application;

[0051] Figure 13 This is a schematic diagram of an electronic device according to another embodiment of this application. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the various embodiments of this application will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details have been provided in the various embodiments of this application to help readers better understand 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 the convenience of description and should not constitute any limitation on the specific implementation of this application. The various embodiments can be combined with and referenced by each other without contradiction.

[0053] The terms "anterior region" and "posterior region" mentioned in the various embodiments of this application are defined according to the classification of teeth in the 2nd edition of *Introduction to Stomatology*, published by Peking University Medical Press, pages 36-38. The posterior region includes premolars and molars, teeth marked as 4-8 using the FDI notation. The anterior region includes teeth marked as 1-3 using the FDI notation, and the teeth in the anterior region include central incisors, lateral incisors, and canines.

[0054] The “occlusal plane” mentioned in the various embodiments of this application is obtained according to the definition and confirmation method on page 83 of the 6th edition of Orthodontics. One method is to connect the occlusal midpoint of the first permanent molar with the midpoint between the upper and lower central incisors (at the 1 / 2 point of overbite or open bite); the other method is to divide the occlusal contact points of the posterior teeth equally, and the occlusal contact points of the first permanent molar and the first deciduous molar or the first premolar are often used.

[0055] To address the aforementioned technical problems, the inventors of this application conducted in-depth research on the design process of orthodontic treatment plans. They proposed evaluating the generated treatment plans, and that the evaluation factors are not limited to commonly used medical considerations but should also consider the actual impact on the user's appearance. This ensures that the resulting orthodontic treatment plan can better improve the user's appearance after treatment, better meet the user's actual needs, and increase user satisfaction with the treatment results. In this process, a multi-dimensional evaluation method can be used to optimize different treatment plans, allowing for a more flexible approach to obtaining a treatment plan that satisfies the user.

[0056] Some embodiments of this application can predict the facial appearance corresponding to the target state of different orthodontic treatment plans based on multiple treatment options, and obtain facial prediction models through computer algorithms to conduct multi-dimensional evaluation of different facial prediction models. The evaluation process can not only automatically evaluate using multiple parameters (such as the degree of tooth alignment, number of treatment steps, etc.), but also incorporate the user's actual needs (smile aesthetics, overall appearance aesthetics, etc.), increasing the influence of the user's decision in the evaluation to achieve a more personalized orthodontic plan. Other embodiments further consider the user's facial appearance during the orthodontic process, combining multiple stages of each treatment plan in addition to the target state, to provide a more comprehensive evaluation of each plan. Still other embodiments can also use appearance prediction to evaluate a single orthodontic plan in multiple stages, combining the target state and multiple stages of the treatment to optimize the plan with an evaluation method that better meets the user's needs. When a state that better meets the user's actual needs is found in the intermediate stage, the orthodontic process can be terminated early, saving the user time, money, and experience, and improving user satisfaction with the orthodontic plan.

[0057] In some embodiments, the selection of the optimal orthodontic treatment plan can be based on the evaluation of the face prediction model of the target state. In some embodiments, the evaluation of the face prediction model may include: the evaluation of the facial shape state, such as the smile curve. In other embodiments, it may also be combined with the orthodontic step count parameter to reach the target state, so as to comprehensively consider the external contour of the face and the dental arch condition in the mouth.

[0058] In some embodiments, when selecting the optimal stage state as the treatment target for a treatment plan, it can be based on the evaluation of the face prediction model of the stage state. The evaluation of the face prediction model of each stage state is similar to the evaluation of the face prediction model of the target state. Different parameters can be selected to evaluate the facial appearance state at that time, and / or combine the teeth alignment, and / or the orthodontic steps required to reach that time state for evaluation.

[0059] In some embodiments, when selecting the optimal treatment plan, the above two methods can be combined. In addition to selecting the face prediction model of the final target state for evaluation, the face prediction models of the stage states in each treatment plan can also be selected for combined evaluation.

[0060] In some embodiments, the evaluation of the face prediction model can be performed using one parameter or multiple parameters simultaneously. The evaluation can be performed automatically by a computer, by a user through instructions, or by a combination of computer and user evaluation, offering a variety of flexible options.

[0061] The following is a detailed description of the implementation details of the method for generating an orthodontic treatment plan in this embodiment. The following content is only for ease of understanding and is not necessary for implementing this solution:

[0062] One embodiment of this application relates to a method for generating an orthodontic treatment plan, the specific process of which can be as follows: Figure 1 As shown, it includes:

[0063] Step 101: Obtain the patient's initial facial composite model, which includes the dental and jaw portion and the soft tissue portion.

[0064] Step 102: Obtain P treatment plans for each patient, with each treatment plan corresponding to a target state of tooth and jaw movement.

[0065] Step 103: Based on the jaw movement of P treatment plans, deform the composite face model and obtain the corresponding P target state face prediction models.

[0066] Step 104: Among the P correction schemes, select the optimal correction scheme as the target correction scheme based on the evaluation of the face prediction model of the target state.

[0067] The method for generating orthodontic treatment plans in this embodiment provides users with a reference for selecting treatment plans by predicting changes in facial features under target states within the treatment plan. Specifically, it predicts changes in facial features under target states for multiple treatment plans, and then evaluates the obtained facial prediction models to select the best treatment plan. This results in a treatment plan that better meets the user's expectations and improves the user experience.

[0068] It should be noted that the method for generating an orthodontic treatment plan in this embodiment can be implemented by hardware or a combination of computer software and hardware. For hardware implementation, the method for generating an orthodontic treatment plan can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, other electronic devices for implementing the function of generating an orthodontic treatment plan, or a selection of combinations of the above devices.

[0069] In step 101, the resulting composite face model is a three-dimensional model that includes the associated dental and occlusal parts and soft tissue parts. The dental and occlusal part may only include the upper and lower jaw dentition, such as... Figure 7a As shown, this method is applied to cases involving only tooth movement, resulting in simplified data for subsequent analysis. It can also include parts of the jawbone and skull in addition to teeth and dentition, making it suitable for cases with both tooth and jaw movement, providing more complete data for subsequent analysis. In some embodiments, the soft tissue portion mainly includes the external appearance, i.e., the outer contour of the soft tissue, such as... Figure 7b As shown above. Figure 7a and Figure 7b The images are presented in black and white, but in some embodiments, color images may also be used, which will not be listed here.

[0070] In some embodiments, the method for forming the face composite model in acquiring the face composite model in the patient's initial state is as follows: Figure 2 As shown, it specifically includes:

[0071] Step 201: Acquire lateral facial radiographs and side profile photos of the patient, register and fuse them to form a composite image.

[0072] In some embodiments, the lateral facial radiograph and profile photograph can utilize pre-orthodontic data currently collected by the doctor. For example, the lateral facial radiograph is a projection of the skull at a 90-degree angle to the head, and is the most commonly used X-ray for orthodontic measurements. The original profile photograph is a two-dimensional photograph taken from a side view (left or right), and can be in color or black and white. Based on the profile photograph and the lateral facial radiograph, image fusion and feature recognition methods can be used to register and align the lateral radiograph and profile photograph, and obtain the marked feature points on the teeth (i.e., dentofacial feature points), such as... Figure 8a and Figure 8b Feature points on the dental arch (such as those indicated by label A), or such as Figure 8a and Figure 8b Feature points on the midjaw (as indicated by label B).

[0073] Specifically, this step involves identifying pre-selected facial contour feature points on the acquired lateral facial radiographs and profile photos of the patient; and then registering and fusing these facial contour feature points to form the composite image. In one embodiment, the facial contour feature points on the lateral facial radiographs can be as follows: Figure 8a and Figure 8b The label C indicates this. In this embodiment, facial contour feature points are acquired from various images for registration. Since lateral facial images simultaneously contain both the jaw and part of the facial contour, the fusion process is highly feasible, resulting in a composite image with rich feature information and more selectable feature points, facilitating subsequent 3D model registration. Specifically, the pre-selected facial contour feature points include the tip of the nose and the protrusions of the upper and lower lips. In this embodiment, the tip of the nose and the protrusions of the upper and lower lips are used as facial contour feature points for registration. These points have distinct features and are more accurately identified during acquisition, ensuring registration accuracy in subsequent registration.

[0074] Step 202: Obtain the face mesh model and the dental model respectively. Register and fuse the face mesh model and the dental model based on the composite image to form the composite face model. This embodiment forms a composite face model by registering and fusing the face mesh model and the dental model, resulting in a composite face model that possesses associated dental and jaw components and soft tissue components representing appearance. Since the methods for obtaining the face mesh model and the dental model are relatively simple, the generation of the composite face model in this embodiment is reliable and easily promoted, while also reducing the difficulty of data collection at the terminal. This embodiment further uses a lateral facial image with both dental and jaw features and some facial contour features, along with a profile photo with facial contour features, for registration and fusion to form a composite image including rich dental and jaw features and facial contour features. This composite image is used as a registration reference for the 3D model. The rich selection of parameters during registration makes the registration result more accurate. Figure 9 The image shown is a rendering of a composite face model formed by fusing a face mesh model 10 with a jaw and dentition model 20 that includes the teeth.

[0075] In some embodiments, the obtained facial mesh model can be obtained by stitching and fusing multi-angle facial photos of the patient. The stitching and fusing method can be as follows: Figure 3 As shown, the details are as follows:

[0076] Step 301: Remove the background from face photos taken from multiple angles. In some embodiments, the K-means++ algorithm can be used to remove the background of images taken from different angles. In addition to the K-means++ algorithm mentioned above, other existing tools can also be used for background removal, which will not be listed here.

[0077] Step 302 involves performing checkerboard pattern processing on the multi-angle captured face photos to achieve calibration and stereo correction, thereby obtaining camera intrinsic parameters. In the field of computer vision, camera calibration refers to calculating the camera's intrinsic parameters using computer vision techniques to facilitate subsequent applications such as 3D reconstruction, target tracking, and image processing. The principle of checkerboard calibration utilizes the regular characteristics of a checkerboard pattern in a 3D coordinate system. This step can be divided into two parts: checkerboard image extraction and camera parameter calculation.

[0078] Regarding the chessboard image extraction, some embodiments can be performed as follows: First, prepare a chessboard image, then take a picture of this image with a camera and save it. Next, proceed to the first step—chessboard image extraction. It's important to note that the purpose of chessboard image extraction is to obtain the corner coordinates of the chessboard in the image. This process requires image processing techniques to extract the corner coordinates, including grayscale transformation, image smoothing, and edge detection, which can be determined based on the actual shape and quality of the image. In some embodiments, the image can be converted to grayscale to simplify subsequent image processing operations. Next, the image needs to be smoothed to remove noise. Common smoothing methods include Gaussian filtering and median filtering. Then, edge detection is performed to find the corner coordinates. Classic edge detection algorithms such as the Sobel operator and the Canny operator can be used in this process. Once the corner coordinates are extracted, the second step—camera parameter calculation—can begin.

[0079] Regarding camera parameter calculation, the camera's intrinsic parameters can be calculated using the extracted corner coordinates. Intrinsic parameters include the camera's focal length and optical center. Calculating these intrinsic parameters requires utilizing the coordinate information of the checkerboard grid in a 3D coordinate system. By measuring the side length and number of squares of the checkerboard, its coordinates in the 3D coordinate system can be calculated. Then, using the images captured by the camera and the extracted corner coordinates, a correspondence between pixel coordinates and 3D coordinates can be established, thereby solving for the camera's intrinsic parameters. In some embodiments, the calculation of camera intrinsic parameters can also be combined with the calculation of camera extrinsic parameters, including the camera's rotation and translation matrices. Calculating these extrinsic parameters requires utilizing the coordinate information of the checkerboard grid in a 3D coordinate system and the corner coordinates in the images captured by the camera. By solving for the correspondence between pixel coordinates and 3D coordinates, the camera's rotation and translation matrices, i.e., the camera's extrinsic parameters, can be obtained. Therefore, the calculation of these camera parameters provides fundamental support for subsequent computer vision applications, and calculating both intrinsic and extrinsic parameters can improve the accuracy of subsequent analysis.

[0080] Step 303: Using the disparity information and camera intrinsic parameters of multi-angle face photos, calculate the depth and 3D coordinates of the face in each face photo. Specifically, stereo matching is performed on images from different angles, and the disparity is calculated.

[0081] In some embodiments, after step 303, a point cloud denoising method can also be used to improve the quality of the point cloud data.

[0082] Step 304: Select two face photos taken from different angles as a group for registration, and register at least two different groups of face photos. In some embodiments, the ICP (Iterative Closest Point) method is used to register the two groups of point clouds (e.g., center-left, center-right).

[0083] Step 305: The registered groups of face photos are stitched together to form a 3D point cloud model. In some embodiments, the ICP algorithm is used to stitch together the two groups of point cloud data to form a more comprehensive and consistent point cloud model. Since the data source is face photos, the pixels in the photos can be used as point data to form the point cloud model.

[0084] Step 306: Process the above 3D point cloud model into a face mesh model.

[0085] As can be seen, steps 301-306 above clearly define the specific method of stitching and fusing multi-angle facial photos into a facial mesh model, using checkerboard pattern processing for positioning and correction, making the positioning and correction accurate and feasible, so as to obtain an accurate three-dimensional mesh model through registration.

[0086] Regarding the methods for obtaining the face mesh model, in addition to generating it using the multi-angle face photo stitching and fusion method described above, some embodiments can also directly obtain it by scanning the patient's face. Specifically, existing third-party scanning equipment can be used for the scanning process, which will not be elaborated further here. It is evident that the above embodiments clearly define multiple methods for obtaining the face mesh model, allowing for the selection of different methods to meet different needs and expanding the application scenarios of this application.

[0087] Regarding the acquisition of dental models, if the dental model only includes a portion of the model in the embodiments, it can be obtained by directly scanning the patient's teeth and jaw, or by taking an impression of the patient's teeth and jaw, creating a plaster model, and then scanning the plaster model. If the dental model also includes parts such as the jawbone, it can be obtained by CBCT scanning reconstruction. It is evident that different acquisition methods can be selected based on the actual application scenario, which will not be elaborated further here.

[0088] In some embodiments, this step specifically includes: identifying pre-selected facial contour feature points on the face mesh model; identifying dental and jaw feature points on the dental and jaw model; and registering and fusing the face mesh model and the dental and jaw model to form a composite face model based on the relationship between the pre-selected dental and jaw feature points, the facial contour feature points, and the composite image. The method for identifying dental and jaw feature points can employ existing methods, such as the method for obtaining landmark points in a cephalometric radiograph submitted by ZhengYa Company on March 21, 2021 (application number: CN202110345400.6), or other feature point identification methods, which will not be listed here. In one embodiment, when obtaining landmark points, the type of point can be pre-selected, such as setting pre-selected occlusal feature points, GO points, etc., or the landmark points can be identified first, and then some points can be selected as dental and jaw feature points from the identified landmark points. In one embodiment, when registering the lateral radiograph and the composite face model, the lateral radiograph 30 and the composite face model 10 can be aligned along the midline (e.g., Figure 10 As shown in the figure, the positional relationship between the lateral view and the composite face model is relatively clear, so centerline alignment can be performed directly, which is fast and effective.

[0089] It's worth noting that since data acquired through different methods may differ in size, image data can be calibrated before registration. Specifically, this can be done as follows: Since point cloud data consists of the pixels in the aforementioned photos, the distance between pixels can be calculated using a set scale length. The scale length refers to the actual length of a straight line segment measured at a specific pixel in the registered and fused image, used to calibrate the actual distance between pixels. The scaling ratio is calculated based on the actual length of the same object in both types of image data. By scaling and other methods, the distance between identical feature points in different image data is unified, ensuring consistent image size after calibration and avoiding registration errors.

[0090] Steps 201-202 above are used to form a composite facial model of the patient in their initial state, including the associated dental and jaw portions and soft tissue portions. It is understood that in other embodiments, an integrated intraoral and facial scanning method can be used to directly obtain the fused composite facial model, requiring third-party equipment, but the model acquisition speed is faster.

[0091] In one embodiment, the initial state can be a state before orthodontic treatment or a state during orthodontic treatment. The specific corresponding stage can be selected according to the actual application scenario, and will not be listed one by one here.

[0092] It should be noted that although the composite image formed by registering and fusing lateral facial images and profile photos is used to register and fuse the facial mesh model and the dental model, and this composite image is equivalent to the registration image used in 3D model fusion, in other embodiments, lateral facial images (such as...) can also be used directly. Figure 8a and Figure 8b The image shown is a registration image. The face mesh model and the dental model are registered and fused. Since there are dental and facial contour feature points on the lateral face image, dental and facial contour feature points can be identified on the lateral face image. Then, the face mesh model and the dental model are registered and fused based on these two types of feature points. The registration and fusion process is roughly the same as the above embodiment, and will not be described in detail here.

[0093] In step 102, P treatment plans are obtained for each patient. These treatment plans can be obtained in advance or when prediction is needed. In one embodiment, P is a natural number greater than 1, such as 2, 5, 10, 40, etc., which will not be listed here.

[0094] In one embodiment, the orthodontic plan may include a target state corresponding to jaw movement, which can be presented in the form of text, tables, two-dimensional images, three-dimensional models, etc. The jaw movement may include tooth movement (orthodontic process) or jawbone movement (orthognathic process). Tooth movement can be presented as single tooth movement or as movement of the entire dentition. In one embodiment, the orthodontic plan may also include various options during the orthodontic process, such as whether to extract teeth, whether to remove enamel, and the method of jawbone segmentation, etc., which will not be listed here.

[0095] Regarding the acquisition of treatment plans, some embodiments may use the same tooth arrangement method, while others may use different methods. The tooth arrangement method can be one of the following or any combination thereof: direct step-by-step method, spatial search method, and intermediate interpolation method. Each tooth arrangement method has its own characteristics, resulting in different treatment plans, thus providing users with a wider range of options and increasing their choices. Furthermore, even with the same tooth arrangement method, using different tooth arrangement parameters will still lead to different final tooth arrangement results, resulting in different treatment plans. Additionally, in some embodiments, when the treatment plan requires both orthodontics and orthognathic surgery, the combination of the two can be different, such as orthodontics first then orthognathic surgery, or orthodontics first then orthognathic surgery then orthodontics, thus obtaining different treatment plans.

[0096] In some embodiments, all P orthodontic treatment plans are obtained using the same tooth arrangement method. In other embodiments, at least two of the P orthodontic treatment plans are obtained using different tooth arrangement methods to further increase the richness of the plans.

[0097] Regarding the value of P, P can be a natural number greater than 1, such as 2, 3, 10, or even more. In existing orthodontic / orthognathic design, modifications are rarely made after the treatment plan is generated. Although there may be pre-communication with the patient in the early stages of treatment plan generation, only some parameters are adjusted in the early stages. After the parameters are determined, a corresponding treatment plan is designed, leaving the user with almost no choice. However, in this implementation, different treatment plans can be obtained by setting different tooth alignment methods, different orthodontic methods, and different treatment parameters. Especially for complex cases, there may be more treatment plans, which will not be listed here.

[0098] In step 103, based on the jaw movement of P orthodontic schemes, the deformed facial composite model is obtained, and corresponding to the P target state facial prediction models.

[0099] Regarding the deformed face composite model, we will take the face prediction model in the target state corresponding to a correction plan as an example for explanation. The deformation process is as follows: Figure 4 As shown, it specifically includes:

[0100] Step 401: Identify pre-selected dental and jaw feature points on the dental and jaw portion of the facial composite model, and record them as the first position of the dental and jaw feature points. Specifically, dental and jaw feature points may include points characterizing features such as the shape and position of the teeth and jaws. Several dental and jaw feature points are pre-selected from these. In one embodiment, the pre-selected dental and jaw feature points may include the occlusal contact points of the maxillary first molar and the mandibular first molar, such as... Figure 8a and Figure 8b U6 and L6, as well as the occlusal contact points of the maxillary and mandibular central incisors, such as Figure 8a and Figure 8b L1 in the model. In this embodiment, the occlusal contact point is used as the dental and jaw feature point used in registration. The occlusal contact point has obvious features and is accurately identified, so as to ensure the accuracy and stability of the subsequent registration results. Regarding the method of identifying dental and jaw feature points on the face composite model, you can refer to various existing recognition methods, such as the method for obtaining landmark points in cephalometric radiographs submitted by ZhengYa Company on March 21, 2021 (application number: CN202110345400.6), and the recognition network based on machine learning method for recognizing face composite models, which will not be listed here.

[0101] Step 402: Based on the jaw movement from the initial state to the target state of the treatment plan, obtain the second position of the jaw feature points in the facial composite model. Specifically, the treatment plan can include the position of the teeth and jaws in the digital orthodontic design, such as the target jaw state, which is the positional state of the jaws after orthodontic treatment in the digital design, or multiple successive intermediate states, i.e., the intermediate states of the jaws when reaching the target jaw state. In this embodiment, the target jaw state is taken as the target state relative to the initial state. Correspondingly, the second position of the jaw feature points is the spatial position of each jaw feature point identified when the jaws are in the target state. Its specific expression can be represented by position coordinates, or by the distance difference (equivalent to the movement amount) between the corresponding feature points in the initial state and the target state. There are various representation forms, which will not be listed here.

[0102] Step 403: Based on the first and second positions of the dental and jaw feature points, the deformation method is used to calculate the relationship between the movement of the dental and jaw feature points and the changes in the mesh vertices in the face composite model.

[0103] In some embodiments, the deformation method can be calculated using an interpolation deformation function. In one embodiment, the interpolation deformation function is specifically a thin-plate spline interpolation function. Using an interpolation deformation function for deformation calculation is more suitable for non-rigid deformation, making the predicted soft tissue deformation results more accurate. Moreover, using a thin-plate spline interpolation function as the deformation function and introducing a Gaussian kernel function into the calculation makes the deformation more consistent with the deformation law of soft tissue; the closer to the moving teeth, the greater the change, and the farther away, the smaller the change, making the prediction results more accurate. Combined with a facial composite model, the basic principle of the thin-plate spline interpolation algorithm is as follows:

[0104] Step S1: Establish the mathematical function relationship between control points and prediction points.

[0105] by Figure 11a Taking the positions of control points and prediction points as an example, the control point corresponds to the first position of the dentofacial feature point, and the prediction point corresponds to the second position of the dentofacial feature point. Figure 11b To determine the deformed model shape, the cusp of the maxillary central incisor is selected as the control point. The coordinates of the maxillary central incisor control point are (x0, y0, z0). It is assumed that the movement of the maxillary central incisor is a buccal translation with a translation amount of d. x Then the amount of tooth movement can be expressed as (d x Given that the coordinates of the predicted point are (x1, y1, z1), then x1 = x0 + d. xy1=y0,z1=z0. Based on the interpolation function, a functional relationship between the control points and the prediction points can be established. The interpolation function can be polynomial interpolation, spline function interpolation, etc. In this example, the thin plate spline interpolation function is selected, and its mathematical expression includes (1)-(3), specifically expressed as:

[0106]

[0107]

[0108]

[0109] In the formula, the left side of the equation represents the position coordinates of the predicted point (x1, y1, z1), and the right side of the equation represents a1, a2, a3, a4, a5, a6, a7, a8, a9, a1, a1, a1, a1, a2 ...1, a2, a1, a1 x a y a z and w i These are the coefficients of the interpolation function, N is the total number of control points requiring deformation, and i is the sequence number of all control points requiring deformation. U(||(x) i ,y i ,z i The smoothing kernel function is constructed by )-(x0,y0,z0)||) to determine the distance between the control points and the prediction points. The smoothing kernel function can typically be a spline kernel function or a Gaussian kernel function; here, a Gaussian kernel function is chosen, and its mathematical form is: Where r is the distance between the control point and the prediction point, and σ is the radius of the Gaussian kernel function.

[0110] Step S2: Based on the functional relationship between the control points and prediction points established in Step S1, solve the system of linear equations to obtain the coefficients of the interpolation function.

[0111] Substitute the coordinates of the control points and predicted points into the interpolation mathematical relationship established in step S1, and also substitute the Gaussian kernel function calculated based on the control points and predicted points. Use the Gauss-Seidel method to solve the linear equation system. In addition to the equations determined by the interpolation mathematical relationship in step S1, the linear equation system also introduces four constraint equations for the interpolation coefficients, the expressions of which are as follows:

[0112]

[0113]

[0114]

[0115]

[0116] Thus, a system of linear equations determined by four equations is obtained. The coefficients {a1, a2, ..., a3} of the interpolation function are then calculated using a computer program.x a y a z and w i}, where N is the total number of control points that need to be deformed, and i is the sequence number of the control point that needs to be deformed.

[0117] Those skilled in the art will understand that the above embodiments use the Thin Plate Spline Interpolation (TPS) method as an example to illustrate deformation. In other embodiments, polynomial interpolation, radial basis function interpolation (RBF), Kriging interpolation, local interpolation methods, machine learning-based methods, etc., can also be used to deform the facial composite model, which will not be listed here. The descriptions of various methods are as follows:

[0118] Polynomial interpolation: Polynomial interpolation approximates a given data point by fitting a polynomial function. Common polynomial interpolation methods include Lagrange interpolation and Newton interpolation, which are computationally simple.

[0119] Radial basis function interpolation (RBF): This method uses radial basis functions to interpolate data. Common radial basis functions include Gaussian functions and multi-aperture radial basis functions. RBF interpolation can flexibly handle irregularly distributed data and is also effective for high-dimensional problems.

[0120] Kriging interpolation: Kriging is a geostatistical interpolation method that estimates the value of unknown points by modeling spatial correlations. Kriging can effectively handle spatial correlations and variability.

[0121] Local interpolation methods: These methods interpolate the grid based on local data, such as locally weighted regression and nearest neighbor-based interpolation methods (e.g., K-nearest neighbor interpolation). These methods can provide good interpolation results within a local range.

[0122] Machine learning-based methods: Machine learning techniques, such as neural networks and support vector machines, are applied to interpolation problems. These methods can perform interpolation by learning complex nonlinear relationships between data, but typically require a large amount of training data and computational resources.

[0123] In addition to thin-plate spline interpolation, other spline interpolation methods can be used, such as natural spline interpolation and Hermite spline interpolation, which will not be listed here. Spline interpolation can effectively approximate data points while maintaining smoothness.

[0124] Step 404: Based on the jaw movement and its changing relationship, deform the facial composite model to obtain the facial prediction model corresponding to the orthodontic plan. The jaw movement can be characterized by the amount of movement relative to the initial position or by the spatial coordinates of the target position. In one embodiment, the coefficients obtained in step S2 are substituted into the expression (1-3) to perform interpolation transformation on all pixels of the profile image, resulting in a new profile image. At this point, the prediction of the post-orthodontic facial profile is completed. The coefficients of the interpolation function calculated in step S2 are substituted into the interpolation function expression (1-3). Based on the target position of the state to be predicted, all pixels in the profile image are interpolated, i.e., all pixels in the image are used as control points. Finally, the predicted positions of all interpolated pixels are calculated, and the predicted points of all pixels form the new profile image.

[0125] In some embodiments, a three-dimensional face prediction model is established by the new positions of the grid vertices. Specifically, the new positions of the grid vertices can be used to establish a three-dimensional face prediction model based on the topological relationships in the original face composite model, so as to facilitate viewing, display, comparison, etc., and enable users to obtain intuitive results.

[0126] In some embodiments, such as Figure 12 As shown, the process of building a face prediction model can also include: adding texture to the established face prediction model based on the texture features of the face composite model. Adding texture to the prediction model makes the model's appearance closer to the effect of a real face. In addition, the model can be updated based on the original texture to make the model more realistic. The original texture can be obtained from the initial state of the face composite model obtained in step 101. It should be noted that... Figure 12 The white frame covering the human eye is a privacy protection measure taken to safeguard the individual's portrait rights in the case, and is not a blank area in the generated model.

[0127] As can be seen, steps 401 to 404 above disclose the process of obtaining a face prediction model corresponding to a target state.

[0128] The above embodiments predict the new positions of the model mesh vertices for a certain state. In other embodiments, the orthodontic scheme may include not only one orthodontic step, but also multiple sequentially executed orthodontic steps. Correspondingly, when obtaining the face prediction model, different face prediction models can be obtained for multiple states to compare the differences between the face prediction models under different states. Specifically, the orthodontic scheme includes multiple sequentially executed orthodontic steps, each corresponding to a target position of the dentition; the step of "given the target position of the dentition in the face composite model, based on the change relationship, obtain the new positions of the mesh vertices of the soft tissue part in the face composite model, and establish a face prediction model" is repeatedly executed to establish multiple face prediction models respectively; each of them is established based on one of the multiple sequentially executed orthodontic steps in the orthodontic scheme. It can be seen that predicting the target positions of multiple orthodontic steps separately can realize the establishment of multiple face prediction models, so that when provided to the user, it is convenient for the user to compare the intermediate change process.

[0129] In step 104, among the P correction schemes, the optimal correction scheme is selected as the target correction scheme based on the evaluation of the face prediction model of the target state.

[0130] Regarding the evaluation of face prediction models, some embodiments are based on the following parameters: facial shape state. Since facial shape state is mainly determined by soft tissue, it better meets the user's needs for aesthetically pleasing facial contours. In one embodiment, commonly used parameters for describing facial shape in medicine, such as the smile curve, can be used. The smile curve is obtained from the frontal or side view of the face prediction model and is composed of the incisal edges of the upper teeth exposed from the upper and lower lips. It is also determined by combining the lip line and the gum area exposed when smiling. After calculating the smile curve, the evaluation is based on the curvature of the smile curve and its distance from the upper and lower lip lines. In one embodiment, the closer the various features of the smile curve are to the ideal values, the higher the evaluation of the face prediction model; conversely, the further the various features of the smile curve are from the ideal values, the lower the evaluation of the face prediction model. Since the calculation of the smile curve combines not only tooth position but also soft tissue morphology such as the lip line, the composite model in this embodiment, which includes related dentition and soft tissue parts, can achieve automatic acquisition and calculation of the smile curve. It is understood that the smile curve is an objective evaluation parameter that takes into account aesthetic factors, so it is easy for computers to perform automatic evaluation. This ensures the degree of automation in this embodiment while providing users with more aesthetically pleasing corrective solutions.

[0131] In some embodiments, the evaluation of the face prediction model is determined based on user instructions. For example, the user can directly send instructions including an evaluation score, and the evaluation of each face prediction model is determined by the score. Since the resulting treatment plan needs to closely meet the user's needs, having the evaluation level determined by user instructions increases the user's participation and decision-making power, so that the subsequent treatment plan better meets the user's needs.

[0132] In some embodiments, the evaluation of the face prediction model for the target state is further combined with the following parameters: the number of orthodontic steps required to achieve the target state and / or the degree of tooth alignment. Since both the number of orthodontic steps and / or the degree of tooth alignment affect the treatment outcome, combining the number of orthodontic steps and / or the degree of tooth alignment increases the objectivity of the evaluation, facilitates automatic evaluation, and provides supplementary information for the user. Regarding the number of orthodontic steps, those skilled in the art will know that the number of orthodontic steps directly affects the orthodontic cycle, the cost of orthodontic treatment, etc. In one embodiment, the user may expect a shorter orthodontic duration and lower cost. Therefore, when other effects of the face prediction model are similar, the number of orthodontic steps can be combined, and the fewer the number of orthodontic steps, the higher the evaluation of the face prediction model. In one embodiment, the user may expect to achieve a more perfect degree of tooth alignment. Therefore, when other effects of the face prediction model are similar, the degree of tooth alignment can be superimposed for evaluation, and the higher the degree of tooth alignment, the higher the evaluation of the face prediction model.

[0133] Regarding tooth alignment, in some embodiments, the evaluation of tooth alignment is based on a comprehensive evaluation of multiple objectives, where each objective is a medical element of orthodontics. Since there are multiple medical elements that can be evaluated for tooth alignment, multiple objectives can be selected as needed to participate in the evaluation of tooth alignment in order to obtain a comprehensive and optimal orthodontic treatment plan. In one embodiment, the medical elements of orthodontics are: arch curve, crowding, overbite, overjet, arch protrusion, Spee curve curvature, Bolton index, arch width, arch symmetry, tooth rotation, tooth axial tilt, or tooth torque. In one embodiment, a multi-objective optimization function can be used for calculation, with each objective corresponding to a medical element, so that the comprehensive optimal result among multiple medical parameters is used as the face prediction model with the highest tooth alignment. In one embodiment, when evaluating tooth alignment, all of the aforementioned medical parameters can be selected, or several of them can be selected. For example, selecting one parameter, such as the arch curve, reduces the amount of data involved in the calculation while improving calculation speed, based on accurate evaluation results. Three parameters can be selected to ensure relatively accurate evaluation results while minimizing the amount of data computation. It is understood that tooth alignment, as an objective medical element in orthodontic treatment plan design, participates in the evaluation, allowing for an objective assessment of the treatment plan. In one embodiment, the elements participating in the evaluation of tooth alignment can also be selected by the user. Since different patients may have different needs and perceptions regarding alignment, allowing the user to select the specific elements for evaluating tooth alignment can enhance the personalization of the orthodontic treatment plan design, thus providing a treatment plan that meets the user's individual needs.

[0134] In some embodiments, multiple parameters can be selected for evaluation and combined for evaluation. Combining multiple parameters allows users to consider multiple factors comprehensively, making the evaluation results more reliable. In one embodiment, the user can determine the evaluation level of the face prediction model for the target state based on subjective needs using scoring instructions, selection instructions, etc., such as determining the evaluation level according to the score in the scoring instruction, or selecting the face prediction model with the highest evaluation according to the selection instruction. In another embodiment, the user can specify the parameters and medical elements involved in the evaluation, and the computer can calculate the evaluation score or evaluation level according to predetermined formulas and rules to determine the evaluation level of the face prediction model. In yet another embodiment, user instructions can be combined with computer evaluation. For example, the computer can first provide a predetermined number of face prediction models with higher evaluations, and then the user can further select from the predetermined number of face prediction models to reduce the user's selection range and facilitate the user to select a face prediction model with a higher evaluation more quickly. It can be understood that choosing different evaluation methods can adjust the influence of the user's subjective judgment and objective evaluation on the final evaluation result.

[0135] In one embodiment, if there are more than one parameter involved in evaluating the face prediction model, different weights are assigned to different parameters. Since the impact of multiple parameters on the treatment outcome varies, and different patients pay different attention to different parameters, the importance of the parameters involved in the evaluation can be adjusted by setting weights, so as to obtain evaluation results that better meet the user's needs.

[0136] Regarding the selection of face prediction models based on evaluation results, in some embodiments, only one parameter is used for evaluation, and the optimal face prediction model is directly selected based on the evaluation result of that single parameter. In other embodiments, multiple parameters are used for evaluation, and the optimal face prediction model is selected by comprehensively considering all parameters. This comprehensive optimization can be achieved in various forms. In one embodiment, different parameters can be scored separately and then summed. It is understood that in the scoring method, the optimal face prediction model can be selected based on the highest total score. The summation process can also assign weight values ​​to different parameters; the calculation process after adding weight values ​​will not be elaborated here. In another embodiment, the evaluation results of different parameters can be output, and the optimal face prediction model can be determined by the user's specified method. Furthermore, other comprehensive methods can also be used, which will not be listed here.

[0137] After completing any of the evaluation methods described in the above embodiments, the optimal treatment plan is selected as the target treatment plan. In one embodiment, the target treatment plan can be directly output to the user. Specifically, it can be displayed to the user through a face prediction model via a display device, or it can be displayed in the form of text, images, tables, etc., which will not be listed here.

[0138] As can be seen, the method for generating orthodontic treatment plans in this embodiment provides users with a reference for selecting treatment plans by predicting changes in facial features under target states within the treatment plan. Specifically, it predicts changes in facial features under target states for multiple treatment plans, and then evaluates the obtained facial prediction models to select the best treatment plan, making the generated treatment plan more in line with user expectations and improving user experience. Specifically, by determining the relationship of facial feature changes through known changes in the dentition within the treatment plan, the positional changes of other parts can be predicted based on this relationship. Since prediction can be made using only the patient's own data, without needing to combine a large amount of historical data to infer the relationship of changes, the facial feature prediction method in this application involves a small amount of data in the prediction calculation and has high accuracy. Furthermore, the evaluation of the facial prediction model can integrate multiple evaluation methods, avoiding the problem of current orthodontic plan design relying on a single medical standard evaluation without considering the user's personalized needs. This provides users with a richer and more comprehensive evaluation method, enhances the consideration of aesthetic factors in orthodontic plan design, and better meets the user's actual needs for orthodontic treatment.

[0139] Another embodiment of this application also relates to a method for generating an orthodontic treatment plan. The difference between this embodiment and the previous embodiment is that, in the previous embodiment, when evaluating the face prediction model in the orthodontic treatment plan, the face prediction model was only obtained for the target state of the orthodontic treatment plan. In this embodiment, in addition to considering the target state, the various stages of the orthodontic treatment plan are also considered. In addition to predicting the facial deformation of the target state, the facial deformation of the intermediate stages is also predicted. Furthermore, the evaluation combines the target state and the intermediate stages for a comprehensive evaluation, so that the generated target orthodontic treatment plan better meets the user's comprehensive and diverse expectations.

[0140] Specifically, in some embodiments, the treatment plan also includes multiple stages through which the teeth and jaws move from an initial state to a target state. Especially in the orthodontic stage, the treatment plan needs to go through multiple intermediate stages; some stages may adjust the force applied by the orthodontic appliance, and some stages may change the type of orthodontic appliance used. If the treatment plan includes an orthognathic stage, which involves the segmentation and movement of bone blocks and can be achieved by orthognathic surgery, it can be expressed as a single stage in the treatment plan. The combination of the orthognathic and orthodontic stages can still have different order, such as orthodontics first, orthognathic surgery first, or orthodontics first, then orthognathic surgery, and so on. When the orthognathic stage is the final stage of the entire treatment plan, the goal of the orthognathic stage is taken as the target state of the treatment plan; when the orthognathic stage is not the final stage of the entire treatment plan, the target state of the orthognathic stage is taken as an intermediate stage.

[0141] The method for generating an orthodontic treatment plan in this embodiment may further include: obtaining different face prediction models corresponding to different stage states. It can be understood that obtaining each face prediction model is similar to obtaining the face prediction model for the target state. Different face prediction models can be obtained based on the different jaw movements corresponding to different stages, so the process of obtaining face prediction models for each stage state will not be elaborated further. Correspondingly, in this embodiment, the process of selecting the optimal orthodontic plan as the target orthodontic plan based on the evaluation of the face prediction model for the target state among P orthodontic plans specifically includes: selecting the optimal orthodontic plan as the target orthodontic plan based on the evaluation of the face prediction model for the target state and the evaluation of the face prediction models for each stage state among the P orthodontic plans.

[0142] In some embodiments, the evaluation parameters selected for evaluating the face prediction model at each stage can be the same as those selected in the previous embodiment for evaluating the face prediction model at the target state, or different parameters can be selected for evaluation. In this case, the user can specify parameters of greater concern to participate in the evaluation, while removing the user-specified non-concern parameters. The selection of evaluation methods is flexible and convenient, and will not be listed one by one here.

[0143] In some embodiments, the optimal treatment plan is selected as the target treatment plan based on the evaluation of the face prediction model for the target state and the evaluation of the face prediction models for each stage state. This includes: selecting the optimal treatment plan as the target treatment plan based on the evaluation of the face prediction model for the target state and the evaluation of the face prediction models for some stage states. Since the invisible orthodontic process is divided into multiple steps with many intermediate stages, only some stage states can be evaluated to reduce the amount of data processing while obtaining accurate evaluation results. It is understood that the number of face prediction models participating in the evaluation can be limited. For example, all face prediction models for intermediate stage states can be selected as evaluation subjects, or only face prediction models for some stage states can be selected for evaluation. Furthermore, when selecting some stages for evaluation, some consecutive stages can be selected, such as selecting several consecutive stages close to the target state, or some stage states can be selected at intervals, such as selecting several stages with even intervals from the initial state to the target state, or selecting several stages with intervals close to the target state, in order to reduce the amount of data involved in the evaluation while maintaining sufficient accuracy. At the same time, the difference between the states of two adjacent stages involved in the evaluation is increased to improve the evaluation efficiency.

[0144] In some embodiments, when comprehensively evaluating the face prediction model for the target state and the face prediction models for multiple stages, a multi-objective optimization approach can be adopted. The evaluation results of the face prediction models for each state participating in the evaluation within each treatment plan are used as one of the objectives to calculate the optimal comprehensive treatment plan. In one embodiment, each objective can also be assigned a weight value, adjusting the influence of different objectives in the evaluation as needed.

[0145] Regarding the acquisition of treatment plans, in some embodiments, at least two treatment plans are obtained using intermediate interpolation. Specifically, the intermediate interpolation method can refer to the digital tooth alignment method disclosed in application number CN202110746416.8, so that the teeth at the designed target position are accurately aligned relative to the target dental arch curve, and the result objectively meets medical indicators and aesthetic requirements. Specifically, the initial state of the patient's teeth before treatment can be obtained, and the doctor determines the final target state based on the initial tooth state. Using computer algorithms, interpolation is performed in the middle from the initial state to the target state. The target state can be the designed target state at the end of orthodontic treatment, or it can be a stage target state during the treatment process. That is to say, during the entire orthodontic stage, the teeth can go from the initial state through several stage target states in sequence, and finally reach the designed orthodontic target state, so that the teeth can move smoothly from the initial state to the target state. For changes in adjacent stage target states, interpolation calculations are also used to move the teeth from the previous stage target state to the next stage target state. Those skilled in the art will understand that, although the target state (such as the target position of the dentition) of the orthodontic treatment plan obtained by the intermediate interpolation method is the same, the number and position of the intermediate interpolations can still be adjusted according to different needs. Therefore, even if different orthodontic plans all use the intermediate interpolation method for tooth arrangement, the resulting tooth arrangement plans will still be different. Furthermore, different intermediate stages may result in different tooth alignment and facial morphology during the treatment process. For doctors, achieving the target state is sufficient, but for patients, the overall appearance must be considered throughout the entire treatment cycle. Therefore, although orthodontic treatment primarily aims for aesthetic results, the lengthy treatment process cannot be ignored in the design of the treatment plan. If two orthodontic plans, A and B, have similar final target states but significant differences in intermediate stages, and plan A shows a significantly better facial appearance in the intermediate stages than plan B, then to ensure the patient maintains a more aesthetically pleasing appearance during treatment, plan A should be preferred to better meet the patient's actual needs.

[0146] Furthermore, regarding the acquisition of orthodontic plans, some embodiments can employ a direct step-by-step method. For details, please refer to the direct step-by-step method for generating orthodontic states disclosed in patent application number CN201410831582.8. After obtaining a dental model segmented into individual teeth, target parameters for tooth arrangement are determined. These can include multiple medical factors such as arch curve, crowding, interdental enamel removal, overbite, overjet, arch protrusion, Spee curve curvature, Bolton index, arch width, arch symmetry, tooth rotation, tooth axial tilt, tooth torque, and midline. A multi-objective optimization function is then used to calculate and obtain a tooth arrangement plan with fewer steps. In other words, the selection and weighting of target parameters can be adjusted as needed to obtain orthodontic plans for different target states and different stages.

[0147] In addition, regarding the acquisition of the orthodontic plan, spatial search method can be used in some embodiments. For details, please refer to the method for obtaining the target orthodontic state of teeth in the published patent application number CN201410006532.6.

[0148] It is worth mentioning that the above embodiments obtain different orthodontic solutions through different tooth alignment methods. In other embodiments, different tooth alignment methods can be combined to obtain different orthodontic solutions. For example, in one embodiment, the three orthodontic solutions to be selected can be obtained through the direct step-by-step method, the spatial search method, and the intermediate interpolation method, respectively. In another embodiment, four of the five orthodontic solutions to be selected can be obtained through the direct step-by-step method, and the other through the spatial search method. In yet another embodiment, two of the five orthodontic solutions to be selected can be obtained through the direct step-by-step method, two through the spatial search method, and the third through the intermediate interpolation method. Those skilled in the art will understand that the selection of various tooth alignment methods can be chosen according to needs. Only one tooth alignment method can be used in one embodiment, or multiple tooth alignment methods can be used in one embodiment. The specific selection methods are flexible and varied, and will not be listed one by one here.

[0149] As can be seen, in this embodiment, when selecting multiple orthodontic options, in addition to evaluating the face prediction model for the target state of each option, the evaluation also incorporates the face prediction models for the intermediate states within these options. This combination of intermediate states (excluding the target state) allows for a comprehensive consideration of the entire orthodontic process during evaluation. Since orthodontic treatment is lengthy, and considering that patients require not only a superior final target state but also optimal states at each intermediate stage, evaluating both the target and intermediate states separately and selecting the most comprehensive and optimal orthodontic option ensures a satisfactory intermediate process. This approach improves user satisfaction with intermediate states, better meets their actual needs, and increases their willingness to wear the treatment.

[0150] Another embodiment of this application also relates to a method for generating an orthodontic treatment plan. This embodiment is largely the same as the above embodiment, with the main difference being that: in the above embodiment, multiple orthodontic treatment plans are selected, while in this embodiment, an evaluation is performed on different stages based on an orthodontic treatment plan in order to select a more suitable target state, thereby generating an orthodontic treatment plan that better meets the user's needs.

[0151] The method for generating an orthodontic treatment plan in this embodiment is as follows: Figure 5 As shown, the details are as follows:

[0152] Step 501: Obtain the patient's initial facial composite model, which includes the dental and jaw portion and the soft tissue portion. Specifically, this step is similar to step 101 in the first embodiment, and will not be repeated here to avoid repetition.

[0153] Step 502: Obtain the patient's orthodontic plan, which includes N sequentially executed orthodontic steps to achieve tooth and jaw movement from the initial state to the target state. Each orthodontic step corresponds to a stage state.

[0154] Step 503: Based on the initial state and the stage state of a correction step, deform the composite face model of the initial state to obtain the face prediction model for that correction step. This step is explained using the example of obtaining the face prediction model corresponding to the stage state of a correction step; the deformation process is as follows... Figure 6 As shown, it specifically includes:

[0155] Step 601: Identify pre-selected dental and jaw feature points on the dental and jaw portion of the face composite model and obtain the first position of the dental and jaw feature points.

[0156] Step 602: Based on the jaw movement from the initial state to the current stage state, obtain the second position of jaw feature points in the face composite model.

[0157] Step 603: Based on the first and second positions of the dentofacial feature points, a deformation method is used to calculate the relationship between the movement of the dentofacial feature points and the changes in the mesh vertices in the face composite model. In some embodiments, this is calculated using an interpolation deformation function. In some embodiments, the interpolation deformation function is a thin-plate spline interpolation function. This embodiment limits the thin-plate spline interpolation function and introduces a Gaussian kernel function to participate in the calculation, making the deformation conform to the deformation law of soft tissue, with greater changes closer to the moving teeth and smaller changes further away, making the prediction results more accurate. Specifically, the deformation process in this step is similar to that in step 403 of the aforementioned embodiments, and will not be described again here to avoid repetition.

[0158] Step 604: Based on the dental arch movement and the variation relationship, deform the composite human face model to obtain a human face prediction model corresponding to this orthodontic treatment step. That is, based on the dental arch movement from the initial state to this stage state, the starvation, and the variation relationship obtained in step 603, deform the composite human face model obtained in step 501, and then obtain a human face prediction model corresponding to this stage state.

[0159] It can be understood that the acquisition of a human face prediction model for one state is completed through the above steps 601 to 604. In specific applications, this state is the final target state or an intermediate stage state designed. The deformation calculation process is roughly the same, so it is roughly the same as steps 401 to 404 in the foregoing embodiments. To avoid repetition, it will not be elaborated here.

[0160] Step 504: Obtain M human face prediction models corresponding to the stage states of M orthodontic treatment steps. That is, these M orthodontic treatment steps are selected from N sequentially executed orthodontic treatment steps. In one embodiment, the M orthodontic treatment steps are selected from the k-th orthodontic treatment step to the N-th orthodontic treatment step, where k, N, and M are natural numbers greater than or equal to 1, and k and M are less than or equal to N. The process of selecting M from the k-th orthodontic treatment step to the N-th orthodontic treatment step is further described: In some embodiments, it can be set that k = N - M. In one embodiment, taking N as 40 and k as 15 as an example for illustration, it is calculated that M = 40 - 15 = 25. That is, when selecting orthodontic treatment steps, 25 orthodontic treatment steps after the 15th orthodontic treatment step are selected from 40 orthodontic treatment steps. In one embodiment, k can be greater than or equal to N / 2. Taking N as 40 and k as 25 as an example for illustration, it is calculated that M = 40 - 25 = 15. That is, when selecting orthodontic treatment steps, 15 orthodontic treatment steps after the 25th orthodontic treatment step are selected from 40 orthodontic treatment steps. In other embodiments, it can be set that k < N - M. In one embodiment, taking N as 40 and k as 15 as an example for illustration, when selecting orthodontic treatment steps, 10 or 15 orthodontic treatment steps can be selected from the 15th orthodontic treatment step to the 40th orthodontic treatment step among 40 orthodontic treatment steps. It can be understood that this can avoid selecting all orthodontic treatment steps within this stage, reduce the participation of orthodontic treatment steps in judgment, so as to reduce the amount of data participating in evaluation. From the perspective of the entire orthodontic treatment cycle, generally, the stage state closer to the target state is more in line with the ideal orthodontic treatment goal. Relatively speaking, in the early stage of the orthodontic treatment cycle, since it is far from the ideal goal, the possibility of a state meeting the orthodontic treatment goal is low. Therefore, on the basis of ensuring that the stage state meeting the user's needs is made, the amount of data participating in evaluation should be reduced as much as possible to speed up the subsequent evaluation speed.

[0161] It can be understood that step 504 repeatedly executes step 503, and the number of repetitions is determined according to the M human face prediction models to be obtained.

[0162] Step 505: Among the M stage states, select the optimal stage state as the correction target based on the evaluation of each face prediction model.

[0163] The evaluation of the face prediction model in the current stage state is similar to the evaluation process of the face prediction model in the target state in step 104 of the aforementioned embodiments. Different parameters can be selected to evaluate the facial appearance at that time. In some embodiments, the tooth alignment and / or the number of orthodontic steps required to reach the current state can also be combined for evaluation. The parameter selection method and evaluation method are similar, and will not be described in detail here to avoid repetition.

[0164] Step 506: Update the treatment plan based on the treatment goals.

[0165] In some embodiments, the update method can directly delete the orthodontic steps after the optimal stage state selected in step 505, which is equivalent to using the optimal stage state as the design target state of the orthodontic plan. In some embodiments, the optimal stage state can be used as the design target state, and then the tooth arrangement can be redesigned using intermediate interpolation methods to obtain a more suitable orthodontic plan to replace the original orthodontic plan. Those skilled in the art will understand that, in addition to the above-described update methods, other update methods can also be used, which will not be listed here.

[0166] As can be seen, this embodiment predicts facial features at each stage, obtaining different facial prediction models. These models are then evaluated, and the stage with the best evaluation is selected as the new treatment goal. Furthermore, since different users have different actual needs for orthodontic treatment, their available time and financial resources also differ. Therefore, whether to use the original final goal as the treatment completion target can be adjusted according to the user's actual needs. For example, considering the treatment steps, if the facial features and dentition alignment are roughly similar in the 20 steps before the final design goal, the user can end the treatment plan earlier if they want to save on economic and time costs. However, if the user wants a more perfect facial appearance, they can continue treatment to achieve the most perfect facial appearance. Thus, this embodiment uses evaluation to comprehensively assess the treatment design goals, allowing users to consider time, financial costs, and the final orthodontic effect, improving the flexibility of their treatment options. Furthermore, this embodiment specifically obtains a composite facial model including the associated dental and soft tissue parts of the face, determines the relationship between the dental and soft tissue parts, and then determines the facial shape change relationship through known changes in the dental and soft tissue parts in the orthodontic plan. This change relationship is then used to predict the positional changes of other parts. Since prediction can be made using only the patient's own data, without needing to combine a large amount of historical data to infer the change relationship, the facial shape prediction method in this application involves a small amount of data in the prediction calculation and has high accuracy. In addition, the target positions of multiple orthodontic steps can be predicted separately, allowing the establishment of multiple facial prediction models, which are then provided to the user for comparison of intermediate changes. Furthermore, this embodiment limits the prediction of a single facial prediction model to using known changes in the position of dental and soft tissue feature points. The movement of the feature points and the positional changes of the network vertices in the model are calculated through deformation to obtain a facial prediction model that more closely matches the actual state after orthodontic treatment.

[0167] It should be noted that the examples described above in this embodiment are merely illustrative for ease of understanding and do not constitute a limitation on the technical solution of the present invention.

[0168] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split 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.

[0169] Another embodiment of this application relates to an electronic device, such as... Figure 13As shown, it includes: at least one processor 801; and a memory 802 communicatively connected to at least one processor 801; wherein the memory 802 stores instructions executable by at least one processor 801, the instructions being executed by at least one processor 801 to enable at least one processor 801 to perform the methods for generating oral orthodontic solutions in the above embodiments.

[0170] 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.

[0171] 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.

[0172] Another embodiment of this application relates to a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the method embodiments described above.

[0173] 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 USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0174] Those skilled in the art will understand that the above embodiments are specific embodiments for implementing this application, and in practical applications, various changes can be made to them in form and detail without departing from the spirit and scope of this application.

Claims

1. A method for generating an orthodontic treatment plan, characterized in that, include: A composite facial model of the patient in their initial state is obtained, the composite facial model comprising: a dental and jaw portion and a soft tissue portion; Obtain P treatment plans for each patient, each with a target state for tooth and jaw movement, where P is a natural number greater than 1. Based on the jaw movement of the P orthodontic schemes, the facial composite model is deformed to obtain P facial prediction models for target states. Among the P corrective options, the optimal corrective option is selected as the target corrective option based on the evaluation of the face prediction model of the target state.

2. The method for generating an orthodontic treatment plan according to claim 1, characterized in that, The orthodontic plan also includes multiple stages that the teeth and jaws go through successively from the initial state to the target state; The method further includes obtaining different face prediction models corresponding to different stage states; Among the P corrective options, the optimal corrective option is selected as the target corrective option based on the evaluation of the face prediction model for the target state, including: Among the P corrective options, the optimal corrective option is selected as the target corrective option based on the evaluation of the face prediction model for the target state and the evaluation of the face prediction model for each stage state.

3. The method for generating an orthodontic treatment plan according to claim 1, characterized in that, The evaluation of the face prediction model for the target state is based on the following parameter: face shape state.

4. The method for generating an orthodontic treatment plan according to claim 2, characterized in that, The evaluation of the face prediction model for the target state is based on the following parameter: face shape state.

5. The method for generating an orthodontic treatment plan according to any one of claims 1-4, characterized in that, The evaluation of the face prediction model is determined based on the user's instructions.

6. The method for generating an orthodontic treatment plan according to any one of claims 1-4, characterized in that, The evaluation of the face prediction model for the target state is also based on the following parameters: the number of orthodontic steps required to reach the target state and / or the alignment of teeth.

7. The method for generating an orthodontic treatment plan according to any one of claims 1-4, characterized in that, If there are more than one parameter involved in the evaluation of the face prediction model, different weights are assigned to different parameters.

8. The method for generating an orthodontic treatment plan according to claim 7, characterized in that, If the facial shape state is included among the multiple parameters used to evaluate a face prediction model, then the facial shape state has a higher weight.

9. The method for generating an orthodontic treatment plan according to claim 6, characterized in that, The evaluation of the alignment of teeth is based on a comprehensive evaluation of multiple objectives, where each objective is a medical element of orthodontics.

10. The method for generating an orthodontic treatment plan according to claim 9, characterized in that, The medical elements of orthodontics include: dental arch curve, dental crowding, overbite, overjet, dental arch protrusion, Spee curve curvature, Bolton index, dental arch width, dental arch symmetry, tooth rotation, tooth axial tilt, or tooth torque.

11. The method for generating an orthodontic treatment plan according to any one of claims 1-4, characterized in that, Of the P orthodontic treatment plans, any one of the following methods or any combination thereof is obtained based on one of the following tooth alignment methods: direct step-by-step method, spatial search method, and intermediate interpolation method.

12. The method for generating an orthodontic treatment plan according to claim 11, characterized in that, Of the P orthodontic treatment plans, any two plans are obtained by using different tooth alignment methods.

13. The method for generating an orthodontic treatment plan according to claim 2, characterized in that, Of the P orthodontic options, at least two are based on intermediate interpolation for tooth arrangement.

14. The method for generating an orthodontic treatment plan according to any one of claims 1-4, characterized in that, The step of deforming the facial composite model according to the jaw movement based on an orthodontic plan, and obtaining the corresponding target state facial prediction model, includes: On the dental and jaw portion of the facial composite model, pre-selected dental and jaw feature points are identified and recorded as the first position of the dental and jaw feature points; Based on the jaw movement from the initial state to the target state of the orthodontic scheme, the second position of the jaw feature points in the face composite model is obtained. Based on the first and second positions of the dental and jaw feature points, a deformation method is used to calculate the relationship between the movement of the dental and jaw feature points and the changes in the mesh vertices of the face composite model. Based on the jaw movement and the changes described, the facial composite model is deformed to obtain a facial prediction model corresponding to the orthodontic treatment plan.

15. A method for generating an orthodontic treatment plan, characterized in that, include: A composite facial model of the patient in their initial state is obtained, the composite facial model comprising: a dental and jaw portion and a soft tissue portion; Obtain the patient's orthodontic treatment plan, which includes N sequentially executed orthodontic steps to achieve tooth and jaw movement from the initial state to the target state. Each orthodontic step corresponds to a stage state. Based on the initial state and the stage state of a correction step, deform the facial composite model of the initial state to obtain the facial prediction model of the correction step. M face prediction models are obtained based on the stage states of M correction steps; wherein the M correction steps are selected from the kth to the Nth correction steps, and k, N, and M are natural numbers greater than or equal to 1, and k and M are less than or equal to N; Among the M stage states, the optimal stage state is selected as the correction target based on the evaluation of each face prediction model. The treatment plan is updated based on the stated treatment goals.

16. The method for generating an orthodontic treatment plan according to claim 1 or 15, characterized in that, The process of obtaining the composite face model of the patient in the initial state includes: Acquire a registration image; wherein the registration image is a composite image formed by fusing a lateral view of the patient's face and a profile photograph, or is a lateral view of the patient's face; A face mesh model and a dental model are obtained separately. Based on the registration image, the face mesh model and the dental model are registered and fused to form the face composite model.

17. The method for generating an orthodontic treatment plan according to claim 16, characterized in that, The composite image formed by fusing the patient's lateral facial radiograph and profile photograph includes: Identify pre-selected facial contour feature points on acquired lateral radiographs and profile photos of patients; The composite image is formed by registering and fusing the position of the facial contour feature points.

18. The method for generating an orthodontic treatment plan according to claim 17, characterized in that, The pre-selected facial contour feature points include: the tip of the nose and the protrusions of the upper and lower lips.

19. The method for generating an orthodontic treatment plan according to claim 16, characterized in that, The process of registering and fusing the face mesh model and the dental model based on the registered image to form the composite face model includes: Identify pre-selected facial contour feature points on the facial mesh model; Identify dental and jaw feature points on the dental and jaw model; Based on the relationship between the pre-selected dental and jaw feature points and the facial contour feature points and the registered image, the facial mesh model and the dental and jaw model are registered and fused to form the facial composite model.

20. The method for generating an orthodontic treatment plan according to claim 19, characterized in that, The dental and jaw feature points include: the occlusal contact points of the maxillary first molar and the mandibular first molar, as well as the occlusal contact points of the maxillary central incisor and the mandibular central incisor.

21. The method for generating an orthodontic treatment plan according to claim 16, characterized in that, The face mesh model is obtained through the following methods: Obtained by stitching and fusion of multiple facial photos of the patient from different angles; or... Obtained by scanning the patient's face.

22. The method for generating an orthodontic treatment plan according to claim 21, characterized in that, The data obtained by stitching and fusing multi-angle facial photos of the patient includes: Remove the background from photos of faces taken from multiple angles; The camera internal parameters are obtained by performing checkerboard pattern processing on face photos taken from multiple angles to achieve calibration and stereo correction. Using the parallax information of the multi-angle face photos and the camera intrinsic parameters, the depth and three-dimensional coordinates of the face in each face photo are calculated; Select two facial photos taken from different angles as a group for registration, and register at least two different groups of facial photos; The registered groups of face photos are stitched together to form a three-dimensional point cloud model; The 3D point cloud model is processed into the face mesh model.

23. The method for generating an orthodontic treatment plan according to any one of claims 15, 17-22, characterized in that, The process of deforming the facial composite model of the initial state based on the initial state and the stage state of a correction step to obtain the facial prediction model of the correction step includes: On the dental and jaw portion of the facial composite model, pre-selected dental and jaw feature points are identified and recorded as the first position of the dental and jaw feature points; Based on the jaw movement from the initial state to the current stage state, the second position of the jaw feature points in the face composite model is obtained. Based on the first and second positions of the dental and jaw feature points, a deformation method is used to calculate the relationship between the movement of the dental and jaw feature points and the changes in the mesh vertices of the face composite model. Based on the jaw movement at this stage and the changes described therein, the facial composite model is deformed to obtain a facial prediction model corresponding to this orthodontic step.

24. The method for generating an orthodontic treatment plan according to claim 23, characterized in that, The deformation methods include: using interpolation deformation functions, polynomial interpolation, radial basis function interpolation, Kriging interpolation, local interpolation methods, and calculations based on machine learning methods.

25. The method for generating an orthodontic treatment plan according to claim 24, characterized in that, The interpolation deformation function is a thin plate spline interpolation function.

26. 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 method for generating an orthodontic treatment plan as described in any one of claims 1 to 25.

27. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method for generating an orthodontic treatment plan as described in any one of claims 1 to 25.

Images