A tooth alignment method, device, apparatus and readable storage medium

Abstract

This specification discloses a method, apparatus, device, and readable storage medium for tooth alignment. The method involves determining the dental arch curve on a three-dimensional tooth model containing all teeth, generating two-dimensional images of the teeth based on the arch curve, and inputting each tooth's two-dimensional image into a pre-trained feature point recognition model to obtain feature points for each tooth. The method optimizes the pose of each tooth in the three-dimensional tooth model by using at least one of the following as optimization objectives: the distance between the tooth's feature point and the dental arch curve, and the angle between the tooth's rotation direction and the tangent direction of the dental arch curve. By adjusting the tooth pose, the feature points of the teeth are made to fit the dental arch curve as closely as possible, and / or the tooth's rotation direction is aligned with the tangent direction of the dental arch curve, thereby achieving automatic tooth alignment. This reduces workload while improving the efficiency and accuracy of tooth alignment in orthodontic treatment.

Description

Technical Field

[0001] This specification relates to the field of orthodontic technology, and in particular to a method, apparatus, device and readable storage medium for aligning teeth. Background Technology

[0002] Currently, orthodontic treatment has entered the digital age. Aligned teeth not only ensure healthy teeth and reduce the incidence of oral diseases, but also significantly improve facial appearance. Therefore, tooth alignment has become a primary concern for most orthodontic patients. Whether using fixed braces or clear aligners, tooth alignment requires pre-treatment dental models to determine the desired tooth positions.

[0003] Currently, doctors or designers typically use simulation software based on their own experience to simulate the position and posture of the aligned teeth.

[0004] However, the above solutions rely heavily on the clinical experience of doctors or designers, resulting in a large workload and limited efficiency. Summary of the Invention

[0005] This specification provides a method, apparatus, device, and readable storage medium for teeth alignment, in order to partially solve the aforementioned problems existing in the prior art.

[0006] The following technical solution is adopted in this specification:

[0007] This manual provides a method for aligning teeth, including:

[0008] Obtain a three-dimensional tooth model containing each tooth and the dental arch curve of the three-dimensional tooth model;

[0009] The two-dimensional images of each tooth are determined based on the dental arch curve, and the two-dimensional images of each tooth are input into a pre-trained feature point recognition model to obtain the feature points corresponding to each tooth.

[0010] The pose of the tooth in the three-dimensional tooth model is optimized by taking at least one of the following as optimization objectives: the distance between the position of the feature point of the tooth and the dental arch curve, and the angle between the direction of the tooth's torsion and the tangent direction of the dental arch curve.

[0011] Optionally, the method further includes:

[0012] Based on the coordinates of the feature points of the tooth and the dental arch curve, the distance between the position of the feature points of the tooth and the dental arch curve is determined, which serves as the first evaluation function corresponding to the tooth; the first evaluation function is used to determine the optimization target.

[0013] Optionally, the feature points of the tooth include the mesial point and the distal point; the method further includes:

[0014] The direction of the tooth's rotation is determined based on the coordinates of the tooth's mesial point and distal point.

[0015] The nearest point of the tooth on the dental arch curve is determined as the target point corresponding to the tooth, and the tangent direction of the dental arch curve at the target point corresponding to the tooth is determined.

[0016] Based on the angle between the direction of the tooth's torsion and the tangent direction of the dental arch curve at the target point corresponding to the tooth, a second evaluation function is determined for the tooth; the second evaluation function is used to determine the optimization target.

[0017] Optionally, the method further includes:

[0018] Based on the mesial point of the tooth, the distal point of the tooth, the mesial point of the adjacent tooth, and the distal point of the adjacent tooth, a local curve corresponding to the tooth is generated by a curve fitting algorithm.

[0019] Based on the difference between the local curve corresponding to the tooth and the dental arch curve, a third evaluation function is determined for the tooth; the third evaluation function is used to determine the optimization objective.

[0020] Optionally, the method further includes:

[0021] Based on the mesial and distal coordinates of the tooth, as well as the mesial and distal coordinates of the adjacent teeth, the distance between the tooth and its adjacent teeth in a specified direction is determined. Based on the distance between the tooth and its adjacent teeth in the specified direction, a fourth evaluation function corresponding to the tooth is determined. The fourth evaluation function is used to determine the optimization objective.

[0022] Optionally, the distance between the tooth and its adjacent teeth in a specified direction is determined based on the mesial and distal coordinates of the tooth, and the mesial and distal coordinates of the adjacent teeth. This specifically includes:

[0023] Based on the coordinates of the mesial point of the tooth and the coordinates of the distal point of the first adjacent tooth of the tooth, a first distance in a specified direction is determined between the tooth and the first adjacent tooth of the tooth.

[0024] Based on the coordinates of the distal point of the tooth and the coordinates of the proximal point of the second adjacent tooth of the tooth, determine the second distance between the tooth and the second adjacent tooth of the tooth in a specified direction;

[0025] Based on the first distance and the second distance, the distance between the tooth and its adjacent teeth in a specified direction is determined.

[0026] Optionally, determining a two-dimensional image of each tooth based on the dental arch curve specifically includes:

[0027] Based on the tangent direction, normal direction, and occlusal plane direction of the target point of the tooth on the dental arch curve, construct the dental arch curve coordinate system corresponding to the tooth;

[0028] Based on the three-dimensional tooth model, in the dental arch curve coordinate system corresponding to the tooth, determine at least one of the reference width and reference height of the tooth and the projection plane of the tooth in the two-dimensional image;

[0029] A two-dimensional image of the tooth is obtained based on at least one of the reference height of the tooth, the reference height, and the projection plane of the tooth in the two-dimensional image.

[0030] Optionally, for one tooth of at least one tooth, the method satisfies at least one of the following:

[0031] The target point corresponding to the tooth is the closest point of the first designated feature point of the tooth on the dental arch curve;

[0032] The reference width corresponding to the tooth is the width of the tooth in the tangential direction;

[0033] The reference height corresponding to the tooth is the height of the tooth in the jaw plane direction;

[0034] In the two-dimensional image of the tooth to be generated, the specified width and specified height of the tooth are determined by the reference width and reference height corresponding to the tooth.

[0035] The projection direction corresponding to the tooth is the normal direction of the tooth;

[0036] The projection plane corresponding to the tooth is determined based on the projection direction and the three-dimensional tooth model.

[0037] Optionally, the method further includes:

[0038] For each tooth, its feature points are labeled in the two-dimensional image of that tooth to obtain the target image of that tooth;

[0039] Based on at least one of the following: the normal direction in the dental arch curve coordinate system corresponding to the tooth, the three-dimensional tooth model, and the target image of the tooth, determine the coordinate values ​​of the feature points of the tooth in the tangent direction and the coordinate values ​​in the jaw plane direction in the dental arch curve coordinate system corresponding to the tooth.

[0040] Based on the coordinate values ​​of the feature points of the tooth in the tangent direction and the coordinate values ​​in the jaw plane direction in the dental arch curve coordinate system corresponding to the tooth, the three-dimensional coordinates of the reference point corresponding to the tooth are determined.

[0041] Starting from the three-dimensional coordinates of the reference point corresponding to the tooth, a ray corresponding to the tooth is constructed along the normal direction in the coordinate system of the dental arch curve corresponding to the tooth. The three-dimensional coordinates of the intersection point of the ray corresponding to the tooth and the three-dimensional tooth model are used as the three-dimensional coordinates of the feature point of the tooth.

[0042] Optionally, a feature point recognition model is pre-trained, specifically including:

[0043] Two-dimensional reference images are obtained as training samples, and the teeth represented by the two-dimensional reference images include one of complete teeth and missing teeth;

[0044] Obtain the second designated feature point of the tooth in the two-dimensional reference image as the annotation of the training sample;

[0045] The training samples are input into the feature point recognition model to be trained to obtain predicted feature points;

[0046] The feature point recognition model to be trained is trained with the goal of minimizing the difference between the predicted feature points and the annotations of the training samples.

[0047] This manual provides a teeth alignment device, including:

[0048] The dental arch curve determination module is used to obtain a three-dimensional tooth model containing each tooth and the dental arch curve of the three-dimensional tooth model;

[0049] The feature point determination module is used to determine the two-dimensional image of each tooth based on the dental arch curve, and input the two-dimensional image of each tooth into the pre-trained feature point recognition model to obtain the feature points corresponding to each tooth.

[0050] An optimization module is used to optimize the pose of the tooth in the three-dimensional tooth model, with at least one of the following as optimization targets: the distance between the position of the feature point of the tooth and the dental arch curve, and the angle between the direction of the tooth's torsion and the tangent direction of the dental arch curve.

[0051] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described teeth alignment method.

[0052] This specification provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described teeth alignment method.

[0053] The above-mentioned technical solutions adopted in this specification can achieve the following beneficial effects:

[0054] The tooth alignment method provided in this manual involves determining the dental arch curve on a three-dimensional tooth model containing all teeth, generating two-dimensional images of the teeth based on the dental arch curve, and inputting each tooth's two-dimensional image into a pre-trained feature point recognition model to obtain feature points for each tooth. The optimization objective is to optimize the pose of each tooth in the three-dimensional tooth model using at least one of the following: the distance between the tooth's feature point and the dental arch curve, and the angle between the tooth's rotation direction and the tangent direction of the dental arch curve. By adjusting the tooth pose, the feature points of the teeth are made to fit the dental arch curve as closely as possible, and / or the tooth's rotation direction is aligned with the tangent direction of the dental arch curve, thereby achieving automatic tooth alignment. This reduces workload while improving the efficiency and accuracy of tooth alignment in orthodontic treatment. Attached Figure Description

[0055] Figure 1 This is a flowchart illustrating one method for aligning teeth as described in this manual.

[0056] Figure 2 This is a schematic diagram of a dental arch curve as described in this specification;

[0057] Figure 3 This is a schematic diagram of a tooth in this specification;

[0058] Figure 4 This is a flowchart illustrating one method for aligning teeth as described in this manual.

[0059] Figure 5 This is a schematic diagram of a tooth feature point in this specification;

[0060] Figure 6 This is a schematic diagram of a tooth alignment device provided in this specification;

[0061] Figure 7 The corresponding information provided in this specification Figure 1 A schematic diagram of an electronic device. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0063] In the field of orthodontics, tooth alignment is one of the ultimate goals of treatment. Tooth alignment is also a crucial aspect of orthodontic treatment. Aligned teeth not only ensure healthy teeth and reduce the incidence of oral diseases, but also significantly improve facial appearance. Therefore, tooth alignment has become a major concern and focus for most orthodontic patients.

[0064] Current teeth alignment procedures typically involve importing a 3D digital model of the patient's teeth into simulation software. The dentist then manually operates the software based on their clinical experience to position each tooth in the 3D model as close as possible to the normal dental arch curve and adjust any rotational issues, aiming to obtain a properly aligned 3D digital model. However, this manual adjustment method requires the dentist to make numerous fine-tuning adjustments to the position and posture of each tooth in various directions, resulting in a significant workload. Furthermore, the accuracy of manually adjusting tooth position and posture using simulation software is limited, greatly reducing the efficiency and accuracy of teeth alignment.

[0065] Based on this, this specification provides a method for tooth alignment that adjusts the position and orientation of the teeth so that the characteristic points of the teeth fit the arch curve as closely as possible, thereby achieving automatic tooth alignment. This reduces workload while improving the efficiency and accuracy of tooth alignment in orthodontic treatment.

[0066] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0067] Figure 1 This is a flowchart illustrating a method for aligning teeth provided in this instruction manual.

[0068] S100: Obtain a three-dimensional tooth model containing each tooth and the dental arch curve of the three-dimensional tooth model.

[0069] The tooth alignment method provided in the embodiments of this specification can be executed by an electronic device such as a server used for tooth alignment. Furthermore, during the execution of this method, the trained feature point recognition model involved, the electronic device used for model training, and the electronic device used to execute the method can be the same or different; this specification does not impose any limitations on this.

[0070] In this manual, a 3D scanning device inside the oral cavity can be used to acquire 3D morphological data of each of the user's teeth in advance. Then, the 3D morphological data of each tooth is digitized to obtain a 3D tooth model containing each tooth. Information such as the shape, size, and coordinates of each tooth in the 3D coordinate system of the 3D tooth model can be obtained from the 3D tooth model.

[0071] Therefore, based on the position and morphology of each tooth in the 3D dental model, the user's dental arch curve can be analyzed. The dental arch curve is essentially a curve formed by all the teeth in the maxilla or mandible, reflecting the arrangement relationship between the teeth in the dentition. This includes the maxillary and mandibular dental arch curves. Generally, users requiring orthodontic treatment may have certain problems with their dental arches, such as a narrow arch width or abnormal occlusion. Therefore, the user's own dental arch curve may differ from a normal dental arch curve. Thus, in this specification, based on the morphology and position of the user's teeth as represented by the 3D dental model, the user's own dental arch curve can be determined first. Then, based on a normal reference dental arch curve, the user's own dental arch curve can be corrected to obtain the user's dental arch curve after orthodontic treatment.

[0072] Specifically, feature points can be determined on each tooth in a 3D dental model. Then, a preliminary dental arch curve can be obtained by fitting the selected feature points with a specific function or algorithm. After that, the preliminary dental arch curve obtained above can be optimized based on a normal reference dental arch curve that has been collected or calculated in advance, and finally, the ideal dental arch curve for the user after orthodontic treatment can be generated.

[0073] In an optional embodiment of this specification, the dental arch curve can be determined according to the following scheme:

[0074] First, determine the first designated feature points corresponding to each tooth in the three-dimensional tooth model.

[0075] Specifically, in this specification, since the position of the first designated feature point of each tooth is relatively fixed on each tooth, given that the three-dimensional tooth model can represent the shape and position of each tooth, the position of the first designated feature point corresponding to each tooth can be directly determined on each tooth. The first designated feature point may include one or more of the following: labial incisal feature point, mesobuccal apex, distobuccal apex, cusp apex, meslingual apex, and distolingual apex.

[0076] In practical applications, the first designated feature points corresponding to each tooth can be of the same type, such as all being labial incisal feature points. Alternatively, feature points of the appropriate type can be selected based on different tooth types. For example, for incisors, the mesiobuccal apex and distobuccal apex can be selected as feature points for one incisor; for canines, the cusp apex can be selected; and for molars, the mesiobuccal apex, mesilingual apex, distobuccal apex, and distolingual apex can be selected. In practical applications, either of these two methods can be flexibly chosen to determine the first designated feature points for each tooth. This specification does not limit the type or specific number of the first designated feature points corresponding to each tooth.

[0077] Then, based on the first designated feature points corresponding to each tooth, a dental arch curve is generated using a curve fitting algorithm. The dental arch curve includes the maxillary dental arch curve and the mandibular dental arch curve.

[0078] Using a curve fitting algorithm, a curve is fitted to the first specified feature points corresponding to each tooth in the maxilla, serving as the dental arch curve for the maxilla. Similarly, a curve is fitted to the first specified feature points corresponding to each tooth in the mandible, serving as the dental arch curve for the mandible. Figure 2 As shown, the left image is a horizontal cross-sectional view of the maxillary dentition, with the straight line representing the maxillary dental arch curve, and the right image is a horizontal cross-sectional view of the mandibular dentition, with the dashed line representing the mandibular dental arch curve.

[0079] The curve fitting algorithm used above can be any existing type of curve fitting algorithm, such as least squares method, polynomial fitting, spline difference, genetic algorithm, etc., and this specification does not limit it.

[0080] S102: Determine the two-dimensional image of each tooth based on the dental arch curve, and input the two-dimensional image of each tooth into a pre-trained feature point recognition model to obtain the feature points corresponding to each tooth.

[0081] In practical applications, a two-dimensional image of each tooth can be acquired using medical image acquisition equipment. Furthermore, since a three-dimensional tooth model has already been obtained using a three-dimensional scanning device inside the oral cavity in step S100, to reduce unnecessary acquisition and scanning steps and improve tooth alignment efficiency, the two-dimensional image of each tooth can be determined using the dental arch curve obtained in step S100. The method for determining the two-dimensional image of a tooth using the dental arch curve can be any existing method, such as projecting the three-dimensional tooth model onto a two-dimensional plane or constructing a dental arch curve coordinate system corresponding to the tooth on the dental arch curve; this specification does not limit this method.

[0082] Subsequently, using a pre-trained feature point recognition model, at least one feature point corresponding to each tooth is determined in the two-dimensional image of each tooth. In this step, the feature points of each tooth can all be of the same type, such as all being mesial and distal points, or all being labial incisal feature points. Alternatively, the feature points of different teeth can be of different types, similar to the first designated feature point described in S100. For example, the mesiobuccal apex and distal buccal apex can be selected as feature points of an incisor, or the cusp apex of a canine can be selected as a feature point of a canine, etc. This specification does not limit this.

[0083] Furthermore, in this step, the two-dimensional image of the teeth can represent either complete teeth or missing teeth. Since users' teeth may have significant wear or be missing in real-world applications, the pre-trained feature point recognition model can simulate and complete severely worn or incomplete teeth by including both complete and missing 2D reference images in its training samples. This allows the model to predict the feature points of missing teeth, making the feature point calculation more aligned with medical understanding and expanding the application scenarios of the tooth alignment method provided in this manual.

[0084] S104: Optimize the pose of the tooth in the three-dimensional tooth model by taking at least one of the following as optimization objectives: the distance between the position of the feature point of the tooth and the dental arch curve, and the angle between the twisting direction of the tooth and the tangent direction of the dental arch curve.

[0085] Since the dental arch curve determined in step S100 is the user's dental arch curve after orthodontic treatment, it closely matches the user's actual situation and approximates a normal dental arch curve. Therefore, using the dental arch curve determined in S100 as a reference, the pose of each tooth in the 3D dental model is optimized so that the dental arch curve of each tooth after simulated alignment can be as close as possible to the dental arch curve determined in S100, thus obtaining a simulated 3D dental model after tooth alignment. It is evident that obtaining a simulated 3D dental model after tooth alignment automatically eliminates the need for doctors to manually use simulation software, lowering the barrier to entry and improving work efficiency and accuracy.

[0086] Specifically, for each tooth, at least one of the following can be used as optimization targets to optimize the tooth's pose in the 3D tooth model: the distance between the tooth's feature point and the dental arch curve, and the angle between the tooth's rotation direction and the tangent direction of the dental arch curve. Optimizing the distance between the tooth's feature point and the dental arch curve aims to bring the tooth closer to the arch, ensuring the optimized feature point lies on the arch curve, thus aligning the optimized tooth position with the user's ideal dental arch curve after orthodontic treatment. Optimizing the angle between the tooth's rotation direction and the tangent direction of the dental arch curve aims to optimize the tooth's posture, ensuring the optimized posture closely resembles the tilt and rotation of teeth on a normal dental arch curve, thus also aligning with the user's ideal dental arch curve after orthodontic treatment. Since the actual situation of each tooth may be different, some teeth may only need to be optimized in position, some teeth may only need to be optimized in posture, while some teeth may need to be optimized in both position and posture. Therefore, the optimization target when optimizing tooth posture may be one or more of the following: the distance between the position of the tooth's feature point and the dental arch curve, and the angle between the tooth's rotation direction and the tangent direction of the dental arch curve.

[0087] In optimizing the pose of teeth in a 3D dental model, the pose can be optimized sequentially for each tooth or for specific teeth. While optimizing the current tooth, it's also possible to detect collisions with previously optimized teeth. If a collision occurs, the current tooth is moved along the dental arch curve in a preset direction with a preset step size to avoid further collisions. This process of optimizing the pose of each tooth or specific teeth sequentially continues until all teeth requiring optimization are moved to their ideal orthodontic positions, resulting in a properly aligned 3D dental model.

[0088] Of course, the poses of multiple teeth can also be optimized simultaneously. For example, the poses of these teeth can be optimized based on at least one of the following: the sum of the distances between the feature points of multiple teeth and the dental arch curve, and the total angle between the torsion direction of each tooth and the tangent direction of the dental arch curve. One of the aforementioned methods can be flexibly selected depending on the specific application scenario; this specification does not impose any limitations on this.

[0089] The tooth alignment method provided in this specification involves determining the dental arch curve on a three-dimensional tooth model containing each tooth, determining a two-dimensional image of the tooth based on the dental arch curve, inputting the two-dimensional image of each tooth into a pre-trained feature point recognition model to obtain the feature points of each tooth, and optimizing the pose of each tooth in the three-dimensional tooth model by taking at least one of the following as optimization objectives: the distance between the position of the tooth feature point and the dental arch curve, and the angle between the tooth's torsion direction and the tangent direction of the dental arch curve.

[0090] By adjusting the position of the teeth, the characteristic points of the teeth are made to fit the dental arch curve as closely as possible, and / or the direction of tooth rotation is aligned with the tangent direction of the dental arch curve, thereby achieving automatic tooth alignment. This reduces the workload while improving the efficiency and accuracy of tooth alignment in orthodontic treatment.

[0091] In one or more embodiments of this specification, Figure 1 The optimization objective in step S104 can be determined by one or more evaluation functions, which can be determined based on the distance between the location of a tooth's feature point and the dental arch curve, or the angle between the tooth's torsion direction and the tangent direction of the dental arch curve. Specifically, this is achieved through the following implementation method:

[0092] First, for cases where the optimization objective is the distance between the position of a feature point of a tooth and the dental arch curve, the distance between the position of the feature point of the tooth and the dental arch curve can be determined based on the coordinates of the feature point of the tooth and the dental arch curve, and used as the first evaluation function corresponding to the tooth. This first evaluation function is used to determine the optimization objective.

[0093] Specifically, the distance between the coordinates of a tooth's feature point and the corresponding dental arch curve (maxillary teeth correspond to the maxillary dental arch curve, and mandibular teeth correspond to the mandibular dental arch curve) is determined. The method for determining this distance can be any existing method for determining the distance between a point and a curve; this specification does not limit this method.

[0094] Optionally, the total distance can be determined based on the distance between the position of the feature points of each tooth and the dental arch curve. Specifically, the distances between the position of the feature points of each tooth and the dental arch curve can be summed to obtain the total distance between the feature points of each tooth and the dental arch curve. The total distance characterizes the differences between multiple teeth of the user and the dental arch curve. Therefore, using the total distance as the first evaluation function and as the optimization target, when optimizing the pose of each tooth in the 3D tooth model one by one, the geometric constraints of the relative positional relationship between each tooth can be considered, thereby improving the efficiency of tooth alignment.

[0095] Furthermore, since the dental arch curve is derived from a 3D tooth model, it actually resides in the 3D coordinate system of the 3D tooth model. However, the feature points of the teeth are determined in a 2D image of the teeth, and therefore reside in the 2D coordinate system of that image. Therefore, it is necessary to transform the tooth feature points from the 2D coordinate system to the 3D coordinate system, or project the dental arch curve from the 3D coordinate system to the 2D coordinate system, in order to determine the distance between the location of the tooth feature points and the dental arch curve.

[0096] Therefore, the first scenario could be: transforming the feature points of the tooth from a two-dimensional coordinate system to a three-dimensional coordinate system, determining the three-dimensional coordinates of the feature points in the three-dimensional coordinate system, and then, based on the three-dimensional coordinates of the feature points and the dental arch curve in the three-dimensional coordinate system, determining the distance from the location of the feature points to the dental arch curve.

[0097] Specifically, based on the relative position of the tooth's feature points to the tooth itself, the two-dimensional coordinates of the tooth's feature points in the two-dimensional coordinate system of the tooth's two-dimensional image are determined. Based on the attributes of the acquisition device used to acquire the two-dimensional image, the transformation relationship between the two-dimensional coordinate system of the tooth's two-dimensional image and the three-dimensional coordinate system of the three-dimensional tooth model is determined. Based on this transformation relationship and the two-dimensional coordinates of the tooth's feature points in the two-dimensional coordinate system, the three-dimensional coordinates of the tooth's feature points in the three-dimensional coordinate system are determined. Finally, based on the three-dimensional coordinates of the tooth's feature points in the three-dimensional coordinate system and the dental arch curve, the distance between the position of the tooth's feature points and the dental arch curve is determined.

[0098] The three-dimensional coordinate system of the 3D tooth model is actually the same as the three-dimensional coordinate system of the dental arch curve, which can be a geodetic coordinate system. Therefore, based on the attributes of the acquisition device, such as the acquisition angle in the geodetic coordinate system when acquiring the 2D image, the transformation relationship between the 2D and 3D coordinate systems can be determined. Furthermore, the 2D coordinates of feature points in the 2D coordinate system can be transformed to the 3D coordinate system to obtain the 3D coordinates of the tooth's feature points in the 3D coordinate system.

[0099] The second scenario is to project the dental arch curve located in the three-dimensional coordinate system onto the two-dimensional coordinate system in a specific direction to obtain the dental arch curve in the two-dimensional coordinate system. Then, based on the two-dimensional coordinates of the feature points of the teeth in the two-dimensional coordinate system and the dental arch curve in the two-dimensional coordinate system, the distance from the location of the feature points to the dental arch curve can be determined.

[0100] Secondly, for cases where the optimization objective is the angle between the tooth's torsion direction and the tangent direction of the dental arch curve, specifically, the tooth's feature points may include the mesial and distal points. The tooth's torsion direction is determined based on the coordinates of the mesial and distal points. The nearest point of the tooth on the dental arch curve is determined as the target point corresponding to the tooth, and the tangent direction of the dental arch curve at the target point is determined. Based on the angle between the tooth's torsion direction and the tangent direction of the dental arch curve at the target point, a second evaluation function is determined for the tooth. This second evaluation function is used to determine the optimization objective.

[0101] Specifically, the mesial point of a tooth can be a characteristic point near the midline of the tooth, for example... Figure 5 Point A2 is shown in the left image. The distal point of a tooth can be a feature point of the tooth that is far from the midline, for example... Figure 5 Point A1 is shown in the left figure. The aforementioned midline can be an imaginary auxiliary line drawn through the central part of the user's face or dental arch, used in this specification to determine the mesial and distal points of each tooth. Based on the coordinates of the mesial and distal points of the teeth, the rotation state of the teeth, particularly the direction of rotation, can be determined. The dental arch curve determined in step S100 simulates the ideal dental arch curve for the user after orthodontic treatment, reflecting the ideal state of the teeth. Therefore, based on the rotation direction determined by the coordinates of the mesial and distal points of the teeth, and the determined dental arch curve, the rotation state of the tooth relative to its ideal posture can be determined. Optimizing the tooth posture with this rotation state as the optimization target can adjust the teeth to the ideal posture, so that the optimized tooth posture conforms to the user's ideal dental arch curve after orthodontic treatment.

[0102] Based on this, the closest point of the tooth on the dental arch curve can be taken as the target point, and the tangent direction of the dental arch curve at the target point can be used as a reference to measure the difference between the tooth and its ideal posture. Therefore, based on the angle between the determined tooth twisting direction and the tangent direction of the dental arch curve at the target point, the second evaluation function for the tooth is determined. The larger the angle between the tooth twisting direction and the tangent direction of the dental arch curve at the target point, the greater the tooth twist and the farther it is from its ideal state. Conversely, the smaller the angle, the smaller the tooth twist and the closer it is to its ideal state. Therefore, when optimizing the tooth posture using the second evaluation function as the optimization objective, the optimization direction can be the minimization of the second evaluation function.

[0103] In one or more embodiments of this specification, since the user's own dental arch curve can be determined based on the feature points corresponding to each of the user's teeth, and the dental arch curve determined in step S100 is actually the user's ideal dental arch curve after orthodontic treatment, the difference between the user's own dental arch curve and the dental arch curve determined in step S100 can be used as a basis for optimizing tooth pose. However, in practical applications, the overall difference between the user's own complete dental arch curve and the dental arch curve determined in step S100 reflects the difference between all of the user's teeth and the ideal state, making it difficult to directly optimize the pose of all teeth based on this difference. Therefore, for a tooth that needs pose optimization, a local curve representing the actual pose of the tooth and its adjacent teeth can be determined based on the mesial and distal points of the tooth, as well as the mesial and distal points of the adjacent teeth. Based on the difference between the determined local curve and the dental arch curve determined in step S100, a third evaluation function is determined. The determined third evaluation function is then introduced into... Figure 1 In the optimization objective of step S104 shown, the pose of the tooth in the three-dimensional tooth model is optimized by taking at least one of the following as optimization objectives: the distance between the position of the tooth feature point and the dental arch curve (refer to the aforementioned first evaluation function), the angle between the tooth's torsion direction and the tangent direction of the dental arch curve (refer to the aforementioned second evaluation function), and the third evaluation function.

[0104] In one or more embodiments of this specification, in practical applications, since patients requiring orthodontic treatment may have teeth that abnormally protrude buccally or lingually, or have uneven heights between adjacent teeth, the distance between feature points of adjacent teeth in a specified direction can be further incorporated into the optimization objective. Specifically, based on the mesial and distal coordinates of the tooth, and the mesial and distal coordinates of its adjacent teeth, the distance between the tooth and its adjacent teeth in a specified direction is determined, and a fourth evaluation function corresponding to the tooth is determined based on this distance. The fourth evaluation function is used to determine the optimization objective. Thus, Figure 1 Step S104 can be an optimization objective to optimize the pose of the tooth in the three-dimensional tooth model, using at least one of the following: the distance between the position of the tooth's feature point and the dental arch curve (refer to the aforementioned first evaluation function), the angle between the tooth's torsion direction and the tangent direction of the dental arch curve (refer to the aforementioned second evaluation function), the aforementioned determined third evaluation function, and the determined fourth evaluation function.

[0105] In practical applications, each tooth can be adjacent to two other teeth in the same dentition (except for the first and last teeth in the dentition). Therefore, the first and second adjacent teeth can be determined, and a fourth evaluation function corresponding to the tooth can be determined based on the feature points of the first and second adjacent teeth. Specifically: based on the coordinates of the mesial point of the tooth and the coordinates of the distal point of the first adjacent tooth, a first distance in a specified direction is determined between the tooth and the first adjacent tooth; based on the coordinates of the distal point of the tooth and the coordinates of the mesial point of the second adjacent tooth, a second distance in a specified direction is determined between the tooth and the second adjacent tooth; based on the first and second distances, the distance in a specified direction between the tooth and its adjacent teeth is determined.

[0106] The first adjacent tooth refers to the tooth closest to the mesial point of the given tooth, and the second adjacent tooth refers to the tooth closest to the distal point of the given tooth. For example... Figure 3 The image shows three teeth belonging to the same dentition. Taking the middle tooth as an example, the tooth to the right of the middle tooth is closer to the mesial point of the middle tooth, so it is the first adjacent tooth of the middle tooth. The tooth to the left of the middle tooth is closer to the distal point of the middle tooth, so it is the second adjacent tooth of the middle tooth.

[0107] Furthermore, on the one hand, excessive distance between feature points of adjacent teeth in the buccal-lingual direction may lead to buccal-lingual stepping issues, i.e., teeth protruding buccally or lingually. On the other hand, excessive distance between feature points of adjacent teeth in the vertical direction may lead to uneven vertical stepping issues, i.e., teeth being too high or too low. Therefore, the specified direction used to determine the fourth evaluation function can be at least one of the buccal-lingual or vertical directions. Thus, the first and second distances used to determine the distance between a tooth and its adjacent teeth in the specified directions can be specifically divided into the following three cases:

[0108] In the first scenario: To eliminate the aforementioned buccal-lingual step problem, by specifying the direction as the buccal-lingual direction, a first distance in the buccal-lingual direction can be determined between the mesial point of the tooth and the distal point of the first adjacent tooth, and a second distance in the buccal-lingual direction can be determined between the distal point of the tooth and the mesial point of the second adjacent tooth. This determines the distance between the tooth and its adjacent teeth in the buccal-lingual direction.

[0109] The second scenario: To eliminate the aforementioned problem of vertical steps, by specifying the direction as vertical, a first vertical distance can be determined between the mesial point of the tooth and the distal point of the first adjacent tooth, and a second vertical distance can be determined between the distal point of the tooth and the mesial point of the second adjacent tooth. This determines the vertical distance between the tooth and its adjacent teeth.

[0110] The third scenario: In order to simultaneously optimize the aforementioned buccal-lingual step problem and the aforementioned vertical step problem, the specified direction includes the buccal-lingual direction and the vertical direction. Thus, based on the aforementioned first and second scenarios, the distance between the tooth and the adjacent tooth in the buccal-lingual direction and the distance between the tooth and the adjacent tooth in the vertical direction can be determined. Furthermore, based on the distance between the tooth and the adjacent tooth in the buccal-lingual direction and the distance between the tooth and the adjacent tooth in the vertical direction, the distance between the tooth and the adjacent tooth of the tooth in the specified direction can be determined.

[0111] In one optional embodiment of this specification, Figure 1 Step S102, which determines the two-dimensional image of each tooth, can be specifically implemented through the following methods:

[0112] First, based on the tangent direction, normal direction, and occlusal plane direction of the target point of the tooth on the dental arch curve, a dental arch curve coordinate system corresponding to the tooth is constructed.

[0113] As mentioned earlier, the dental arch curves in this specification are obtained based on a three-dimensional tooth model, which is actually located in the three-dimensional coordinate system of the three-dimensional tooth model. Since the teeth in a three-dimensional tooth model are usually closely connected, to obtain a two-dimensional image of each tooth, any existing solution, such as machine learning algorithms or computer vision technology, can be used to segment the three-dimensional tooth model to identify the three-dimensional model of an individual tooth. Then, the two-dimensional image of that tooth is determined based on the three-dimensional model of that individual tooth. In this specification, one or more feature points of the tooth can be determined on the three-dimensional model of each tooth using manual or automatic scanning identification methods. These feature points can be located at the center or edge of the three-dimensional model of the tooth. The specific location of the feature points on the three-dimensional model of the tooth can be determined according to the type and actual structure of the tooth, and this specification does not impose any limitations on this. Then, points corresponding to the feature points of the tooth are determined on the dental arch curve as target points of the tooth. In the three-dimensional coordinate system of the dental arch curve, a local coordinate system corresponding to the tooth is established based on the target points of the tooth, i.e., the dental arch curve coordinate system corresponding to the tooth. In the dental arch curve coordinate system corresponding to the tooth, the target point of the tooth can be the origin. The XYZ axes of the dental arch curve coordinate system can be defined according to the tangent direction, normal direction, and occlusal plane direction of the target point on the dental arch curve. For example, the tangent line of the dental arch curve passing through the target point is determined, and the X-axis of the dental arch curve coordinate system is determined according to the tangent line. The normal line passing through the target point is determined according to the normal line, and the Z-axis of the dental arch curve coordinate system is determined according to the normal line. Then, the Y-axis of the dental arch curve coordinate system is determined according to the occlusal plane direction of the target point of the tooth on the dental arch curve, as well as the determined X-axis and Z-axis.

[0114] Optionally, the target point of the tooth is the nearest point on the dental arch curve to the first designated feature point of the tooth. The first designated feature point can be any type of tooth feature point, such as the mesial point, distal point, mesobuccal apex, distobuccal apex, cusp apex, etc. It can be determined manually or by automatic scanning and identification; this specification does not limit the type, number, or determination method of the first designated feature point. Based on the first designated feature point of the tooth, the nearest point to that first designated feature point on the dental arch curve is determined as the target point of the tooth. When determining the nearest point to the first designated feature point on the dental arch curve, a distance function can be defined. The distance function includes a function representing the dental arch curve and the coordinates of the first designated feature point. By minimizing the distance function, the point on the dental arch curve closest to the first designated feature point can be determined as the target point of the tooth.

[0115] Subsequently, based on the three-dimensional tooth model, in the dental arch curve coordinate system corresponding to the tooth, at least one of the reference width and reference height of the tooth and the projection plane of the tooth in the two-dimensional image is determined.

[0116] Based on the actual application, determine at least one of the following: the reference width, the reference height, and the projection plane of the tooth.

[0117] Specifically, using the 3D coordinate system of the 3D tooth model as the global coordinate system, the dental arch curve coordinate system corresponding to the tooth is actually a 3D local coordinate system within the 3D coordinate system. Since the origin of this dental arch curve coordinate system can be the target point of the tooth, the 3D model of the tooth can also be located within the dental arch curve coordinate system corresponding to the tooth. Based on this, based on the 3D tooth model, or based on the 3D model of the tooth segmented from the 3D tooth model, the reference width and reference height of the tooth can be determined in the dental arch curve coordinate system corresponding to the tooth, so as to determine the width and height of the tooth in the 2D image to be generated. In addition, based on the 3D tooth model, or based on the 3D model of the tooth segmented from the 3D tooth model, the projection surface of the tooth in a specific direction can be determined. The determined projection surface determines the 2D image of the tooth, which can restore the details of the tooth in the 2D image and improve the accuracy of the 2D image.

[0118] Optionally, based on the three-dimensional tooth model, in the dental arch curve coordinate system corresponding to the tooth, the width of the tooth in the tangential direction is determined as the reference width of the tooth, and the height of the tooth in the occlusal plane direction is determined as the reference height of the tooth. By determining the reference width and reference height of the tooth, the specified width and specified height of the tooth in the generated two-dimensional image can be determined, thereby improving the accuracy of the width and height of the tooth image in the two-dimensional image.

[0119] Alternatively, the projection surface of a tooth can be determined by the following method: determining the projection direction of the tooth based on the normal direction of the dental arch curve coordinate system, and determining the projection surface of the tooth based on the projection direction and the three-dimensional tooth model (or based on the three-dimensional model of the tooth segmented from the three-dimensional tooth model).

[0120] Then, a two-dimensional image of the tooth is obtained based on at least one of the reference height of the tooth, the reference height, and the projection plane of the tooth in the two-dimensional image.

[0121] Specifically, a two-dimensional image of the tooth can be obtained using a three-dimensional rendering method based on at least one of the aforementioned determined reference width, reference height, and projection plane of the tooth. This three-dimensional rendering method can be any existing type of three-dimensional rendering method for generating two-dimensional images, and this specification does not limit it.

[0122] Furthermore, in an optional embodiment of this specification, based on the aforementioned established dental arch curve coordinate system corresponding to the tooth, the three-dimensional coordinates of the tooth's feature points can also be determined. Using the three-dimensional coordinates of the tooth's feature points and the dental arch curve in the three-dimensional coordinate system, the distance between the position of the tooth's feature points and the dental arch curve is determined, thereby determining the optimization target, or the aforementioned first evaluation function. Specifically:

[0123] Step 1: For each tooth, mark its feature points on the 2D image of that tooth to obtain the target image of that tooth.

[0124] The timing for determining the three-dimensional coordinates of feature points of a tooth can be... Figure 1 After obtaining the feature points corresponding to the teeth in step S102, and before optimizing the pose of the teeth in the three-dimensional tooth model in S104, the purpose of determining the unit coordinates of the tooth feature points is to map the tooth feature points in the two-dimensional coordinate system to the three-dimensional coordinate system. Based on the determined three-dimensional coordinates of the tooth feature points, they can be combined with the dental arch curve, which is also in the three-dimensional coordinate system, to obtain the distance between the position of the tooth feature points and the dental arch curve.

[0125] Specifically, the tooth feature points obtained in S102 are identified from the two-dimensional image of the tooth. Therefore, the position of the tooth feature points in the two-dimensional image of the tooth can also be obtained. Based on the obtained position, the tooth feature points can be marked in the two-dimensional image of the tooth to obtain the target image of the tooth. That is, the target image of the tooth can reflect both the two-dimensional shape of the tooth and the position of the tooth feature points in the two-dimensional shape of the tooth.

[0126] Step 2: Based on at least one of the following: the normal direction in the dental arch curve coordinate system corresponding to the tooth, the three-dimensional tooth model, and the target image of the tooth, determine the coordinate values ​​of the feature points of the tooth in the tangent direction and the occlusal plane direction in the dental arch curve coordinate system corresponding to the tooth.

[0127] Subsequently, the dental arch curve coordinate system corresponding to the tooth, as determined in the aforementioned embodiments, is used as the target three-dimensional coordinate system for transforming the tooth's feature points from two dimensions to three dimensions. Within this dental arch curve coordinate system, based on one or more of the normal direction, the three-dimensional tooth model, and the target image of the tooth, the feature points of the tooth annotated in the target image are mapped to the dental arch curve coordinate system. Specifically, under the constraint of the geometric information of the tooth provided by the three-dimensional tooth model, coordinate information reflecting the specific location of the tooth's feature points is determined, such as the coordinate values ​​of the tooth's feature points in the tangential direction and in the occlusal plane direction.

[0128] Step 3: Determine the three-dimensional coordinates of the reference point corresponding to the tooth based on the coordinates of the feature point of the tooth in the tangent direction and the coordinates in the jaw plane direction in the dental arch curve coordinate system corresponding to the tooth.

[0129] Subsequently, based on the calculated coordinate values, the reference point corresponding to the tooth is located in the dental arch curve coordinate system, providing an accurate spatial reference for mapping the feature points of the tooth to the dental arch curve coordinate system, guiding the final mapping of the tooth's feature points, and making the mapping results more reliable.

[0130] Step 4: Starting from the three-dimensional coordinates of the reference point corresponding to the tooth, construct the ray corresponding to the tooth along the normal direction in the coordinate system of the dental arch curve corresponding to the tooth. Use the three-dimensional coordinates of the intersection point of the ray corresponding to the tooth and the three-dimensional tooth model as the three-dimensional coordinates of the feature point of the tooth.

[0131] Starting from the reference point, a ray is constructed along the discovery direction defined by the dental arch curve coordinate system. Using the ray-model intersection detection algorithm, the intersection point of the ray and the three-dimensional tooth model is determined. The three-dimensional coordinates of this intersection point are recorded as the three-dimensional coordinates of the tooth's feature points, thus completing the mapping of the tooth's feature points from the two-dimensional coordinate system to the three-dimensional coordinate system.

[0132] thereby, Figure 1 In step S104, the distance between the position of the tooth's feature point and the dental arch curve can be determined based on the distance between the three-dimensional coordinates of the tooth's feature point and the dental arch curve.

[0133] In one or more embodiments of this specification, the pre-trained feature point recognition model used in S102 can be obtained by iterative training according to the following scheme, such as... Figure 4 As shown.

[0134] S200: Obtain a two-dimensional reference image as a training sample, wherein the teeth represented by the two-dimensional reference image include either complete teeth or missing teeth.

[0135] Specifically, the two-dimensional reference image is a two-dimensional image of the user's teeth acquired through medical image acquisition equipment, and each two-dimensional reference image represents one tooth. In practical applications, a user's teeth may be in a normal shape (i.e., a complete tooth) or severely worn and incomplete (i.e., a tooth missing at least partially). Therefore, in this specification, the teeth represented by the two-dimensional reference images can be either complete teeth or missing teeth.

[0136] S202: Obtain the second designated feature point of the tooth in the two-dimensional reference image as the annotation of the training sample.

[0137] Specifically, the second feature points on the teeth in the two-dimensional reference image can be determined manually. The number of second feature points can be one or more, and this specification does not limit this. However, since the second feature points on the teeth in the two-dimensional reference image are used as annotations for training samples in the feature point recognition model, the second feature points on the teeth in different two-dimensional reference images generally belong to the same type, such as mesial and distal points, or cusp apexes, etc.

[0138] In this specification, the second designated feature points of a tooth in a two-dimensional reference image are taken as the mesial point and the distal point, which are located on the two sides of the incisal ridge of a tooth. Figure 5 As shown, the left image is a 2D reference image containing a complete tooth, where point A1 is the distal midpoint of the complete tooth and point A2 is the mesial midpoint. The right image is a 2D reference image containing a missing tooth, where point B1 is the distal midpoint of the missing tooth and point B2 is the mesial midpoint. It can be seen that the location of the second designated feature point of the tooth in the 2D reference image containing the missing tooth may not be on the foreground image corresponding to the tooth, but rather on the background image.

[0139] S204: Input the training samples into the feature point recognition model to be trained to obtain predicted feature points.

[0140] Specifically, the feature point recognition model to be trained serves as the training sample, i.e., the two-dimensional reference image. Based on the input two-dimensional reference image, the feature point recognition model can identify feature points on teeth within the two-dimensional reference image and use these as the output predicted feature points. This specification does not limit the model structure of the feature point recognition model; it can be constructed from any existing model structure used for processing two-dimensional images. Furthermore, this specification also does not limit the number of predicted feature points output by the feature point recognition model to be trained.

[0141] S206: The feature point recognition model to be trained is trained with the goal of minimizing the difference between the predicted feature points and the annotations of the training samples.

[0142] In this specification, since the second designated feature point of the teeth in the two-dimensional reference image is used as the annotation of the training sample, the training method of the feature point recognition model to be trained is supervised training. Therefore, the training objective of the feature point recognition model to be trained is to minimize the difference between the predicted feature points output by the feature point recognition model to be trained and the annotation of the training sample. That is, the loss of the feature point recognition model to be trained during the training process can be determined based on the difference between the predicted feature points and the annotation of the training sample. As for the type of loss function used, it can be any existing type, and this specification does not limit it.

[0143] Once the feature point recognition model meets preset conditions, the trained feature point recognition model can be obtained. The preset conditions may be that the number of iterations of training reaches a threshold, or that the difference between the predicted feature points output by the feature point recognition model and the annotations of the training samples is less than a preset difference threshold.

[0144] The above are one or more embodiments of the tooth alignment method provided in this specification. Based on the same idea, this specification also provides corresponding tooth alignment devices, such as... Figure 6 As shown.

[0145] Figure 6 This specification provides a schematic diagram of a tooth alignment device, which specifically includes:

[0146] The dental arch curve determination module 300 is used to obtain a three-dimensional dental model containing each tooth and the dental arch curve of the three-dimensional dental model.

[0147] The feature point determination module 302 is used to determine the two-dimensional image of each tooth based on the dental arch curve, and input the two-dimensional image of each tooth into the pre-trained feature point recognition model to obtain the feature points corresponding to each tooth.

[0148] The optimization module 304 optimizes the pose of the tooth in the three-dimensional tooth model by taking at least one of the following as optimization targets: the distance between the position of the feature point of the tooth and the dental arch curve, and the angle between the direction of the tooth's torsion and the tangent direction of the dental arch curve.

[0149] Optionally, the device further includes:

[0150] The first evaluation function determination module 306 is specifically used to determine the distance between the position of the feature point of the tooth and the dental arch curve based on the coordinates of the feature point of the tooth and the dental arch curve, and use this distance as the first evaluation function corresponding to the tooth; the first evaluation function is used to determine the optimization target.

[0151] Optionally, the feature points of the tooth include the mesial point and the distal point;

[0152] Optionally, the device further includes:

[0153] The second evaluation function determination module 308 is specifically used to determine the direction of tooth rotation based on the coordinates of the mesial point and the distal point of the tooth; determine the nearest point of the tooth on the dental arch curve as the target point corresponding to the tooth, and determine the tangent direction of the dental arch curve at the target point corresponding to the tooth; determine the second evaluation function corresponding to the tooth based on the angle between the direction of tooth rotation and the tangent direction of the dental arch curve at the target point corresponding to the tooth; the second evaluation function is used to determine the optimization target.

[0154] Optionally, the device further includes:

[0155] The third evaluation function determination module 310 is specifically used to generate a local curve corresponding to the tooth using a curve fitting algorithm based on the mesial point of the tooth, the distal point of the tooth, the mesial point of the adjacent tooth, and the distal point of the adjacent tooth; and to determine the third evaluation function corresponding to the tooth based on the difference between the local curve corresponding to the tooth and the dental arch curve; the third evaluation function is used to determine the optimization target.

[0156] Optionally, the device further includes:

[0157] The fourth evaluation function determination module 312 is specifically used to determine the distance between the tooth and its adjacent teeth in a specified direction based on the mesial and distal coordinates of the tooth, as well as the mesial and distal coordinates of the adjacent teeth, and to determine the fourth evaluation function corresponding to the tooth based on the distance between the tooth and its adjacent teeth in the specified direction; the fourth evaluation function is used to determine the optimization target.

[0158] Optionally, the fourth evaluation function determination module 312 is specifically used to: determine a first distance in a specified direction between the tooth and the first adjacent tooth of the tooth based on the coordinates of the mesial point of the tooth and the coordinates of the distal point of the first adjacent tooth of the tooth; determine a second distance in a specified direction between the tooth and the second adjacent tooth of the tooth based on the coordinates of the distal point of the tooth and the coordinates of the mesial point of the second adjacent tooth of the tooth; and determine the distance in a specified direction between the tooth and the adjacent tooth of the tooth based on the first distance and the second distance.

[0159] Optionally, the feature point determination module 302 is specifically used to: construct a dental arch curve coordinate system corresponding to the tooth based on the tangent direction, normal direction, and occlusal plane direction of the target point of the tooth on the dental arch curve; determine, based on the three-dimensional tooth model, at least one of the reference width and reference height of the tooth and the projection plane of the tooth in the dental arch curve coordinate system corresponding to the tooth; and obtain a two-dimensional image of the tooth based on the reference height of the tooth, the reference height, and at least one of the projection plane of the tooth in the two-dimensional image.

[0160] Optionally, for one tooth in at least one tooth, the feature point determination module 302 satisfies at least one of the following: the target point corresponding to the tooth is the nearest point of the first designated feature point of the tooth on the dental arch curve; the reference width corresponding to the tooth is the width of the tooth in the tangential direction; the reference height corresponding to the tooth is the height of the tooth in the occlusal plane direction; the designated width and the designated height of the tooth in the two-dimensional image of the tooth to be generated are determined by the reference width and the reference height corresponding to the tooth; the projection direction corresponding to the tooth is the normal direction of the tooth; the projection plane corresponding to the tooth is determined according to the projection direction and the three-dimensional tooth model.

[0161] Optionally, the device further includes:

[0162] The feature point 3D coordinate determination module 314, for each tooth, marks the feature points of the tooth in the 2D image of the tooth to obtain the target image of the tooth; determines the coordinate values ​​of the feature points of the tooth in the tangent direction and the occlusal plane direction in the dental arch curve coordinate system corresponding to the tooth based on at least one of the normal direction in the dental arch curve coordinate system corresponding to the tooth, the 3D tooth model, and the target image of the tooth; determines the 3D coordinates of the reference point corresponding to the tooth based on the coordinate values ​​of the feature points of the tooth in the tangent direction and the occlusal plane direction in the dental arch curve coordinate system corresponding to the tooth; constructs a ray corresponding to the tooth along the normal direction in the dental arch curve coordinate system corresponding to the tooth, starting from the 3D coordinates of the reference point corresponding to the tooth; and uses the 3D coordinates of the intersection point of the ray corresponding to the tooth and the 3D tooth model as the 3D coordinates of the feature points of the tooth.

[0163] Optionally, the device further includes:

[0164] The training module 316 is specifically used to: acquire a two-dimensional reference image as a training sample, wherein the teeth represented by the two-dimensional reference image include either complete teeth or missing teeth; acquire a second designated feature point of the teeth in the two-dimensional reference image as an annotation of the training sample; input the training sample into the feature point recognition model to be trained to obtain predicted feature points; and train the feature point recognition model to be trained with the goal of minimizing the difference between the predicted feature points and the annotation of the training sample.

[0165] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 The method shown is for aligning teeth.

[0166] This instruction manual also provides Figure 7 The diagram shows a schematic structural representation of the electronic device. Figure 7 At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for the business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above-mentioned functions. Figure 1 The method for aligning teeth is shown. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0167] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0168] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0169] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0170] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0171] Those skilled in the art will understand that embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0172] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0173] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0174] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0175] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0176] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0177] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0178] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0179] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0180] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0181] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0182] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for aligning teeth, characterized in that, include: Obtain a three-dimensional tooth model containing each tooth and the dental arch curve of the three-dimensional tooth model; The two-dimensional images of each tooth are determined based on the dental arch curve, and the two-dimensional images of each tooth are input into a pre-trained feature point recognition model to obtain the feature points corresponding to each tooth. The pose of the tooth in the three-dimensional tooth model is optimized by taking at least one of the following as optimization objectives: the distance between the position of the feature point of the tooth and the dental arch curve, and the angle between the direction of the tooth's torsion and the tangent direction of the dental arch curve.

2. The method as described in claim 1, characterized in that, The method further includes: Based on the coordinates of the feature points of the tooth and the dental arch curve, the distance between the position of the feature points of the tooth and the dental arch curve is determined, which serves as the first evaluation function corresponding to the tooth; the first evaluation function is used to determine the optimization target.

3. The method as described in any one of claims 1 or 2, characterized in that, The characteristic points of the tooth include the mesial point and the distal point; the method further includes: The direction of the tooth's rotation is determined based on the coordinates of the tooth's mesial point and distal point. The nearest point of the tooth on the dental arch curve is determined as the target point corresponding to the tooth, and the tangent direction of the dental arch curve at the target point corresponding to the tooth is determined. Based on the angle between the direction of the tooth's torsion and the tangent direction of the dental arch curve at the target point corresponding to the tooth, a second evaluation function is determined for the tooth; the second evaluation function is used to determine the optimization target.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Based on the mesial point of the tooth, the distal point of the tooth, the mesial point of the adjacent tooth, and the distal point of the adjacent tooth, a local curve corresponding to the tooth is generated by a curve fitting algorithm. Based on the difference between the local curve corresponding to the tooth and the dental arch curve, a third evaluation function is determined for the tooth; the third evaluation function is used to determine the optimization objective.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Based on the mesial and distal coordinates of the tooth, as well as the mesial and distal coordinates of the adjacent teeth, the distance between the tooth and its adjacent teeth in a specified direction is determined. Based on the distance between the tooth and its adjacent teeth in the specified direction, a fourth evaluation function corresponding to the tooth is determined. The fourth evaluation function is used to determine the optimization objective.

6. The method as described in claim 5, characterized in that, Based on the mesial and distal coordinates of the tooth, and the mesial and distal coordinates of the adjacent teeth, the distance between the tooth and its adjacent teeth in a specified direction is determined, specifically including: Based on the coordinates of the mesial point of the tooth and the coordinates of the distal point of the first adjacent tooth of the tooth, a first distance in a specified direction is determined between the tooth and the first adjacent tooth of the tooth. Based on the coordinates of the distal point of the tooth and the coordinates of the proximal point of the second adjacent tooth of the tooth, determine the second distance between the tooth and the second adjacent tooth of the tooth in a specified direction; Based on the first distance and the second distance, the distance between the tooth and its adjacent teeth in a specified direction is determined.

7. The method as described in claim 1, characterized in that, Determining a two-dimensional image of each tooth based on the dental arch curve specifically includes: Based on the tangent direction, normal direction, and occlusal plane direction of the target point of the tooth on the dental arch curve, construct the dental arch curve coordinate system corresponding to the tooth; Based on the three-dimensional tooth model, in the dental arch curve coordinate system corresponding to the tooth, determine at least one of the reference width and reference height of the tooth and the projection plane of the tooth in the two-dimensional image; A two-dimensional image of the tooth is obtained based on at least one of the reference height of the tooth, the reference height, and the projection plane of the tooth in the two-dimensional image.

8. The method as described in claim 7, characterized in that, For at least one tooth, the method satisfies at least one of the following: The target point corresponding to the tooth is the closest point of the first designated feature point of the tooth on the dental arch curve; The reference width corresponding to the tooth is the width of the tooth in the tangential direction; The reference height corresponding to the tooth is the height of the tooth in the jaw plane direction; In the two-dimensional image of the tooth to be generated, the specified width and specified height of the tooth are determined by the reference width and reference height corresponding to the tooth. The projection direction corresponding to the tooth is the normal direction of the tooth; The projection plane corresponding to the tooth is determined based on the projection direction and the three-dimensional tooth model.

9. The method as described in claim 8, characterized in that, The method further includes: For each tooth, its feature points are labeled in the two-dimensional image of that tooth to obtain the target image of that tooth; Based on at least one of the following: the normal direction in the dental arch curve coordinate system corresponding to the tooth, the three-dimensional tooth model, and the target image of the tooth, determine the coordinate values ​​of the feature points of the tooth in the tangent direction and the coordinate values ​​in the jaw plane direction in the dental arch curve coordinate system corresponding to the tooth. Based on the coordinate values ​​of the feature points of the tooth in the tangent direction and the coordinate values ​​in the jaw plane direction in the dental arch curve coordinate system corresponding to the tooth, the three-dimensional coordinates of the reference point corresponding to the tooth are determined. Starting from the three-dimensional coordinates of the reference point corresponding to the tooth, a ray corresponding to the tooth is constructed along the normal direction in the coordinate system of the dental arch curve corresponding to the tooth. The three-dimensional coordinates of the intersection point of the ray corresponding to the tooth and the three-dimensional tooth model are used as the three-dimensional coordinates of the feature point of the tooth.

10. The method according to any one of claims 1-9, characterized in that, Pre-trained feature point recognition models include: Two-dimensional reference images are obtained as training samples, and the teeth represented by the two-dimensional reference images include one of complete teeth and missing teeth; Obtain the second designated feature point of the tooth in the two-dimensional reference image as the annotation of the training sample; The training samples are input into the feature point recognition model to be trained to obtain predicted feature points; The feature point recognition model to be trained is trained with the goal of minimizing the difference between the predicted feature points and the annotations of the training samples.

11. A tooth alignment device, characterized in that, include: The dental arch curve determination module is used to obtain a three-dimensional tooth model containing each tooth and the dental arch curve of the three-dimensional tooth model; The feature point determination module is used to determine the two-dimensional image of each tooth based on the dental arch curve, and input the two-dimensional image of each tooth into the pre-trained feature point recognition model to obtain the feature points corresponding to each tooth. An optimization module is used to optimize the pose of the tooth in the three-dimensional tooth model, with at least one of the following as optimization targets: the distance between the position of the feature point of the tooth and the dental arch curve, and the angle between the direction of the tooth's torsion and the tangent direction of the dental arch curve.

12. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1 to 10.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method described in any one of claims 1 to 10.

Images