Method of detecting attachment position deviation

Abstract

One aspect of this application provides a computer-executed method for detecting accessory position deviation, comprising: acquiring first, second, and third three-dimensional digital models, wherein the third three-dimensional digital model is a three-dimensional digital model representing a first accessory, the first three-dimensional digital model is a three-dimensional digital model representing a first tooth without the first accessory installed, and the second three-dimensional digital model is a three-dimensional digital model representing the first tooth with the first accessory actually installed; coarsely registering the first and second three-dimensional digital models based on their local coordinate systems; finely registering the coarsely registered first and second three-dimensional digital models using an ICP method; and based on the result of the fine registration, searching along the bottom surface of the third three-dimensional digital model located at a target installation position, so that the third three-dimensional digital model is partially aligned with the first accessory of the second three-dimensional digital model, thereby obtaining the deviation between the actual installation position of the first accessory and the target installation position.

Description

Technical Field

[0001] This application generally relates to a method for detecting whether the actual installation position of an accessory deviates from the designed target installation position. Background Technology

[0002] Due to its advantages in convenience, hygiene, and aesthetics, orthodontic treatment using shell-shaped dental appliances made of polymer materials is becoming increasingly popular.

[0003] In some cases, in order to improve the effectiveness of orthodontic treatment, it is necessary to place attachments on the teeth and accordingly form a cavity in the shell-shaped orthodontic appliance to accommodate the attachments. Through the interaction of the two, the forces and / or torques required for orthodontic treatment are generated.

[0004] Currently, attachments are generally bonded to the tooth surface manually. Because the precision of manual operation highly depends on the operator's experience and skills, the actual installation position of the attachment on the tooth surface may deviate from the designed target installation position. This can result in the force and / or torque applied to the teeth by the shell-shaped orthodontic appliance not matching the desired force and / or torque, thus affecting the orthodontic treatment outcome.

[0005] Therefore, it is necessary to provide a method for detecting whether the actual installation position of the accessory deviates from the designed target installation position, so that dental professionals can promptly detect and correct the deviation of the accessory installation position to ensure the orthodontic treatment effect. Summary of the Invention

[0006] One aspect of this application provides a computer-executed method for detecting accessory position deviation, comprising: acquiring first, second, and third three-dimensional digital models, wherein the third three-dimensional digital model represents a three-dimensional digital model of a first accessory, the first three-dimensional digital model represents a three-dimensional digital model of a first tooth without the first accessory installed, and the second three-dimensional digital model represents a three-dimensional digital model of the first tooth with the first accessory actually installed; acquiring a target installation position of the third three-dimensional digital model on the first three-dimensional digital model; coarsely registering the first and second three-dimensional digital models based on their local coordinate systems; finely registering the coarsely registered first and second three-dimensional digital models using an ICP method; and based on the result of the fine registration, searching along the bottom surface of the third three-dimensional digital model located at the target installation position to align the third three-dimensional digital model with a portion of the first accessory in the second three-dimensional digital model, thereby obtaining the deviation between the actual installation position of the first accessory and the target installation position.

[0007] In some implementations, the coarse registration is based on the SVD method.

[0008] In some implementations, the coarse registration includes selecting a plurality of corresponding reference points in the local coordinate systems of the first and second three-dimensional digital models, respectively, wherein each pair of reference points has the same coordinate values, and the coarse registration of the first and second three-dimensional digital models is based on these reference points.

[0009] In some implementations, the weights of the point pairs on which the fine registration is based are assigned according to at least one of the following: (1) assigning weights according to the major axis coordinate of the local coordinate system: point pairs closer to the incisal edge or occlusal surface of the tooth have higher weights, and point pairs closer to the gingival line have lower weights; (2) assigning weights according to the distance sorting of point pairs: in each iteration, the distances of point pairs are sorted from largest to smallest, and point pairs with larger distances have lower weights; and (3) assigning weights according to a distance threshold: in each iteration, if the distance of a point pair exceeds a preset distance threshold, its weight is reduced.

[0010] In some embodiments, the computer-executed method for detecting attachment position deviation further includes: calculating the confidence level of the fine registration based on the proportion of registered point pairs.

[0011] In some embodiments, the computer-executed method for detecting attachment position deviation further includes: drawing rays along the normal direction from a vertex of one of the first and second three-dimensional digital models based on the coarse registration, obtaining the intersection points of these rays with the other of the first and second three-dimensional digital models, the intersection points and the corresponding vertices forming a first set of point pairs including multiple point pairs, as the point pairs on which the fine registration is based.

[0012] In some implementations, the second three-dimensional digital model is obtained by scanning the first tooth on which the first accessory is installed.

[0013] In some implementations, the bottom surface of the third three-dimensional digital model is a plane.

[0014] In some embodiments, the computer-executed method for detecting attachment position deviation further includes: drawing rays along the normal direction through multiple points on the bottom surface of the third three-dimensional digital model, taking the intersection of each ray with the second and third three-dimensional digital models as a point pair, forming a second set of point pairs including multiple point pairs, and the objective function of the search is the sum of the distances between the point pairs in the second set of point pairs.

[0015] In some embodiments, the computer-executed method for detecting attachment position deviation further includes: if a ray from a vertex on the bottom surface of the third three-dimensional digital model does not intersect with the second three-dimensional digital model, assuming that there is a pair of points on the ray, and assigning a preset distance value to the pair of points as the distance between the pair of points.

[0016] In some implementations, the preset distance value is greater than or equal to the maximum height of the first attachment.

[0017] In another aspect, this application provides a computer system for detecting attachment position deviation, comprising a storage device and a processor. The storage device stores a computer program for detecting attachment position deviation, and when the program is run, the processor executes the method for detecting attachment position deviation. Attached Figure Description

[0018] The above and other features of this application will be further described below with reference to the accompanying drawings and their detailed description. It should be understood that these drawings only illustrate several exemplary embodiments according to this application and should not be considered as limiting the scope of protection of this application. Unless otherwise specified, the drawings are not necessarily to scale, and similar reference numerals denote similar parts.

[0019] Figure 1 This is a schematic flowchart illustrating a computer-implemented method for detecting attachment position deviation in one embodiment of this application;

[0020] Figure 2A This schematically illustrates the relative positional relationship of the two attachments before alignment; and

[0021] Figure 2B schematically shown Figure 2A The relative positions of the two attachments after alignment are shown. Detailed Implementation

[0022] The following detailed description references the accompanying drawings, which form part of this specification. The illustrative embodiments mentioned in the specification and drawings are for illustrative purposes only and are not intended to limit the scope of this application. Those skilled in the art will understand, based on the teachings of this application, that many other embodiments can be employed and various changes can be made to the described embodiments without departing from the spirit and scope of this application. It should be understood that the various aspects of this application illustrated herein can be arranged, substituted, combined, separated, and designed in many different configurations, all of which are within the scope of this application.

[0023] One aspect of this application provides a computer-executed method for detecting attachment position deviation.

[0024] In another aspect, this application provides a computer system for detecting attachment position deviation, comprising a storage device and a processor. The storage device stores a computer program for detecting attachment position deviation, which, when executed by the processor, performs the method for detecting attachment position deviation.

[0025] Currently, the design and fabrication process for the most common shell-shaped orthodontic appliances is as follows. The process will be briefly described below using a single jaw (maxilla or mandible) as an example.

[0026] First, a three-dimensional digital model of the dentition is obtained through scanning, representing the patient's initial tooth layout (i.e., the tooth layout before orthodontic treatment). This three-dimensional digital model can be obtained through intraoral scanning, or by scanning a physical model of the dentition (e.g., a plaster model) or impression.

[0027] Next, based on the initial three-dimensional digital model of the jawbone with the initial tooth layout, a series of successive three-dimensional digital models of the jawbone are generated, each representing a successive tooth layout. For cases requiring attachments, multiple consecutive attachments are placed at selected locations on selected teeth in the series of successive three-dimensional digital models of the jawbone; these selected locations are referred to below as the designed target installation locations.

[0028] Then, shell-shaped orthodontic appliances are fabricated based on the series of successive three-dimensional digital models of the jaws. Currently, the most common fabrication method is to first use a control device (such as a stereolithography device) to create a series of corresponding solid models of the jaws, and then use a thermoforming process to press heated film material onto these solid models of the jaws to form a series of successive shell-shaped orthodontic appliances.

[0029] Before orthodontic treatment using shell-shaped dental appliances with attachments, attachments need to be installed at selected locations on the patient's chosen teeth. However, as mentioned in the background section, the position of artificially cemented attachments may deviate from the designed target installation position. If the deviation is too large, it may affect the orthodontic treatment outcome. Therefore, it is necessary to check whether the installation position deviates from the designed target installation position after the attachment is installed.

[0030] In one embodiment, it is possible to detect whether the installation position of the accessory deviates from the designed target installation position immediately after the accessory is installed.

[0031] In another embodiment, the installation position of the accessory can also be checked during orthodontic treatment and at the patient's follow-up visit to see if it deviates from the designed target installation position.

[0032] Please refer to Figure 1 This is a schematic flowchart of a computer-executed method 100 for detecting attachment position deviation in one embodiment of this application.

[0033] In 101, obtain the first, second, and third three-dimensional digital models.

[0034] The first and second three-dimensional digital models are three-dimensional digital models of the same tooth.

[0035] The first three-dimensional digital model is a three-dimensional digital model of the teeth obtained by scanning prior to the installation of the attachment.

[0036] The second three-dimensional digital model is a model of the deviation of the attachment position to be detected. It is a three-dimensional digital model of the tooth obtained by scanning after the attachment is cemented onto the tooth.

[0037] The third three-dimensional digital model is the three-dimensional digital model of the attachment.

[0038] In one embodiment, the first and third three-dimensional digital models can be three-dimensional digital models used to design orthodontic treatment plans, that is, they are in the same world coordinate system, and the installation position of the third three-dimensional digital model on the first three-dimensional digital model (i.e. the designed target installation position) is known.

[0039] In step 103, the first and second three-dimensional digital models are coarsely registered.

[0040] Since a typical scan yields a three-dimensional digital model of the entire dentition (maxillary or mandibular dentition), in one embodiment, each tooth in the three-dimensional digital model of the dentition can be numbered in a predetermined manner. Based on the tooth numbering, teeth from two three-dimensional digital models of the same dentition can be paired up to ensure that the two three-dimensional digital models used for morphological comparison are three-dimensional digital models of the same tooth.

[0041] As is known to those skilled in the art, in the processing of three-dimensional digital models of teeth, in order to facilitate calculation, in addition to the world coordinate system, a local coordinate system is usually set for the three-dimensional digital model of each tooth.

[0042] Because current technologies (e.g., deep learning-based local coordinate system establishment methods) can achieve extremely high accuracy and consistency in establishing local coordinate systems, in one embodiment, coarse registration can be performed on two 3D digital models of the same tooth based on the local coordinate system.

[0043] In one embodiment, for the first and second three-dimensional digital models, at least three points in their local coordinate systems can be selected as reference points, and coarse registration of the two three-dimensional digital models of the tooth can be performed based on these reference points. For example, the four points (0, 0, 0), (1, 0, 0), (0, 1, 0), and (0, 0, 1) can be used as reference points. It is understood that the selection of reference points is not limited to this example, as long as they are not on the same straight line.

[0044] In some cases, the morphology of the tooth portion of the first and second three-dimensional digital models may differ, for example, due to tooth wear, attachments, or changes in the gingival line (e.g., possibly due to the growth of erupting teeth, vertical movement or tilting of teeth, etc.).

[0045] If two 3D digital models of the same tooth differ significantly—for example, if the morphological differences between 3D digital models obtained from scans at different time points during tooth eruption are substantial—coarse registration based on a local coordinate system may not be feasible. In such cases, feature points can be used as reference points for registration, such as the buccal apex, FA point, and adjacent points. Currently, there are various methods for identifying feature points on 3D digital models of teeth, such as deep learning-based feature point recognition methods. A detailed description of feature point recognition will not be provided here.

[0046] In one embodiment, two 3D digital models of the same tooth can be measured, such as the mesiodistal width and crown height. By comparing the measured differences with a preset threshold, it can be determined whether there are significant differences between the two 3D digital models of the same tooth. If there are significant differences, feature points are used as reference points for coarse registration; otherwise, for convenience, coarse registration can be performed based on a local coordinate system.

[0047] In one embodiment, the Singular Value Decomposition (SVD) method can be used to coarsely register the first and second three-dimensional digital models based on the reference point.

[0048] In step 105, based on the coarse registration result, the first and second three-dimensional digital models are finely registered.

[0049] After the coarse registration, the first and second three-dimensional digital models are roughly aligned. Based on this, the teeth can be finely registered pairwise.

[0050] In one embodiment, the Iterative Closest Point (ICP) algorithm can be used to precisely register two three-dimensional digital models of the same tooth.

[0051] In one embodiment, the first and second three-dimensional digital models can be finely registered based on a vertex-to-face approach.

[0052] In one embodiment, the point pairs on which fine registration is based can be determined according to the following method: Sample some vertices, or select all vertices, on a first 3D digital model as a first set of points for fine registration. For each point in the first set of points, draw a ray from that point along its normal direction, find the intersection point of the ray with the second 3D digital model (i.e., the intersection point with a facet of the second 3D digital model), and take the origin of the ray and the intersection point as a point pair.

[0053] Since the relative positional relationship between the first and second three-dimensional digital models is unknown, the intersection of a unidirectional ray with the second three-dimensional digital model may not be a valid intersection. Therefore, rays can be drawn from the vertices of the first three-dimensional digital model along the normal in two opposite directions, or straight lines can be drawn through the vertices of the first three-dimensional digital model. This may result in two intersection points with the second three-dimensional digital model. The intersection point that is closer to the first three-dimensional digital model can be selected.

[0054] In addition, the second three-dimensional digital model may be missing a part of the first three-dimensional digital model. Therefore, a threshold can be set. If the distance between a vertex and all its corresponding intersections is greater than the threshold, then it is considered that the ray from the vertex along its normal has no valid intersection with the second three-dimensional digital model.

[0055] In another embodiment, the first and second three-dimensional digital models can be finely registered in a vertex-to-vertex manner.

[0056] In one embodiment, the point pairs upon which the fine registration is based can be determined according to the following method: A portion of the vertices, or all vertices, are sampled on the first 3D digital model as a first point set for fine registration. For each point in the first point set, the nearest vertex on the second 3D digital model is found, and these two vertices are considered as a point pair.

[0057] In one embodiment, a first distance threshold can be set. During the iteration process, if the distance between a pair of points is less than the first distance threshold, the pair of points is considered to have completed registration. In another embodiment, the first distance threshold can be determined based on the accuracy of the scanning device that generates the first and / or second 3D digital models. For example, if the accuracy of the scanning device is 0.1 mm, then the first distance threshold can be set to 0.08 mm, 0.1 mm, or 0.12 mm, etc. It is understood that the first distance threshold is not required to be equal to the scanning accuracy. Depending on the specific circumstances and requirements, a value can be selected as the first threshold within a certain range above and below the scanning accuracy.

[0058] In one embodiment, a ratio threshold can be set. If the proportion of registered point pairs is greater than the ratio threshold, the fine registration of the first and second three-dimensional digital models is considered to be complete.

[0059] In one embodiment, the following conditions can be set, and if any one of these conditions is met, the iteration will stop: (1) the proportion of registered point pairs is greater than the proportion threshold; (2) the number of iterations exceeds a preset number of iterations threshold; and (3) the pose after this iteration is less than a preset pose difference threshold (based on a comprehensive evaluation of translation and rotation).

[0060] Although the first and second 3D digital models correspond to the same tooth, as mentioned earlier, they may not perfectly align due to wear, attachments, and changes in the gingival line. Therefore, it is necessary to minimize the influence of these factors during the registration process.

[0061] In one embodiment, at least one of the following methods can be used to assign weights to the points on which fine registration is based, in order to minimize the impact of the above factors on fine registration:

[0062] (1) Assign weights based on the major axis coordinates of the local coordinate system: point pairs closer to the incisal edge of the tooth or the occlusal surface have higher weights, while point pairs closer to the gingival line have lower weights, in order to minimize the interference caused by changes in the gingival line.

[0063] (2) Assign weights based on the distance between point pairs: In each iteration, sort the distance between point pairs from largest to smallest, and assign lower weights to point pairs with larger distances, so as to minimize the interference caused by morphological differences.

[0064] (3) Assign weights based on distance threshold: A distance threshold can be preset. For example, the distance threshold can be set according to the scanning accuracy. In each iteration, if the distance of a pair of points exceeds the threshold, it is considered that the distance of the pair of points is caused by morphological differences, and its weight is reduced accordingly. It can even reduce its weight to zero, even if the pair of points does not participate in this iteration.

[0065] When the fine registration iteration stops, the following results are output:

[0066] (1) Rigid transformations (translation and rotation in three-dimensional space) between the first and second models;

[0067] (2) Confidence: The percentage of point pairs that have been successfully registered. The higher the percentage, the higher the confidence, indicating that the registration result is more reliable and can be used as a reference for subsequent processing.

[0068] (3) Outliers: Point pairs that have not been registered after the iteration stops. For example, the distance between these point pairs can be compared with the distance threshold mentioned above, and point pairs that are greater than the distance threshold are regarded as the morphological differences between the first and second models.

[0069] Through the precise registration, the first, second, and third 3D digital models are transformed to the same world coordinate system. Since the installation position of the third 3D digital model on the first 3D digital model is known, the deviation of the attachment position of the second 3D digital model can be detected based on the results of the precise registration and the designed target installation position.

[0070] In step 107, based on the results of the fine registration, the deviation between the attachment portion of the second three-dimensional digital model and the third three-dimensional digital model located at the target installation position is detected.

[0071] After the fine registration, if the position of the attachment of the second three-dimensional digital model is not deviated, it should be aligned with the third three-dimensional digital model located at the target installation position of the design.

[0072] Detecting the deviation of the attachment position is essentially done by moving the third or second three-dimensional digital model to align the two attachments. The distance and direction of the movement are the distance and direction of the deviation.

[0073] In one embodiment, the bottom surface (i.e., the mounting surface) of the third 3D digital model can be used as a reference surface, and some vertices or all vertices can be sampled on it to obtain a third point set. For each point in the third point set, a ray is drawn from that point along its normal direction, and the intersection points of the ray with the second and third 3D digital models are calculated respectively. Two intersection points on the ray are considered as a pair of points. The sum of the distances of all these pairs of points is calculated and used as the objective function.

[0074] In one embodiment, if a ray does not intersect with the second 3D digital model, a point pair can be assumed to exist, and a preset distance value can be assigned to this point pair. In one embodiment, the preset distance value can be the maximum height of the attachment or a value greater than it. This allows the objective function to achieve a larger result even when the attachment of the second 3D digital model deviates from its normal position.

[0075] Typically, the bottom surface of the attachment is a plane. Since the deviation of the attachment's position is not too large, it can be approximated as a deviation along the bottom surface of the attachment. Therefore, the search can be performed along the direction of the attachment's bottom surface. If moving the second or third 3D digital model along the four directions of the bottom surface of the third 3D digital model does not reduce the objective function, then the two attachments are considered to be aligned, and the direction and distance of the movement are taken as the deviation of the attachment.

[0076] Please refer to Figure 2A The diagram schematically illustrates the relative positions of two attachments before alignment. The boxes represent the third 3D digital model, the semicircles represent the attachment portions of the second 3D digital model, and the arrows represent rays passing through the vertices of the bottom surface of the third 3D digital model. The boxes and semicircles in the diagram do not represent the actual shapes of the attachments; they are only used to distinguish the two 3D digital models of the attachments to illustrate their positions.

[0077] Please refer to Figure 2B It schematically demonstrates Figure 2A The relative positions of the two attachments after alignment are shown.

[0078] Although various aspects and embodiments of this application have been disclosed herein, other aspects and embodiments of this application will be apparent to those skilled in the art upon inspiration from this application. The various aspects and embodiments disclosed herein are for illustrative purposes only and not for limiting purposes. The scope and spirit of this application are determined solely by the appended claims.

[0079] Similarly, the diagrams may illustrate exemplary architectures or other configurations of the disclosed methods and systems, which aid in understanding the features and functions that may be included in the disclosed methods and systems. The claims are not limited to the exemplary architectures or configurations shown, and the desired features may be implemented with various alternative architectures and configurations. Furthermore, the order of the blocks given herein with respect to flowcharts, functional descriptions, and method claims should not be limited to various embodiments implemented in the same order to perform the said functions, unless explicitly indicated in the context.

[0080] Unless otherwise expressly stated, the terms and phrases used herein, and their variations thereof, should be interpreted as open-ended rather than restrictive. In some instances, the appearance of extended words and phrases such as “one or more,” “at least,” “but not limited to,” or other similar expressions should not be construed as an intention or necessity to indicate a narrower scope in examples where such extended expressions might not exist.

Claims

1. A computer-executed method for detecting attachment position deviation, comprising: Obtain first, second, and third three-dimensional digital models, wherein the third three-dimensional digital model is a three-dimensional digital model representing the first accessory, the first three-dimensional digital model is a three-dimensional digital model representing the first tooth without the first accessory installed, and the second three-dimensional digital model is a three-dimensional digital model representing the first tooth with the first accessory actually installed. Obtain the target installation position of the third three-dimensional digital model on the first three-dimensional digital model; Based on the local coordinate systems of the first and second three-dimensional digital models, the two are coarsely registered; The coarsely registered first and second 3D digital models were finely registered using the ICP method; and Based on the results of the fine registration, a search is performed along the bottom surface of the third three-dimensional digital model located at the target installation position, so that the third three-dimensional digital model is partially aligned with the first attachment of the second three-dimensional digital model, thereby obtaining the deviation between the actual installation position of the first attachment and the target installation position.

2. The computer-executed method for detecting attachment position deviation as described in claim 1, characterized in that, The coarse registration is based on the SVD method.

3. The computer-executed method for detecting accessory position deviation as described in claim 1, characterized in that, The coarse registration includes selecting multiple corresponding reference points in the local coordinate systems of the first and second three-dimensional digital models, respectively. Each pair of reference points has the same coordinate values, and the coarse registration of the first and second three-dimensional digital models is based on these reference points.

4. The computer-executed method for detecting attachment position deviation as described in claim 1, characterized in that, In the fine registration, the weights of the point pairs it is based on are assigned according to at least one of the following: (1) Assign weights based on the major axis coordinates of the local coordinate system: point pairs closer to the incisal edge of the tooth or the occlusal surface have higher weights, while point pairs closer to the gingival line have lower weights. (2) Assign weights based on the distance between point pairs: In each iteration, sort the point pairs by distance from largest to smallest, and point pairs with larger distances have lower weights; as well as (3) Assign weights based on distance thresholds: In each iteration, if the distance between a pair of points exceeds a preset distance threshold, its weight is reduced.

5. The computer-executed method for detecting attachment position deviation as described in claim 1, characterized in that, It also includes: calculating the confidence level of the fine registration based on the proportion of point pairs that have completed registration.

6. The computer-executed method for detecting attachment position deviation as described in claim 1, characterized in that, It also includes: based on the first and second three-dimensional digital models of the coarse registration, drawing rays along the normal from a vertex of one of the first and second three-dimensional digital models to obtain the intersection points of these rays with the other of the first and second three-dimensional digital models, the intersection points and the corresponding vertices forming a first set of point pairs including multiple point pairs, as the point pairs on which the fine registration is based.

7. The computer-executed method for detecting attachment position deviation as described in claim 1, characterized in that, The second three-dimensional digital model was obtained by scanning the first tooth on which the first accessory was installed.

8. The computer-executed method for detecting attachment position deviation as described in claim 1, characterized in that, The bottom surface of the third three-dimensional digital model is a plane.

9. The computer-executed method for detecting attachment position deviation as described in claim 1, characterized in that, It also includes: drawing rays along the normal direction from multiple points on the bottom surface of the third three-dimensional digital model, taking the intersection of each ray with the second and third three-dimensional digital models as a point pair, forming a second set of point pairs including multiple point pairs, and the objective function of the search is the sum of the distances between the point pairs in the second set of point pairs.

10. The computer-executed method for detecting attachment position deviation as described in claim 9, characterized in that, It also includes: if a ray from a vertex on the bottom surface of the third three-dimensional digital model does not intersect with the second three-dimensional digital model, it is assumed that there is a pair of points on the ray, and a preset distance value is assigned to the pair of points as the distance between the pair of points.

11. The computer-executed method for detecting attachment position deviation as described in claim 10, characterized in that, The preset distance value is greater than or equal to the maximum height of the first attachment.

12. A computer system for detecting attachment position deviation, comprising a storage device and a processor, the storage device storing a computer program for detecting attachment position deviation, wherein when the program is run, the processor executes the method for detecting attachment position deviation as described in claim 1.

Images