Method for generating digital data set representing target tooth layout

Abstract

A computer-implemented method (100) for generating a digital data set representing a target tooth layout, comprising: acquiring a first three-dimensional digital model representing a first dentition in an initial tooth layout (101); acquiring a set of predetermined constraints, including target positions of selected teeth of the first dentition in a selected direction; using a trained first deep neural network to perform initial alignment on the first three-dimensional digital model (103); and performing first optimization on the first three-dimensional digital model having undergone initial alignment (105), the first optimization comprising: moving the selected teeth of the first three-dimensional digital model having undergone initial alignment to the target positions in the selected direction; and optimizing a dental arch curve of the first three-dimensional digital model, and performing collision cancellation and / or diastema closure on the first three-dimensional digital model at the same time.

Description

Method for generating a digital data set representing a target tooth layout Technical Field

[0001] The present application generally relates to methods for generating a digital dataset representing a target tooth placement in conjunction with a deep learning neural network and predetermined constraints. Background Art

[0002] With the rapid development of computer technology, dental diagnosis and treatment are increasingly relying on computer technology. When formulating an orthodontic treatment plan, a three-dimensional digital model representing the dentition in the target tooth layout is usually generated based on the three-dimensional digital model representing the dentition in the initial tooth layout.

[0003] At present, there are mainly two methods for generating a three-dimensional digital model of the dentition under the target tooth layout based on a three-dimensional digital model representing the dentition under the initial tooth layout. One is to align the teeth based on pre-established rules, which are generally derived from the doctor's experience. The inventors of the present application found that due to the large differences in tooth shape and posture (position and posture) of different patients, it is difficult to formulate a set of universal rules applicable to various situations. Therefore, this method has great limitations. The other is a method based on deep learning, for example, a deep neural network is trained with a training data set (including multiple sets of three-dimensional digital models representing the dentition under the initial layout and a three-dimensional digital model representing the dentition under the target layout), and the teeth are aligned using the deep neural network trained by the path. The inventors of the present application found that due to the lack of constraints, the results produced by this method may not meet the requirements of clinical medicine.

[0004] Therefore, it is necessary to provide a new method for generating a digital data set representing a target tooth layout.

[0005] Summary of the Invention

[0006] One aspect of the present application provides a computer-implemented method for generating a digital data set representing a target tooth layout, comprising: obtaining a first three-dimensional digital model representing a first dental row under an initial tooth layout; obtaining a set of predetermined constraints, which include target positions of selected teeth of the first dental row in a selected direction; using a trained first deep neural network to preliminarily align the first three-dimensional digital model; and performing a first optimization on the preliminarily aligned first three-dimensional digital model, the first optimization comprising: moving the selected teeth of the preliminarily aligned first three-dimensional digital model to the target positions in the selected direction; and optimizing the dental arch curve of the first three-dimensional digital model, while performing collision elimination and / or gap closing on the first three-dimensional digital model.

[0007] In some embodiments, if the constraints include a collision contact and / or gap closing scheme of the first dentition, the collision contact and / or gap closing of the first three-dimensional digital model is based on the collision contact and / or gap closing scheme of the first dentition.

[0008] In some embodiments, the collision relief and / or space closing scheme of the first dentition includes one of the following: tooth extraction, tooth implantation, posterior tooth distalization, posterior tooth mesialization, arch expansion, arch retraction, lip inclination, anterior tooth retraction, slice cutting, space reservation and any combination thereof.

[0009] In some embodiments, if the constraints include a slice cutting and gap reservation scheme for the first dental arch obtained by analyzing the width of each tooth of the first dental arch, the requirements for collision resolution and / or gap closure of the first three-dimensional digital model are determined based on the slice cutting and gap reservation scheme.

[0010] In some embodiments, during the dental arch curve optimization, the posture of the selected tooth remains unchanged after it is moved to the target position in the selected direction.

[0011] In some embodiments, moving the selected tooth to the target position in the selected direction is performed simultaneously with the dental arch curve optimization and the collision contact and / or space closing.

[0012] In some embodiments, the method for generating a digital data set representing a target tooth layout further includes: obtaining a second three-dimensional digital model representing a second tooth row under the initial tooth layout, the second tooth row being the opposing tooth row of the first tooth row; using a trained second deep neural network to preliminarily align the second three-dimensional digital model based on the first optimized first three-dimensional digital model; performing a second optimization on the preliminarily aligned second three-dimensional digital model, the second optimization including: performing occlusion optimization on the preliminarily aligned second three-dimensional digital model based on the first optimized first three-dimensional digital model, so that the occlusion relationship between the second optimized second three-dimensional digital model and the first optimized first three-dimensional digital model meets the requirements.

[0013] In some embodiments, while the occlusion is being optimized, collision resolution and / or space closing are performed on the updated second three-dimensional digital model according to a collision resolution and / or space closing scheme of the second dentition in the constraint.

[0014] In some embodiments, the collision relief and / or space closing scheme for the second dentition includes one of the following: tooth extraction, tooth implantation, posterior tooth distalization, posterior tooth mesialization, arch expansion, arch retraction, lip inclination, anterior tooth retraction, slice cutting, space reservation and any combination thereof.

[0015] In some embodiments, if the constraints include a slice cutting and gap reservation scheme for the second dental arch obtained based on an analysis of the width of each tooth of the second dental arch, the requirements for collision resolution and / or gap closure of the second three-dimensional digital model are determined based on the slice cutting and gap reservation scheme.

[0016] In some embodiments, the target position of the selected tooth in the selected direction includes one of the following: tooth midline target position, anterior tooth sagittal target position, anterior tooth vertical target position, posterior tooth vertical target position, posterior tooth sagittal target position, posterior tooth horizontal target position, canine horizontal target position and any combination of the above.

[0017] In some embodiments, the first dentition is the maxillary dentition and the second dentition is the mandibular dentition.

[0018] In some embodiments, the occlusal optimization is based on an energy function of an occlusal relationship, where the occlusal relationship is defined by the positional relationship between selected key points of the teeth.

[0019] In some embodiments, the method of generating a digital dataset representing a target tooth layout further comprises: further aligning the first optimized first three-dimensional digital model and the second optimized second three-dimensional digital model using a trained third deep neural network.

[0020] In some embodiments, the first three-dimensional digital model is input into the first deep neural network, which outputs a digital dataset representing the tooth layout of the preliminary aligned first three-dimensional digital model.

[0021] In some embodiments, the first optimized first three-dimensional digital model and the second three-dimensional digital model are input into the second deep neural network, which outputs a digital dataset representing the tooth layout of the preliminary aligned second three-dimensional digital model.

[0022] In some embodiments, the first optimized first three-dimensional digital model and the second optimized second three-dimensional digital model are input into the third deep neural network, which outputs a digital dataset representing the tooth layout of the further aligned first three-dimensional digital model and the second three-dimensional digital model. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other features of the present application will be further described below in conjunction with the accompanying drawings and detailed description thereof. It should be understood that these drawings only illustrate several exemplary embodiments of the present application and should not be considered to limit the scope of protection of the present application. Unless otherwise specified, the drawings are not necessarily to scale, and similar reference numerals represent similar components.

[0024] FIG1 is a schematic flow chart of a method for generating a digital data set representing a target tooth layout in one embodiment of the present application;

[0025] FIG2 schematically illustrates the basic structure of a first deep neural network in one embodiment of the present application;

[0026] FIG3 is a schematic flow chart of a method for generating constraints for tooth arrangement in one embodiment of the present application;

[0027] FIG4 shows an example of the target positions of the maxillary anterior teeth (including sagittal and vertical directions) and the vertical target positions of the maxillary posterior teeth marked by the fifth deep neural network on a lateral radiograph; and

[0028] FIG5 is a schematic module diagram of a computer program for generating collision resolution and gap closing solutions in one embodiment of the present application. DETAILED DESCRIPTION

[0029] The following detailed description refers to the accompanying drawings that form a part of this specification. The exemplary embodiments mentioned in the specification and drawings are for illustrative purposes only and are not intended to limit the scope of protection of this application. In light of this application, those skilled in the art will understand that many other embodiments can be adopted and various changes can be made to the described embodiments without departing from the subject matter and scope of protection of this application. It should be understood that the various aspects of the present application described and illustrated herein can be arranged, replaced, combined, separated and designed according to many different configurations, all of which are within the scope of protection of this application.

[0030] One aspect of the present application provides a computer-implemented method for generating a digital data set representing a target tooth layout, which combines tooth arrangement using a deep neural network and optimization based on pre-established constraints, has wide applicability, and the results generated meet clinical medical requirements and the special requirements of dental professionals for orthodontic treatment of specific cases (if any).

[0031] The target tooth arrangement refers to the tooth arrangement that is expected to be achieved through orthodontic treatment. It is understood that the target tooth arrangement may be different for different patients.

[0032] Please refer to FIG1 , which is a schematic flowchart of a method 100 for generating a digital data set representing a target tooth layout and executed by a computer in one embodiment of the present application.

[0033] In 101 , a first three-dimensional digital model of a first dentition and a second three-dimensional digital model of a second dentition are obtained, each representing an initial tooth layout.

[0034] The first dentition may be the patient's maxillary dentition or mandibular dentition, and the second dentition is the opposing dentition of the first dentition.

[0035] The initial tooth layout is the layout of the patient's teeth based on which the digital data set representing the target tooth layout is generated using the method of the present application. For example, the initial tooth layout can be the patient's tooth layout before orthodontic treatment begins, or it can be the patient's tooth layout at any time during orthodontic treatment (when the treatment plan is being re-formulated during orthodontic treatment).

[0036] The first and second three-dimensional digital models are segmented three-dimensional digital models, that is, the teeth are independent of each other and each tooth can be moved individually.

[0037] In one embodiment, a three-dimensional digital model representing the patient's dentition in the initial dental configuration can be obtained by directly scanning the patient's jaw. In another embodiment, a physical model of the patient's jaw, such as a plaster model, can be scanned to obtain a three-dimensional digital model representing the patient's dentition in the initial dental configuration. In yet another embodiment, an impression of the patient's jaw can be scanned to obtain a three-dimensional digital model representing the patient's dentition in the initial dental configuration.

[0038] In 103 , the first three-dimensional digital model is preliminarily aligned using a trained first deep neural network.

[0039] In one embodiment, the first three-dimensional digital model can be input into the trained first deep neural network, which preliminarily aligns the first three-dimensional digital model and outputs the rotation matrix and translation matrix of each tooth. These rotation matrices and translation matrices are applied to the first three-dimensional digital model to obtain the preliminarily aligned first three-dimensional digital model.

[0040] In one embodiment, the training data set used to train the first deep neural network may include multiple sets of training data. In the case where the first dentition is the maxillary dentition, each set of training data includes a three-dimensional digital model of the misaligned maxillary dentition and a three-dimensional digital model of the aligned maxillary dentition.

[0041] In one embodiment, the first deep neural network may be a Transformer-based deep neural network.

[0042] Please refer to Figure 2, which schematically shows the basic structure of the first deep neural network 200 in one embodiment of the present application.

[0043] The first deep neural network 200 includes a Point Encoder 201 , a Transformer Layer 203 , and a Transformer Decoder 205 .

[0044] Before inputting the first three-dimensional digital model into the first deep neural network 200, it is first converted into a point cloud.

[0045] Point Encoder 201 encodes a single tooth and the neighborhood of the single tooth selected by Point Encoder 201 to generate an embedding (also called a feature vector) of the single tooth. In one embodiment, Point Encoder 201 can encode based on the three-dimensional coordinates and normal vector of the point.

[0046] The Transformer Layer 203 fuses the Embeddings of the teeth of the first dentition to generate preliminarily aligned Embeddings of the teeth of the first dentition.

[0047] Transform Decoder 205 converts the embeddings of each tooth in the preliminarily aligned first dentition into rotation and translation matrices. The rotation and translation matrices corresponding to each tooth represent the difference between the tooth's initial position (including position and posture) and its position after the preliminarily aligned teeth. These rotation and translation matrices are applied to the corresponding teeth in the first 3D digital model to obtain the preliminarily aligned first 3D digital model.

[0048] In light of this application, it can be understood that, in addition to the above network structure, the first deep neural network can adopt any other applicable neural network.

[0049] In a preferred embodiment, the first dentition is the maxillary dentition. In light of this application, it is understood that the first dentition may also be the mandibular dentition.

[0050] In 105 , a first optimization is performed on the preliminarily aligned first three-dimensional digital model based on predetermined constraints.

[0051] During orthodontic treatment planning, certain parameters of the treatment goal can be determined based on the patient's specific dental situation. For example, target positions of selected teeth in selected directions, collision resolution and / or space closure strategies, and slice and space preparation strategies based on tooth width analysis.

[0052] In one embodiment, the target position of the selected tooth in the selected direction may include one of the following: tooth midline target position, anterior tooth sagittal target position, anterior tooth vertical target position, posterior tooth sagittal target position, posterior tooth horizontal target position, canine horizontal target position, posterior tooth vertical target position and any combination of the above.

[0053] In one embodiment, the first three-dimensional digital model of the preliminary alignment can be operated accordingly according to the target position of the selected teeth of the first dental row in the constraint in the selected direction, that is, the position of the selected teeth of the first three-dimensional digital model of the preliminary alignment in the selected direction can be repositioned to the target position.

[0054] In one embodiment, the target tooth centerline position can be achieved by adjusting the position of the anterior teeth in the mesiodistal direction.

[0055] Moving the preselected teeth in the preliminarily aligned first three-dimensional digital model to the target position in the preselected direction may result in a less smooth dental arch curve in the first three-dimensional digital model. In one embodiment, the dental arch curve may be optimized while moving the preselected teeth to the target position in the preselected direction.

[0056] In one embodiment, an initial dental arch curve may be fitted based on the preliminarily aligned first three-dimensional digital model, and the dental arch curve may be optimized based on the initial dental arch curve.

[0057] Methods for fitting dental arch curves and the characteristic points used are well known in the art. For example, a spline curve or polynomial function can be used to fit the dental arch curve. For example, the dental arch curve can be fitted using the tooth's FA point, or the molar cusp, canine cusp, and central incisor midpoint as characteristic points.

[0058] In one embodiment, the preselected teeth may be moved one by one to the target position in the preselected direction, or a plurality of the preselected teeth may be moved simultaneously to the target position in the preselected direction.

[0059] In one embodiment, for the pre-selected teeth that have been moved to the target position in the pre-selected direction, their characteristic points are used as control points. During the optimization process of the dental arch curve, the positions of these control points are kept stationary, so that the optimization of the dental arch curve does not change the posture of these teeth, thereby preventing the posture of these teeth from deviating from the target position in the pre-selected direction.

[0060] In one embodiment, while optimizing the dental arch curve, the first three-dimensional digital model may also be subjected to collision and contact and / or gap closure, such that the first optimized first three-dimensional digital model meets collision and gap requirements. If the constraints include a collision resolution and / or gap closure scheme for the first dentition, the collision and contact and / or gap closure are performed according to the scheme.

[0061] The collision resolution and / or space closure plan may include one of the following: tooth extraction, tooth implantation, arch expansion, arch reduction, posterior tooth distalization, posterior tooth mesialization, lip inclination, anterior tooth retraction, slice cutting, space reservation and any combination of the above.

[0062] In one embodiment, the collision resolution and / or gap closing scheme may only specify which means may be used to perform collision resolution and / or gap closing without specifying specific parameters for these means.

[0063] If the constraints include a slice cutting and / or space reservation scheme for the first dental arch obtained based on an analysis of the tooth width, the requirements for collision resolution and / or space closure can be determined based on the slice cutting and / or space reservation scheme, and the first three-dimensional digital model can be subjected to collision resolution and / or space closure according to the requirements.

[0064] In one embodiment, the allowed collision amount may represent the slice amount, and the allowed gap amount may represent the gap reserve amount. Thus, the first 3D digital model does not need to be modified before performing collision resolution and / or gap closing on the first 3D digital model.

[0065] In another embodiment, before performing collision resolution and / or gap closure on the first three-dimensional digital model, the first three-dimensional digital model may also be modified according to the slice cutting and / or gap reservation scheme. For example, the corresponding teeth may be sliced ​​according to the slice cutting amount, denture cavities may be added according to the gap reservation amount, and then collision resolution and / or gap closure may be performed on the modified first three-dimensional digital model. It should be noted that both of these schemes fall under the aforementioned requirement of determining the collision resolution and / or gap closure based on the slice cutting and / or gap reservation scheme, and performing collision resolution and / or gap closure on the first three-dimensional digital model in accordance with such requirement.

[0066] In another embodiment, the preselected teeth may be moved to the target position in the preselected direction first, and then the dental arch curve may be optimized and the collision contact and / or gap closing may be performed.

[0067] The pre-selected teeth of the preliminarily aligned first three-dimensional digital model are moved to the target position in the pre-selected direction, and the dental arch curve is optimized and the collision contact and / or gap closing are performed on the first three-dimensional digital model. Thus, the first optimized first three-dimensional digital model is obtained. At this time, it meets both aesthetic requirements and clinical medical requirements as well as special requirements of dental professionals for orthodontic treatment of the case (if any).

[0068] Then, the second three-dimensional digital model may be aligned based on the first optimized first three-dimensional digital model.

[0069] In 107 , the second three-dimensional digital model is preliminarily aligned based on the first optimized first three-dimensional digital model using a trained second deep neural network.

[0070] The first optimized first three-dimensional digital model and the second three-dimensional digital model are input into the trained second deep neural network, which uses the first optimized first three-dimensional digital model as a reference to preliminarily align the second three-dimensional digital model and output the preliminarily aligned second three-dimensional digital model.

[0071] In one embodiment, the second deep neural network can adopt the same structure as the first deep neural network. Under the guidance of this application, it can be understood that the second deep neural network can also adopt any other applicable deep neural network.

[0072] Unlike the first deep neural network, the input of the second deep neural network includes a three-dimensional digital model of the aligned first dental row and a three-dimensional digital model of the unaligned second dental row. When preliminarily aligning the second three-dimensional digital model, not only the positional relationship between the corresponding teeth of the second dental row is considered, but also the relative positional relationship between each tooth of the second dental row and the relevant teeth of the first dental row is considered.

[0073] In one embodiment, the training data set used to train the second deep neural network may include multiple sets of training data. When the first dentition is the maxillary dentition, each set of training data includes a three-dimensional digital model of the aligned maxillary dentition, a three-dimensional digital model of the misaligned mandibular dentition, and a three-dimensional digital model of the aligned mandibular dentition.

[0074] In 109 , a second optimization is performed on the preliminarily aligned second three-dimensional digital model based on the predetermined constraints and the first optimized first three-dimensional digital model.

[0075] The occlusal relationship between the first optimized first three-dimensional digital model and the preliminarily aligned second three-dimensional digital model may not meet the requirements.

[0076] Therefore, the occlusal optimization of the preliminarily aligned second three-dimensional digital model can be performed based on the first optimized first three-dimensional digital model, so that the occlusal relationship of the upper and lower teeth is normal after optimization.

[0077] In one embodiment, an energy function may be defined according to the occlusal relationship between the upper and lower teeth, and then an optimization algorithm may be used to optimize the overall position of the updated second three-dimensional digital model and the posture of the corresponding teeth.

[0078] In one embodiment, the occlusal relationship of the maxillary and mandibular teeth may be defined based on the positional relationship between key points on the respective teeth, such as the cusp points and the central sulcus.

[0079] It is understood that the optimization based on the energy function may adopt any applicable optimization algorithm, such as second-order Newton optimization, numerical optimization, stochastic gradient descent optimization, etc.

[0080] In one embodiment, if the constraint includes a collision resolution and / or gap closing scheme for the second dental arch, during the occlusion optimization process, the collision resolution and / or gap closing scheme can be used to simultaneously resolve the collision and / or close the gap of the second three-dimensional digital model that is preliminarily aligned, so that the second optimized second three-dimensional digital model meets the collision and gap requirements.

[0081] The collision resolution and / or space closure plan may include one of the following: tooth extraction, tooth implantation, arch expansion, arch reduction, posterior tooth distalization, posterior tooth mesialization, lip inclination, anterior tooth retraction, slice cutting, space reservation and any combination of the above.

[0082] In some special cases, the desired occlusal relationship may differ from the standard occlusal relationship. For example, in an overbite or overjet, correction may be desired to a deep overbite rather than a normal overbite. In this case, the constraints may include this special occlusal relationship provided by the dental professional, so that the occlusal optimization is performed according to this special occlusal relationship.

[0083] If the constraints include a slicing and / or gap reservation scheme for the second dentition based on an analysis of tooth width, the collision resolution and / or gap closing requirements can be determined based on the slicing and / or gap reservation scheme. Similarly, in one embodiment, the slicing amount can represent an allowable collision amount, and the gap reservation amount can represent an allowable gap amount. When performing collision resolution and / or gap closing on the second three-dimensional digital model, the requirements are followed.

[0084] At this time, the first three-dimensional digital model after the first optimization and the second three-dimensional digital model after the second optimization may not fully conform to the statistical laws of aligning teeth. Therefore, the trained third deep neural network can be used to further align the two to make them further conform to the statistical laws of aligning teeth.

[0085] In 111 , the first optimized first three-dimensional digital model and the second optimized second three-dimensional digital model are further aligned using a trained third deep neural network.

[0086] The first optimized first three-dimensional digital model and the second optimized second three-dimensional digital model are input into the trained third deep neural network, which further aligns the first and second three-dimensional digital models and outputs the further aligned first and second three-dimensional digital models, which are the goals of the orthodontic treatment plan.

[0087] In light of this application, it can be understood that, based on different network designs, the third deep neural network can output a three-dimensional digital model, or can output the translation and rotation matrices of each tooth, or can output the target pose of each tooth, all of which can be referred to as a digital dataset representing the target tooth layout. Similarly, the first and second deep neural networks can also output a three-dimensional digital model of the dentition, or the translation and rotation matrices, or poses of each tooth in the dentition, based on different network designs.

[0088] In one embodiment, the third deep neural network can adopt the same structure as the first deep neural network. Under the guidance of this application, it can be understood that the third deep neural network can also adopt any other applicable deep neural network.

[0089] In one embodiment, the training data set for training the third deep neural network may include multiple sets of training data, each set of training data including a three-dimensional digital model of the misaligned upper and mandibular dentition and a three-dimensional digital model of the aligned upper and mandibular dentition.

[0090] Another aspect of the present application provides a computer-implemented method for generating the constraint conditions.

[0091] In one embodiment, the constraints may be generated based on a three-dimensional digital model representing the patient's initial dental configuration, a frontal open-mouth radiograph, and a lateral radiograph.

[0092] Please refer to FIG3 , which is a schematic flowchart of a method 300 for generating constraint conditions for tooth arrangement executed by a computer in one embodiment of the present application.

[0093] In 301 , a third three-dimensional digital model, a frontal open-mouth radiograph, and a lateral radiograph representing the initial dental arrangement of the patient are acquired.

[0094] The methods for obtaining the third three-dimensional digital model, the frontal open-mouth radiograph, and the lateral radiograph representing the patient's initial dental layout are well known in the art and will not be described in detail here.

[0095] The front open-mouth photo is a photo of the patient taken from the front with the mouth open and teeth showing. A typical example is a front smiling photo of the patient.

[0096] In one embodiment, the third three-dimensional digital model includes the upper and lower jaw dentition in an occluded state, that is, it includes the first and second three-dimensional digital models in an occluded state.

[0097] In 303 , a first registration is performed on the third three-dimensional digital model and the front opening photograph.

[0098] In one embodiment, the third three-dimensional digital model and the frontal opening photograph may be registered using a simple size matching method.

[0099] In some cases, the direction of the front opening shot may not be strictly correct. Therefore, in one embodiment, a trained deep neural network can be used to adjust the direction of the front opening shot to correct it.

[0100] In one embodiment, the training data set for correcting the front open-face photo includes multiple sets of training data, each set of training data includes an original front open-face photo and the rotation angle required to correct it.

[0101] In one embodiment, the third three-dimensional digital model can be projected from front to back, and then the front open-mouth view can be scaled so that the teeth in the front open-mouth view overlap with the corresponding teeth in the projection. After registration, the physical dimensions of the front open-mouth view are obtained based on the third three-dimensional digital model.

[0102] In light of the present application, it can be understood that, in addition to the size matching method, the registration of the third three-dimensional digital model and the front opening photograph may also be performed using any other applicable method.

[0103] In 305 , a second registration is performed on the third three-dimensional digital model and the lateral radiograph.

[0104] The registration of the third three-dimensional digital model and the lateral film can be viewed as a process of searching for camera intrinsic and extrinsic parameters, i.e., finding a set of camera intrinsic and extrinsic parameters in the parameter space, such that the projections of preselected key points on the third three-dimensional digital model based on the set of camera intrinsic and extrinsic parameters have the highest degree of match with the corresponding key points in the lateral film.

[0105] In one embodiment, the registration may adopt a PnP (Perspective-n-Point) algorithm or an iterative optimization method.

[0106] After registration, the physical size of the lateral view based on the third three-dimensional digital model is obtained.

[0107] In 307 , a trained fourth deep neural network is used to generate a facial midline based on the frontal open-face radiograph, and a tooth midline target position is determined based on the position of the facial midline and the result of the first registration.

[0108] In one embodiment, it is only necessary to determine the position of the plane midline in the horizontal direction.

[0109] In one embodiment, the fourth deep neural network can be used to generate a heat map based on the frontal open-face view, and then the heat map can be post-processed to obtain the location of the facial midline. In the heat map, the key point used to generate the facial midline has the highest value. In one example, the tip of the nose has the highest value in the heat map, and a vertical line drawn through the tip of the nose can obtain the facial midline.

[0110] In one embodiment, the training data set used to train the fourth deep neural network may include multiple sets of training data, each set of training data including a frontal open-face photo and the position of the face midline of the frontal open-face photo.

[0111] In one embodiment, the fourth deep neural network may adopt HRNet. In light of this application, it can be understood that in addition to HRNet, the fourth neural network may also adopt any other applicable deep neural network.

[0112] In light of this application, it can be understood that in addition to deep neural networks, a regression method using machine learning can also be used to generate the facial midline based on the frontal open-face photography.

[0113] In another embodiment, the fourth deep neural network can also be used to directly predict the location of the facial midline based on the frontal open-face view, without converting the frontal open-face view into a heat map. For example, the fourth deep neural network can be used to determine the location of the nose tip in the frontal open-face view, and a line perpendicular to the horizontal direction can be drawn through the nose tip to obtain the facial midline.

[0114] After obtaining the facial midline, the tooth midline target position of the third three-dimensional digital model may be determined based on the result of the first registration.

[0115] In 309, the trained fifth deep neural network is used to predict the sagittal target position of the anterior teeth, the vertical target position of the anterior teeth, the sagittal target position of the posterior teeth, and the vertical target position of the posterior teeth in the lateral film based on the lateral film, and the sagittal target position of the anterior teeth, the vertical target position of the anterior teeth, the sagittal target position of the posterior teeth, and the vertical target position of the posterior teeth in the third three-dimensional digital model are calculated based on the result of the second alignment and the predicted target position.

[0116] In one embodiment, the fifth deep neural network may adopt HRNet. In light of the present application, it can be understood that in addition to HRNet, the fifth neural network may also adopt any other applicable deep neural network.

[0117] In one embodiment, the training data set used to train the fifth deep neural network may include multiple sets of training data, each set of training data including a lateral radiograph without the target position marked and a lateral radiograph with the target position marked.

[0118] Please refer to Figure 4, which shows an example of lateral radiographs of the target positions (including sagittal target positions and vertical target positions) of the maxillary anterior teeth (tooth numbers 11 and 21) and the vertical target positions of the maxillary posterior teeth (tooth numbers 16 and 26) labeled by the fifth deep neural network.

[0119] Since the lateral view includes not only teeth but also other tissues, during training, the fifth deep neural network not only learns the positional relationship between teeth, but also learns the positional relationship between teeth and other corresponding tissues, so that the predicted target position further meets medical requirements.

[0120] In 311 , a trained sixth deep neural network is used to predict a target position of the posterior teeth in the horizontal direction based on the WALA ridge and corresponding key points of the first or second three-dimensional digital model.

[0121] It should be noted that the horizontal direction in this application refers to the left and right direction of the patient's jaw.

[0122] In one embodiment, the trained seventh deep neural network may be used to mark the WALA ridges and pre-selected key points of each tooth in the first or second three-dimensional digital model, such as the FA point and the cusp point.

[0123] In one embodiment, the seventh deep neural network may adopt a Point Transformer network. In the light of this application, it is understood that in addition to Point Transformer, the seventh deep neural network may also adopt any other applicable network.

[0124] Next, the WALA ridge and key points are input into the sixth deep neural network to obtain the horizontal target position of the posterior teeth.

[0125] In one embodiment, the sixth deep neural network may adopt HRNet. In light of the present application, it can be understood that in addition to HRNet, the sixth neural network may also adopt any other applicable deep neural network.

[0126] In one embodiment, the training data set used to train the sixth deep neural network can be extracted from existing tooth arrangement cases.

[0127] In one embodiment, the sixth deep neural network may be used to predict the horizontal target position of the posterior teeth and / or canines of the first dentition based on the WALA ridges of the first three-dimensional digital model and selected key points of each tooth.

[0128] In another embodiment, the sixth deep neural network can also be used to predict the horizontal target position of the posterior teeth of the second dental arch based on the WALA ridge and selected key points of each tooth of the second three-dimensional digital model, and then calculate the horizontal target position of the posterior teeth of the first dental arch based on the normal occlusal relationship.

[0129] According to clinical experience, the mandible is generally more stable. Therefore, if the first dentition is the maxillary dentition, a preferred embodiment is to use the sixth neural network to predict the horizontal target position of the posterior teeth of the second dentition based on the WALA ridge and selected key points of each tooth in the second three-dimensional digital model, and then calculate the horizontal target position of the posterior teeth of the first dentition based on the normal occlusal relationship.

[0130] In one embodiment, the positions of the corresponding key points of the teeth may be used to represent the sagittal target position of the anterior teeth, the vertical target position of the anterior teeth, the vertical target position of the posterior teeth, and the horizontal target position of the posterior teeth.

[0131] In 313 , the trained eighth deep neural network is used to predict whether the left and right sides of each tooth need to be sliced ​​or a gap is reserved based on the width of each tooth in the third three-dimensional digital model.

[0132] In orthodontic treatment, in addition to tooth position, the width ratio between the maxillary and mandibular teeth, known as the Bolton index, must also be considered. For example, the ratio of the total crown widths of the maxillary and mandibular anterior teeth, as well as the total crown widths of all maxillary and mandibular teeth, can be used to determine if there is a crown width disparity between the patient's maxillary and mandibular dentitions.

[0133] The eighth deep neural network is essentially a Bolton exponential optimization network.

[0134] The width and tooth number of each tooth in the third three-dimensional digital model are input into the eighth deep neural network to obtain the required slice cutting amount and reserved gap amount on the left and right sides of each tooth.

[0135] In one embodiment, for teeth that are too small, it is not recommended to slice the opposing teeth in order to obtain the required tooth width ratio. In this case, gaps can be reserved on both sides of the teeth, which is equivalent to artificially increasing their width.

[0136] In one embodiment, the width of a tooth in the third three-dimensional digital model may be the maximum width of the tooth in the direction of the Y-axis (the coordinate axis having the smallest angle with the mesiodistal direction) of its local coordinate system.

[0137] In one embodiment, the sixth deep neural network may adopt Tranformer. In light of this application, it can be understood that in addition to Transformer, the sixth neural network may also adopt any other applicable deep neural network, such as CNN (Convolutional Neural Network) or RNN (Recurrent Neural Network).

[0138] The training data set for the eighth deep neural network includes multiple sets of training data, each set of training data including the tooth number and width of each tooth in an existing case, as well as the slice cutting amount and / or space reservation amount for each tooth in the orthodontic treatment plan for that case, which is optimized based on the Bolton index. It should be noted that the training data set for the eighth deep neural network may include slice cutting and space reservation plans manually designed by dental professionals based on the specific circumstances of actual cases, and some of these plans may not strictly comply with the standard Bolton index.

[0139] At this point, the target positions of the pre-selected teeth in the pre-selected directions and the required slicing or gap preparation for each tooth to meet the required ratio of maxillary and mandibular tooth widths have been determined. However, a collision resolution and gap closure solution is still lacking.

[0140] In 315, the third three-dimensional digital model is aligned based on the obtained constraints, and a collision resolution and gap closing solution is generated based on the aligned third three-dimensional digital model. The constraints are then updated based on the generated collision resolution and gap closing solution, and a final collision resolution and gap closing solution is obtained after multiple iterations.

[0141] Methods for relieving collisions and closing gaps include, but are not limited to: tooth extraction, tooth implantation, slice cutting, space reservation, molar distalization, molar mesialization, arch expansion, arch retraction, lip inclination, anterior tooth retraction, slice cutting, and space reservation.

[0142] In one embodiment, the tooth arrangement method used to generate the collision resolution and gap closing solution can be the above-mentioned method 100 for generating a digital data set representing the target tooth layout. In light of this application, it can be understood that in addition to the above-mentioned tooth arrangement method, any other suitable tooth arrangement method can also be used.

[0143] Please refer to FIG5 , which schematically illustrates a module diagram of a computer program for generating a collision resolution and gap closing solution in one embodiment of the present application.

[0144] The obtained constraints 401 and the third 3D digital model 403 are input into the tooth arrangement module 405. The tooth arrangement module 405 generates a tooth arrangement plan (i.e., the aligned third 3D digital model) and outputs it to the collision resolution and gap closing module 407. Since the constraints at this time do not include a collision resolution and gap closing plan, collision resolution and gap closing can be omitted during the first tooth arrangement.

[0145] In one embodiment, the teeth arrangement module 405 may be a computer program that implements the method 100 of generating a digital dataset representing a target teeth arrangement.

[0146] The collision resolution and gap closing module 407 generates a collision resolution and gap closing solution based on the initial third three-dimensional digital model and the aligned third three-dimensional digital model. The collision resolution and gap closing solution generated for the first time may not be perfect. In other words, if the tooth arrangement is performed again based on the obtained constraints and the collision resolution and gap closing solution, the collision amount and gap amount of the tooth arrangement result obtained may not meet the requirements, or may be greater than the predetermined collision threshold and gap threshold. Therefore, the current constraints can be updated based on the current collision resolution and gap closing solution, and the tooth arrangement can be performed again based on the updated constraints and a new collision resolution and gap closing solution can be generated. This process can be repeated multiple times until the collision and gap amount of the tooth arrangement result meet the requirements.

[0147] In one embodiment, the number of iterations N can be preset, and the iterations are stopped after N iterations, with the last output collision resolution and gap closing solution being used as the final result. In another embodiment, a collision threshold and a gap threshold can also be preset, and the iterations are stopped when the collision and gap values ​​of the tooth arrangement results obtained through iterations converge to less than the collision threshold and gap threshold, and the last output collision resolution and gap closing solution being used as the final result.

[0148] In one embodiment, a trained ninth deep neural network may be used to generate collision resolution and gap closing solutions based on the initial third three-dimensional digital model and the third three-dimensional digital model aligned based on the current constraints.

[0149] In one embodiment, the ninth deep neural network may include an encoder and a decoder. The encoder is used to encode the initial third three-dimensional digital model and the aligned third three-dimensional digital model. The decoder generates a collision resolution and gap closing solution based on the data output by the encoder. In one embodiment, the encoder may adopt a Point Transformer, and the decoder may adopt an RNN. In light of this application, it can be understood that in addition to the above network structure, the ninth deep neural network may also adopt any other applicable network.

[0150] In one embodiment, the training data set of the ninth deep neural network may include multiple sets of training data, each set of training data including a three-dimensional digital model of an unaligned jaw, a three-dimensional digital model of an aligned jaw, and corresponding collision resolution and gap closing solutions.

[0151] In one embodiment, in addition to the deep neural network, the computer may also generate collision resolution and gap closing solutions based on the initial third 3D digital model and the aligned third 3D digital model according to pre-defined rules.

[0152] In fact, there are many rules for removing collisions and closing gaps in this field. Different doctors may use different rules, so these rules will not be listed in detail here.

[0153] Although various aspects and embodiments of the present application are disclosed herein, other aspects and embodiments of the present application will be readily apparent to those skilled in the art in light of this disclosure. The various aspects and embodiments disclosed herein are for illustrative purposes only and are not intended to be limiting. The scope and subject matter of this application are determined solely by the appended claims.

[0154] Similarly, various diagrams may illustrate exemplary architectures or other configurations of the disclosed methods and systems that aid in understanding the features and functionality that may be included in the disclosed methods and systems. The claimed content is not limited to the exemplary architectures or configurations shown, and the desired features may be implemented using a variety of alternative architectures and configurations. Furthermore, for flow charts, functional descriptions, and method claims, the order of blocks presented herein should not limit various embodiments to being implemented in the same order to perform the described functionality, unless the context clearly dictates otherwise.

[0155] Unless otherwise expressly stated, the terms and phrases used herein and their variations should be interpreted as open ended rather than restrictive. In some instances, the appearance of broad words and phrases such as "one or more," "at least," "but not limited to," or other similar terms should not be understood as intending or requiring a narrowing of the context in which such broad terms may not be used.

Claims

1. A computer-implemented method for generating a digital data set representing a target tooth configuration, comprising: Acquire a first three-dimensional digital model representing a first dentition in an initial tooth arrangement; obtaining a set of predetermined constraints including target positions of selected teeth of the first dentition in selected directions; Preliminarily aligning the first three-dimensional digital model using a trained first deep neural network; as well as The first three-dimensional digital model is optimized. The first optimization includes: Moving the selected teeth of the first three-dimensional digital model of the preliminary alignment to the target position in the selected direction; as well as The dental arch curve of the first three-dimensional digital model is optimized, and collision elimination and / or gap closing are performed on the first three-dimensional digital model.

2. The method for generating a digital data set representing a target tooth configuration according to claim 1, wherein: If the constraints include a collision contact and / or gap closing scheme of the first dentition, the collision contact and / or gap closing of the first three-dimensional digital model is based on the collision contact and / or gap closing scheme of the first dentition.

3. The method for generating a digital data set representing a target tooth configuration according to claim 2, wherein: The collision relief and / or gap closing scheme of the first dentition includes one of the following: tooth extraction, tooth implantation, posterior tooth distalization, posterior tooth mesialization, arch expansion, arch contraction, lip inclination, anterior tooth retraction, slice cutting, gap reservation and any combination thereof.

4. The method for generating a digital data set representing a target tooth configuration according to claim 1, wherein: If the constraints include a slice cutting and gap reservation scheme for the first dentition obtained by analyzing the width of each tooth of the first dentition, the requirements for collision resolution and / or gap closure of the first three-dimensional digital model are determined based on the slice cutting and gap reservation scheme.

5. The method for generating a digital data set representing a target tooth configuration according to claim 1, wherein: In the dental arch curve optimization, the position and posture of the selected tooth remains unchanged after it moves to the target position in the selected direction.

6. The method of generating a digital data set representing a target tooth configuration according to claim 1, wherein: The operation of moving the selected tooth to the target position in the selected direction is performed simultaneously with the dental arch curve optimization and the collision contact and / or space closing.

7. The method of generating a digital data set representing a target tooth configuration according to claim 1, wherein: It also includes: Acquire a second three-dimensional digital model representing a second dentition in the initial tooth layout, where the second dentition is the opposing dentition of the first dentition; Using a trained second deep neural network to preliminarily align the second three-dimensional digital model based on the first optimized first three-dimensional digital model; Performing a second optimization on the preliminarily aligned second three-dimensional digital model, the second optimization comprising: Based on the first optimized first three-dimensional digital model, the preliminarily aligned second three-dimensional digital model is subjected to occlusion optimization, so that the occlusion relationship between the second optimized second three-dimensional digital model and the first optimized first three-dimensional digital model meets the requirements.

8. The method of generating a digital data set representing a target tooth configuration according to claim 7, wherein: While the occlusion is being optimized, collision elimination and / or gap closing are performed on the updated second three-dimensional digital model according to the collision elimination and / or gap closing scheme of the second dentition in the constraint.

9. The method of generating a digital data set representing a target tooth configuration according to claim 8, wherein: The collision relief and / or gap closing scheme of the second dentition includes one of the following: tooth extraction, tooth implantation, posterior tooth distalization, posterior tooth mesialization, arch expansion, arch contraction, lip inclination, anterior tooth retraction, slice cutting, gap reservation and any combination thereof.

10. The method of generating a digital data set representing a target tooth configuration according to claim 8, wherein: If the constraints include a slice cutting and gap reservation scheme for the second dentition obtained based on an analysis of the width of each tooth of the second dentition, the requirements for collision resolution and / or gap closing of the second three-dimensional digital model are determined based on the slice cutting and gap reservation scheme.

11. The method of generating a digital data set representing a target tooth configuration according to claim 1, wherein: The target position of the selected tooth in the selected direction includes one of the following: tooth midline target position, anterior tooth sagittal target position, anterior tooth vertical target position, posterior tooth vertical target position, posterior tooth sagittal target position, posterior tooth horizontal target position, canine horizontal target position and any combination thereof.

12. The method of generating a digital data set representing a target tooth configuration according to claim 7, wherein: The first dentition is the maxillary dentition and the second dentition is the mandibular dentition.

13. The method of generating a digital data set representing a target tooth configuration according to claim 7, wherein: The occlusal optimization is an energy function based on the occlusal relationship, which is defined by the positional relationship between selected key points of the teeth.

14. The method of generating a digital data set representing a target tooth configuration according to claim 7, wherein: It also includes: using a trained third deep neural network to further align the first optimized first three-dimensional digital model and the second optimized second three-dimensional digital model.

15. The method of generating a digital data set representing a target tooth configuration according to claim 1, wherein: The first three-dimensional digital model is input into the first deep neural network, which outputs a digital data set representing the tooth layout of the first three-dimensional digital model of the preliminary alignment.

16. The method of generating a digital data set representing a target tooth configuration according to claim 7, wherein: The first optimized first three-dimensional digital model and the second three-dimensional digital model are input into the second deep neural network, which outputs a digital data set representing the tooth layout of the preliminary aligned second three-dimensional digital model.

17. The method of generating a digital data set representing a target tooth configuration according to claim 14, wherein: The first optimized first three-dimensional digital model and the second optimized second three-dimensional digital model are input into the third deep neural network, which outputs a digital data set representing the tooth layout of the further aligned first three-dimensional digital model and the second three-dimensional digital model.

Images