Method, device, electronic device and storage medium for generating three-dimensional data of dental crown
Through the combination of spherical depth projection and depth data prediction model, the problems of high labor costs, low efficiency and poor accuracy in the generation of crown three-dimensional model are solved, and the automated generation and efficient and accurate generation of crown three-dimensional data are achieved.
Patent Information
- Application Number
- CN202410867952.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-01
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-01
AI Technical Summary
During the generation of the three-dimensional crown model, the labor cost is high, the efficiency is low, the accuracy is poor, and the artificial error is easily introduced.
By obtaining the three-dimensional data of the target tooth position and surrounding tooth body for spherical depth projection, the crown depth data is determined using the crown depth data prediction model, and the crown three-dimensional data is generated through the spherical depth back projection, realizing automatic generation.
It improves the accuracy and efficiency of the generation of 3D crown data, reduces labor costs, and realizes the automated generation of 3D crown data.
Smart Images

Figure CN118411479B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of tooth model digitization, and in particular to a method, device, electronic equipment and storage medium for generating three-dimensional data of a tooth crown. Background Art
[0002] During tooth restoration, doctors need to reasonably design crowns to repair prepared teeth. During dental implantation, doctors need to design crowns for implants. The acquisition of crowns includes two processes, namely, the generation of crown 3D models and the physical production of crowns. Among them, the generation of crown 3D models is a relatively complex process, which requires ensuring that the crown shape adapts to the user's tooth arrangement, satisfies the chewing function and maintains beauty.
[0003] In the prior art, professionals are usually required to observe the user's tooth shape and arrangement with their naked eyes, and then use the observed information to operate the 3D design software to design a 3D crown model. This solution requires high professional skills from professionals and requires professional training for professionals, which has high labor costs. Moreover, this process is not completed automatically. Manual operation by professionals will not only reduce the efficiency of generating the 3D crown model, but also easily introduce human errors in the 3D crown model, making the 3D crown model inaccurate. Summary of the invention
[0004] The present invention provides a method, device, electronic equipment and storage medium for generating three-dimensional data of a dental crown, so as to solve the defects existing in the prior art.
[0005] The present invention provides a method for generating three-dimensional data of a tooth crown, comprising: obtaining three-dimensional data of a target tooth position and three-dimensional data of a tooth body surrounding the target tooth position, performing spherical depth projection on the three-dimensional data of the tooth position and the three-dimensional data of the tooth body surrounding the target tooth position, and obtaining tooth position depth data and surrounding tooth body depth data; based on the tooth position depth data and the surrounding tooth body depth data, applying a tooth crown depth data prediction model to determine the tooth crown depth data of the target tooth position; based on the tooth crown depth data of the target tooth position, generating the three-dimensional data of the tooth crown of the target tooth position.
[0006] The present invention also provides a device for generating three-dimensional data of a tooth crown, comprising: an acquisition module, used to acquire the three-dimensional data of the tooth position of a target tooth position and the three-dimensional data of the surrounding tooth body of the target tooth position, and perform spherical depth projection on the three-dimensional data of the tooth position and the three-dimensional data of the surrounding tooth body to obtain the tooth position depth data and the surrounding tooth body depth data; a prediction module, used to determine the crown depth data of the target tooth position based on the tooth position depth data and the surrounding tooth body depth data and apply a crown depth data prediction model; and a generation module, used to generate the three-dimensional data of the crown of the target tooth position based on the crown depth data of the target tooth position.
[0007] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned methods for generating three-dimensional data of a dental crown is implemented.
[0008] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating three-dimensional data of a dental crown as described above is implemented.
[0009] The present invention also provides a computer program product, comprising a computer program, which implements any of the above-mentioned methods for generating three-dimensional data of a dental crown when executed by a processor.
[0010] The method, device, electronic device and storage medium for generating three-dimensional crown data provided by the present invention can obtain the tooth position depth data and the surrounding tooth body depth data by performing spherical depth projection on the tooth position three-dimensional data of the target tooth position and the surrounding tooth body three-dimensional data, which is more accurate and reliable than other methods of obtaining depth data. Moreover, the method uses a crown depth data prediction model to determine the crown depth data of the target tooth position, which can improve the prediction efficiency and accuracy of the crown depth data. Finally, the method uses the crown depth data to generate the crown three-dimensional data of the target tooth position, which can improve the generation efficiency and accuracy of the crown three-dimensional data, realize the automatic generation of the crown three-dimensional data, and reduce the labor cost generated by generating the crown three-dimensional data. On the whole, the method determines each depth data by means of spherical depth projection, and realizes the prediction of the crown depth data by means of a prediction model, and then generates the crown three-dimensional data simply, directly and efficiently by means of spherical depth back projection. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings in the following description without paying any creative work.
[0012] Figure 1 It is a schematic diagram of the process of the method for generating three-dimensional data of a dental crown provided by the present invention;
[0013] Figure 2 It is a schematic diagram of the three-dimensional data of tooth position in a three-dimensional rectangular coordinate system in the method for generating three-dimensional data of tooth crown provided by the present invention;
[0014] Figure 3 It is a schematic diagram of a tooth depth image in the method for generating three-dimensional data of a tooth crown provided by the present invention;
[0015] Figure 4It is a schematic diagram of the three-dimensional data of the opposite tooth at the target tooth position in the three-dimensional rectangular coordinate system in the method for generating three-dimensional data of the tooth crown provided by the present invention;
[0016] Figure 5 It is a schematic diagram of a tooth depth image in the method for generating three-dimensional data of a tooth crown provided by the present invention;
[0017] Figure 6 It is a schematic diagram of the three-dimensional data of the adjacent teeth of the target tooth position in the three-dimensional rectangular coordinate system in the method for generating three-dimensional data of the tooth crown provided by the present invention;
[0018] Figure 7 It is a schematic diagram of the adjacent tooth depth image in the method for generating three-dimensional data of a tooth crown provided by the present invention;
[0019] Figure 8 It is a schematic diagram of a process of inputting the superposition result into a crown depth data prediction model to obtain a crown depth image of a target tooth position in the crown three-dimensional data generation method provided by the present invention;
[0020] Fig. 9 It is a schematic diagram of the three-dimensional data of the tooth position edge of the target tooth position in the three-dimensional rectangular coordinate system in the method for generating three-dimensional data of the tooth crown provided by the present invention;
[0021] Fig.10 It is a schematic diagram of two-dimensional lines of tooth position edges in the method for generating three-dimensional data of tooth crowns provided by the present invention;
[0022] Fig.11 It is a schematic diagram of a correction mask in the method for generating three-dimensional data of a dental crown provided by the present invention;
[0023] Fig.12 It is a schematic diagram of the process of performing spherical depth back-projection on the corrected crown depth data to obtain the crown three-dimensional data of the target tooth position in the crown three-dimensional data generation method provided by the present invention;
[0024] Fig.13 It is a schematic diagram of the morphology of the front and rear upper and lower jaws determined by the three-dimensional crown data of the target tooth position in the method for generating three-dimensional crown data provided by the present invention;
[0025] Fig.14 It is a structural schematic diagram of a device for generating three-dimensional data of a dental crown provided by the present invention;
[0026] Fig.15 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0027] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative work belong to the scope of protection of the present invention. The features of the terms "first" and "second" in the specification and claims of the present invention may explicitly or implicitly include one or more of the features. In the description of the invention, unless otherwise specified, the meaning of "multiple" is two or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship. In the related art, in the process of generating a three-dimensional model of a crown, it is usually necessary to give a user an intraoral scan model with a prepared tooth or a base connected to an implant, and a professional first observes the tooth shape and arrangement of the intraoral scan model with the naked eye, and then uses the observed information to operate the three-dimensional design software to design a three-dimensional model of the crown. This solution not only has high labor costs, but also limits the efficiency and accuracy of generating the three-dimensional model of the crown. Based on this, a method for generating three-dimensional data of a dental crown is provided in an embodiment of the present invention to solve the problems of high labor cost, low generation efficiency, and poor accuracy in the process of generating a three-dimensional model of a dental crown.
[0028] Figure 1 FIG. 1 is a flow chart of a method for generating three-dimensional data of a tooth crown provided in an embodiment of the present invention. Figure 1 As shown, the method includes: S1, obtaining the three-dimensional tooth position data of the target tooth position and the three-dimensional tooth body data around the target tooth position, performing spherical depth projection on the three-dimensional tooth position data and the three-dimensional tooth body data around the target tooth position, and obtaining the tooth position depth data and the surrounding tooth body depth data; S2, based on the tooth position depth data and the surrounding tooth body depth data, applying the crown depth data prediction model to determine the crown depth data of the target tooth position; S3, based on the crown depth data of the target tooth position, generating the three-dimensional crown data of the target tooth position.
[0029] Specifically, the method for generating three-dimensional data of a dental crown provided in an embodiment of the present invention is executed by a processor, which can be configured in a computer. The computer can be a local computer or a cloud computer. The local computer can be a computer, a tablet, etc., which is not specifically limited here.
[0030] When executing step S1, the three-dimensional tooth position data of the target tooth position and the three-dimensional tooth body data of the surrounding tooth body of the target tooth position are obtained. The target tooth position refers to the tooth position whose crown three-dimensional data needs to be determined. At the target tooth position, a target object can be included. The target object can be a target prepared tooth obtained by grinding around the tooth body of the patient's natural tooth, or a base connected to an implant installed for the patient's implant. It can be seen that the crown three-dimensional data generation method provided in the embodiment of the present invention can be applied to dental restoration scenarios to design crowns for prepared teeth, and can also be applied to dental implant scenarios to design crowns for implants.
[0031] When applied to a dental restoration scenario, the acquired three-dimensional tooth position data of the target tooth position is three-dimensional scanning data of the target tooth position where the target preparation already exists.
[0032] When applied to a dental implant scenario, the acquired three-dimensional data of the target tooth position is three-dimensional scanning data of the target tooth position with the base installed.
[0033] The three-dimensional tooth position data refers to the three-dimensional data of the target object at the target tooth position, which can be a three-dimensional model or a three-dimensional point cloud. The representation form of the three-dimensional data of the target tooth position is not specifically limited here.
[0034] The three-dimensional data of the surrounding teeth refers to the three-dimensional data of the surrounding teeth of the target tooth position, and can also be a three-dimensional model or a three-dimensional point cloud. The form of expression of the three-dimensional data of the surrounding teeth is not specifically limited. Among them, the surrounding teeth of the target tooth position can include at least one of the adjacent teeth and the opposing teeth of the target tooth position. The opposing teeth of the target tooth position can include the teeth directly opposite the teeth of the target tooth position, and on this basis, can also include the adjacent teeth directly opposite the teeth. The adjacent teeth of the target tooth position can include at least one, and the opposing teeth of the target tooth position can also include at least one.
[0035] The 3D data of tooth position and surrounding tooth can be obtained by scanning the user intraorally with the help of artificial intelligence (AI) technology, and then the intraoral 3D data is divided into tooth 3D data and non-tooth 3D data, and finally obtained from the tooth 3D data. It can also be obtained by manual molding with materials such as alginate and silicone rubber. In addition, the surrounding tooth 3D data can also be obtained through the user's historical scanning data, and the tooth position 3D data can be obtained by scanning the target tooth position.
[0036] By performing spherical depth projection on the tooth position three-dimensional data and the surrounding tooth body three-dimensional data, the tooth position depth data and the surrounding tooth body depth data can be obtained. Here, the tooth position three-dimensional data and the surrounding tooth body three-dimensional data can be simultaneously projected on the spherical depth, or the tooth position three-dimensional data and the surrounding tooth body three-dimensional data can be separately projected on the spherical depth, that is, the tooth position depth data is obtained by performing spherical depth projection on the tooth position three-dimensional data, and the surrounding tooth body depth data is obtained by performing spherical depth projection on the surrounding tooth body three-dimensional data.
[0037] Spherical depth projection refers to the process of converting three-dimensional data to depth data. Usually, a fixed point can be selected as the center of the sphere first, and then each data point in the three-dimensional data is converted to each data point in the depth data according to the distance from the fixed point to each data point in the three-dimensional data and the direction of the line connecting the fixed point and each data point in the three-dimensional data. Each data point in the depth data can represent the distance from the fixed point to each data point in the three-dimensional data in the direction of the line connecting the fixed point and each data point in the three-dimensional data. Here, the depth data can be a depth image, and each data point in the depth data can be each pixel point in the depth image. Fixed points can be selected as needed, preferably points other than three-dimensional data.
[0038] Therefore, the tooth position depth data can be the depth data of the target object at the target tooth position, and each data point in the tooth position depth data can represent the distance from the first fixed point to each data point in the tooth position three-dimensional data in the direction of the line connecting the first fixed point and each data point in the tooth position three-dimensional data. The surrounding tooth body depth data can be the depth data of the surrounding tooth body of the target tooth position, and each data point in the surrounding tooth body depth data can represent the distance from the second fixed point to each data point in the surrounding tooth body three-dimensional data in the direction of the line connecting the second fixed point and each data point in the surrounding tooth body three-dimensional data. Among them, the first fixed point and the second fixed point can be the same or different, and no specific limitation is made here.
[0039] When executing step S2, a pre-trained crown depth data prediction model is introduced. After training, the crown depth data prediction model can learn the correspondence between the tooth position depth data, the surrounding tooth body depth data and the crown depth data of the target tooth position, and then input the tooth position depth data and the surrounding tooth body depth data into the crown depth data prediction model, and the crown depth data of the target tooth position output by the crown depth data prediction model can be obtained.
[0040] Among them, the crown depth data prediction model can be obtained by constructing an initial prediction model through a neural network model, and selecting appropriate training samples to perform supervised training on the initial prediction model. The specific structure of the neural network model can be set as needed, for example, it can be a convolutional neural network, Transformer, etc., which is not specifically limited here. The crown depth data of the target tooth position refers to the depth data of the crown of the target tooth position, and its representation can be a depth image.
[0041] It should be noted that, since the surrounding tooth body of the target tooth position includes at least one of the adjacent teeth and the opposing teeth of the target tooth position, when the surrounding tooth body only has opposing teeth but no adjacent teeth, the adjacent tooth depth data is missing in the surrounding tooth depth data obtained by spherical depth projection. Therefore, when applying the crown depth data prediction model, the adjacent tooth depth data can be introduced on the basis of the tooth position depth data and the surrounding tooth depth data, and the tooth position depth data, the surrounding tooth depth data and the adjacent tooth depth data are all input into the crown depth data prediction model, and the crown depth data of the target tooth position is output by the crown depth data prediction model. Here, the adjacent tooth depth data can be the mean of the adjacent tooth depth data of the predetermined target tooth position, or can be predicted by AI technology in combination with the tooth position depth data and the surrounding tooth depth data. For example, the missing adjacent tooth depth data can be obtained by inputting the tooth position depth data and the surrounding tooth depth data into the AI model, and predicting the missing adjacent tooth depth data through the AI model.
[0042] When there are only adjacent teeth but no opposing teeth in the surrounding tooth body, the opposing tooth depth data is missing in the surrounding tooth depth data obtained by spherical depth projection. Therefore, when applying the crown depth data prediction model, the opposing tooth depth data can be introduced on the basis of the tooth position depth data and the surrounding tooth depth data. The tooth position depth data, the surrounding tooth depth data and the opposing tooth depth data are all input into the crown depth data prediction model, and the crown depth data of the target tooth position is output by the crown depth data prediction model. Here, the opposing tooth depth data can be the mean of the opposing tooth depth data of the predetermined target tooth position, or it can be predicted by combining the tooth position depth data and the surrounding tooth depth data through AI technology. For example, the missing opposing tooth depth data can be obtained by inputting the tooth position depth data and the surrounding tooth depth data into the AI model, and predicting it through the AI model.
[0043] In particular, when the target tooth preparation or abutment at the target tooth position is missing or the shape of the target tooth preparation or abutment is too special, the tooth position depth data can be a predetermined fixed depth data of the target tooth position, or the mean depth data of the target tooth position, which is not specifically limited here.
[0044] When executing step S3, the crown depth data of the target tooth position, i.e., the depth data of the crown of the target tooth position, is used to generate the crown three-dimensional data of the target tooth position. Here, the crown three-dimensional data of the target tooth position may include the outer surface three-dimensional data and / or the inner surface three-dimensional data of the crown of the target tooth position, i.e., the crown three-dimensional data of the target tooth position may only include the outer surface three-dimensional data of the crown of the target tooth position, may only include the inner surface three-dimensional data of the crown of the target tooth position, or may simultaneously include the outer surface three-dimensional data and the inner surface three-dimensional data of the crown of the target tooth position.
[0045] The outer surface three-dimensional data is a three-dimensional model or a three-dimensional point cloud of the outer surface of the crown of the target tooth position, which can be obtained by performing a spherical depth back projection on the crown depth data of the target tooth position. The inner surface three-dimensional data is a three-dimensional model or a three-dimensional point cloud of the inner surface of the crown of the target tooth position, and the outer surface three-dimensional data of the target tooth preparation or abutment at the target tooth position can be directly used as the inner surface three-dimensional data of the crown of the target tooth position.
[0046] When applied to dental restoration scenarios, the crown of the target tooth position can be made or 3D printed through the three-dimensional data of the crown of the target tooth position. When applied to dental implant scenarios, according to individual implant needs, the crown needs to be threaded to connect with the base, or the threaded hole data can be designed on the three-dimensional data of the crown of the target tooth position to open the threaded hole for the crown.
[0047] It can be understood that spherical depth back projection is the inverse process of spherical depth projection, that is, the process of converting depth data into three-dimensional data. Usually, we can first determine the fixed points selected during spherical depth projection, and then determine each data point in the three-dimensional data based on the continuous direction and distance corresponding to each data point in the depth data.
[0048] If the surrounding teeth only have opposing teeth but no adjacent teeth and the input of the crown depth data prediction model does not have adjacent tooth depth data, then since the adjacent teeth can be used to constrain the width of the crown of the target tooth, the crown width data can be introduced when the crown depth data of the target tooth is back-projected on the spherical surface, so that the three-dimensional crown data of the target tooth meets the requirements for the crown width. The crown width data can be the mean value of the crown width of the target tooth determined in advance.
[0049] If the surrounding teeth only have adjacent teeth but no opposing teeth and the input of the crown depth data prediction model does not have opposing tooth depth data, then since opposing teeth can be used to constrain the height of the crown of the target tooth, the crown height data can be introduced when the crown depth data of the target tooth is back-projected on the spherical surface, so that the three-dimensional crown data of the target tooth meets the requirements for the crown height. The crown height data can be the mean value of the crown height of the target tooth determined in advance.
[0050] If the target tooth preparation or abutment at the target tooth position is missing or the shape of the target tooth preparation or abutment is too special, the predetermined crown fixed height data and width data of the target tooth position can be introduced when performing spherical depth back projection on the crown depth data of the target tooth position, which is not specifically limited here.
[0051] In addition, the crown depth data of the target tooth position may be screened first, data points with larger distance values may be filtered out from the crown depth data of the target tooth position, and the crown three-dimensional data of the target tooth position may be obtained by performing spherical depth back-projection on the screening results, which is not specifically limited here.
[0052] The method for generating three-dimensional crown data provided in the embodiment of the present invention can obtain the tooth position depth data and the surrounding tooth body depth data by performing spherical depth projection on the tooth position three-dimensional data of the target tooth position and the surrounding tooth body three-dimensional data, which is more accurate and reliable than other methods of obtaining depth data. Moreover, the method uses a crown depth data prediction model to determine the crown depth data of the target tooth position, which can improve the prediction efficiency and accuracy of the crown depth data. Finally, the method uses the crown depth data to generate the three-dimensional crown data of the target tooth position, which can improve the generation efficiency and accuracy of the crown three-dimensional data, realize the automatic generation of the crown three-dimensional data of the target tooth position, and reduce the labor cost generated by generating the crown three-dimensional data.
[0053] In some optional embodiments, based on the crown depth data of the target tooth position, three-dimensional crown data of the target tooth position is generated, including: obtaining three-dimensional data of the tooth edge of the target tooth position; based on the three-dimensional data of the tooth edge, correcting the crown depth data of the target tooth position to obtain corrected crown depth data; performing spherical depth back-projection on the corrected crown depth data to obtain three-dimensional crown data of the target tooth position.
[0054] Specifically, when generating the three-dimensional data of the crown of the target tooth, the three-dimensional data of the tooth edge of the target tooth can be obtained. The three-dimensional data of the tooth edge refers to the three-dimensional data of the edge closed line of the target object at the target tooth, which can be obtained by preprocessing the three-dimensional data of the crown of the target tooth.
[0055] Thereafter, the three-dimensional data of the tooth position edge can be used to correct the crown depth data of the target tooth position to obtain the corrected crown depth data. Since the crown depth data of the target tooth position is two-dimensional data, the three-dimensional data of the tooth position edge can be first converted into a two-dimensional line of the tooth position edge, and then the crown depth data of the target tooth position can be corrected by the two-dimensional line of the tooth position edge. For example, the crown depth data of the target tooth position can be corrected by the area enclosed by the two-dimensional lines of the tooth position edge in the two-dimensional space to obtain the corrected crown depth data. It can be understood that the correction process of the crown depth data of the target tooth position is the screening process of the crown depth data of the target tooth position by the area enclosed by the two-dimensional lines of the tooth position edge in the two-dimensional space to filter out the data points with larger distance values in the crown depth data of the target tooth position.
[0056] Furthermore, by performing spherical depth back-projection on the corrected crown depth data, the obtained three-dimensional crown data of the target tooth position can be made more accurate, reducing the influence of error data points in the crown depth data of the target tooth position on the determination of the three-dimensional crown data of the target tooth position.
[0057] In some optional embodiments, the tooth position edge three-dimensional data includes at least one of the maximum circumference data and the neck margin line data of the target object at the target tooth position. Specifically, the tooth position edge three-dimensional data used in the embodiment of the present invention may include the maximum circumference data of the target tooth position, may also include the neck margin line data of the target tooth position, and may also include the maximum circumference data of the target tooth position and the neck margin line data of the target tooth position at the same time.
[0058] Among them, the maximum circumference data of the target tooth position refers to the three-dimensional data of the edge closed line of the maximum circumference of the target object at the target tooth position on each cross section perpendicular to the tooth height direction. The neck margin line data of the target tooth position refers to a thin line around the neck of the target object at the target tooth position, located at the gingival edge, and is the dividing line between the crown and root of the target tooth position.
[0059] The maximum circumference data and cervical margin line data of the target tooth position can be obtained through artificial intelligence technology. For example, the tooth depth data of the target tooth position can be input into a pre-trained edge data prediction model to obtain the three-dimensional data of the tooth position edge output by the edge data prediction model. The edge data prediction model can be trained by tooth position samples carrying maximum circumference data labels and / or cervical margin line data labels.
[0060] In the embodiment of the present invention, the three-dimensional data of the tooth position edge at least includes the content provided, which not only provides a basis for the correction of the crown depth data of the target tooth position, but also improves the flexibility of the correction of the crown depth data of the target tooth position. Moreover, by using the maximum circumference data of the target tooth position, the crown of the target tooth position obtained can be more closely matched with the size of the target object at the target tooth position. By using the neck margin line data of the target tooth position, the crown of the target tooth position obtained can be more closely fitted with the target object at the target tooth position at the neck.
[0061] In some optional embodiments, the crown depth data of the target tooth position is corrected based on the three-dimensional data of the tooth position edge to obtain the corrected crown depth data, including: determining a correction mask based on the three-dimensional data of the tooth position edge; and determining the data in the crown depth data of the target tooth position that is within the selected area of the correction mask as the corrected crown depth data.
[0062] Specifically, when correcting the crown depth data of the target tooth position, the three-dimensional data of the tooth position edge can be used to determine a correction mask. The correction mask can be a two-dimensional image, and its size can be the same as the area size of the crown depth data of the target tooth position. The correction mask can be obtained by converting the three-dimensional data of the tooth position edge into a two-dimensional line of the tooth position edge, and constructing it using the two-dimensional line of the tooth position edge.
[0063] The selected area of the correction mask can be the area surrounded by the two-dimensional lines of the tooth edge as a transparent area, and the area other than the selected area in the correction mask can be a non-transparent area, for example, a completely black area.
[0064] Then, the correction mask may be overlaid on the crown depth data of the target tooth position, and the data in the crown depth data of the target tooth position that is within the selected area of the correction mask may be screened out and determined as the corrected crown depth data.
[0065] In an embodiment of the present invention, the crown depth data of the target tooth position is screened by using a correction mask corresponding to the three-dimensional data of the tooth edge, so that noise data in the crown depth data of the target tooth position can be filtered out, making the obtained corrected crown depth data more accurate, and further improving the accuracy of the three-dimensional data of the crown of the target tooth position.
[0066] In some optional embodiments, spherical depth projection is performed on the tooth position three-dimensional data and the surrounding tooth body three-dimensional data to obtain the tooth position depth data and the surrounding tooth body depth data, including: determining a common sphere center; based on the common sphere center, spherical depth projection is performed on the tooth position three-dimensional data and the surrounding tooth body three-dimensional data to obtain the tooth position depth data and the surrounding tooth body depth data.
[0067] Specifically, since the implementation of spherical depth projection requires the determination of the sphere center, in the embodiment of the present invention, the common sphere center can be determined first, that is, the same sphere center is used to perform spherical depth projection on different depth data. The position of the common sphere center can be set as needed, for example, it can be determined by the position information of the cervical margin line data of the target tooth position. The position determination standard of the common sphere center can be the minimum value of the cervical margin line data that is on the same vertical line as the center point of the target tooth position and slightly lower than the target tooth position.
[0068] After that, the common sphere center can be used to perform spherical depth projection on the tooth position three-dimensional data and the surrounding tooth body three-dimensional data to obtain the tooth position depth data and the surrounding tooth body depth data. For example, the tooth position depth data and the surrounding tooth body depth data can be determined based on the distance from the common sphere center to each data point in the tooth position three-dimensional data and the surrounding tooth body three-dimensional data, and the direction of the line connecting the common sphere center and each data point in the tooth position three-dimensional data and the surrounding tooth body three-dimensional data.
[0069] In an embodiment of the present invention, by performing spherical depth projection on the tooth position three-dimensional data and the surrounding tooth body three-dimensional data through a common sphere center, the obtained surrounding tooth body depth data and the tooth position depth data can be quickly and accurately combined and used together to determine the crown depth data of the target tooth position.
[0070] In some optional embodiments, the tooth position depth data and the surrounding tooth body depth data are represented based on a depth image; a spherical depth projection is performed on the tooth position three-dimensional data and the surrounding tooth body three-dimensional data to obtain the tooth position depth data and the surrounding tooth body depth data, including: constructing a three-dimensional rectangular coordinate system; for any type of object in the tooth position three-dimensional data and the surrounding tooth body three-dimensional data, the following operations are performed: sampling multiple first rays with the origin of the three-dimensional rectangular coordinate system as a fixed point, and based on the unit direction of each first ray, determining the position information of each pixel point in the depth image corresponding to the object that has a mapping relationship with each first ray; and determining the distance information from the intersection of each first ray and the three-dimensional data of the object to the origin, and based on the distance information, determining the pixel value of each pixel point in the depth image corresponding to the object that has a mapping relationship with each first ray.
[0071] Specifically, in the embodiment of the present invention, the tooth position depth data and the surrounding tooth body depth data can be expressed in the form of a depth image, so when the spherical depth projection of the tooth position three-dimensional data and the surrounding tooth body three-dimensional data is performed, a three-dimensional rectangular coordinate system can be constructed first. The construction of the three-dimensional rectangular coordinate system can be determined as needed, and only its origin and three coordinate axes need to be determined. Among them, the three coordinate axes include the horizontal axis (i.e., the X-axis), the longitudinal axis (i.e., the Y-axis), and the vertical axis (i.e., the Z-axis).
[0072] In order to save computational costs, the construction standard of the three-dimensional rectangular coordinate system can be: the vertical axis of the three-dimensional rectangular coordinate system is perpendicular to the intraoral occlusal plane, and the three-dimensional data of various objects are in the positive direction of the vertical axis. Here, various objects can include target objects such as target preparations or abutments at target tooth positions, and surrounding teeth such as opposing teeth or adjacent teeth.
[0073] After that, a spherical surface with the origin of the three-dimensional rectangular coordinate system as the center can be determined, and multiple rays on the spherical surface can be obtained from the origin. In particular, if the three-dimensional data of various objects are in the positive direction of the three-dimensional rectangular coordinate system, multiple rays on the hemispherical surface with the origin as the center and facing the positive direction of the vertical axis can be determined.
[0074] For any type of object in the tooth position three-dimensional data and the surrounding tooth body three-dimensional data, that is, the target object or the surrounding tooth body, multiple first rays with the origin as the fixed point can be sampled, and the unit direction of each first ray can be used to determine the position information of each pixel point that has a mapping relationship with each first ray in the depth image corresponding to the object of this type. If the object of this type is the target object, the depth image corresponding to the object of this type is the tooth position depth data of the target tooth position. If the object of this type is the surrounding tooth body, the depth image corresponding to the object of this type is the surrounding tooth body depth data. The position information of each pixel point can be the coordinates of each pixel point in the depth image.
[0075] The process of spherical depth projection can be understood as the process of determining the pixel value of each pixel in the depth image corresponding to each type of object through the three-dimensional data in the three-dimensional rectangular coordinate system. In the process of spherical depth projection, there is a mapping relationship between each pixel in the depth image corresponding to each type of object and each first ray corresponding to the object. For any first ray, the unit direction of the first ray is (Rx, Ry, Rz), and the coordinates of the pixel in the depth image corresponding to the object are (Px, Py). The mapping relationship between the first ray and the pixel can be expressed as:
[0076]
[0077]
[0078] Wherein, H is the size of the depth image. The depth image is a square, so the length and width of the depth image are both H.
[0079] Through the above mapping relationship, the position information of the pixel points on the depth image that have a mapping relationship with it can be determined according to the unit direction of the first ray, and vice versa, the unit direction of the first ray that has a mapping relationship with it can also be determined according to the position information of the pixel points on the depth image. It should be noted that in the mapping relationship that satisfies the above formula, not all pixels on the depth image can be mapped to the same first ray.
[0080] Thereafter, the intersection points between each first ray and the three-dimensional data of the object of this type may be determined. Each first ray may have no intersection point, one intersection point, or multiple intersection points with the three-dimensional data of the object of this type.
[0081] The distance information between each intersection point and the origin of the three-dimensional rectangular coordinate system is determined. The distance information can be calculated by the coordinates of the intersection point and the coordinates of the origin in the three-dimensional rectangular coordinate system.
[0082] Finally, the calculated distance information can be used to determine the pixel value of each pixel point in the depth image corresponding to the object that has a mapping relationship with each first ray, that is, the calculated distance information corresponding to each first ray can be used as the pixel value of the pixel point that has a mapping relationship with it.
[0083] like Figure 2 As shown in FIG. 1 , it is a schematic diagram of the three-dimensional tooth position data in a three-dimensional rectangular coordinate system. By performing spherical depth projection on the three-dimensional tooth position data, the obtained tooth position depth data can be expressed as follows: Figure 3 Image of tooth depth shown.
[0084] In an embodiment of the present invention, by converting each data point in the three-dimensional data of various objects in a three-dimensional rectangular coordinate system into the pixel value of each pixel point in a depth image in a two-dimensional space, spherical depth projection can be achieved to improve the accuracy of the depth image.
[0085] In some optional embodiments, constructing a three-dimensional rectangular coordinate system includes: determining the direction of the coordinate axis of the three-dimensional rectangular coordinate system based on the three-dimensional data of the tooth position and the three-dimensional data of the surrounding teeth, or based on the three-dimensional data of the teeth in the mouth where the target tooth position is located; determining the origin of the three-dimensional rectangular coordinate system based on the data range of the cervical margin line data of the target tooth position in the vertical axis direction of the three-dimensional rectangular coordinate system.
[0086] Specifically, when constructing a three-dimensional rectangular coordinate system, if the target tooth position has a large number of missing teeth in the mouth, the three-dimensional data of the tooth position and the three-dimensional data of the surrounding teeth can be used to determine the coordinate axis direction of the three-dimensional rectangular coordinate system. If the target tooth position has a small number of missing teeth in the mouth, the three-dimensional data of the teeth in the mouth where the target tooth position is located can be used to determine the coordinate axis direction of the three-dimensional rectangular coordinate system.
[0087] For example, the occlusal plane in the mouth can be determined by using the three-dimensional data of the tooth position and the three-dimensional data of the surrounding teeth, or the three-dimensional data of the teeth in the mouth, and then the normal direction of the occlusal plane in the mouth is used as the vertical axis direction of the three-dimensional rectangular coordinate system, and the horizontal axis direction and the vertical axis direction of the three-dimensional rectangular coordinate system are selected in the occlusal plane in the mouth. Among them, determining the occlusal plane by using the three-dimensional data of the whole mouth teeth with at least one occlusal state can simplify the steps of determining the coordinate system and speed up the calculation efficiency.
[0088] Thereafter, the origin of the three-dimensional rectangular coordinate system is determined by using the data range of the cervical margin line data of the target tooth position in the vertical axis direction of the three-dimensional rectangular coordinate system, with the three-dimensional data of the tooth position being in the positive direction of the vertical axis as the standard. For example, the origin can be set at a position slightly lower than the lowest point of the data range of the cervical margin line data of the target tooth position in the vertical axis direction of the three-dimensional rectangular coordinate system.
[0089] In an embodiment of the present invention, the three-dimensional data of tooth positions and the three-dimensional data of surrounding teeth are used to determine the coordinate axis directions of the three-dimensional rectangular coordinate system, which can improve the construction efficiency of the three-dimensional rectangular coordinate system and facilitate unified calculation of data.
[0090] In some optional embodiments, the three-dimensional data of the surrounding teeth include the three-dimensional data of the opposite teeth of the target tooth position and the three-dimensional data of the adjacent teeth of the target tooth position; based on the three-dimensional tooth position data and the three-dimensional data of the surrounding teeth, the coordinate axis direction of the three-dimensional rectangular coordinate system is determined, including: based on the three-dimensional tooth position data, determining the center point of the target tooth position, and based on the three-dimensional tooth data, determining the center point of each surrounding tooth of the target tooth position; based on the center point of the target tooth position and the center point of each surrounding tooth, determining the tooth fitting plane, and determining the normal direction of the tooth fitting plane as the horizontal axis direction of the three-dimensional rectangular coordinate system; determining at least two objects in the same dental jaw in the target tooth position and each surrounding tooth, and determining the direction of the line connecting the center points of the at least two objects as the vertical axis direction of the three-dimensional rectangular coordinate system; based on the horizontal axis direction and the vertical axis direction, determining the vertical axis direction of the three-dimensional rectangular coordinate system.
[0091] Specifically, when the surrounding tooth body includes the adjacent teeth and the opposing teeth of the target tooth position, that is, the three-dimensional data of the surrounding tooth body includes the three-dimensional data of the opposing teeth of the target tooth position and the three-dimensional data of the adjacent teeth of the target tooth position, when determining the coordinate axis direction of the three-dimensional rectangular coordinate system, the three-dimensional data of the tooth position can be used to first determine the center point of the target tooth position. The center point of the target tooth position refers to the center point of the target object at the target tooth position, and the center point can be extracted by AI technology to obtain the feature points of the three-dimensional data of the tooth position. For example, the three-dimensional data of the tooth position can be input into a feature point extraction model to obtain the feature points of the three-dimensional data of the tooth position output by the feature point extraction model. The feature point extraction model can be trained by three-dimensional data of tooth position samples carrying feature point labels.
[0092] Then, the center point of the target tooth position is obtained by the difference between the feature points.
[0093] Similarly, the surrounding tooth three-dimensional data can be used to determine the center point of each surrounding tooth of the target tooth position, that is, to determine the center point of each adjacent tooth and the center point of each opposite tooth of the target tooth position. For example, the surrounding tooth three-dimensional data can also be input into a feature point extraction model to obtain the feature points of the surrounding tooth three-dimensional data output by the feature point extraction model. Then, the center point of the surrounding tooth is obtained by the difference between the feature points.
[0094] Afterwards, the center point of the target tooth position and the center points of the surrounding teeth can be used to determine the tooth fitting plane based on the principle of three points determining a plane. Afterwards, the normal direction of the tooth fitting plane can be determined as the horizontal axis direction of the three-dimensional rectangular coordinate system.
[0095] After that, the target tooth position and at least two objects in the same tooth jaw in each surrounding tooth body can be determined, for example, the target object and its adjacent teeth, or the target object's opposite tooth and the opposite tooth's adjacent teeth. The direction of the line connecting the center points of the at least two objects in the same tooth jaw is determined as the longitudinal axis direction of the three-dimensional rectangular coordinate system.
[0096] At this time, the intraoral occlusal plane can be constructed by the normal direction of the tooth fitting plane and the direction of the line connecting the center points of at least two objects in the same jaw, that is, the horizontal and vertical axes of the three-dimensional rectangular coordinate system.
[0097] The vertical axis direction of the three-dimensional rectangular coordinate system is determined by using the horizontal axis direction and the vertical axis direction of the three-dimensional rectangular coordinate system, that is, the direction perpendicular to the horizontal axis direction and the vertical axis direction, that is, the normal direction of the intraoral occlusal plane is taken as the vertical axis direction.
[0098] In the embodiment of the present invention, the coordinate axis directions of the three-dimensional rectangular coordinate system are determined through each center point, which can simplify the coordinate system construction process and improve the efficiency of generating three-dimensional data of the dental crown.
[0099] In some optional embodiments, the three-dimensional data of the surrounding teeth include the three-dimensional data of the opposing teeth of the target tooth position and the three-dimensional data of the adjacent teeth of the target tooth position; the surrounding tooth depth data is determined by performing spherical depth projection on the three-dimensional data of the opposing teeth and the three-dimensional data of the adjacent teeth to obtain the depth data of the opposing teeth of the target tooth position and the depth data of the adjacent teeth of the target tooth position, respectively.
[0100] Specifically, since the tooth body surrounding the target tooth position may include the opposing tooth of the target tooth position and the adjacent tooth of the target tooth position, the surrounding tooth body three-dimensional data may include the opposing tooth three-dimensional data of the target tooth position and the adjacent tooth three-dimensional data of the target tooth position.
[0101] On this basis, when determining the surrounding tooth depth data, the spherical depth projection can be performed on the three-dimensional data of the opposing teeth and the three-dimensional data of the adjacent teeth to obtain the opposing tooth depth data of the target tooth position and the adjacent tooth depth data of the target tooth position, respectively. For example, the three-dimensional data of the opposing teeth can be projected with a spherical depth to obtain the opposing tooth depth data of the target tooth position, and the three-dimensional data of the adjacent teeth can be projected with a spherical depth to obtain the adjacent tooth depth data of the target tooth position, and the three-dimensional data of the adjacent teeth can be projected with a spherical depth to obtain the opposing tooth depth data of the target tooth position and the adjacent tooth depth data of the target tooth position, respectively.
[0102] like Figure 4 As shown in FIG. 1 , it is a schematic diagram of the three-dimensional data of the target tooth position in the three-dimensional rectangular coordinate system. By performing spherical depth projection on the three-dimensional data of the target tooth, the obtained depth data of the target tooth can be expressed as follows: Figure 5 Depth image of opposing teeth shown.
[0103] from Figure 4 and Figure 5 It can be seen that the opposing teeth of the target tooth position include the opposing tooth and the two adjacent teeth on the left side and the two adjacent teeth on the right side of the opposing tooth.
[0104] like Figure 6 As shown in FIG. 1 , it is a schematic diagram of the adjacent tooth three-dimensional data of the target tooth position in a three-dimensional rectangular coordinate system. By performing spherical depth projection on the adjacent tooth three-dimensional data, the adjacent tooth depth data obtained can be expressed as follows: Figure 7 Depth image of adjacent teeth shown.
[0105] from Figure 6 and Figure 7 It can be seen that the adjacent teeth of the target tooth position include one adjacent tooth on the left side and one adjacent tooth on the right side of the target tooth position.
[0106] When the crown depth data of the target tooth position is determined by using the crown depth data prediction model, the tooth depth image of the target tooth position, the opposite tooth depth image and the adjacent tooth depth image can be superimposed by channel, and then the superposition result is input into the crown depth data prediction model to obtain the crown depth image of the target tooth position output by the crown depth data prediction model. Figure 8 Shown is a schematic diagram of the crown depth image of the target tooth position.
[0107] In the embodiment of the present invention, the types of teeth surrounding the target tooth position are specifically refined, so that the three-dimensional data of the crown of the target tooth position can be more accurate.
[0108] In some optional embodiments, based on the three-dimensional data of the teeth in the mouth where the target tooth position is located, determining the coordinate axis direction of the three-dimensional rectangular coordinate system includes: determining the occlusal plane of the teeth in the mouth based on the three-dimensional data of the teeth in the mouth; determining the vertical axis direction of the three-dimensional rectangular coordinate system based on the occlusal plane of the teeth in the mouth, and determining the tooth fitting plane, and determining the normal direction of the tooth fitting plane as the horizontal axis direction of the three-dimensional rectangular coordinate system;
[0109] Based on the horizontal axis direction and the vertical axis direction, the vertical axis direction of the three-dimensional rectangular coordinate system is determined.
[0110] Specifically, when the coordinate axis direction of the three-dimensional rectangular coordinate system is determined using the three-dimensional data of the teeth in the mouth where the target tooth position is located, the three-dimensional data of the teeth in the mouth can be used to determine the occlusal plane of the teeth in the mouth. The three-dimensional data of the teeth in the mouth can be all the three-dimensional data of the teeth acquired under the condition of occlusion in the mouth, and the occlusal plane of the teeth in the mouth can be obtained by fitting the contact positions of the upper teeth and the lower teeth in the three-dimensional data of all the teeth.
[0111] Afterwards, the vertical axis direction of the three-dimensional rectangular coordinate system can be determined using the intraoral tooth occlusal plane. Here, the normal line of the intraoral tooth occlusal plane can be directly used as the vertical axis direction of the three-dimensional rectangular coordinate system.
[0112] Furthermore, the vertical plane of the occlusal plane of the teeth in the mouth can be used as the tooth fitting plane, or the tooth fitting plane can be determined by the center point of the target tooth position and the center points of the surrounding teeth, which is not specifically limited here. The normal direction of the tooth fitting plane is the horizontal axis direction of the three-dimensional rectangular coordinate system.
[0113] Finally, the vertical axis direction of the three-dimensional rectangular coordinate system can be determined through the vertical relationship of the coordinate axes of the three-dimensional rectangular coordinate system.
[0114] In the embodiment of the present invention, the directions of the coordinate axes of the three-dimensional rectangular coordinate system can be determined simply and quickly with the help of the three-dimensional data of the teeth in the mouth.
[0115] In some optional embodiments, the vertical axis direction is from the jaw where the target tooth position is located toward the contralateral jaw;
[0116] The position information of the origin in the vertical axis direction is smaller than the minimum position information of the cervical margin line data of the target tooth position in the vertical axis direction.
[0117] Specifically, the vertical axis direction of the three-dimensional rectangular coordinate system can be the positive direction from the jaw where the target tooth position is located toward the opposite jaw.
[0118] At the same time, the position information of the origin of the three-dimensional rectangular coordinate system in the vertical axis direction can be smaller than the minimum position information of the cervical margin line data of the target tooth position in the vertical axis direction, so that the vertical coordinate of each data point in the three-dimensional data of any type of object is greater than 0, which is convenient for subsequent data calculation.
[0119] In some optional embodiments, based on the distance information, the pixel value of each pixel point in the depth image corresponding to the object that has a mapping relationship with each first ray is determined, including: for any first ray, if the first ray and the three-dimensional data of the object include multiple intersection points, then the minimum value of the distance information from the multiple intersection points to the origin is determined, and the minimum value is used as the pixel value of the pixel point in the depth image corresponding to the object that has a mapping relationship with the first ray.
[0120] Specifically, when using distance information to determine the pixel value of each pixel point in the depth image corresponding to any type of object that has a mapping relationship with each first ray, the following same operation can be performed for any first ray: that is, to determine whether the first ray and the three-dimensional data of the object of this type include multiple intersection points. If the object of this type includes multiple intersection points, the first ray and the three-dimensional data of each object in this type of object may have intersection points, that is, the first ray and the three-dimensional data of this type of object may include multiple intersection points, then the distance information between the multiple intersection points and the origin of the three-dimensional rectangular coordinate system can be determined, and the minimum value is selected as the pixel value of the pixel point in the depth image corresponding to the object of this type that has a mapping relationship with the first ray, so as to avoid the situation where a pixel point in the depth image has a mapping relationship with multiple first rays and has multiple pixel values. Moreover, selecting the minimum value as the pixel value of the pixel point that has a mapping relationship with the first ray can make the crown depth data of the target tooth position obtained more accurate.
[0121] In some optional implementations, determining a correction mask based on the tooth edge three-dimensional data includes:
[0122] Perform spherical projection on the three-dimensional data of the tooth position edge to obtain the two-dimensional line of the tooth position edge; based on the two-dimensional line of the tooth position edge, determine the correction mask.
[0123] Specifically, when determining the correction mask, the three-dimensional data of the tooth position edge can be firstly spherically projected to obtain a two-dimensional line of the tooth position edge. The two-dimensional line of the tooth position edge refers to the two-dimensional data of the edge of the target object at the target tooth position, for example, it can include at least one of the maximum circumference line and the neck edge line of the target tooth position.
[0124] The spherical projection refers to the process of converting three-dimensional data to two-dimensional data. Usually, a fixed point can be selected first, and then each data point in the three-dimensional data is converted to each data point in the two-dimensional data according to the direction of the line connecting the fixed point and each data point in the three-dimensional data. Each data point in the two-dimensional data can represent the direction of the line connecting the fixed point and each data point in the three-dimensional data. Here, each data point in the two-dimensional data can be each pixel point in the two-dimensional image. The fixed point can be the same as the fixed point used in the spherical depth projection.
[0125] When the three-dimensional tooth edge data includes both the maximum circumference data and the cervical margin line data of the target tooth, the maximum circumference data and the cervical margin line data can be spherically projected respectively to obtain the maximum circumference line and the cervical margin line line.
[0126] Finally, when the three-dimensional data of the tooth position edge include the maximum circumference data of the target tooth position, the two-dimensional line of the tooth position edge may include the maximum circumference line, and the correction mask may be determined using the maximum circumference line.
[0127] When the three-dimensional tooth position edge data includes the cervical margin line data of the target tooth position, the two-dimensional tooth position edge line may include the cervical margin line, and the correction mask may be determined using the cervical margin line.
[0128] When the three-dimensional data of the tooth position edge includes both the maximum circumference data and the cervical margin line data of the target tooth position, the two-dimensional lines of the tooth position edge may include the maximum circumference lines and the cervical margin lines, and the maximum circumference lines and the cervical margin lines may be used to determine the correction mask. For example, the lines with a larger area enclosed by the maximum circumference lines and the cervical margin lines may be selected to determine the correction mask.
[0129] In an embodiment of the present invention, by performing spherical projection on the three-dimensional data of the tooth edge and determining the correction mask using the obtained two-dimensional lines of the tooth edge, the accuracy of the correction mask can be improved, and the noise data in the crown depth data of the target tooth can be accurately filtered out.
[0130] In some optional embodiments, the three-dimensional data of the tooth position edge includes multiple line segments; spherical projection is performed on the three-dimensional data of the tooth position edge to obtain a two-dimensional line of the tooth position edge, including: determining each second ray from the origin of the three-dimensional rectangular coordinate system of the target tooth position to the endpoint of each line segment in the multiple line segments, and based on the unit direction of each second ray, determining the position information of each pixel point in the two-dimensional image that has a mapping relationship with each second ray; according to the connection relationship between the endpoints of each line segment in the three-dimensional data of the tooth position edge, each pixel point in the two-dimensional image is connected to obtain a two-dimensional line of the tooth position edge; wherein the pixel value of the pixel point in the two-dimensional image located within a preset range around the two-dimensional line of the tooth position edge is set to 1, and the pixel value of the pixel point outside the preset range is set to 0.
[0131] Specifically, the three-dimensional data of the tooth position edge can be composed of multiple line segments. Therefore, when performing spherical projection on the three-dimensional data of the tooth position edge, the second rays from the origin of the three-dimensional rectangular coordinate system of the target tooth position to the endpoint of each line segment can be determined first. Then, the unit direction of each second ray is used to determine the position information of each pixel point in the two-dimensional image that has a mapping relationship with each second ray. During the spherical projection process, there is a mapping relationship between each pixel point in the two-dimensional image and each second ray. This mapping relationship and the mapping relationship between the first ray and the pixel point can be expressed by the same formula, that is, the formulas of Px and Py mentioned above.
[0132] Thereafter, the pixel points in the two-dimensional image are connected according to the connection relationship between the endpoints of each line segment in the three-dimensional data of the tooth position edge, so as to obtain the two-dimensional line of the tooth position edge.
[0133] Finally, the pixel values of the pixels in the two-dimensional image within the preset range around the two-dimensional line of the tooth position edge can be set to 1, and the pixel values of the remaining pixels in the two-dimensional image can be set to 0. It can be understood that the preset range can be set as needed, for example, it can be the area formed by the two-dimensional line of the tooth position edge and at least one pixel around it.
[0134] In the embodiment of the present invention, a spherical projection method for three-dimensional data of tooth margins is provided, which is simple and easy to implement and is convenient for improving calculation efficiency.
[0135] In some optional embodiments, the modified crown depth data is represented based on a modified crown depth image;
[0136] The corrected crown depth data is subjected to spherical depth back-projection to obtain the crown three-dimensional data of the target tooth position, including: based on the position information of the target pixel point with non-zero pixel value on the corrected crown depth image, determining a plurality of third rays with the origin of the three-dimensional rectangular coordinate system of the target tooth position as the fixed point and having a mapping relationship with the target pixel point; for any third ray, determining the three-dimensional point in the unit direction of the third ray, and the distance information between the three-dimensional point and the origin is the pixel value of the pixel point having a mapping relationship with the third ray; based on the three-dimensional point corresponding to the target pixel point and the three-dimensional point corresponding to the designated neighborhood pixel point of the target pixel point, determining the crown three-dimensional data of the target tooth position; the designated neighborhood pixel point is a pixel point with non-zero pixel value within the neighborhood range of the target pixel point.
[0137] Specifically, in the embodiment of the present invention, the depth data can be represented as a depth image, that is, the corrected crown depth data can be represented as a corrected crown depth image. When the corrected crown depth data is subjected to spherical depth back-projection, since spherical depth back-projection is the inverse process of spherical depth projection, the position information of the target pixel point with a non-zero pixel value on the corrected crown depth image can be first used, and with the aid of the mapping relationship between the pixel point and the first ray in the spherical depth projection process, a plurality of third rays with the origin of the three-dimensional rectangular coordinate system of the target tooth position as a fixed point and having a mapping relationship with the target pixel point can be determined.
[0138] Thereafter, for any third ray, the three-dimensional point whose distance information from the origin of the three-dimensional rectangular coordinate system of the target tooth position is the pixel value can be determined in the unit direction of the third ray according to the pixel value of the pixel point having a mapping relationship with the third ray.
[0139] After that, the three-dimensional point corresponding to the target pixel point and the three-dimensional point corresponding to the neighboring pixel point of the target pixel point can be used to determine the three-dimensional data of the crown of the target tooth position. For example, the three-dimensional point corresponding to the target pixel point and the three-dimensional point corresponding to the neighboring pixel point of the target pixel point can be connected to form a surface patch. The surface patches corresponding to all the target pixels can constitute the three-dimensional data of the crown of the target tooth position.
[0140] It can be understood that the neighborhood pixel points may include pixel points with non-zero pixel values adjacent to the right side of the target pixel point and pixel points with non-zero pixel values adjacent to the top side, and may also include pixel points with non-zero pixel values adjacent to the left side of the target pixel point and pixel points with non-zero pixel values adjacent to the bottom side.
[0141] In the embodiment of the present invention, a spherical depth back-projection method is provided, which is simple and easy to implement and is convenient for improving calculation efficiency.
[0142] In some optional implementations, the crown depth data prediction model is trained based on the depth data of the tooth site sample, the surrounding tooth body depth data of the tooth site sample, and the crown depth data label of the tooth site sample.
[0143] Specifically, during the training process of the crown depth data prediction model, the depth data of the tooth position sample and the surrounding tooth depth data of the tooth position sample can be input into the initial prediction model to obtain the prediction result output by the initial prediction model, and then the loss function value is calculated based on the prediction result and the crown depth data label of the tooth position sample. Finally, according to the loss function value, the structural parameters of the initial prediction model are updated; the above-mentioned input process and calculation process are iteratively executed until the loss function converges or reaches a preset number of iterations to obtain the crown depth data prediction model.
[0144] It is understandable that the initial prediction model can be a deep learning model or any other type of machine learning model.
[0145] In an embodiment of the present invention, a crown depth data prediction model is obtained by model training, so that the crown depth data prediction model can learn the ability to generate crown depth data, and then the crown depth data of the target tooth position can be quickly generated through the crown depth data prediction model.
[0146] like Fig. 9 As shown in the figure, it is a schematic diagram of the three-dimensional data of the tooth position edge of the target tooth position in the three-dimensional rectangular coordinate system. By performing spherical projection on the three-dimensional data of the tooth position edge, the two-dimensional line of the tooth position edge is obtained as shown in Fig.10 The correction mask determined based on the two-dimensional line of the tooth edge is as follows Fig.11 shown.
[0147] The data in the selected area of the correction mask in the crown depth data of the target tooth is determined as the corrected crown depth data, and the corrected crown depth data is back-projected on the spherical surface to obtain the three-dimensional crown data of the target tooth. Fig.12 shown.
[0148] like Fig.13As shown in FIG. 1 , if the target tooth position is the third tooth from the left in the upper jaw, the 3D data of the upper jaw (i.e., the front upper jaw) when the 3D data of the crown of the target tooth position is not determined, the 3D data of the lower jaw (i.e., the front lower jaw) when the 3D data of the crown of the target tooth position is not determined, and the 3D data of the upper jaw (i.e., the back upper jaw) obtained by fusing the 3D data of the crown of the target tooth position with the 3D data of the upper jaw is as shown in FIG. Fig.13 shown.
[0149] In summary, in the embodiment of the present invention, by means of spherical depth projection technology, the three-dimensional data of the target tooth position and its adjacent teeth and opposing teeth are expressed respectively through a single depth image, which can make full use of the prediction model for the depth image and reduce the computational loss. This method has good robustness for different forms of intraoral environments and teeth in different positions. Moreover, in the embodiment of the present invention, the predicted depth image is subjected to spherical depth back-projection, and the three-dimensional data of the crown of the target tooth position can be directly obtained without the need for complex post-processing steps, which is simple, direct and efficient. In addition, in the embodiment of the present invention, the prediction model can be used to predict the pixel-level prediction of the crown depth data of the target tooth position, which is equivalent to predicting the vertex position of the three-dimensional crown data of the target tooth position at the order of millions, thereby ensuring the ability to retain the details of the generated crown. Compared with the method of manually designing the crown, the speed of this method has been significantly improved. On an ordinary personal computer, this method only takes a few seconds to complete the design of a crown.
[0150] like Fig.14 As shown, an embodiment of the present invention further provides a device for generating three-dimensional data of a tooth crown, comprising:
[0151] The acquisition module 141 is used to acquire the three-dimensional data of the target tooth position and the three-dimensional data of the surrounding tooth body of the target tooth position, and perform spherical depth projection on the three-dimensional data of the tooth position and the three-dimensional data of the surrounding tooth body to obtain the tooth position depth data and the surrounding tooth body depth data; the prediction module 142 is used to determine the crown depth data of the target tooth position based on the tooth position depth data and the surrounding tooth body depth data by applying the crown depth data prediction model; the generation module 143 is used to generate the three-dimensional crown data of the target tooth position based on the crown depth data of the target tooth position.
[0152] In some optional embodiments, the three-dimensional crown data generating device provided in the embodiments of the present invention, the generating module is specifically used for: obtaining the three-dimensional data of the tooth position edge of the target tooth position; the three-dimensional data of the tooth position edge at least includes one of the maximum circumference data and the cervical margin line data of the target tooth position; based on the three-dimensional data of the tooth position edge, correcting the crown depth data of the target tooth position to obtain corrected crown depth data; performing spherical depth back-projection on the corrected crown depth data to obtain the three-dimensional crown data of the target tooth position.
[0153] In some optional embodiments, the three-dimensional crown data generating device provided in the embodiments of the present invention, the generating module is specifically used to: determine the correction mask based on the three-dimensional data of the tooth edge; and determine the data in the crown depth data of the target tooth position that is within the selected area of the correction mask as the corrected crown depth data.
[0154] In some optional embodiments, in the tooth crown three-dimensional data generating device provided in the embodiments of the present invention, the acquisition module is specifically used to: determine the common sphere center; based on the common sphere center, perform spherical depth projection on the tooth position three-dimensional data and the surrounding tooth body three-dimensional data to obtain the tooth position depth data and the surrounding tooth body depth data.
[0155] In some optional embodiments, in the tooth crown three-dimensional data generation device provided in the embodiments of the present invention, the tooth position depth data and the surrounding tooth body depth data are represented based on the depth image; the acquisition module is specifically used to: construct a three-dimensional rectangular coordinate system; for any type of object in the tooth position three-dimensional data and the surrounding tooth body three-dimensional data, perform the following operations: sample multiple first rays with the origin of the three-dimensional rectangular coordinate system as the fixed point, and based on the unit direction of each first ray, determine the position information of each pixel point in the depth image corresponding to the object that has a mapping relationship with each first ray; and determine the distance information from the intersection of each first ray and the three-dimensional data of the object to the origin, and based on the distance information, determine the pixel value of each pixel point in the depth image corresponding to the object that has a mapping relationship with each first ray.
[0156] In some optional embodiments, the acquisition module of the tooth crown three-dimensional data generating device provided in the embodiments of the present invention is specifically used to: determine the coordinate axis direction of the three-dimensional rectangular coordinate system based on the three-dimensional data of the tooth position and the three-dimensional data of the surrounding teeth, or based on the three-dimensional data of the teeth in the mouth where the target tooth position is located; determine the origin of the three-dimensional rectangular coordinate system based on the data range of the cervical margin line data of the target tooth position in the vertical axis direction of the three-dimensional rectangular coordinate system.
[0157] In some optional embodiments, in the tooth crown three-dimensional data generating device provided in the embodiment of the present invention, the surrounding tooth body three-dimensional data includes the three-dimensional data of the opposing tooth of the target tooth position and the three-dimensional data of the adjacent tooth of the target tooth position;
[0158] The acquisition module is specifically used for: determining the center point of the target tooth position based on the three-dimensional tooth position data, and determining the center points of each surrounding tooth of the target tooth position based on the three-dimensional data of the surrounding teeth; determining the tooth fitting plane based on the center point of the target tooth position and the center points of each surrounding tooth, and determining the normal direction of the tooth fitting plane as the horizontal axis direction of the three-dimensional rectangular coordinate system; determining at least two objects in the target tooth position and each surrounding tooth in the same dental jaw, and determining the direction of the line connecting the center points of the at least two objects as the vertical axis direction of the three-dimensional rectangular coordinate system; determining the vertical axis direction of the three-dimensional rectangular coordinate system based on the horizontal axis direction and the vertical axis direction.
[0159] In some optional embodiments, in the tooth crown three-dimensional data generating device provided in the embodiments of the present invention, the acquisition module is specifically used to: perform spherical depth projection on the three-dimensional data of the opposing teeth and the three-dimensional data of the adjacent teeth, and obtain the depth data of the opposing teeth of the target tooth position and the depth data of the adjacent teeth of the target tooth position, respectively.
[0160] In some optional embodiments, the acquisition module of the device for generating three-dimensional data of dental crowns provided in the embodiments of the present invention is specifically used to: determine the occlusal plane of the teeth in the mouth based on the three-dimensional data of the teeth in the mouth; determine the vertical axis direction of the three-dimensional rectangular coordinate system based on the occlusal plane of the teeth in the mouth, and determine the tooth fitting plane, and determine the normal direction of the tooth fitting plane as the horizontal axis direction of the three-dimensional rectangular coordinate system; determine the longitudinal axis direction of the three-dimensional rectangular coordinate system based on the horizontal axis direction and the vertical axis direction.
[0161] In some optional embodiments, the three-dimensional crown data generating device provided in the embodiments of the present invention has a vertical axis direction from the jaw where the target tooth is located toward the opposite jaw; the position information of the origin in the vertical axis direction is smaller than the minimum position information of the cervical margin line data of the target tooth in the vertical axis direction.
[0162] In some optional embodiments, in the dental crown three-dimensional data generating device provided in the embodiments of the present invention, the acquisition module is specifically used for: for any first ray, if the first ray and the three-dimensional data of the object include multiple intersection points, then determine the minimum value of the distance information from the multiple intersection points to the origin, and use the minimum value as the pixel value of the pixel point having a mapping relationship with the first ray in the depth image corresponding to the object.
[0163] In some optional embodiments, the generation module of the three-dimensional crown data generation device provided in the embodiments of the present invention is specifically used to: perform spherical projection on the three-dimensional data of the tooth edge to obtain the two-dimensional lines of the tooth edge; and determine the correction mask based on the two-dimensional lines of the tooth edge.
[0164] In some optional embodiments, in the tooth crown three-dimensional data generating device provided in the embodiment of the present invention, the tooth position edge three-dimensional data includes multiple line segments; the generating module is specifically used to: determine each second ray from the origin of the three-dimensional rectangular coordinate system to the endpoint of each line segment in the multiple line segments, and based on the unit direction of each second ray, determine the position information of each pixel point in the two-dimensional image that has a mapping relationship with each second ray; according to the connection relationship between the endpoints of each line segment in the tooth position edge three-dimensional data, connect each pixel point in the two-dimensional image to obtain a two-dimensional line of the tooth position edge; wherein the pixel value of the pixel point in the two-dimensional image located within a preset range around the two-dimensional line of the tooth position edge is set to 1, and the pixel value of the pixel point outside the preset range is set to 0.
[0165] In some optional embodiments, in the dental crown three-dimensional data generating device provided in the embodiments of the present invention, the corrected dental crown depth data is represented based on the corrected dental crown depth image; the generating module is specifically used to: determine multiple third rays with the origin of the three-dimensional rectangular coordinate system as the fixed point and having a mapping relationship with the target pixel point based on the position information of the target pixel point with non-zero pixel value on the corrected dental crown depth image; for any third ray, determine the three-dimensional point in the unit direction of the third ray, and the distance information between the three-dimensional point and the origin is the pixel value of the pixel point having a mapping relationship with the third ray; determine the dental crown three-dimensional data of the target tooth position based on the three-dimensional point corresponding to the target pixel point and the three-dimensional point corresponding to the designated neighborhood pixel point of the target pixel point; the designated neighborhood pixel point is the pixel point with non-zero pixel value within the neighborhood range of the target pixel point.
[0166] In some optional embodiments, in the tooth crown three-dimensional data generating device provided in the embodiment of the present invention, the tooth crown depth data prediction model is trained based on the depth data of the tooth position sample, the surrounding tooth body depth data of the tooth position sample and the tooth crown depth data label of the tooth position sample.
[0167] Specifically, the functions of each module in the dental crown three-dimensional data generating device provided in the embodiment of the present invention correspond one-to-one to the operation flow of each step in the above method embodiment, and the effects achieved are also consistent. Please refer to the above embodiment for details, which will not be repeated in the embodiment of the present invention.
[0168] Fig.15 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.15 As shown, the electronic device may include: a processor 1510, a communication interface 1520, a memory 1530 and a communication bus 1540, wherein the processor 1510, the communication interface 1520 and the memory 1530 communicate with each other through the communication bus 1540. The processor 1510 may call the logic instructions in the memory 1530 to execute the method for generating three-dimensional data of a dental crown provided in the above-mentioned embodiments.
[0169] In addition, the logic instructions in the above-mentioned memory 1530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.
[0170] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for generating three-dimensional data of dental crowns provided in the above embodiments.
[0171] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the method for generating three-dimensional data of a dental crown provided in the above-mentioned embodiments.
[0172] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.
[0173] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention is described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the above embodiments, or replace some of the technical features therein by equivalent; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for generating three-dimensional data of a dental crown, It is characterized in that include: Acquire three-dimensional tooth position data of a target tooth position and three-dimensional tooth body data surrounding the target tooth position, perform spherical depth projection on the three-dimensional tooth position data and the three-dimensional tooth body data surrounding the target tooth position, and obtain tooth position depth data and surrounding tooth body depth data; Based on the tooth position depth data and the surrounding tooth body depth data, a crown depth data prediction model is applied to determine the crown depth data of the target tooth position; Based on the crown depth data of the target tooth position, generating three-dimensional crown data of the target tooth position; The step of performing spherical depth projection on the three-dimensional tooth position data and the three-dimensional tooth body data to obtain the tooth position depth data and the surrounding tooth body depth data includes: Determine the common sphere center; Based on the common spherical center, spherical depth projection is performed on the tooth position three-dimensional data and the surrounding tooth body three-dimensional data to obtain the tooth position depth data and the surrounding tooth body depth data.
2. The method for generating three-dimensional data of a dental crown according to claim 1, It is characterized in that The step of generating three-dimensional data of the tooth crown of the target tooth position based on the tooth crown depth data of the target tooth position comprises: Acquire the three-dimensional data of the tooth position edge of the target tooth position; the three-dimensional data of the tooth position edge includes at least one of the maximum circumference data and the cervical margin line data of the target tooth position; Based on the three-dimensional data of the tooth position edge, the crown depth data of the target tooth position is corrected to obtain corrected crown depth data; The modified crown depth data is subjected to spherical depth back-projection to obtain the crown three-dimensional data of the target tooth position.
3. The method for generating three-dimensional data of a dental crown according to claim 2, It is characterized in that The method of correcting the crown depth data of the target tooth position based on the tooth position edge three-dimensional data to obtain the corrected crown depth data includes: Determining a correction mask based on the three-dimensional data of the tooth position edge; The data of the crown depth data of the target tooth position that is within the selected area of the correction mask is determined as the corrected crown depth data.
4. The method for generating three-dimensional data of a dental crown according to claim 1, It is characterized in that The tooth position depth data and the surrounding tooth body depth data are represented based on a depth image; The step of performing spherical depth projection on the tooth position three-dimensional data and the surrounding tooth body three-dimensional data to obtain tooth position depth data and surrounding tooth body depth data includes: Construct a three-dimensional rectangular coordinate system; For any type of object in the tooth position three-dimensional data and the surrounding tooth body three-dimensional data, the following operations are performed: Sampling a plurality of first rays with the origin of the three-dimensional rectangular coordinate system as a fixed point, and determining position information of each pixel point having a mapping relationship with each first ray in the depth image corresponding to the object based on the unit direction of each first ray; and Determine distance information from intersection points of each first ray with the three-dimensional data of the object to the origin, and determine pixel values of each pixel point in the depth image corresponding to the object that has a mapping relationship with each first ray based on the distance information.
5. The method for generating three-dimensional data of a dental crown according to claim 4, It is characterized in that The constructing of a three-dimensional rectangular coordinate system comprises: Based on the three-dimensional data of the tooth position and the three-dimensional data of the surrounding tooth body, or based on the three-dimensional data of the teeth in the mouth where the target tooth position is located, determine the direction of the coordinate axis of the three-dimensional rectangular coordinate system; Based on the data range of the cervical margin line data of the target tooth position in the vertical axis direction of the three-dimensional rectangular coordinate system, the origin of the three-dimensional rectangular coordinate system is determined.
6. The method for generating three-dimensional data of a dental crown according to claim 5, It is characterized in that The surrounding tooth three-dimensional data includes the three-dimensional data of the teeth opposite to the target tooth position and the three-dimensional data of the adjacent teeth of the target tooth position; Determining the coordinate axis direction of the three-dimensional rectangular coordinate system based on the three-dimensional tooth position data and the three-dimensional data of the surrounding tooth body includes: Based on the three-dimensional tooth position data, determine the center point of the target tooth position, and based on the three-dimensional tooth body data, determine the center point of each surrounding tooth body of the target tooth position; Based on the center point of the target tooth position and the center points of each of the surrounding teeth, a tooth fitting plane is determined, and the normal direction of the tooth fitting plane is determined as the horizontal axis direction of the three-dimensional rectangular coordinate system; Determine the target tooth position and at least two objects in the surrounding tooth bodies that are in the same tooth jaw, and determine the direction of the line connecting the center points of the at least two objects as the longitudinal axis direction of the three-dimensional rectangular coordinate system; Based on the horizontal axis direction and the vertical axis direction, the vertical axis direction of the three-dimensional rectangular coordinate system is determined.
7. The method for generating three-dimensional data of a dental crown according to claim 6, It is characterized in that The surrounding tooth depth data is determined in the following manner: Spherical depth projection is performed on the three-dimensional data of the opposing teeth and the three-dimensional data of the adjacent teeth to obtain the depth data of the opposing teeth of the target tooth position and the depth data of the adjacent teeth of the target tooth position respectively.
8. The method for generating three-dimensional data of a dental crown according to claim 5, It is characterized in that Determining the coordinate axis direction of the three-dimensional rectangular coordinate system based on the three-dimensional data of the teeth in the mouth where the target tooth position is located includes: Determine the occlusal plane of the teeth in the mouth based on the three-dimensional data of the teeth in the mouth; Based on the intraoral tooth occlusal plane, determine the vertical axis direction of the three-dimensional rectangular coordinate system, determine the tooth fitting plane, and determine the normal direction of the tooth fitting plane as the horizontal axis direction of the three-dimensional rectangular coordinate system; Based on the horizontal axis direction and the vertical axis direction, the vertical axis direction of the three-dimensional rectangular coordinate system is determined.
9. The method for generating three-dimensional data of a dental crown according to claim 6, It is characterized in that The vertical axis direction is from the jaw where the target tooth position is located toward the opposite jaw; The position information of the origin in the vertical axis direction is smaller than the minimum position information of the cervical margin line data of the target tooth position in the vertical axis direction.
10. The method for generating three-dimensional data of a dental crown according to claim 4, It is characterized in that The determining, based on the distance information, the pixel value of each pixel point in the depth image corresponding to the object and having a mapping relationship with each first ray includes: For any first ray, if the first ray includes multiple intersection points with the three-dimensional data of the object, the minimum value of the distance information from the multiple intersection points to the origin is determined, and the minimum value is used as the pixel value of the pixel point in the depth image corresponding to the object that has a mapping relationship with the first ray.
11. The method for generating three-dimensional data of a dental crown according to claim 3, It is characterized in that The step of determining a correction mask based on the tooth position edge three-dimensional data includes: Performing spherical projection on the three-dimensional data of the tooth position edge to obtain a two-dimensional line of the tooth position edge; The correction mask is determined based on the two-dimensional line of the tooth edge.
12. The method for generating three-dimensional data of a dental crown according to claim 11, It is characterized in that The tooth position edge three-dimensional data includes a plurality of line segments; The step of performing spherical projection on the three-dimensional data of the tooth position edge to obtain a two-dimensional line of the tooth position edge includes: Determine each second ray from the origin of the three-dimensional rectangular coordinate system to the endpoint of each of the plurality of line segments, and determine, based on the unit direction of each second ray, position information of each pixel point in the two-dimensional image that has a mapping relationship with each second ray; According to the connection relationship between the endpoints of each line segment in the three-dimensional data of the tooth position edge, each pixel point in the two-dimensional image is connected to obtain the two-dimensional line of the tooth position edge; The pixel values of the pixels in the two-dimensional image that are within a preset range around the two-dimensional line of the tooth edge are set to 1, and the pixel values of the pixels outside the preset range are set to 0.
13. The method for generating three-dimensional data of a dental crown according to claim 2, It is characterized in that The modified crown depth data is represented based on the modified crown depth image; The step of performing spherical depth back-projection on the corrected crown depth data to obtain the crown three-dimensional data of the target tooth position includes: Based on the position information of the target pixel point with a non-zero pixel value on the modified crown depth image, a plurality of third rays are determined with the origin of the three-dimensional rectangular coordinate system as a fixed point and having a mapping relationship with the target pixel point; For any third ray, determine a three-dimensional point in a unit direction of the third ray, where the distance information between the three-dimensional point and the origin is a pixel value of a pixel point having a mapping relationship with the third ray; The three-dimensional data of the tooth crown of the target tooth position is determined based on the three-dimensional point corresponding to the target pixel point and the three-dimensional point corresponding to the designated neighborhood pixel point of the target pixel point; the designated neighborhood pixel point is a pixel point with a non-zero pixel value within the neighborhood range of the target pixel point.
14. The method for generating three-dimensional data of a dental crown according to any one of claims 1 to 13, It is characterized in that The crown depth data prediction model is trained based on the depth data of the tooth site sample, the surrounding tooth body depth data of the tooth site sample and the crown depth data label of the tooth site sample.
15. A device for generating three-dimensional data of a dental crown, It is characterized in that include: An acquisition module is used to acquire the three-dimensional data of the target tooth position and the three-dimensional data of the tooth body around the target tooth position, and perform spherical depth projection on the three-dimensional data of the tooth position and the three-dimensional data of the surrounding tooth body to obtain the depth data of the tooth position and the depth data of the surrounding tooth body; A prediction module, for determining the crown depth data of the target tooth position by applying a crown depth data prediction model based on the tooth position depth data and the surrounding tooth body depth data; A generating module, used for generating three-dimensional data of a tooth crown of the target tooth position based on the tooth crown depth data of the target tooth position; Wherein, the acquisition module is also used to: determine a common sphere center; based on the common sphere center, perform spherical depth projection on the tooth position three-dimensional data and the surrounding tooth body three-dimensional data to obtain the tooth position depth data and the surrounding tooth body depth data.
16. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method for generating three-dimensional data of a dental crown according to any one of claims 1 to 14 is implemented.
17. A non-transitory computer readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method for generating three-dimensional data of a dental crown according to any one of claims 1 to 14 is implemented.
