Method for segmenting teeth of three-dimensional oral scan data by using tooth library model, and computer-readable recording medium on which program for executing same in computer is recorded

Abstract

This method for segmenting teeth of three-dimensional oral scan data by using a tooth library model comprises the steps of: extracting a margin line of a tooth of interest from three-dimensional oral scan data; segmenting a tooth region of interest of the three-dimensional oral scan data on the basis of the margin line; acquiring a tooth library model corresponding to the tooth identification number of the tooth of interest; aligning the tooth region of interest with the tooth library model; and generating a tooth segmentation model by causing the shape of the tooth library model to change to correspond to the shape of the tooth region of interest.

Description

A method for separating teeth from three-dimensional oral scan data using a tooth library model and a computer-readable recording medium having recorded thereon a program for executing the method on a computer

[0001] The present invention relates to a method for separating teeth from three-dimensional oral scan data using a tooth library model and a computer-readable recording medium having recorded thereon a program for executing the method on a computer, and more particularly, to a method for separating teeth from three-dimensional oral scan data using a tooth library model, which is performed by aligning a tooth region of interest from three-dimensional oral scan data and a tooth library model based on feature points, and a computer-readable recording medium having recorded thereon a program for executing the method on a computer.

[0002] In digital dentistry, obtaining patient oral data is essential for treatment planning. 3D oral scan data refers to data obtained by scanning teeth, the oral cavity, or a model or reconstruction of these objects using a 3D scanner. Dental treatments such as prosthetic treatments (inlays, onlays, crowns), implants, and orthodontic treatment can utilize patient oral data to design prosthetics or implants, and fabricate orthodontic appliances.

[0003] Treatment using 3D intraoral scanners is increasingly being used in dental clinics and dental laboratories because it allows for faster diagnosis and preparation than traditional impression-based treatment, while also reducing patient burden. These 3D intraoral scan data not only scans the teeth to be treated, but also the adjacent and opposing teeth. Therefore, a single intraoral scan model can represent the entire maxilla or mandible, or the teeth to be treated and their surrounding teeth. Furthermore, because the scan extends beyond the teeth to the gum area, prosthetic fabrication or orthodontic treatment planning requires separating the teeth from the 3D intraoral scan data.

[0004] Due to the precision, physical, and technical limitations of 3D intraoral scanners, 3D intraoral scan data may not accurately represent the space between adjacent teeth. Consequently, even if only the tooth region is isolated from 3D intraoral scan data, the resulting model will leave the area where the adjacent teeth were located empty.

[0005] In order to establish a precise treatment plan for a patient, such as orthodontic treatment, a precise tooth model is required. However, as explained above, individual tooth models with empty areas make it difficult to establish a precise treatment plan.

[0006] The purpose of the present invention is to provide a method for separating teeth from 3D oral scan data using a tooth library model, which can preserve lost tooth region information between teeth by aligning a tooth region of interest from 3D oral scan data and a tooth library model, and modifying the tooth library model to correspond to the tooth region of interest.

[0007] Another object of the present invention is to provide a computer-readable recording medium having recorded thereon a program for executing a method of separating teeth from three-dimensional oral scan data using the above-described tooth library model on a computer.

[0008] According to one embodiment of the present invention for realizing the above-described object, a method for separating teeth from 3D oral scan data using a tooth library model includes the steps of extracting a margin line of a tooth of interest from 3D oral scan data, separating a tooth region of interest from the 3D oral scan data based on the margin line, obtaining a tooth library model corresponding to a tooth identification number of the tooth of interest, aligning the tooth region of interest with the tooth library model, and generating a tooth separation model by deforming a shape of the tooth library model to correspond to a shape of the tooth region of interest.

[0009] In one embodiment of the present invention, the method for separating teeth from 3D oral scan data using the tooth library model may further include the steps of extracting a first feature point of the tooth region of interest and acquiring a second feature point of the tooth library model. The tooth region of interest and the tooth library model may be aligned based on the first feature point and the second feature point.

[0010] In one embodiment of the present invention, the number and positions of the first feature points may be determined differently depending on whether the tooth of interest is included in the maxilla or the mandible, and whether the tooth of interest is an incisor, a canine, a premolar, or a molar. The number and positions of the second feature points may be determined differently depending on whether the target tooth of the tooth library model is included in the maxilla or the mandible, and whether the target tooth of the tooth library model is an incisor, a canine, a premolar, or a molar. When the tooth of interest and the target tooth of the tooth library model are the same tooth, the number of the first feature points may be equal to the number of the second feature points.

[0011] In one embodiment of the present invention, the step of aligning the tooth region of interest and the tooth library model may further include the step of determining the center point of the tooth of interest and the arrangement direction of the tooth of interest within the tooth region of interest and the step of determining the center point of the target tooth of the tooth library model and the arrangement direction of the target tooth. The tooth region of interest and the tooth library model may be aligned based on the center point of the tooth of interest, the arrangement direction of the tooth of interest, the center point of the target tooth, and the arrangement direction of the target tooth.

[0012] In one embodiment of the present invention, the step of aligning the tooth region of interest and the tooth library model may further include the step of iteratively finding an optimal transformation between a first point cloud of the tooth region of interest and a second point cloud of the tooth library model.

[0013] In one embodiment of the present invention, the step of aligning the tooth region of interest and the tooth library model may further include the step of converting the tooth region of interest into a first hash value, the step of converting the tooth library model into a second hash value, and the step of determining the similarity between the tooth region of interest and the tooth library model using the first hash value and the second hash value.

[0014] In one embodiment of the present invention, the margin line of the tooth of interest may be extracted through a first artificial intelligence neural network. The input of the first artificial intelligence neural network may be the three-dimensional oral scan data, and the output of the first artificial intelligence neural network may be the margin line of the tooth of interest.

[0015] In one embodiment of the present invention, in the step of extracting the margin line of the tooth of interest, the margin line can be extracted by grouping and segmenting geographical features within the 3D oral scan data.

[0016] In one embodiment of the present invention, in the step of extracting the margin line of the tooth of interest, the margin line may be extracted using surface curvature information or plane segmentation information within the 3D oral scan data.

[0017] In one embodiment of the present invention, the tooth area of ​​interest may be a model in which at least a portion of the interdental area between the tooth of interest and an adjacent tooth of the tooth of interest is empty.

[0018] In one embodiment of the present invention, the step of generating the tooth separation model may include the step of obtaining a first skeleton or a first bone of a mesh of the tooth region of interest and the step of obtaining a second skeleton or a second bone of a mesh of the tooth library model. Using the first skeleton and the second skeleton or the first bone and the second bone, the shape of the tooth library model may be deformed to correspond to the shape of the tooth region of interest.

[0019] In one embodiment of the present invention, the step of generating the tooth separation model may include the step of blending a mesh of the tooth region of interest and a mesh of the tooth library model.

[0020] In one embodiment of the present invention, the step of generating the tooth separation model may include the step of dividing the mesh of the tooth region of interest into a first grid and obtaining points within the first grid, and the step of dividing the mesh of the tooth library model into a second grid and obtaining points within the second grid. Using the points within the first grid and the points within the second grid, the shape of the tooth library model may be deformed to correspond to the shape of the tooth region of interest.

[0021] In one embodiment of the present invention, in the step of generating the tooth separation model, the shape of the tooth library model can be deformed to correspond to the shape of the tooth region of interest by using local similarity between the mesh of the tooth region of interest and the mesh of the tooth library model.

[0022] In one embodiment of the present invention, the margin line of the tooth of interest may be extracted through a first artificial intelligence neural network. An input of the first artificial intelligence neural network may be the three-dimensional oral scan data, and an output of the first artificial intelligence neural network may be the margin line of the tooth of interest. A method for segmenting teeth from three-dimensional oral scan data using the tooth library model may further include a step of extracting a first feature point of the tooth region of interest. The first feature point may be extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network. An input of the second artificial intelligence neural network may be the tooth region of interest, and an output of the second artificial intelligence neural network may be the three-dimensional coordinates of the first feature point.

[0023] In one embodiment of the present invention, the method for separating teeth from 3D oral scan data using the tooth library model may further include a step of obtaining the tooth identification number of the tooth of interest.

[0024] In one embodiment of the present invention, the margin line of the tooth of interest may be extracted through a first artificial intelligence neural network. An input of the first artificial intelligence neural network may be the three-dimensional oral scan data, and an output of the first artificial intelligence neural network may be the margin line of the tooth of interest. A method for segmenting teeth from three-dimensional oral scan data using the tooth library model may further include a step of extracting a first feature point of the tooth region of interest. The first feature point may be extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network. An input of the second artificial intelligence neural network may be the tooth region of interest, and an output of the second artificial intelligence neural network may be the three-dimensional coordinates of the first feature point. The tooth identification number of the tooth of interest may be obtained through a third artificial intelligence neural network. An input of the third artificial intelligence neural network may be the three-dimensional oral scan data, and an output of the third artificial intelligence neural network may be the tooth identification number of the tooth of interest.

[0025] In one embodiment of the present invention, the margin line of the tooth of interest may be extracted through a first artificial intelligence neural network. An input of the first artificial intelligence neural network may be the three-dimensional oral scan data, and an output of the first artificial intelligence neural network may be the margin line of the tooth of interest. A method for segmenting teeth from three-dimensional oral scan data using the tooth library model may further include a step of extracting a first feature point of the tooth region of interest and a step of extracting a second feature point of the tooth library model corresponding to the tooth identification number of the tooth of interest. The first feature point may be extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network, and the second feature point may be extracted through a fourth artificial intelligence neural network different from the first artificial intelligence neural network and the second artificial intelligence neural network. An input of the second artificial intelligence neural network may be the tooth region of interest, and an output of the second artificial intelligence neural network may be a three-dimensional coordinate of the first feature point. The input of the fourth artificial intelligence neural network may be the tooth library model corresponding to the tooth identification number of the tooth of interest, and the output of the fourth artificial intelligence neural network may be the three-dimensional coordinates of the second feature point.

[0026] In one embodiment of the present invention, the margin line of the tooth of interest may be extracted through a first artificial intelligence neural network. An input of the first artificial intelligence neural network may be the three-dimensional oral scan data, and an output of the first artificial intelligence neural network may be the margin line of the tooth of interest. A method for segmenting teeth from three-dimensional oral scan data using the tooth library model may further include a step of extracting a first feature point of the tooth region of interest and a step of extracting a second feature point of the tooth library model corresponding to the tooth identification number of the tooth of interest. The first feature point and the second feature point may be extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network. A first input of the second artificial intelligence neural network may be the tooth region of interest, and a first output of the second artificial intelligence neural network may be a three-dimensional coordinate of the first feature point. The second input of the second artificial intelligence neural network may be the tooth library model corresponding to the tooth identification number of the tooth of interest, and the second output of the second artificial intelligence neural network may be the three-dimensional coordinates of the second feature point.

[0027] In one embodiment of the present invention, a program for executing a method for separating teeth from three-dimensional oral scan data using the tooth library model on a computer can be recorded on a computer-readable recording medium.

[0028] According to a method for separating teeth from three-dimensional oral scan data using a tooth library model according to the present invention, the tooth region of interest of the three-dimensional oral scan data and the tooth library model are aligned, and the tooth library model is modified to correspond to the tooth region of interest, thereby preserving lost tooth region information between teeth.

[0029] According to the method for separating teeth from 3D oral scan data using a dental library model according to the present invention, each individual tooth model of a patient can be separated from the patient's tooth model generated through a single scan. Due to the scanner's precision, the interdental space between individual teeth, which cannot be identified in 3D oral scan data, can be predicted, and individual teeth can be moved, enabling easy and rapid treatment planning for the patient. This reduces the workload of dentists or dental technicians, increases work efficiency, and facilitates the provision of high-quality medical services.

[0030] FIG. 1 is a flowchart illustrating a method for separating teeth from three-dimensional oral scan data using a tooth library model according to one embodiment of the present invention.

[0031] Figure 2a is a drawing showing an example of 3D oral scan data.

[0032] Figure 2b is a drawing showing an example of 3D oral scan data.

[0033] Figure 3a is a drawing showing two adjacent teeth attached within three-dimensional oral scan data.

[0034] Figure 3b is a drawing showing that the tooth region of interest is separated within the 3D oral scan data of Figure 3a.

[0035] Figure 4a is a drawing showing the extracted margin line of the tooth of interest from the 3D oral scan data.

[0036] Figure 4b is a diagram showing a user manually adjusting the margin line of a tooth of interest in 3D oral scan data.

[0037] Figure 5 is a drawing showing an example of a tooth library model.

[0038] Figure 6a is a diagram showing a tooth region of interest in 3D oral scan data.

[0039] Figure 6b is a diagram showing a tooth library model corresponding to the tooth identification number of the tooth of interest in the 3D oral scan data.

[0040] Figure 6c is a drawing showing that the tooth library model corresponding to the tooth identification number of the tooth of interest and the tooth region of interest are aligned.

[0041] Figure 7 is a drawing showing a tooth separation model created by transforming the shape of the tooth library model to correspond to the shape of the tooth region of interest.

[0042] Fig. 8 is a drawing showing the entire tooth separation models separated through the tooth separation method of 3D oral scan data using the tooth library model of the present embodiment.

[0043] FIG. 9 is a flowchart illustrating a method for separating teeth from three-dimensional oral scan data using a tooth library model according to one embodiment of the present invention.

[0044] FIG. 10 is a flowchart illustrating a method for separating teeth from three-dimensional oral scan data using a tooth library model according to one embodiment of the present invention.

[0045] With respect to the embodiments of the present invention disclosed in the text, specific structural and functional descriptions are merely illustrative for the purpose of explaining the embodiments of the present invention, and the embodiments of the present invention may be implemented in various forms and should not be construed as being limited to the embodiments described in the text.

[0046] The present invention is susceptible to various modifications and takes various forms. Specific embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit the present invention to specific disclosed forms, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention.

[0047] While terms like "first" and "second" may be used to describe various components, these components should not be limited by these terms. These terms may be used to distinguish one component from another. For example, without departing from the scope of the present invention, a first component could be referred to as a "second component," and similarly, a second component could also be referred to as a "first component."

[0048] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. Conversely, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions that describe the relationship between components, such as "between" and "directly between" or "adjacent to" and "directly adjacent to", should be interpreted similarly.

[0049] The terminology used in this application is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" indicate the presence of a described feature, number, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0050] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by those of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and shall not be construed in an idealized or overly formal sense unless explicitly defined herein.

[0051] Meanwhile, if a particular embodiment can be implemented differently, the functions or operations specified within a particular block may occur in a different order than specified in the flowchart. For example, two consecutive blocks may actually be executed substantially simultaneously, or, depending on the related functions or operations, the blocks may be executed in reverse order.

[0052] Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings. Identical components in the drawings are designated by the same reference numerals, and redundant descriptions of identical components are omitted.

[0053] FIG. 1 is a flowchart illustrating a method for separating teeth from three-dimensional oral scan data using a tooth library model according to one embodiment of the present invention.

[0054] Referring to FIG. 1, a method for separating teeth from 3D oral scan data using a tooth library model includes a step of receiving 3D oral scan data (step S100), a step of extracting a margin line of a tooth of interest from the 3D oral scan data (step S200), a step of separating a tooth region of interest from the 3D oral scan data based on the margin line (step S300), a step of obtaining a tooth library model corresponding to a tooth identification number of the tooth of interest (step S500), a step of aligning the tooth region of interest and the tooth library model (step S600), and a step of generating a tooth separation model by deforming a shape of the tooth library model to correspond to a shape of the tooth region of interest (step S700).

[0055] The method for separating teeth from 3D oral scan data using the above-described tooth library model may further include a step of extracting a first feature point of the tooth region of interest (step S400) and a step of acquiring a second feature point of the tooth library model. The tooth region of interest and the tooth library model may be aligned based on the first feature point and the second feature point.

[0056] In this embodiment, the second feature point of the tooth library model may be information already included in the tooth library model. Accordingly, the second feature point may be acquired together when the tooth library model is acquired.

[0057] In contrast, if the tooth library model does not include information on the second feature point, a step of extracting the second feature point from the tooth library model may be required.

[0058] The number and positions of the first feature points may be determined differently depending on whether the tooth of interest is included in the maxilla or the mandible, and whether the tooth of interest is an incisor, a canine, a premolar, or a molar. The number and positions of the second feature points may be determined differently depending on whether the target tooth of the tooth library model is included in the maxilla or the mandible, and whether the target tooth of the tooth library model is an incisor, a canine, a premolar, or a molar. When the tooth of interest and the target tooth of the tooth library model are the same tooth, the number of the first feature points may be the same as the number of the second feature points.

[0059] For example, the number of the first feature points of the tooth region of interest of the three-dimensional oral scan data may be at least three or more. For example, the number of the second feature points of the target tooth of the tooth library model may be at least three or more.

[0060] Here, a method for separating teeth from 3D oral scan data using the above-mentioned tooth library model can be performed by a computing device.

[0061] Here, the dental library model is a kind of sample tooth (standard tooth) used for manufacturing prosthetics, implants, braces, etc., and may have a typical tooth shape. The dental library model may have one sample tooth (standard tooth) for each tooth identification number. The 3D oral scan data is captured by a scanner, and thus the mesh may have a somewhat low degree of completion. If the mesh has a low degree of completion, it may not be suitable for manufacturing prosthetics, implants, braces, etc. by 3D printing. Conversely, the 3D dental library model may be a dental model with a high degree of completion of the mesh. Therefore, when modifying the 3D dental library model to manufacture prosthetics, implants, braces, etc., it may be very suitable for using a 3D printing method. Therefore, when the 3D dental library model is aligned with the patient's oral scan data, it can be a suitable intermediate model for manufacturing prosthetics, implants, braces, etc. digitally.

[0062] Figure 2a is a diagram illustrating an example of 3D oral scan data. Figure 2b is a diagram illustrating an example of 3D oral scan data. Figure 3a is a diagram illustrating two adjacent teeth being attached within the 3D oral scan data. Figure 3b is a diagram illustrating a tooth region of interest being separated within the 3D oral scan data of Figure 3a.

[0063] Referring to FIGS. 1 to 3b, the three-dimensional oral scan data may include the entire upper or lower jaw as in FIG. 2a, or may include a tooth to be treated and its surrounding teeth as in FIG. 2b.

[0064] Furthermore, since the oral scanner scans not only the teeth but also the gum area, it is necessary to isolate only the tooth area from the 3D oral scan data for prosthesis production or orthodontic treatment planning. Due to the precision, physical limitations, and technical limitations of the 3D oral scanner, the 3D oral scan data may not accurately represent the space between adjacent teeth, as shown in Fig. 3a. Therefore, even if only the tooth area is isolated from the 3D oral scan data, if there are adjacent teeth, the model will be empty in the area where the adjacent teeth were, as shown in Fig. 3b.

[0065] Fig. 4a is a diagram showing the extraction of the margin line (ML) of the tooth of interest from 3D oral scan data. Fig. 4b is a diagram showing the user manually adjusting the margin line (ML) of the tooth of interest from 3D oral scan data.

[0066] Referring to FIGS. 1 to 4B, for example, the margin line (ML) of the tooth of interest can be extracted through a first artificial intelligence neural network. The input of the first artificial intelligence neural network may be the 3D oral scan data, and the output of the first artificial intelligence neural network may be the margin line (ML) of the tooth of interest. For example, the first artificial intelligence neural network may be primarily based on a 3D CNN (Convolutional Neural Network) and may use structures such as PointNet and PointNet++.

[0067] For example, in the step of extracting the margin line (ML) of the tooth of interest, the margin line (ML) can be extracted by grouping and segmenting geographical features within the 3D oral scan data.

[0068] For example, in the step of extracting the margin line (ML) of the tooth of interest, the margin line (ML) can be extracted using surface curvature information or plane segmentation information within the 3D oral scan data.

[0069] Combining multiple techniques can also help refine 3D meshes more effectively. For example, hybrid methods can be used, combining machine learning with traditional geometry-based methods to improve performance.

[0070] As shown in Fig. 4a, the margin line (ML), which is the boundary between each individual tooth and gum, can be automatically obtained using the above methods. The margin line (ML) extracted in this way can also be manually adjusted by the user.

[0071] As shown in Fig. 4b, a user can directly click on points corresponding to the boundaries of the teeth and gum areas in the 3D oral scan data and use the points to create a parametric curve such as a Bezier Curve or Spline Curve, or a curve passing through the scan mesh.

[0072] Fig. 5 is a diagram showing an example of a tooth library model. Fig. 6a is a diagram showing a tooth region of interest of 3D oral scan data. Fig. 6b is a diagram showing a tooth library model corresponding to a tooth identification number of a tooth of interest of 3D oral scan data. Fig. 6c is a diagram showing alignment of the tooth region of interest and the tooth library model corresponding to the tooth identification number of the tooth of interest. Fig. 7 is a diagram showing a tooth separation model created by deforming the shape of the tooth library model to correspond to the shape of the tooth region of interest. Fig. 8 is a diagram showing entire tooth separation models separated through a tooth separation method of 3D oral scan data using the tooth library model of the present embodiment.

[0073] Referring to FIGS. 1 to 8, although the area of ​​each individual tooth can be roughly extracted from the patient's 3D oral scan data through the process of extracting the margin line (ML), it may be difficult to accurately separate the area of ​​each individual tooth through this. In order to obtain a more accurate area of ​​interest of the tooth of interest, a process of cutting the mesh model of the 3D oral scan data with the margin line (ML) may be necessary.

[0074] The mesh model of the tooth area of ​​interest separated from the above 3D oral scan data may appear as if it is connected to the adjacent teeth in the scan model even though it is actually separated from the adjacent teeth due to the precision of the scanner when adjacent teeth exist. Therefore, if the tooth area of ​​interest is separated from the 3D oral scan data using the margin line (ML), a model in which the interdental area is empty can be created, as shown in Fig. 3b. That is, the tooth area of ​​interest may be a model in which at least a portion of the interdental area between the tooth of interest and the adjacent teeth of the tooth of interest is empty.

[0075] As shown in Fig. 5, the tooth library model may include individual tooth models of all tooth identification numbers. However, the coordinate system of the tooth library model and the coordinate system of the three-dimensional oral scan data may be different from each other. As a result, the positions and orientations of the target teeth of the tooth library model and the teeth of interest separated from the three-dimensional oral scan data may be different from each other. In addition, the two models may also have different scales. In the present embodiment, in order to properly generate the tooth separation model by modifying the shape of the tooth library model to correspond to the shape of the tooth region of interest, it is necessary to match the positions, orientations, and scales of the target teeth of the tooth library model and the teeth of interest separated from the three-dimensional oral scan data.

[0076] The step of aligning the tooth region of interest and the tooth library model (step S600) may further include a step of determining a center point of the tooth of interest and an arrangement direction of the tooth of interest within the tooth region of interest and a step of determining a center point of a target tooth of the tooth library model and an arrangement direction of the target tooth. The tooth region of interest and the tooth library model may be aligned based on the center point of the tooth of interest, the arrangement direction of the tooth of interest, the center point of the target tooth, and the arrangement direction of the target tooth.

[0077] For example, the step of aligning the tooth region of interest and the tooth library model (step S600) may further include a step of iteratively finding an optimal transformation between the first point cloud of the tooth region of interest and the second point cloud of the tooth library model.

[0078] For example, the step of aligning the tooth region of interest and the tooth library model (step S600) may further include the step of converting the tooth region of interest into a first hash value, the step of converting the tooth library model into a second hash value, and the step of determining the similarity between the tooth region of interest and the tooth library model using the first hash value and the second hash value.

[0079] Referring to FIGS. 6A to 6C, a tooth library model corresponding to the tooth identification number of the tooth region of interest separated from the 3D oral scan data can be used. The position and direction of the tooth region of interest separated from the 3D oral scan data can be calculated to align the tooth library model to the tooth region of interest. The tooth region of interest and the tooth library model can be aligned through a process of extracting feature points of different shapes of tooth models, calculating the position and direction of each model using these feature points, and matching them with each other. FIG. 6C and FIG. 7 show the results of aligning the tooth region of interest and the tooth library model.

[0080] As described above, the margin line (ML) of the tooth of interest can be extracted through a first artificial intelligence neural network. The input of the first artificial intelligence neural network may be the three-dimensional oral scan data, and the output of the first artificial intelligence neural network may be the margin line (ML) of the tooth of interest. The first feature point may be extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network. The input of the second artificial intelligence neural network may be the tooth area of ​​interest, and the output of the second artificial intelligence neural network may be the three-dimensional coordinates of the first feature point.

[0081] For example, the step of generating the tooth separation model (step S700) may include the step of obtaining a first skeleton or a first bone of the mesh of the tooth region of interest and the step of obtaining a second skeleton or a second bone of the mesh of the tooth library model. Using the first skeleton and the second skeleton or the first bone and the second bone, the shape of the tooth library model may be deformed to correspond to the shape of the tooth region of interest.

[0082] For example, the step of generating the tooth separation model (step S700) may include a step of blending a mesh of the tooth region of interest and a mesh of the tooth library model.

[0083] For example, the step of generating the tooth separation model (step S700) may include the step of dividing the mesh of the tooth region of interest into a first grid and obtaining points within the first grid, and the step of dividing the mesh of the tooth library model into a second grid and obtaining points within the second grid. Using the points within the first grid and the points within the second grid, the shape of the tooth library model may be deformed to correspond to the shape of the tooth region of interest.

[0084] For example, in the step of generating the tooth separation model (step S700), the shape of the tooth library model can be deformed to correspond to the shape of the tooth region of interest by using the local similarity between the mesh of the tooth region of interest and the mesh of the tooth library model.

[0085] Figure 7 shows the result of transforming the tooth library model into a shape similar to the tooth region of interest separated from the 3D oral scan data.

[0086] FIG. 8 illustrates that tooth separation models are formed for all teeth in the 3D oral scan data by repeatedly performing steps S100 to S700 for each tooth separated from the 3D oral scan data.

[0087] According to the present embodiment, the tooth region of interest of the three-dimensional oral scan data and the tooth library model are aligned, and the tooth library model is deformed to correspond to the tooth region of interest, thereby preserving lost tooth region information between teeth.

[0088] According to the method for separating teeth from 3D oral scan data using a dental library model according to the present invention, each individual tooth model of a patient can be separated from the patient's tooth model generated through a single scan. Due to the scanner's precision, the interdental space between individual teeth, which cannot be identified in 3D oral scan data, can be predicted, and individual teeth can be moved, enabling easy and rapid treatment planning for the patient. This reduces the workload of dentists or dental technicians, increases work efficiency, and facilitates the provision of high-quality medical services.

[0089] FIG. 9 is a flowchart illustrating a method for separating teeth from three-dimensional oral scan data using a tooth library model according to one embodiment of the present invention.

[0090] The method for separating teeth from 3D oral scan data using a tooth library model according to the present embodiment is substantially the same as the method for separating teeth from 3D oral scan data using a tooth library model of FIGS. 1 to 8, except that it further includes a step of obtaining a tooth identification number of a tooth of interest. Therefore, the same reference numbers are used for identical or similar components, and redundant descriptions are omitted.

[0091] Referring to FIG. 9, a method for separating teeth from 3D oral scan data using a tooth library model includes a step of receiving 3D oral scan data (step S100), a step of extracting a tooth identification number of a tooth of interest and a margin line of the tooth of interest from the 3D oral scan data (step S200A), a step of separating a tooth region of interest from the 3D oral scan data based on the margin line (step S300), a step of obtaining a tooth library model corresponding to the tooth identification number of the tooth of interest (step S500), a step of aligning the tooth region of interest and the tooth library model (step S600), and a step of generating a tooth separation model by deforming a shape of the tooth library model to correspond to a shape of the tooth region of interest (step S700).

[0092] The method for separating teeth from 3D oral scan data using the above-described tooth library model may further include a step of extracting a first feature point of the tooth region of interest (step S400) and a step of acquiring a second feature point of the tooth library model. The tooth region of interest and the tooth library model may be aligned based on the first feature point and the second feature point.

[0093] For example, the margin line of the tooth of interest may be extracted through a first artificial intelligence neural network. An input of the first artificial intelligence neural network may be the three-dimensional oral scan data, and an output of the first artificial intelligence neural network may be the margin line (ML) of the tooth of interest. The first feature point may be extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network. An input of the second artificial intelligence neural network may be the tooth region of interest, and an output of the second artificial intelligence neural network may be the three-dimensional coordinates of the first feature point. The tooth identification number of the tooth of interest may be obtained through a third artificial intelligence neural network. An input of the third artificial intelligence neural network may be the three-dimensional oral scan data, and an output of the third artificial intelligence neural network may be the tooth identification number of the tooth of interest.

[0094] According to the present embodiment, the tooth region of interest of the three-dimensional oral scan data and the tooth library model are aligned, and the tooth library model is deformed to correspond to the tooth region of interest, thereby preserving lost tooth region information between teeth.

[0095] According to the method for separating teeth from 3D oral scan data using a dental library model according to the present invention, each individual tooth model of a patient can be separated from the patient's tooth model generated through a single scan. Due to the scanner's precision, the interdental space between individual teeth, which cannot be identified in 3D oral scan data, can be predicted, and individual teeth can be moved, enabling easy and rapid treatment planning for the patient. This reduces the workload of dentists or dental technicians, increases work efficiency, and facilitates the provision of high-quality medical services.

[0096] FIG. 10 is a flowchart illustrating a method for separating teeth from three-dimensional oral scan data using a tooth library model according to one embodiment of the present invention.

[0097] The method for separating teeth from 3D oral scan data using a tooth library model according to the present embodiment is substantially the same as the method for separating teeth from 3D oral scan data using a tooth library model of FIGS. 1 to 8, except that it further includes a step of extracting a second feature point of the tooth library model. Therefore, the same reference numbers are used for the same or similar components, and redundant descriptions are omitted.

[0098] Referring to FIG. 10, a method for separating teeth from 3D oral scan data using a tooth library model includes a step of receiving 3D oral scan data (step S100), a step of extracting a margin line of a tooth of interest from the 3D oral scan data (step S200), a step of separating a tooth region of interest from the 3D oral scan data based on the margin line (step S300), a step of obtaining a tooth library model corresponding to a tooth identification number of the tooth of interest (step S500), a step of aligning the tooth region of interest and the tooth library model (step S600), and a step of generating a tooth separation model by deforming a shape of the tooth library model to correspond to a shape of the tooth region of interest (step S700).

[0099] The method for separating teeth from 3D oral scan data using the above tooth library model may further include a step of extracting a first feature point of the tooth region of interest (step S400) and a step of extracting a second feature point of the tooth library model corresponding to the tooth identification number of the tooth of interest (step S550). The tooth region of interest and the tooth library model may be aligned based on the first feature point and the second feature point.

[0100] In this embodiment, information about the second feature point of the tooth library model is not included in the tooth library model and can be extracted separately.

[0101] The second feature point of the above tooth library model can be extracted through an artificial intelligence neural network, or can be extracted through a mesh algorithm.

[0102] For example, the second feature point of the tooth library model may be extracted through an artificial intelligence neural network different from the first feature point of the tooth region of interest.

[0103] Specifically, the margin line (ML) of the tooth of interest may be extracted through a first artificial intelligence neural network. An input of the first artificial intelligence neural network may be the three-dimensional oral scan data, and an output of the first artificial intelligence neural network may be the margin line (ML) of the tooth of interest. The first feature point may be extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network, and the second feature point may be extracted through a fourth artificial intelligence neural network different from the first artificial intelligence neural network and the second artificial intelligence neural network. An input of the second artificial intelligence neural network may be the tooth region of interest, and an output of the second artificial intelligence neural network may be the three-dimensional coordinates of the first feature point. An input of the fourth artificial intelligence neural network may be the tooth library model corresponding to the tooth identification number of the tooth of interest, and an output of the fourth artificial intelligence neural network may be the three-dimensional coordinates of the second feature point.

[0104] For example, the second feature point of the tooth library model can be extracted through the same artificial intelligence neural network as the first feature point of the tooth region of interest.

[0105] Specifically, the margin line (ML) of the tooth of interest may be extracted through a first artificial intelligence neural network. An input of the first artificial intelligence neural network may be the three-dimensional oral scan data, and an output of the first artificial intelligence neural network may be the margin line (ML) of the tooth of interest. A method for segmenting teeth from three-dimensional oral scan data using the tooth library model may further include a step of extracting a first feature point of the tooth area of ​​interest and a step of extracting a second feature point of the tooth library model corresponding to the tooth identification number of the tooth of interest. The first feature point and the second feature point may be extracted through a second artificial intelligence neural network that is different from the first artificial intelligence neural network. A first input of the second artificial intelligence neural network may be the tooth area of ​​interest, and a first output of the second artificial intelligence neural network may be a three-dimensional coordinate of the first feature point. The second input of the second artificial intelligence neural network may be the tooth library model corresponding to the tooth identification number of the tooth of interest, and the second output of the second artificial intelligence neural network may be the three-dimensional coordinates of the second feature point.

[0106] According to the present embodiment, the tooth region of interest of the three-dimensional oral scan data and the tooth library model are aligned, and the tooth library model is deformed to correspond to the tooth region of interest, thereby preserving lost tooth region information between teeth.

[0107] According to the method for separating teeth from 3D oral scan data using a dental library model according to the present invention, each individual tooth model of a patient can be separated from the patient's tooth model generated through a single scan. Due to the scanner's precision, the interdental space between individual teeth, which cannot be identified in 3D oral scan data, can be predicted, and individual teeth can be moved, enabling easy and rapid treatment planning for the patient. This reduces the workload of dentists or dental technicians, increases work efficiency, and facilitates the provision of high-quality medical services.

[0108] According to one embodiment of the present invention, a computer-readable recording medium having recorded thereon a program for executing a method for separating teeth from three-dimensional oral scan data using a dental library model according to the above embodiments on a computer may be provided. The above-described method can be written as a program that can be executed on a computer, and can be implemented on a general-purpose digital computer that executes the program using the computer-readable medium. In addition, the structure of data used in the above-described method can be recorded on a computer-readable medium through various means. The computer-readable medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the medium may be those specially designed and configured for the present invention, or may be known and usable by those skilled in the art in the field of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specially configured to store and execute program commands such as ROMs, RAMs, and flash memories. Examples of program instructions include not only machine language codes, such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention.

[0109] Additionally, the method for separating teeth from three-dimensional oral scan data using the aforementioned tooth library model can also be implemented in the form of a computer program or application executed by a computer and stored in a recording medium.

[0110] The present invention relates to a method for separating teeth from 3D oral scan data using a dental library model, and to a computer-readable recording medium storing a program for executing the method on a computer. The method can preserve tooth area information that would otherwise be lost between teeth when separating teeth from 3D oral scan data. This method can reduce the work fatigue of dentists or dental technicians and increase work efficiency, thereby enabling the provision of high-quality medical services.

[0111] Although the present invention has been described above with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and changes may be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

Claims

1. A step of extracting a margin line of a tooth of interest from 3D oral scan data; A step of separating a tooth area of ​​interest of the 3D oral scan data based on the margin line; A step of obtaining a tooth library model corresponding to the tooth identification number of the tooth of interest; A step of aligning the tooth region of interest and the tooth library model; and A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that it comprises a step of generating a tooth separation model by deforming the shape of the tooth library model to correspond to the shape of the tooth region of interest.

2. In the first paragraph, a step of extracting a first feature point of the tooth area of ​​interest; and Further comprising a step of obtaining a second feature point of the above tooth library model, A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that the tooth region of interest and the tooth library model are aligned based on the first feature point and the second feature point.

3. In the second paragraph, the number and location of the first characteristic points are determined differently depending on whether the tooth of interest is included in the upper jaw or the lower jaw, and whether the tooth of interest is an incisor, a canine, a premolar, or a molar. The number and location of the second feature points are determined differently depending on whether the target tooth of the tooth library model is included in the maxilla or the mandible, and whether the target tooth of the tooth library model is an incisor, a canine, a premolar, or a molar. A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that when the tooth of interest and the target tooth of the tooth library model are the same teeth, the number of the first feature points is the same as the number of the second feature points.

4. In the second paragraph, the step of aligning the tooth region of interest and the tooth library model A step of determining the center point of the tooth of interest and the arrangement direction of the tooth of interest within the region of the tooth of interest; and Further comprising a step of determining the center point of the target tooth of the above tooth library model and the arrangement direction of the target tooth, A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that the tooth region of interest and the tooth library model are aligned based on the center point of the tooth of interest, the arrangement direction of the tooth of interest, the center point of the target tooth, and the arrangement direction of the target tooth.

5. In the second paragraph, the step of aligning the tooth region of interest and the tooth library model A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that it further includes a step of repeatedly finding an optimal transformation between a first point cloud of the tooth region of interest and a second point cloud of the tooth library model.

6. In the second paragraph, the step of aligning the tooth region of interest and the tooth library model A step of converting the above-mentioned tooth region of interest into a first hash value; A step of converting the above tooth library model into a second hash value; and A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that it further comprises a step of determining the similarity between the tooth region of interest and the tooth library model using the first hash value and the second hash value.

7. In the first paragraph, the margin line of the tooth of interest is extracted through the first artificial intelligence neural network, A method for separating teeth from 3D oral scan data using a tooth library model, wherein the input of the first artificial intelligence neural network is the 3D oral scan data, and the output of the first artificial intelligence neural network is the margin line of the tooth of interest.

8. A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that in the step of extracting the margin line of the tooth of interest in the first paragraph, the margin line is extracted by grouping and segmenting geographical features within the 3D oral scan data.

9. A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that in the step of extracting the margin line of the tooth of interest in the first paragraph, the margin line is extracted using surface curvature information or plane segmentation information within the 3D oral scan data.

10. A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that in the first paragraph, the tooth area of ​​interest is a model in which at least a portion of the interdental area between the tooth of interest and the adjacent teeth of the tooth of interest is empty.

11. In the first paragraph, the step of creating the tooth separation model comprises: A step of obtaining a first skeleton or first bone of the mesh of the above-mentioned tooth region of interest; and comprising a step of obtaining a second skeleton or second bone of the mesh of the above tooth library model, A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that the shape of the tooth library model is deformed to correspond to the shape of the tooth region of interest using the first skeleton and the second skeleton or the first bone and the second bone.

12. In the first paragraph, the step of creating the tooth separation model comprises: A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that it comprises a step of blending a mesh of the tooth region of interest and a mesh of the tooth library model.

13. In the first paragraph, the step of creating the tooth separation model comprises: A step of dividing the mesh of the above-mentioned tooth region of interest into a first grid and obtaining points within the first grid; and A step of dividing the mesh of the above tooth library model into a second grid and obtaining points within the second grid, A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that the shape of the tooth library model is transformed to correspond to the shape of the tooth region of interest using the points in the first grid and the points in the second grid.

14. In the step of generating the tooth separation model in paragraph 1, A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that the shape of the tooth library model is deformed to correspond to the shape of the tooth region of interest by using local similarity between the mesh of the tooth region of interest and the mesh of the tooth library model.

15. In the first paragraph, the margin line of the tooth of interest is extracted through the first artificial intelligence neural network, The input of the first artificial intelligence neural network is the 3D oral scan data, and the output of the first artificial intelligence neural network is the margin line of the tooth of interest. Further comprising a step of extracting a first feature point of the tooth area of ​​interest, The above first feature point is extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network, A method for separating teeth from 3D oral scan data using a tooth library model, wherein the input of the second artificial intelligence neural network is the tooth region of interest, and the output of the second artificial intelligence neural network is the 3D coordinates of the first feature point.

16. A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that the method further comprises a step of obtaining the tooth identification number of the tooth of interest in the first paragraph.

17. In the 16th paragraph, the margin line of the tooth of interest is extracted through the first artificial intelligence neural network, The input of the first artificial intelligence neural network is the 3D oral scan data, and the output of the first artificial intelligence neural network is the margin line of the tooth of interest. Further comprising a step of extracting a first feature point of the tooth area of ​​interest, The above first feature point is extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network, The input of the second artificial intelligence neural network is the tooth region of interest, and the output of the second artificial intelligence neural network is the 3D coordinates of the first feature point. The tooth identification number of the tooth of interest is obtained through the third artificial intelligence neural network, A method for separating teeth from 3D oral scan data using a tooth library model, wherein the input of the third artificial intelligence neural network is the 3D oral scan data, and the output of the third artificial intelligence neural network is the tooth identification number of the tooth of interest.

18. In the first paragraph, the margin line of the tooth of interest is extracted through the first artificial intelligence neural network, The input of the first artificial intelligence neural network is the 3D oral scan data, and the output of the first artificial intelligence neural network is the margin line of the tooth of interest. Further comprising a step of extracting a first feature point of the tooth area of ​​interest and a step of extracting a second feature point of the tooth library model corresponding to the tooth identification number of the tooth of interest, The first feature point is extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network, and the second feature point is extracted through a fourth artificial intelligence neural network different from the first artificial intelligence neural network and the second artificial intelligence neural network. The input of the second artificial intelligence neural network is the tooth region of interest, and the output of the second artificial intelligence neural network is the 3D coordinates of the first feature point. A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that the input of the fourth artificial intelligence neural network is the tooth library model corresponding to the tooth identification number of the tooth of interest, and the output of the fourth artificial intelligence neural network is the 3D coordinates of the second feature point.

19. In the first paragraph, the margin line of the tooth of interest is extracted through the first artificial intelligence neural network, The input of the first artificial intelligence neural network is the 3D oral scan data, and the output of the first artificial intelligence neural network is the margin line of the tooth of interest. Further comprising a step of extracting a first feature point of the tooth area of ​​interest and a step of extracting a second feature point of the tooth library model corresponding to the tooth identification number of the tooth of interest, The above first feature point and the above second feature point are extracted through a second artificial intelligence neural network different from the first artificial intelligence neural network, The first input of the second artificial intelligence neural network is the tooth region of interest, and the first output of the second artificial intelligence neural network is the three-dimensional coordinates of the first feature point. A method for separating teeth from 3D oral scan data using a tooth library model, characterized in that the second input of the second artificial intelligence neural network is the tooth library model corresponding to the tooth identification number of the tooth of interest, and the second output of the second artificial intelligence neural network is the 3D coordinates of the second feature point.

20. A computer-readable recording medium having recorded thereon a program for executing the method of any one of claims 1 to 19 on a computer.

Images