Method for automatically generating a prosthesis from 3D scan data, and computer-readable recording medium having recorded thereon a program for executing the method on a computer

Abstract

To provide a method of automatically generating a prosthesis from three-dimensional scan data and a computer-readable recording medium recording a program for causing a computer to perform the same.SOLUTION: A method of automatically generating a prosthesis from three-dimensional scan data includes the following steps of: automatically extracting from the three-dimensional scan data teeth information on each tooth included in the three-dimensional scan data; automatically extracting a margin line with respect to a prepared tooth; generating a plurality of two-dimensional images having the prepared tooth and an adjacent tooth adjacent to the prepared tooth; automatically generating three-dimensional temporary prosthesis data on the basis of the plurality of two-dimensional images; and deforming a single tooth model corresponding to the prepared tooth by using the margin line and the three-dimensional temporary prosthesis data, and generating three-dimensional prosthesis data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a method for automatically generating a prosthesis from 3D scan data and a computer-readable recording medium having a program recorded thereon for executing the method on a computer. More particularly, the present invention relates to a method for automatically generating a prosthesis from 3D scan data, which can shorten the time and process for manufacturing the prosthesis and improve its quality, and a computer-readable recording medium having a program recorded thereon for executing the method on a computer. [Background technology]

[0002] 3D oral scan data refers to data obtained by scanning teeth and the oral cavity, or a replica or reconstruction of the same, using a 3D scanner. Dental treatments such as prosthetic treatments (inlays, onlays, crowns, etc.), implants, and orthodontics require the acquisition of a patient's oral data, which is used for prosthetic or implant design, or for the manufacture of orthodontic devices.

[0003] Conventionally, prosthetics have mainly been created manually after directly imitating the oral cavity using alginate or other materials. To create an anatomically correct prosthesis, a dentist or dental technician must first determine the degree of wear on the surrounding teeth, and then comprehensively understand the tooth number and occlusion information of the opposing teeth before creating the prosthesis. Conventional prosthetic creation methods require manual adjustments based on this information, typically based on the shape of a tooth, to suit the oral condition of each patient.

[0004] Furthermore, since the conventional prosthetic manufacturing process is performed manually, there are problems such as increased work fatigue for the medical doctor or dental technician, reduced accuracy of the resulting product, and reduced productivity. There are also problems such as large variations in the quality of the prosthetic and the required time depending on the skill level of the worker. Summary of the Invention [Problem to be solved by the invention]

[0005] An object of the present invention is to provide a method for automatically generating a prosthesis from 3D scan data, which can reduce the time and process of manufacturing the prosthesis and improve its quality.

[0006] Another object of the present invention is to provide a computer-readable recording medium having recorded thereon a program for causing a computer to execute the method for automatically generating a prosthesis from 3D scan data. [Means for solving the problem]

[0007] According to one embodiment of the present invention, there is provided a method for automatically generating a prosthesis from 3D scan data, the method comprising the steps of: automatically extracting tooth information for each tooth contained in the 3D scan data from the 3D scan data; automatically extracting a margin line for each prepared tooth; generating a plurality of two-dimensional images having the prepared tooth and adjacent teeth adjacent to the prepared tooth; automatically generating three-dimensional temporary prosthesis data based on the plurality of two-dimensional images; and automatically generating three-dimensional temporary prosthesis data by deforming a single-tooth model corresponding to the prepared tooth using the margin line and the three-dimensional temporary prosthesis data.

[0008] The tooth information includes the tooth number, whether the tooth has been prepared, the position of the tooth, and the direction of the tooth.

[0009] The step of automatically extracting the tooth information includes the steps of pre-processing the 3D scan data into a model input, inputting the model input into a backbone network to obtain a feature map, and extracting the tooth information from the feature map.

[0010] To train the backbone network, a regression loss is used for the tooth position and the tooth orientation, and a classification loss is used for the tooth number.

[0011] The step of automatically extracting the margin line includes the steps of extracting partial scan data corresponding to the prepared tooth from the 3D scan data, mapping the partial scan data into a predetermined two-dimensional space using a transformation matrix, determining a curvature value from the data mapped in the two-dimensional space to obtain a two-dimensional margin line, and converting the two-dimensional margin line into a three-dimensional margin line using an inverse matrix of the transformation matrix.

[0012] The plurality of two-dimensional images includes a first two-dimensional image having the prepared tooth and a first adjacent tooth to the prepared tooth, and a second two-dimensional image having the prepared tooth and a second adjacent tooth to the prepared tooth.

[0013] The center of the first two-dimensional image and the center of the second two-dimensional image are the same, and the projection direction of the first two-dimensional image is different from the projection direction of the second two-dimensional image.

[0014] The center of the first two-dimensional image and the center of the second two-dimensional image are the centers of the prepared teeth.

[0015] The step of automatically generating the three-dimensional temporary prosthesis data uses a cGAN (conditional generative adversarial network).

[0016] The cGAN includes an encoder that receives the plurality of 2D images, camera position information, and camera direction information, a latent vector connected to the encoder, and a decoder connected to the latent vector, and the decoder outputs the 3D temporary prosthesis data.

[0017] The step of generating the three-dimensional prosthesis data includes aligning the template model to the position of the prepared tooth, and deforming the single-tooth model using the margin line as a first constraint and the three-dimensional temporary prosthesis data as a second constraint.

[0018] Let L be the Laplacian matrix of the template model, Ppos be the point set of the three-dimensional temporary prosthesis data, Pmargin be the point set of the margin line, Cpred be the constraint to be close to Ppos, Cmargin be the constraint not to exceed Pmargin, and xopt be the vertex position of the three-dimensional prosthesis data. JPEG0007774884000001.jpg19170 Meet the following.

[0019] Furthermore, the method for automatically generating a prosthesis from the 3D scan data includes, before the step of automatically extracting tooth information, a step of aligning the 3D scan data to the origin of a predetermined coordinate system in the direction of the predetermined coordinate system.

[0020] The step of automatically extracting tooth information is performed by a first artificial intelligence neural network, the step of automatically extracting margin lines is performed by a second artificial intelligence neural network, and the step of automatically generating three-dimensional temporary prosthesis data is performed by a third artificial intelligence neural network.

[0021] A method for automatically generating a prosthesis from 3D scan data according to one embodiment for achieving the above-mentioned object of the present invention includes the steps of automatically extracting tooth information of each tooth included in the 3D scan data from the 3D scan data, determining whether or not a prepared tooth exists based on the tooth information, automatically extracting a margin line for the prepared tooth if the prepared tooth exists, generating a plurality of two-dimensional images including the prepared tooth and adjacent teeth adjacent to the prepared tooth if the prepared tooth exists, automatically generating three-dimensional temporary prosthesis data based on the plurality of two-dimensional images, and automatically generating three-dimensional temporary prosthesis data by deforming a single tooth model corresponding to the prepared tooth using the margin line and the three-dimensional temporary prosthesis data.

[0022] In one embodiment of the present invention, a program for causing a computer to execute the method for automatically generating a prosthesis from 3D scan data is recorded on a computer-readable recording medium. [Effects of the Invention]

[0023] In the method for automatically generating a prosthesis from 3D scan data according to the present invention, tooth information is automatically extracted from the 3D scan data, margin lines are automatically extracted from partial scan data of the prepared tooth, 3D temporary prosthesis data is automatically generated based on multiple 2D images of the prepared tooth and adjacent teeth, and a single tooth model is automatically deformed based on the boundary point information and margin lines of the 3D temporary prosthesis data, thereby automatically generating 3D prosthesis data.

[0024] In this way, by automatically generating a prosthesis from the 3D scan data, the time and process for manufacturing the prosthesis can be shortened, and the quality of the prosthesis can be improved.

[0025] In particular, at least one of the steps of automatically extracting tooth information from the 3D scan data, automatically extracting margin lines from the partial scan data of the prepared teeth, and automatically generating 3D temporary prosthesis data is performed using an artificial intelligence neural network, which can shorten the time and process of manufacturing the prosthesis and improve the quality of the prosthesis. [Brief explanation of the drawings]

[0026] [Figure 1] FIG. 1 is a flow chart illustrating a method for automatically generating a prosthesis from 3D scan data according to one embodiment of the present invention. [Figure 2] FIG. 2 is a diagram illustrating the steps for automatically aligning the 3D scan data of FIG. [Figure 3] FIG. 3 is a diagram showing the steps of automatically extracting tooth information in FIG. [Figure 4] FIG. 4 is a flow chart showing the steps for automatically extracting tooth information in FIG. [Figure 5] FIG. 5 is a diagram showing the steps for automatically extracting the margin lines in FIG. [Figure 6] FIG. 6 is a diagram illustrating the steps for generating the multiple two-dimensional images of FIG. [Figure 7] FIG. 7 is a diagram showing the steps of automatically generating the three-dimensional temporary prosthesis data of FIG. [Figure 8] FIG. 8 is a diagram showing steps for automatically generating the three-dimensional prosthetic data of FIG. [Figure 9] FIG. 9 is a flow chart illustrating a method for automatically generating a prosthesis from 3D scan data according to one embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0027] Specific structural or functional descriptions of the embodiments of the present invention set forth herein are merely exemplary for purposes of describing the embodiments of the present invention, and the example embodiments of the present invention may be embodied in various forms and should not be construed as being limited to the embodiments set forth herein.

[0028] The present invention can be modified in various ways and can have various forms, and specific embodiments have been shown by way of example in the drawings and will be described in detail herein, but it should be understood that this is not to limit the invention to the particular forms disclosed, but rather to include all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

[0029] Terms such as "first" and "second" are used to describe various components, but the components should not be limited by these terms. These terms are used only to distinguish one component from another. For example, a first component can be referred to as a second component, and similarly, a second component can be referred to as a first component, without departing from the scope of the present invention.

[0030] When a component is said to be "coupled" or "connected" to another component, it should be understood that the component may be directly coupled or connected to the other component, but there may also be other components in between. On the other hand, when a component is said to be "directly coupled" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions describing the relationship between components, such as "between" and "immediately between," or "adjacent to" and "directly adjacent to," should be interpreted similarly.

[0031] The terms used in this application are merely used to describe specific embodiments and are not intended to limit the present invention. The singular expressions include the plural expressions unless the context clearly dictates otherwise. In this application, the terms "comprise" or "have" are intended to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and should be understood not to preclude the presence or possibility of addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0032] Unless otherwise defined, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Terms as defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning they have in the context of the relevant art, and should not be interpreted as having an idealized or overly formal meaning unless expressly defined in this application.

[0033] However, when an embodiment can be implemented differently, the functions or operations specified in a particular block may occur differently from the sequence specified in the flowchart. For example, two consecutive blocks may actually occur substantially simultaneously, or the blocks may be reversed depending on the functions or operations involved.

[0034] Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings. The same reference numerals are used to designate the same components in the drawings, and redundant description of the same components will be omitted.

[0035] FIG. 1 is a flow chart illustrating a method for automatically generating a prosthesis from 3D scan data according to one embodiment of the present invention.

[0036] As shown in FIG. 1 , the method for automatically generating a prosthesis from 3D scan data according to this embodiment includes the steps of: automatically extracting tooth information for each tooth included in the 3D scan data from the 3D scan data (Step S200); automatically extracting a margin line for each prepared tooth (Step S300); generating a plurality of 2D images including the prepared tooth and adjacent teeth adjacent to the prepared tooth (Step S400); automatically generating 3D temporary prosthesis data based on the plurality of 2D images (Step S500); and automatically generating 3D temporary prosthesis data by deforming a single tooth model corresponding to the prepared tooth using the margin line and the 3D temporary prosthesis data (Step S600).

[0037] The method for automatically generating a prosthesis from the 3D scan data further includes, before the step of automatically extracting tooth information, a step of aligning the 3D scan data to the origin of a predetermined coordinate system and in the direction of the predetermined coordinate system (step S100).

[0038] Here, the 3D scan data refers to data obtained by scanning teeth and an oral cavity, or an object that is modeled or reconstructed therefrom, using a 3D scanner. For example, the 3D scan data is mesh data including 3D points (vertices) and triangles or rectangles generated by connecting the points. The file extension of the 3D scan data is not limited, and may be, for example, one of ply, obj, or stl.

[0039] Here, the prepared tooth means a tooth prepared for a crown, or a tooth with a portion of the tooth ground away.

[0040] FIG. 2 is a diagram showing the step of automatically aligning the 3D scan data (step S100) of FIG.

[0041] 1 and 2, in the step of aligning the 3D scan data (step S100), PCA is used to obtain a normalization matrix that normalizes the position and orientation of the 3D scan data. Multiplying each point of the 3D scan data by the normalization matrix aligns the 3D scan data to a predetermined coordinate and a predetermined orientation.

[0042] The state in which the various 3D scan data are aligned with the predetermined coordinates and the predetermined direction is shown in FIG.

[0043] When the 3D scan data is aligned in a specific position and in a specific direction, the accuracy of the method for automatically generating a prosthesis from the 3D scan data can be further improved.

[0044] Fig. 3 is a diagram showing the step of automatically extracting tooth information (step S200) in Fig. 1. Fig. 4 is a flowchart showing the step of automatically extracting tooth information (step S200) in Fig. 1.

[0045] 1 to 4, the tooth information includes the tooth number (dental formula), whether the tooth is a prepared tooth, the tooth position, and the tooth direction. Here, the tooth position means the key position of the tooth. Here, the tooth direction means the front-back direction of the tooth, the up-down direction of the tooth, and the left-right direction of the tooth.

[0046] Let N be the number of teeth in the 3D scan data, the state of the teeth (number and whether or not the tooth has been prepared) be class, the position of the teeth be pos, and the direction of the teeth be orient. JPEG0007774884000002.jpg27170 It is expressed as follows.

[0047] In FIG. 3, x_world, y_world, and z_world represent directions of a predetermined coordinate system, and x_local, y_local, and z_local represent the front-to-back direction of a particular tooth, the up-down direction of the particular tooth, and the left-to-right direction of the particular tooth.

[0048] For example, the step of automatically extracting the tooth information (step S200) includes the steps of preprocessing the 3D scan data with a model input, inputting the model input into a backbone network to obtain a feature map, and extracting the tooth information from the feature map.

[0049] The preprocessing step can convert the 3D scan data into a form that can be input to the backbone network. For example, the model input can be a point cloud, a depth map, a parameterized mesh, a mesh with a fixed topology, etc. For example, the model input can be 2D image data. Alternatively, the model input can be 3D image data.

[0050] In FIG. 4, the tooth condition information is described as Box Classification, the tooth position information is described as Box Regression, and the tooth direction information is described as Axis Regression.

[0051] For training the backbone network, a regression loss is used for the tooth position and the tooth orientation, and a classification loss is used for the tooth number.

[0052] FIG. 5 is a diagram showing the step (step S300) of automatically extracting the margin lines in FIG.

[0053] 1 to 5, the step of automatically extracting the margin line (step S300) includes the steps of extracting partial scan data corresponding to the prepared tooth from the 3D scan data, mapping the partial scan data into a predetermined 2D space using a transformation matrix (T), determining a curvature value from the data mapped into the 2D space to obtain a 2D margin line (F), and converting the 2D margin line into a 3D margin line using an inverse matrix (T-1) of the transformation matrix.

[0054] For example, the curvature value is one of a maximum curvature value, a minimum curvature value, a Gaussian curvature value, and a mean curvature value.

[0055] The curvature value is relatively constant for the upper surface of the tooth, but varies greatly at the boundary between teeth or at the area where the tooth meets the gums. Therefore, the curvature value can be used to determine the margin line of the tooth.

[0056] Alternatively, the step of automatically extracting the margin line (step S300) can directly find the 3D margin line from the 3D scan data.

[0057] FIG. 6 is a diagram showing the step of generating a plurality of two-dimensional images (step S400) of FIG.

[0058] As shown in FIGS. 1 to 6, the plurality of two-dimensional images (I1, I2, I3) includes the prepared tooth and adjacent teeth adjacent to the prepared tooth.

[0059] For example, the plurality of two-dimensional images includes a first two-dimensional image (e.g., I1) including the prepared tooth and a first adjacent tooth to the prepared tooth, and a second two-dimensional image (e.g., I3) including the prepared tooth and a second adjacent tooth to the prepared tooth.

[0060] For example, the center of the first two-dimensional image (e.g., I1) and the center of the second two-dimensional image (e.g., I3) are identical to each other, and the projection direction of the first two-dimensional image (e.g., I1) is different from the projection direction of the second two-dimensional image (e.g., I3). For example, the center of the first two-dimensional image and the center of the second two-dimensional image are the centers of the prepared teeth.

[0061] Although three two-dimensional images are shown in Figure 6, the present invention is not limited to this. The number of two-dimensional images is at least two. The more two-dimensional images there are, the more accurate the three-dimensional temporary prosthesis data will be.

[0062] For example, the plurality of two-dimensional images are image data of the prepared tooth and adjacent teeth of the prepared tooth captured by a camera.

[0063] FIG. 7 is a diagram showing the step (S500) of automatically generating three-dimensional temporary prosthesis data in FIG.

[0064] As shown in FIGS. 1 to 7, three-dimensional temporary prosthesis data can be automatically generated based on the plurality of two-dimensional images (I1, I2, I3).

[0065] For example, the step of automatically generating the 3D temporary prosthesis data uses a conditional generative adversarial network (cGAN). The cGAN includes an encoder that receives the plurality of 2D images, position information of a camera that generated the 2D images, and orientation information of the camera that generated the 2D images, a latent vector connected to the encoder, and a decoder that connects to the latent vector. The decoder outputs the 3D temporary prosthesis data.

[0066] FIG. 8 is a diagram showing the step of automatically generating three-dimensional prosthetic data (step S600) in FIG.

[0067] Referring to FIGS. 1 to 8, the margin line and the three-dimensional temporary prosthesis data can be used to deform a single tooth model corresponding to the prepared tooth to generate three-dimensional prosthesis data.

[0068] Here, the single model is a template model that is pre-designed to some extent for each dental formula (tooth number), and is mesh data generated by an individual such as a dental technician or dentist.

[0069] The template model is a type of sample tooth (standard tooth) used to manufacture prostheses, implants, orthodontics devices, etc., and has a typical tooth shape. The template model has one sample tooth (standard tooth) for each tooth number. The 3D scan data is captured by a scanner, and the mesh has a relatively low degree of perfection. If the mesh has a low degree of perfection, it is unsuitable for manufacturing prostheses, implants, orthodontics devices, etc., by 3D printing. In contrast, the template model is a tooth model with a relatively high degree of perfection in the mesh. Therefore, if the template model is modified to manufacture prostheses, implants, orthodontics devices, etc., it is very suitable for using the 3D printing method.

[0070] For example, the step of generating the three-dimensional prosthesis data (step S600) includes aligning the single tooth model to the position of the prepared tooth, and deforming the single tooth model using the margin line as a first constraint and the three-dimensional temporary prosthesis data as a second constraint.

[0071] Let L be the Laplacian matrix of the single tooth model, Ppos be the point set of the 3D temporary prosthesis data, Pmargin be the point set of the margin line, Cpred be the constraint to be close to Ppos, Cmargin be the constraint not to exceed Pmargin, and xopt be the vertex position of the 3D prosthesis data. JPEG0007774884000003.jpg20170 can be satisfied.

[0072] By solving the linear equation using the least squares method, xopt, which means the position of the vertices of the 3D prosthesis data, can be obtained. In other words, by using the constraints, the 3D prosthesis data will be a prosthesis that does not cross the margin line, taking into account the opposing and adjacent teeth, and can be applied clinically.

[0073] The margin line information generated in step S300 corresponds to the margin line of the final prosthesis data, and the 3D temporary prosthesis data generated in step S500 corresponds to the shape of the upper teeth of the final prosthesis data.

[0074] The method of automatically generating a prosthesis from three-dimensional scan data in this embodiment is performed by a computer device.

[0075] For example, the step of automatically extracting tooth information (step S200) is performed by a first artificial intelligence neural network, the step of automatically extracting margin lines (step S300) is performed by a second artificial intelligence neural network, and the step of automatically generating three-dimensional temporary prosthesis data (step S500) is performed by a third artificial intelligence neural network.

[0076] That is, the present invention uses at least three different artificial intelligence neural networks to automate each step, thereby greatly improving the speed and accuracy of the work.

[0077] According to this embodiment, tooth information is automatically extracted from the 3D scan data, margin lines are automatically extracted from the partial scan data of the prepared tooth, 3D temporary prosthesis data is automatically generated based on multiple 2D images of the prepared tooth and adjacent teeth, and a single tooth model is automatically deformed based on the boundary point information and the margin lines of the 3D temporary prosthesis data, thereby automatically generating 3D prosthesis data.

[0078] In this way, the prosthesis is automatically generated from the 3D scan data, which can shorten the time and process for manufacturing the prosthesis and improve the quality of the prosthesis.

[0079] In particular, at least one of the steps of automatically extracting tooth information from the 3D scan data, automatically extracting margin lines from the partial scan data of the prepared teeth, and automatically generating 3D temporary prosthesis data is performed using an artificial intelligence neural network, thereby reducing the time and process required to manufacture the prosthesis and improving the quality of the prosthesis.

[0080] FIG. 9 is a flow chart illustrating a method for automatically generating a prosthesis from 3D scan data according to one embodiment of the present invention.

[0081] The method for automatically generating a prosthesis from 3D scan data according to this embodiment is similar to the method for automatically generating a prosthesis from 3D scan data shown in Figures 1 to 8, except that it further includes a step of determining whether prepared teeth exist. Therefore, the same or similar components are designated by the same reference numerals, and redundant explanations will be omitted.

[0082] As shown in FIG. 9, the three-dimensional scan data is aligned to the origin of a predetermined coordinate system in the direction of the predetermined coordinate system (step S100).

[0083] From the three-dimensional scan data, tooth information of each tooth included in the three-dimensional scan data is automatically extracted (step S200).

[0084] It is determined whether or not prepared teeth exist in the 3D scan data (step S250). If prepared teeth do not exist, there is no need to generate a prosthesis, and the procedure ends.

[0085] If the prepared tooth exists, a margin line is automatically extracted for the prepared tooth (step S300).

[0086] Furthermore, if the prepared tooth exists, a plurality of two-dimensional images including the prepared tooth and adjacent teeth adjacent to the prepared tooth are generated (step S400).

[0087] Based on the plurality of two-dimensional images, three-dimensional temporary prosthesis data is automatically generated (step S500).

[0088] The three-dimensional temporary prosthesis data is used to deform a single tooth model corresponding to the prepared tooth to generate three-dimensional prosthesis data (step S600).

[0089] FIG. 9 illustrates an example in which there is one prepared tooth. If there is more than one prepared tooth, steps S300 to S600 can be repeated until there are no more prepared teeth.

[0090] According to this embodiment, tooth information is automatically extracted from the 3D scan data, margin lines are automatically extracted from the partial scan data of the prepared tooth, 3D temporary prosthesis data is automatically generated based on multiple 2D images of the prepared tooth and adjacent teeth, and a single tooth model is automatically deformed based on the boundary point information and the margin lines of the 3D temporary prosthesis data, thereby automatically generating 3D prosthesis data.

[0091] In this way, the prosthesis is automatically generated from the 3D scan data, which can shorten the time and process for manufacturing the prosthesis and improve the quality of the prosthesis.

[0092] In particular, at least one of the steps of automatically extracting tooth information from the 3D scan data, automatically extracting margin lines from the partial scan data of the prepared teeth, and automatically generating 3D temporary prosthesis data is performed using an artificial intelligence neural network, which can shorten the time and process of manufacturing the prosthesis and improve the quality of the prosthesis.

[0093] According to one embodiment of the present invention, a computer-readable recording medium is provided that stores a program for executing a method for automatically generating a prosthesis from 3D scan data according to the embodiment. The method can be implemented by a computer-executable program and by a general-purpose digital computer that runs the program using the computer-readable medium. Furthermore, data structures used in the method can be stored on the computer-readable medium through multiple means. The computer-readable medium can include program instructions, data files, data structures, and the like, alone or in combination. The program instructions stored on the medium can be those specifically designed and constructed for the present invention, or those well known and available to those of ordinary skill in the computer software field. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as protocol disks, and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Program instructions include not only machine language code, such as that produced by a compiler, but also high-level language code, which can be executed by a computer using an interpreter, for example. The aforementioned hardware devices are configured to operate as one or more software modules to perform the operations of the present invention.

[0094] The method for automatically generating a prosthesis from 3D scan data described above can also be implemented in the form of a computer program or application that is stored on a recording medium and executed by a computer. [Industrial Applicability]

[0095] The present invention relates to a method for automatically generating a prosthesis from 3D scan data, and a computer-readable recording medium having a program recorded thereon for executing the method on a computer, which can reduce the effort required for producing a prosthesis and improve the accuracy and productivity of the prosthesis.

[0096] Although the present invention has been described above with reference to preferred embodiments, those skilled in the art will appreciate that various modifications and variations of the present invention may be made without departing from the spirit and scope of the present invention as set forth in the following claims.

Claims

1. automatically extracting tooth information for each tooth from the 3D scan data for all teeth included in the 3D scan data, the tooth information including the tooth number, whether the tooth is a prepared tooth, the tooth position, and the tooth orientation; automatically extracting a margin line from the three-dimensional scan data for a prepared tooth, which is a tooth that has been partially removed; generating a plurality of two-dimensional images having the prepared tooth and adjacent teeth adjacent to the prepared tooth, each of the two-dimensional images having a different projection direction; automatically generating three-dimensional temporary prosthesis data corresponding to the upper tooth shape of the final prosthesis data based on the plurality of two-dimensional images; generating three-dimensional prosthesis data as the final prosthesis data by transforming a single-tooth model, which is a template model corresponding to the prepared tooth number among template models previously generated for each tooth number, using the margin line of the prepared tooth and the three-dimensional temporary prosthesis data; Including, The step of automatically extracting tooth information is performed by a first artificial intelligence neural network; converting the 3D scan data into a model input that is a form of data that can be input to a backbone network; inputting the model input to the backbone network and extracting a feature map, which is feature data, from the model input; extracting the tooth information from the feature map, the tooth information including the tooth number and tooth status information including whether the tooth is a prepared tooth, the tooth position information, and the tooth direction information; Including, The step of automatically extracting the margin line is performed by a second artificial intelligence neural network; extracting partial scan data corresponding to the prepared tooth from the three-dimensional scan data; mapping the partial scan data into a predetermined two-dimensional space using a transformation matrix; A step of determining a portion where the curvature value changes significantly from the data mapped in the two-dimensional space to obtain a two-dimensional margin line; transforming the two-dimensional margin line into a three-dimensional margin line using an inverse of the transformation matrix; Including, the margin line generated in the step of automatically extracting the margin line corresponds to the margin line of the final prosthesis data; the step of automatically generating the three-dimensional temporary prosthesis data is performed using a conditional generative adversarial network (cGAN); The plurality of two-dimensional images are a first two-dimensional image having the prepared tooth and a first adjacent tooth to the prepared tooth; a second two-dimensional image having the prepared tooth and a second adjacent tooth to the prepared tooth; Including, a center of the first two-dimensional image and a center of the second two-dimensional image are the same; a projection direction of the first two-dimensional image is different from a projection direction of the second two-dimensional image; the center of the first two-dimensional image and the center of the second two-dimensional image are the centers of the prepared teeth; the cGAN includes an encoder that receives the plurality of 2D images, camera position information, and camera direction information, a latent vector coupled to the encoder, and a decoder that is coupled to the latent vector; the decoder outputs the three-dimensional temporary prosthesis data corresponding to the upper tooth shape of the final prosthesis data; The step of generating three-dimensional prosthesis data includes: aligning the template model to the prepared tooth position; deforming the single tooth model using the margin line as a first constraint and the three-dimensional temporary prosthesis data as a second constraint; Including, Let L be the Laplacian matrix of the template model, Ppos be the point set of the three-dimensional temporary prosthesis data, Pmargin be the point set of the margin line, Cpred be the constraint to be close to Ppos, Cmargin be the constraint not to exceed Pmargin, and xopt be the vertex position of the three-dimensional prosthesis data. characterized in that A method for automatically generating prosthetic data from 3D scan data.

2. For training the backbone network, a regression loss is used for the tooth position and the tooth orientation, and a classification loss is used for the tooth number. The method for automatically generating prosthetic data from three-dimensional scan data according to claim 1.

3. A computer-readable recording medium having a program recorded thereon for causing a computer to execute the method according to claim 1 or 2.

Images