Method for automatically generating prosthesis from three-dimensional scan data, and computer-readable recording medium having recorded thereon program for executing same on computer

Abstract

A method for automatically generating a prosthesis from three-dimensional scan data comprises the steps of: automatically extracting, from three-dimensional scan data, tooth information of each tooth included in the three-dimensional scan data; extracting occlusal surface information of a prepared tooth; extracting region of interest data including the prepared tooth; extracting a margin line of the prepared tooth; and generating three-dimensional prosthesis data on the basis of the occlusal surface information, the region of interest data, and the margin line.

Description

A method for automatically generating a prosthesis from three-dimensional scan data 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 automatically generating a prosthesis from three-dimensional scan data and a computer-readable recording medium having recorded thereon a program for executing the same on a computer, and more particularly, to a method for automatically generating a prosthesis from three-dimensional scan data, which can shorten the time and process for producing a prosthesis and improve its quality, and to a computer-readable recording medium having recorded thereon a program for executing the same on a computer.

[0002] 3D oral scan data refers to data obtained by scanning teeth, the oral cavity, or their replicas or reconstructions using a 3D scanner. Dental treatments such as prosthetic treatments (inlays, onlays, crowns), implants, and orthodontics can utilize patient oral data to design prosthetics or implants, and manufacture orthodontic appliances.

[0003] Traditionally, prosthetics were primarily fabricated by hand, using alginate or other methods to create a direct impression of the oral cavity. To create an anatomically correct prosthesis, dentists or dental technicians must assess the degree of wear on adjacent teeth, as well as a comprehensive understanding of tooth numbers and the occlusion of opposing teeth. Conventional prosthetic fabrication methods, taking this information into account, allow for manual modifications based on a general tooth shape to suit each patient's oral condition.

[0004] Traditionally, the process of creating prosthetics was performed manually, which increased the fatigue of dentists and dental technicians and reduced the accuracy and productivity of the results. Furthermore, the quality of the prosthesis and the time required varied significantly depending on the skill level of the worker.

[0005] The purpose of the present invention is to provide a method for automatically generating a prosthesis from three-dimensional scan data, which can shorten the time and process for manufacturing a 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 executing a method for automatically generating a prosthesis from the three-dimensional scan data.

[0007] In order to achieve the above-described object of the present invention, a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment includes a step of automatically extracting tooth information of each tooth included in the three-dimensional scan data from the three-dimensional scan data, a step of extracting occlusal surface information of a prepared tooth, a step of extracting region of interest data including the prepared tooth, a step of extracting a margin line of the prepared tooth, and a step of generating three-dimensional prosthesis data based on the occlusal surface information, the region of interest data, and the margin line.

[0008] In one embodiment of the present invention, the step of extracting the occlusal surface information may be performed by a second artificial intelligence neural network. The input of the second artificial intelligence neural network may be a two-dimensional image obtained from a direction set to best view the upper surface of the prepared tooth. The output of the second artificial intelligence neural network may be a first three-dimensional point cloud representing the occlusal surface information of the prepared tooth.

[0009] In one embodiment of the present invention, the step of extracting the region of interest data may include the step of extracting partial scan data corresponding to the region of interest including the prepared tooth from the 3D scan data and the step of converting the partial scan data into a second 3D point cloud.

[0010] In one embodiment of the present invention, the step of extracting the margin line may be performed by a third artificial intelligence neural network. The input of the third artificial intelligence neural network may be partial scan data including the prepared tooth. The output of the third artificial intelligence neural network may be a third 3D point cloud representing the margin line of the prepared tooth.

[0011] In one embodiment of the present invention, the step of extracting the margin line may include the step of extracting the partial scan data including the prepared tooth from the three-dimensional scan data, the step of mapping the partial scan data into a predetermined two-dimensional space using a transformation matrix, the step of obtaining a two-dimensional margin line by determining a curvature value from the data mapped into the two-dimensional space, and the step of converting the two-dimensional margin line into a three-dimensional margin line using an inverse matrix of the transformation matrix.

[0012] In one embodiment of the present invention, the step of generating the three-dimensional prosthesis data may be performed by an artificial intelligence generator and may include a step of generating a three-dimensional prosthesis point cloud corresponding to the shape of the prosthesis. The input of the artificial intelligence generator may be a first three-dimensional point cloud representing the occlusal surface information of the prepared tooth, a second three-dimensional point cloud converted from partial scan data extracted corresponding to an area of ​​interest including the prepared tooth from the three-dimensional scan data, and a third three-dimensional point cloud representing the margin line of the prepared tooth. The output of the artificial intelligence generator may be the three-dimensional prosthesis point cloud.

[0013] In one embodiment of the present invention, the step of generating the three-dimensional prosthesis data may further include the step of generating three-dimensional prosthesis mesh data by reconstructing the surface of the three-dimensional prosthesis point cloud.

[0014] In one embodiment of the present invention, the step of generating the three-dimensional prosthesis data may be performed by an artificial intelligence generator, and may include a step of generating a three-dimensional signed distance field corresponding to the shape of the prosthesis. The signed distance field may have a value of 0 for a surface of the prosthesis, a positive value whose absolute value increases as it moves away from the surface of the prosthesis in a first direction, and a negative value whose absolute value increases as it moves away from the surface of the prosthesis in a second direction opposite to the first direction. The input of the artificial intelligence generator may be a first three-dimensional point cloud representing the occlusal surface information of the prepared tooth, a second three-dimensional point cloud obtained by converting partial scan data extracted from the three-dimensional scan data corresponding to a region of interest including the prepared tooth, and a third three-dimensional point cloud representing the margin line of the prepared tooth. The output of the artificial intelligence generator may be the three-dimensional signed distance field.

[0015] In one embodiment of the present invention, the step of generating the three-dimensional prosthesis data may further include the step of converting the three-dimensional signed distance field into mesh data to generate the three-dimensional prosthesis mesh data.

[0016] In one embodiment of the present invention, the step of extracting the occlusal surface information may be performed by a second artificial intelligence neural network. The input of the second artificial intelligence neural network may be a two-dimensional image obtained from a direction set to best view the upper surface of the prepared tooth. The output of the second artificial intelligence neural network may be a first voxel representing the occlusal surface information of the prepared tooth.

[0017] In one embodiment of the present invention, the step of extracting the region of interest data may include the step of extracting partial scan data corresponding to the region of interest including the prepared tooth from the 3D scan data, the step of converting the partial scan data into a second 3D point cloud, and the step of converting the second 3D point cloud into a second voxel.

[0018] In one embodiment of the present invention, the step of extracting the margin line may be performed by a third artificial intelligence neural network. The input of the third artificial intelligence neural network may be partial scan data including the prepared tooth. The output of the third artificial intelligence neural network may be a third 3D point cloud representing the margin line of the prepared tooth. The third 3D point cloud may be converted into a third voxel.

[0019] In one embodiment of the present invention, the step of generating the three-dimensional prosthesis data may be performed by an artificial intelligence generator and may include a step of generating a prosthesis voxel corresponding to the shape of the prosthesis. The input of the artificial intelligence generator may be a first voxel representing the occlusal surface information of the prepared tooth, a second voxel converted from partial scan data extracted from the three-dimensional scan data corresponding to an area of ​​interest including the prepared tooth, and a third voxel representing the margin line of the prepared tooth. The output of the artificial intelligence generator may be the prosthesis voxel.

[0020] In one embodiment of the present invention, the step of generating the three-dimensional prosthesis data may further include the step of flattening the surface of the prosthesis voxel.

[0021] In order to achieve the above object of the present invention, a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment includes a step of automatically extracting tooth information of each tooth included in the three-dimensional scan data from the three-dimensional scan data, a step of performing segmentation of a prepared tooth and adjacent teeth of the prepared tooth, a step of extracting region-of-interest data including the prepared tooth, a step of extracting a margin line of the prepared tooth, and a step of generating three-dimensional prosthesis data based on the segmentation information of the prepared tooth and the adjacent teeth, the region-of-interest data, and the margin line.

[0022] In one embodiment of the present invention, the step of performing segmentation of the prepared tooth and the adjacent teeth may be performed by a second artificial intelligence neural network. The output of the second artificial intelligence neural network may be two-dimensional segmentation information in which the prepared tooth and the adjacent teeth are projected onto a first plane.

[0023] In one embodiment of the present invention, the step of extracting the region of interest data may include the step of extracting partial scan data corresponding to the region of interest including the prepared tooth from the three-dimensional scan data and the step of converting the partial scan data into a two-dimensional depth map on a first plane.

[0024] In one embodiment of the present invention, the step of extracting the margin line may be performed by a third artificial intelligence neural network. The output of the third artificial intelligence neural network may be a two-dimensional margin line that projects the margin line of the prepared tooth onto a first plane.

[0025] In one embodiment of the present invention, the step of generating the three-dimensional prosthesis data may be performed by an artificial intelligence generator and may include a step of generating a three-dimensional neural implicit representation corresponding to the shape of the prosthesis. The input of the artificial intelligence generator may be two-dimensional segmentation information in which the prepared tooth and the adjacent teeth are projected onto a first plane, a two-dimensional depth map on the first plane obtained by converting partial scan data extracted from the three-dimensional scan data corresponding to an area of ​​interest including the prepared tooth, a two-dimensional margin line projecting the margin line of the prepared tooth onto the first plane, and direction information with respect to the first plane. The output of the artificial intelligence generator may be the three-dimensional neural implicit representation.

[0026] In one embodiment of the present invention, the step of generating the three-dimensional prosthesis data may further include the step of converting the three-dimensional neural implicit representation into mesh data to generate the three-dimensional prosthesis mesh data.

[0027] In one embodiment of the present invention, a method for automatically generating a prosthesis from three-dimensional scan data may further include a step of extracting occlusal surface information of the prepared tooth. The step of generating the three-dimensional prosthesis data may generate the three-dimensional prosthesis data based on segmentation information of the prepared tooth and the adjacent teeth, the region of interest data, the margin line, and the occlusal surface information.

[0028] In one embodiment of the present invention, a program for executing a method for automatically generating a prosthesis from the three-dimensional scan data on a computer can be recorded on a computer-readable recording medium.

[0029] According to a method for automatically generating a prosthesis from three-dimensional scan data according to the present invention, tooth information is automatically extracted from the three-dimensional scan data, and three-dimensional prosthesis data can be automatically generated based on the occlusal surface information of the prepared tooth, the region of interest data including the prepared tooth, and the margin line of the prepared tooth.

[0030] Alternatively, three-dimensional prosthesis data can be automatically generated based on segmentation information of the prepared tooth and the adjacent teeth, the region of interest data including the prepared tooth, and the margin line of the prepared tooth.

[0031] In this way, a prosthesis is automatically created from the above 3D scan data, which can shorten the time and process for manufacturing the prosthesis and improve the quality of the prosthesis.

[0032] In particular, at least one of the steps of automatically extracting tooth information from the 3D scan data, the step of extracting the occlusal surface information of the prepared tooth, the step of extracting the margin line of the prepared tooth, and the step of generating the 3D prosthesis data is performed using an artificial intelligence neural network, so that the time and process for manufacturing the prosthesis can be shortened, and the quality of the prosthesis can be improved.

[0033] FIG. 1 is a flowchart illustrating a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment of the present invention.

[0034] Figure 2 is a drawing showing a step of automatically aligning the 3D scan data of Figure 1.

[0035] Figure 3 is a drawing showing a step of automatically extracting tooth information of Figure 1.

[0036] Fig. 4 is a flowchart showing the steps for automatically extracting tooth information of Fig. 1.

[0037] Figure 5 is a drawing showing a step of extracting the margin line of Figure 1.

[0038] FIG. 6 and FIG. 7 are drawings showing a step of generating the first prosthesis data and a step of generating the second prosthesis data of FIG. 1.

[0039] FIGS. 8 and 9 are drawings showing a first step of generating prosthesis data and a second step of generating prosthesis data in a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment of the present invention.

[0040] FIG. 10 and FIG. 11 are drawings showing a first step of generating prosthesis data and a second step of generating prosthesis data in a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment of the present invention.

[0041] FIG. 12 is a flowchart illustrating a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment of the present invention.

[0042] FIG. 13 and FIG. 14 are drawings showing the step of generating the first prosthesis data and the step of generating the second prosthesis data of FIG. 12.

[0043] FIG. 15 is a flowchart illustrating a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment of the present invention.

[0044] 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.

[0045] 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.

[0046] 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."

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] FIG. 1 is a flowchart illustrating a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment of the present invention.

[0053] Referring to FIG. 1, a method for automatically generating a prosthesis from three-dimensional scan data according to the present embodiment includes a step of automatically extracting tooth information of each tooth included in the three-dimensional scan data from the three-dimensional scan data (step S200), a step of extracting occlusal surface information of a prepared tooth (step S300), a step of extracting region of interest data including the prepared tooth (step S400), a step of extracting a margin line of the prepared tooth (step S500), and a step of generating three-dimensional prosthesis data based on the occlusal surface information, the region of interest data, and the margin line (steps S600 and S700).

[0054] The above tooth information may include information about the prepared tooth. The step of extracting occlusal surface information of the prepared tooth (step S300), the step of extracting region of interest data including the prepared tooth (step S400), and the step of extracting the margin line of the prepared tooth (step S500) may be performed by utilizing the results of the step of automatically extracting the tooth information (step S200).

[0055] The step of generating the above 3D prosthesis data (steps S600 and S700) may include a step of generating first prosthesis data based on the occlusal surface information, the region of interest data, and the margin line (step S600) and a step of generating second prosthesis data based on the first prosthesis data (step S700).

[0056] The method for automatically generating a prosthesis from the above 3D scan data may further include, prior to the step of automatically extracting the tooth information, a step (step S100) of aligning the 3D scan data to the origin of the predetermined coordinate system in the direction of the predetermined coordinate system.

[0057] Here, the 3D scan data refers to data obtained by scanning teeth, the oral cavity, or a model or reconstruction thereof using a 3D scanner. For example, the 3D scan data may be mesh data including 3D points (vertexes) and triangular or rectangular faces (rectangles) created by connecting the points. There is no restriction on the file extension of the 3D scan data, and may be, for example, one of ply, obj, and stl.

[0058] Here, the prepared tooth may mean a tooth prepared for a crown, and the prepared tooth may mean a tooth from which a portion of a natural tooth has been shaved.

[0059] The method for automatically generating a prosthesis from three-dimensional scan data of the present embodiment can be performed by a computing device.

[0060] For example, the step of automatically extracting the dental information (step S200) may be performed by a first artificial intelligence neural network. The step of extracting the occlusal surface information (step S300) may be performed by a second artificial intelligence neural network. The step of extracting the margin line (step S500) may be performed by a third artificial intelligence neural network. The step of generating the first prosthesis data (step S600) may be performed by an artificial intelligence generator.

[0061] FIG. 2 is a drawing showing a step (step S100) of automatically aligning the 3D scan data of FIG. 1.

[0062] Referring to FIGS. 1 and 2, in the step of aligning the 3D scan data (step S100), a normalization matrix that normalizes the position and direction of the 3D scan data can be obtained using PCA. By multiplying each point of the 3D scan data by the normalization matrix, the 3D scan data can be aligned to predetermined coordinates and a predetermined direction.

[0063] The appearance of the various 3D scan data aligned to the predetermined coordinates and the predetermined direction is shown in Fig. 2.

[0064] When the above 3D scan data is aligned in a specific direction at a specific location, the accuracy of the method for automatically generating a prosthesis from the above 3D scan data can be further improved.

[0065] Fig. 3 is a diagram illustrating a step (step S200) for automatically extracting tooth information of Fig. 1. Fig. 4 is a flowchart illustrating a step (step S200) for automatically extracting tooth information of Fig. 1.

[0066] Referring to FIGS. 1 to 4, the tooth information may include the number (dental type) of the tooth, whether the tooth is prepared, the position of the tooth, and the direction of the tooth. Here, the position of the tooth may refer to the center position of the tooth. Here, the direction of the tooth may refer to the front-back direction of the tooth, the up-down direction of the tooth, and the left-right direction of the tooth.

[0067] If the number of teeth in the above 3D scan data is N, the status of the teeth (number and whether prepared) is class, the location of the teeth is pos, and the direction of the teeth is orient, , , can be expressed as

[0068] In FIG. 3, x_world, y_world, and z_world can represent directions of a predetermined coordinate system, and x_local, y_local, and z_local can represent the front-back direction of a specific tooth, the up-down direction of the specific tooth, and the left-right direction of the specific tooth.

[0069] For example, the step of automatically extracting the tooth information (step S200) may include a step of preprocessing the 3D scan data into a model input, a step of inputting the model input into a backbone network to obtain a feature map, and a step of extracting the tooth information from the feature map. Here, the backbone network may be the first artificial intelligence neural network.

[0070] The above preprocessing step may convert the 3D scan data into a form that can be input to the backbone network. For example, the model input may be a point cloud, a depth map, a parameterized mesh, a mesh with a fixed topology, etc. For example, the model input may be 2D image data. Alternatively, the model input may be 3D image data.

[0071] In Fig. 4, the condition information of the tooth is described as Box Classification, the location information of the tooth is described as Box Regression, and the direction information of the tooth is described as Axis Regression.

[0072] For learning the above backbone network, regression loss can be used for the position and direction of the tooth, and classification loss can be used for the number of the tooth.

[0073] Figure 5 is a drawing showing a step (step S500) of extracting a margin line of Figure 1.

[0074] Referring to FIGS. 1 to 5, the step of extracting the occlusal surface information (step S300) may be performed by the second artificial intelligence neural network. For example, the input of the second artificial intelligence neural network may be a two-dimensional image obtained from a direction set to best view the upper surface of the prepared tooth. For example, the output of the second artificial intelligence neural network may be a first three-dimensional point cloud representing the occlusal surface information of the prepared tooth.

[0075] For example, the input of the second artificial intelligence neural network may be a two-dimensional image obtained from a direction set to best view the upper surface of the prepared tooth and a two-dimensional image including the prepared tooth and adjacent teeth of the prepared tooth.

[0076] For example, the input of the second artificial intelligence neural network may be a two-dimensional image obtained from a direction set to best view the upper surface of the prepared tooth, a two-dimensional image including the prepared tooth and an adjacent tooth of the prepared tooth, and a two-dimensional image including the prepared tooth and an antagonist tooth of the prepared tooth.

[0077] For example, the output of the second artificial intelligence neural network may be a two-dimensional depth map representing the occlusal surface information of the prepared tooth. In this case, the two-dimensional depth map may be converted into the first three-dimensional point cloud.

[0078] Here, a 3D point cloud refers to a collection of 3D points, and the 3D points in the 3D point cloud do not have a connection relationship with each other. That is, the 3D point cloud may include 3D points that do not have a connection relationship. On the other hand, 3D scan data and 3D mesh data may include 3D points that have a connection relationship.

[0079] The step of extracting the region of interest data (step S400) may include a step of extracting partial scan data corresponding to the region of interest including the prepared tooth from the 3D scan data and a step of converting the partial scan data into a second 3D point cloud.

[0080] The step of extracting the above margin line (step S500) may be performed by the third artificial intelligence neural network. The input of the third artificial intelligence neural network may be partial scan data including the prepared tooth. The output of the third artificial intelligence neural network may be a third 3D point cloud representing the margin line of the prepared tooth.

[0081] For example, the step of extracting the margin line (step S500) includes the steps of extracting the partial scan data including the prepared tooth from the 3D scan data, the step of mapping the partial scan data into a predetermined 2D space using a transformation matrix (T), the step of obtaining a 2D margin line by determining a curvature value from the data mapped into the 2D space (F), and the step of obtaining the inverse matrix (T) of the transformation matrix. -1 ) may include a step of converting the two-dimensional margin line into a three-dimensional margin line.

[0082] For example, the curvature value may be any one of a maximum curvature value, a minimum curvature value, a Gaussian curvature value, and an average curvature value.

[0083] For the upper surface of the tooth, the curvature value may have a relatively constant value. On the other hand, the curvature value may vary significantly at the boundary between teeth or at the point where the tooth and gums come into contact. Therefore, the curvature value can be used to determine the margin line of the tooth.

[0084] In contrast, the step of extracting the above margin line (step S500) may directly find the 3D margin line from the 3D scan data.

[0085] FIG. 6 and FIG. 7 are drawings showing a step of generating the first prosthesis data (step S600) and a step of generating the second prosthesis data (step S700) of FIG. 1.

[0086] Referring to FIGS. 1 to 7, in the present embodiment, the step of generating the three-dimensional prosthesis data may include a step (step S600) of generating a three-dimensional prosthesis point cloud corresponding to the shape of the prosthesis. The step of generating the three-dimensional prosthesis point cloud may be performed by the artificial intelligence generator (GNR). In the present embodiment, the first prosthesis data may be the three-dimensional prosthesis point cloud.

[0087] The input of the artificial intelligence generator (GNR) may be a first 3D point cloud representing the occlusal surface information of the prepared tooth, a second 3D point cloud converted from partial scan data extracted from the 3D scan data corresponding to an area of ​​interest including the prepared tooth, and a third 3D point cloud representing the margin line of the prepared tooth.

[0088] The output of the above artificial intelligence generator (GNR) may be the 3D prosthesis point cloud. The 3D prosthesis point cloud may be points on the surface of the prosthesis shape.

[0089] As shown in Fig. 7, the artificial intelligence generator (GNR) may include an encoder (Menc) and a decoder (Mdec). However, the artificial intelligence generator (GNR) of the present invention is not limited thereto.

[0090] For example, the encoder (Menc) can extract features from an input point cloud and convert them into a low-dimensional feature vector. The decoder (Mdec) can reconstruct an output point cloud using the low-dimensional feature vector.

[0091] The step of generating the above 3D prosthesis data may further include a step (step S700) of generating 3D prosthesis mesh data (the second prosthesis data) by reconstructing the surface of the 3D prosthesis point cloud.

[0092] According to the present embodiment, tooth information is automatically extracted from the three-dimensional scan data, and three-dimensional prosthesis data can be automatically generated based on the occlusal surface information of the prepared tooth, the region of interest data including the prepared tooth, and the margin line of the prepared tooth.

[0093] In this way, a prosthesis is automatically created from the above 3D scan data, which can shorten the time and process for manufacturing the prosthesis and improve the quality of the prosthesis.

[0094] In particular, at least one of the steps of automatically extracting tooth information from the 3D scan data (step S200), the step of extracting the occlusal surface information of the prepared tooth (step S300), the step of extracting the margin line of the prepared tooth (step S500), and the step of generating the 3D prosthesis data (steps S600 and S700) is performed using an artificial intelligence neural network, so that the time and process for manufacturing the prosthesis can be shortened, and the quality of the prosthesis can be improved.

[0095] FIGS. 8 and 9 are drawings showing a step of generating first prosthesis data (step S600) and a step of generating second prosthesis data (step S700) of a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment of the present invention.

[0096] The method for automatically generating a prosthesis from 3D scan data according to the present embodiment is substantially the same as the method for automatically generating a prosthesis from 3D scan data of FIGS. 1 to 8, except for the step of generating first prosthesis data (step S600) and the step of generating second prosthesis data (step S700). Therefore, the same reference numbers are used for identical or similar components, and redundant descriptions are omitted.

[0097] Referring to FIGS. 1 to 5, 8 and 9, in the present embodiment, the step of generating the three-dimensional prosthesis data may include a step (step S600) of generating a three-dimensional signed distance field corresponding to the shape of the prosthesis. The step of generating the three-dimensional signed distance field may be performed by an artificial intelligence generator (GNR). In the present embodiment, the first prosthesis data may be the three-dimensional signed distance field.

[0098] The signed distance field may have a value of 0 for the surface of the prosthesis, a positive value whose absolute value increases as it moves away from the surface of the prosthesis in a first direction (e.g., an internal direction of a closed mesh formed by the prosthesis), and a negative value whose absolute value increases as it moves away from the surface of the prosthesis in a second direction opposite to the first direction (e.g., an external direction of a closed mesh formed by the prosthesis).

[0099] The input of the artificial intelligence generator (GNR) may be a first 3D point cloud representing the occlusal surface information of the prepared tooth, a second 3D point cloud converted from partial scan data extracted from the 3D scan data corresponding to an area of ​​interest including the prepared tooth, and a third 3D point cloud representing the margin line of the prepared tooth.

[0100] The output of the above artificial intelligence generator (GNR) may be the three-dimensional signed distance field.

[0101] As shown in Fig. 9, the artificial intelligence generator (GNR) may include an encoder (Menc) and a decoder (Mdec). However, the artificial intelligence generator (GNR) of the present invention is not limited thereto.

[0102] The step of generating the above 3D prosthesis data may further include a step (step S700) of converting the above 3D signed distance field into mesh data to generate 3D prosthesis mesh data (the above 2nd prosthesis data).

[0103] For example, a marching cube technique can be used to convert the above three-dimensional signed distance field into mesh data.

[0104] According to the present embodiment, tooth information is automatically extracted from the three-dimensional scan data, and three-dimensional prosthesis data can be automatically generated based on the occlusal surface information of the prepared tooth, the region of interest data including the prepared tooth, and the margin line of the prepared tooth.

[0105] In this way, a prosthesis is automatically created from the above 3D scan data, which can shorten the time and process for manufacturing the prosthesis and improve the quality of the prosthesis.

[0106] In particular, at least one of the steps of automatically extracting tooth information from the 3D scan data (step S200), the step of extracting the occlusal surface information of the prepared tooth (step S300), the step of extracting the margin line of the prepared tooth (step S500), and the step of generating the 3D prosthesis data (steps S600 and S700) is performed using an artificial intelligence neural network, so that the time and process for manufacturing the prosthesis can be shortened, and the quality of the prosthesis can be improved.

[0107] FIG. 10 and FIG. 11 are drawings showing a step of generating first prosthesis data (step S600) and a step of generating second prosthesis data (step S700) of a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment of the present invention.

[0108] The method for automatically generating a prosthesis from 3D scan data according to the present embodiment is substantially the same as the method for automatically generating a prosthesis from 3D scan data of FIGS. 1 to 8, except that the input and output of the artificial intelligence generator are in the form of voxels rather than point clouds. Therefore, the same reference numbers are used for the same or similar components, and redundant descriptions are omitted.

[0109] Referring to FIGS. 1 to 5, 10 and 11, in the present embodiment, the step of extracting the occlusal surface information (step S300) can be performed by the second artificial intelligence neural network.

[0110] The input of the second artificial intelligence neural network may be a two-dimensional image obtained from a direction set to best view the upper surface of the prepared tooth.

[0111] The output of the second artificial intelligence neural network may be a first voxel representing the occlusal surface information of the prepared tooth. Alternatively, the output of the second artificial intelligence neural network may be a first point cloud representing the occlusal surface information of the prepared tooth. The first point cloud may be converted into a first voxel.

[0112] The step of extracting the region of interest data (step S400) may include a step of extracting partial scan data corresponding to the region of interest including the prepared tooth from the 3D scan data, a step of converting the partial scan data into a second 3D point cloud, and a step of converting the second 3D point cloud into a second voxel.

[0113] The step of extracting the above margin line (step S500) can be performed by the third artificial intelligence neural network.

[0114] The input of the third artificial intelligence neural network may be partial scan data including the prepared tooth.

[0115] The output of the third artificial intelligence neural network may be a third 3D point cloud representing the margin line of the prepared tooth. The third 3D point cloud may be converted into a third voxel.

[0116] The step of generating the above three-dimensional prosthesis data may include a step (step S600) of generating a prosthesis voxel corresponding to the shape of the prosthesis. The step of generating the prosthesis voxel (step S600) may be performed by an artificial intelligence generator (GNR). In the present embodiment, the first prosthesis data may be the prosthesis voxel.

[0117] The input of the artificial intelligence generator (GNR) may be a first voxel representing the occlusal surface information of the prepared tooth, a second voxel converted from partial scan data extracted from the 3D scan data corresponding to an area of ​​interest including the prepared tooth, and a third voxel representing the margin line of the prepared tooth.

[0118] The output of the above artificial intelligence generator may be the above prosthesis voxel.

[0119] As shown in Fig. 11, the artificial intelligence generator (GNR) may include an encoder (Menc) and a decoder (Mdec). However, the artificial intelligence generator (GNR) of the present invention is not limited thereto.

[0120] The step of generating the above three-dimensional prosthesis data may further include a step (step S700) of flattening the surface of the prosthesis voxel. In the present embodiment, the second prosthesis data may be a prosthesis voxel whose surface has been flattened.

[0121] According to the present embodiment, tooth information is automatically extracted from the three-dimensional scan data, and three-dimensional prosthesis data can be automatically generated based on the occlusal surface information of the prepared tooth, the region of interest data including the prepared tooth, and the margin line of the prepared tooth.

[0122] In this way, a prosthesis is automatically created from the above 3D scan data, which can shorten the time and process for manufacturing the prosthesis and improve the quality of the prosthesis.

[0123] In particular, at least one of the steps of automatically extracting tooth information from the 3D scan data (step S200), the step of extracting the occlusal surface information of the prepared tooth (step S300), the step of extracting the margin line of the prepared tooth (step S500), and the step of generating the 3D prosthesis data (steps S600 and S700) is performed using an artificial intelligence neural network, so that the time and process for manufacturing the prosthesis can be shortened, and the quality of the prosthesis can be improved.

[0124] Fig. 12 is a flowchart illustrating a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment of the present invention. Figs. 13 and 14 are diagrams illustrating a step of generating the first prosthesis data and a step of generating the second prosthesis data of Fig. 12.

[0125] The method for automatically generating a prosthesis from three-dimensional scan data according to the present embodiment is substantially the same as the method for automatically generating a prosthesis from three-dimensional scan data of FIGS. 1 to 8, except that the input of the artificial intelligence generator is two-dimensional data and the output of the artificial intelligence generator is a neural implicit representation. Therefore, the same reference numbers are used for the same or similar components, and redundant descriptions are omitted.

[0126] Referring to FIGS. 12 to 14, a method for automatically generating a prosthesis from three-dimensional scan data according to the present embodiment includes a step of automatically extracting tooth information of each tooth included in the three-dimensional scan data from the three-dimensional scan data (step S200), a step of performing segmentation of a prepared tooth and adjacent teeth of the prepared tooth (step S300A), a step of extracting region of interest data including the prepared tooth (step S400A), a step of extracting a margin line of the prepared tooth (step S500A), and a step of generating three-dimensional prosthesis data based on the segmentation information of the prepared tooth and the adjacent teeth, the region of interest data, and the margin line (steps S600A and S700A).

[0127] The step of generating the above 3D prosthesis data (steps S600A and S700A) may include a step of generating first prosthesis data based on segmentation information of the prepared tooth and the adjacent teeth, the region of interest data, and the margin line (step S600A), and a step of generating second prosthesis data based on the first prosthesis data (step S700A).

[0128] The method for automatically generating a prosthesis from the above 3D scan data may further include, prior to the step of automatically extracting the tooth information, a step (step S100) of aligning the 3D scan data to the origin of the predetermined coordinate system in the direction of the predetermined coordinate system.

[0129] For example, the step of automatically extracting the tooth information (step S200) may be performed by a first artificial intelligence neural network. The step of performing segmentation of the prepared tooth and the adjacent teeth (step S300A) may be performed by a second artificial intelligence neural network. The step of extracting the margin line (step S500A) may be performed by a third artificial intelligence neural network. The step of generating the first prosthesis data (step S600A) may be performed by an artificial intelligence generator.

[0130] The step of performing segmentation of the above-mentioned prepared teeth and the adjacent teeth (step S300A) can be performed by the second artificial intelligence neural network.

[0131] The output of the second artificial intelligence neural network may be two-dimensional segmentation information in which the prepared tooth and the adjacent teeth are projected onto a first plane.

[0132] The input of the second artificial intelligence neural network may be three-dimensional partial scan data including the prepared tooth and the adjacent teeth. Alternatively, the input of the second artificial intelligence neural network may be a first two-dimensional input depth map that projects the three-dimensional partial scan data including the prepared tooth and the adjacent teeth onto a first plane.

[0133] The step of extracting the region of interest data (step S400A) may include a step of extracting partial scan data corresponding to the region of interest including the prepared tooth from the three-dimensional scan data and a step of converting the partial scan data into a two-dimensional depth map on a first plane.

[0134] The step of extracting the above margin line (step S500A) can be performed by the third artificial intelligence neural network.

[0135] The output of the third artificial intelligence neural network may be a two-dimensional margin line that projects the three-dimensional margin line of the prepared tooth onto the first plane.

[0136] The input of the third artificial intelligence neural network may be three-dimensional partial scan data including the prepared tooth. Alternatively, the input of the third artificial intelligence neural network may be a third two-dimensional input depth map that projects the three-dimensional partial scan data including the prepared tooth onto a first plane.

[0137] The step of generating the above 3D prosthesis data may include a step (step S600A) of generating a 3D neural implicit representation corresponding to the shape of the prosthesis. The step (step S600A) of generating the 3D neural implicit representation may be performed by the artificial intelligence generator (GNR).

[0138] Alternatively, step S600A may generate a 3D neural hybrid representation corresponding to the shape of the prosthesis. The 3D neural hybrid representation may be a combination of the 3D neural implicit representation and the 3D neural explicit representation. For example, the 3D neural explicit representation may have the form of a voxel or a 3D point cloud.

[0139] The input of the artificial intelligence generator may be two-dimensional segmentation information in which the prepared tooth and the adjacent teeth are projected onto a first plane, a two-dimensional depth map on the first plane converted from partial scan data extracted corresponding to an area of ​​interest including the prepared tooth from the three-dimensional scan data, a two-dimensional margin line projecting the three-dimensional margin line of the prepared tooth onto the first plane, and direction information (PD) for the first plane.

[0140] The output of the above artificial intelligence generator may be the three-dimensional neural implicit representation. The three-dimensional neural implicit representation may be an internalized representation for a neural network related to the shape of the prosthesis.

[0141] As shown in Fig. 14, the artificial intelligence generator (GNR) may include an encoder (Menc) and a decoder (Mdec). However, the artificial intelligence generator (GNR) of the present invention is not limited thereto.

[0142] The step of generating the above 3D prosthesis data may further include a step (step S700A) of converting the 3D neural implicit representation into mesh data to generate 3D prosthesis mesh data (the second prosthesis data).

[0143] According to the present embodiment, tooth information is automatically extracted from the three-dimensional scan data, and three-dimensional prosthesis data can be automatically generated based on segmentation information of the prepared tooth and the adjacent teeth, the region of interest data including the prepared tooth, and the margin line of the prepared tooth.

[0144] In this way, a prosthesis is automatically created from the above 3D scan data, which can shorten the time and process for manufacturing the prosthesis and improve the quality of the prosthesis.

[0145] In particular, at least one of the steps of automatically extracting tooth information from the 3D scan data (step S200), the step of extracting the occlusal surface information of the prepared tooth (step S300), the step of extracting the margin line of the prepared tooth (step S500), and the step of generating the 3D prosthesis data (steps S600 and S700) is performed using an artificial intelligence neural network, so that the time and process for manufacturing the prosthesis can be shortened, and the quality of the prosthesis can be improved.

[0146] FIG. 15 is a flowchart illustrating a method for automatically generating a prosthesis from three-dimensional scan data according to one embodiment of the present invention.

[0147] The method for automatically generating a prosthesis from 3D scan data according to the present embodiment is substantially the same as the method for automatically generating a prosthesis from 3D scan data of FIGS. 12 to 14, except that occlusal surface information is further input to the artificial intelligence generator. Therefore, the same reference numbers are used for identical or similar components, and redundant descriptions are omitted.

[0148] Referring to FIG. 15, a method for automatically generating a prosthesis from three-dimensional scan data according to the present embodiment includes a step of automatically extracting tooth information of each tooth included in the three-dimensional scan data from the three-dimensional scan data (step S200), a step of performing segmentation of a prepared tooth and adjacent teeth of the prepared tooth (step S300A), a step of extracting region of interest data including the prepared tooth (step S400A), a step of extracting a margin line of the prepared tooth (step S500A), a step of extracting occlusal surface information of the prepared tooth (S550A), and a step of generating three-dimensional prosthesis data based on segmentation information of the prepared tooth and the adjacent teeth, the region of interest data, the margin line, and the occlusal surface information (steps S600A and S700A).

[0149] The step of generating the above 3D prosthesis data (steps S600A and S700A) may include a step of generating first prosthesis data based on segmentation information of the prepared tooth and the adjacent teeth, the region of interest data, the margin line, and the occlusal surface information (step S600A), and a step of generating second prosthesis data based on the first prosthesis data (step S700A).

[0150] The step of generating the above 3D prosthesis data may include a step (step S600A) of generating a 3D neural implicit representation corresponding to the shape of the prosthesis. The step (step S600A) of generating the 3D neural implicit representation may be performed by the artificial intelligence generator (GNR).

[0151] The input of the artificial intelligence generator may be two-dimensional segmentation information in which the prepared tooth and the adjacent teeth are projected onto a first plane, a two-dimensional depth map on the first plane converted from partial scan data extracted from the three-dimensional scan data corresponding to an area of ​​interest including the prepared tooth, a two-dimensional margin line projecting a three-dimensional margin line of the prepared tooth onto the first plane, two-dimensional occlusal surface information of the prepared tooth, and direction information (PD) for the first plane.

[0152] The output of the above artificial intelligence generator may be the three-dimensional neural implicit representation. Alternatively, the output of the above artificial intelligence generator may be the three-dimensional neural hybrid representation.

[0153] According to the present embodiment, tooth information is automatically extracted from the three-dimensional scan data, and three-dimensional prosthesis data can be automatically generated based on segmentation information of the prepared tooth and the adjacent teeth, the region of interest data including the prepared tooth, the margin line of the prepared tooth, and the occlusal surface information of the prepared tooth.

[0154] In this way, a prosthesis is automatically created from the above 3D scan data, which can shorten the time and process for manufacturing the prosthesis and improve the quality of the prosthesis.

[0155] In particular, at least one of the steps of automatically extracting tooth information from the 3D scan data (step S200), the step of extracting the occlusal surface information of the prepared tooth (step S300), the step of extracting the margin line of the prepared tooth (step S500), and the step of generating the 3D prosthesis data (steps S600 and S700) is performed using an artificial intelligence neural network, so that the time and process for manufacturing the prosthesis can be shortened, and the quality of the prosthesis can be improved.

[0156] According to one embodiment of the present invention, a computer-readable recording medium having recorded thereon a program for executing a method for automatically generating a prosthesis from three-dimensional scan data 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 in 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.

[0157] Additionally, the method for automatically generating a prosthesis from the aforementioned three-dimensional scan data can also be implemented in the form of a computer program or application executed by a computer and stored in a recording medium.

[0158] The present invention relates to a method for automatically generating a prosthesis from three-dimensional scan data and a computer-readable recording medium having recorded thereon a program for executing the method on a computer, which can reduce the effort and time required for manufacturing a prosthesis and improve the accuracy and productivity of the prosthesis.

[0159] 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 automatically extracting tooth information of each tooth included in the 3D scan data from the 3D scan data; A step of extracting occlusal information of a prepared tooth; A step of extracting region of interest data including the above prepared tooth; A step of extracting the margin line of the above prepared tooth; and A method for automatically generating a prosthesis from three-dimensional scan data, comprising the step of generating three-dimensional prosthesis data based on the occlusal surface information, the region of interest data, and the margin line.

2. In the first paragraph, the step of extracting the occlusal surface information is performed by a second artificial intelligence neural network, The input of the second artificial intelligence neural network is a two-dimensional image obtained from a direction set to best view the upper surface of the prepared tooth. A method for automatically generating a prosthesis from 3D scan data, characterized in that the output of the second artificial intelligence neural network is a first 3D point cloud representing the occlusal surface information of the prepared tooth.

3. In the first paragraph, the step of extracting the region of interest data is A step of extracting partial scan data corresponding to an area of ​​interest including the prepared tooth from the three-dimensional scan data; and A method for automatically generating a prosthesis from three-dimensional scan data, characterized in that it comprises a step of converting the above partial scan data into a second three-dimensional point cloud.

4. In the first paragraph, the step of extracting the margin line is performed by a third artificial intelligence neural network, The input of the third artificial intelligence neural network is partial scan data including the prepared tooth, A method for automatically generating a prosthesis from three-dimensional scan data, characterized in that the output of the third artificial intelligence neural network is a third three-dimensional point cloud representing the margin line of the prepared tooth.

5. In the fourth paragraph, the step of extracting the margin line A step of extracting the partial scan data including the prepared tooth from the three-dimensional scan data; A step of mapping the partial scan data into a predetermined two-dimensional space using a transformation matrix; A step of obtaining a two-dimensional margin line by determining a curvature value from data mapped within the two-dimensional space; and A method for automatically generating a prosthesis from three-dimensional scan data, characterized in that it comprises a step of converting the two-dimensional margin line into a three-dimensional margin line using an inverse matrix of the above transformation matrix.

6. In the first paragraph, the step of generating the three-dimensional prosthesis data is performed by an artificial intelligence generator and includes a step of generating a three-dimensional prosthesis point cloud corresponding to the shape of the prosthesis, The input of the artificial intelligence generator is a first 3D point cloud representing the occlusal surface information of the prepared tooth, a second 3D point cloud converted from partial scan data extracted from the 3D scan data corresponding to an area of ​​interest including the prepared tooth, and a third 3D point cloud representing the margin line of the prepared tooth. A method for automatically generating a prosthesis from 3D scan data, characterized in that the output of the artificial intelligence generator is the 3D prosthesis point cloud.

7. A method for automatically generating a prosthesis from 3D scan data, characterized in that in the 6th paragraph, the step of generating the 3D prosthesis data further includes the step of generating 3D prosthesis mesh data by reconstructing the surface of the 3D prosthesis point cloud.

8. In the first paragraph, the step of generating the three-dimensional prosthesis data is performed by an artificial intelligence generator and includes a step of generating a three-dimensional signed distance field corresponding to the shape of the prosthesis, The signed distance field has a value of 0 for the surface of the prosthesis, a positive value whose absolute value increases as it moves away from the surface of the prosthesis in a first direction, and a negative value whose absolute value increases as it moves away from the surface of the prosthesis in a second direction opposite to the first direction. The input of the artificial intelligence generator is a first 3D point cloud representing the occlusal surface information of the prepared tooth, a second 3D point cloud converted from partial scan data extracted from the 3D scan data corresponding to an area of ​​interest including the prepared tooth, and a third 3D point cloud representing the margin line of the prepared tooth. A method for automatically generating a prosthesis from three-dimensional scan data, wherein the output of the artificial intelligence generator is the three-dimensional signed distance field.

9. A method for automatically generating a prosthesis from 3D scan data, characterized in that in the 8th paragraph, the step of generating the 3D prosthesis data further includes the step of generating 3D prosthesis mesh data by converting the 3D signed distance field into mesh data.

10. In the first paragraph, the step of extracting the occlusal surface information is performed by a second artificial intelligence neural network, The input of the second artificial intelligence neural network is a two-dimensional image obtained from a direction set to best view the upper surface of the prepared tooth. A method for automatically generating a prosthesis from three-dimensional scan data, characterized in that the output of the second artificial intelligence neural network is a first voxel representing the occlusal surface information of the prepared tooth.

11. In the first paragraph, the step of extracting the region of interest data is A step of extracting partial scan data corresponding to an area of ​​interest including the prepared tooth from the above 3D scan data; A step of converting the above partial scan data into a second 3D point cloud; and A method for automatically generating a prosthesis from three-dimensional scan data, characterized in that it comprises a step of converting the second three-dimensional point cloud into a second voxel.

12. In the first paragraph, the step of extracting the margin line is performed by a third artificial intelligence neural network, The input of the third artificial intelligence neural network is partial scan data including the prepared tooth, The output of the third artificial intelligence neural network is a third 3D point cloud representing the margin line of the prepared tooth, A method for automatically generating a prosthesis from three-dimensional scan data, characterized in that the third three-dimensional point cloud is converted into a third voxel.

13. In the first paragraph, the step of generating the three-dimensional prosthesis data is performed by an artificial intelligence generator and includes a step of generating a prosthesis voxel corresponding to the shape of the prosthesis, The input of the artificial intelligence generator is a first voxel representing the occlusal surface information of the prepared tooth, a second voxel converted from partial scan data extracted from the 3D scan data corresponding to an area of ​​interest including the prepared tooth, and a third voxel representing the margin line of the prepared tooth. A method for automatically generating a prosthesis from three-dimensional scan data, wherein the output of the artificial intelligence generator is the prosthesis voxel.

14. A method for automatically generating a prosthesis from 3D scan data, characterized in that the step of generating the 3D prosthesis data in the 13th paragraph further includes a step of flattening the surface of the prosthesis voxel.

15. A step of automatically extracting tooth information of each tooth included in the 3D scan data from the 3D scan data; A step of performing segmentation of a prepared tooth and adjacent teeth of the prepared tooth; A step of extracting region of interest data including the above prepared tooth; A step of extracting the margin line of the above prepared tooth; and A method for automatically generating a prosthesis from three-dimensional scan data, comprising the step of generating three-dimensional prosthesis data based on segmentation information of the prepared tooth and the adjacent teeth, the region of interest data, and the margin line.

16. In paragraph 15, the step of performing segmentation of the prepared tooth and the adjacent teeth is performed by a second artificial intelligence neural network, A method for automatically generating a prosthesis from three-dimensional scan data, characterized in that the output of the second artificial intelligence neural network is two-dimensional segmentation information in which the prepared tooth and the adjacent teeth are projected onto a first plane.

17. In paragraph 15, the step of extracting the region of interest data is A step of extracting partial scan data corresponding to an area of ​​interest including the prepared tooth from the three-dimensional scan data; and A method for automatically generating a prosthesis from three-dimensional scan data, characterized in that it comprises a step of converting the above partial scan data into a two-dimensional depth map on a first plane.

18. In paragraph 15, the step of extracting the margin line is performed by a third artificial intelligence neural network, A method for automatically generating a prosthesis from three-dimensional scan data, characterized in that the output of the third artificial intelligence neural network is a two-dimensional margin line that projects the margin line of the prepared tooth onto a first plane.

19. In the 15th paragraph, the step of generating the 3D prosthesis data is performed by an artificial intelligence generator and includes a step of generating a 3D neural implicit representation corresponding to the shape of the prosthesis, The input of the artificial intelligence generator is two-dimensional segmentation information in which the prepared tooth and the adjacent teeth are projected onto a first plane, a two-dimensional depth map on the first plane converted from partial scan data extracted corresponding to an area of ​​interest including the prepared tooth from the three-dimensional scan data, a two-dimensional margin line projecting the margin line of the prepared tooth onto the first plane, and direction information for the first plane. A method for automatically generating a prosthesis from three-dimensional scan data, wherein the output of the artificial intelligence generator is the three-dimensional neural implicit representation.

20. A method for automatically generating a prosthesis from 3D scan data, characterized in that in claim 19, the step of generating the 3D prosthesis data further includes the step of generating the 3D prosthesis mesh data by converting the 3D neural implicit representation into mesh data.

21. In paragraph 15, Further comprising a step of extracting occlusal surface information of the above prepared teeth, A method for automatically generating a prosthesis from 3D scan data, characterized in that the step of generating the 3D prosthesis data generates the 3D prosthesis data based on segmentation information of the prepared tooth and the adjacent teeth, the region of interest data, the margin line, and the occlusal surface information.

22. A computer-readable recording medium having recorded thereon a program for executing the method of any one of claims 1 to 21 on a computer.

Images