JP2022070992A - Data generation device, scanner system, data generation method, and data generation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a data generation device, a scanner system including the data generation device, a data generation method, and a data generation program which can produce an appropriate prosthesis more easily than before.

SOLUTION: A data generation device 100 includes: an input section 1102 to which three-dimensional data including an anodontia which is at least a missing tooth are input; and a generation section 1104 for generating prosthesis data for producing a prosthesis fitted in a missing place of the anodontia on the basis of the three-dimensional data input from the input section 1102 and a generation model 114. The generation model 114 is mechanically learned on the basis of identification result of whether the prosthesis data generated by the generation section 1104 is appropriate.

SELECTED DRAWING: Figure 4

COPYRIGHT: (C)2022,JPO&INPIT

Description

The present invention relates to a data generation device, a scanner system including the data generation device, a data generation method, and a data generation program.

Conventionally, in the field of dentistry, a three-dimensional scanner that acquires a three-dimensional shape of a portion including a defective tooth, which is a defective tooth, has been known in order to digitally design a prosthesis or the like on a computer. For example, Patent Document 1 discloses a technique for recording the shape of the oral cavity by imaging the oral cavity using a three-dimensional camera of a three-dimensional scanner.

Japanese Unexamined Patent Publication No. 2000-74635

A surgeon such as a dentist can record shape data (hereinafter, also referred to as "three-dimensional data") in the oral cavity of a patient by using the technique disclosed in Patent Document 1. The recorded three-dimensional data is used to prepare a prosthesis for compensating for a defective portion of a defective tooth. For example, the surgeon acquires three-dimensional data including the missing tooth of the patient with a three-dimensional scanner, and based on the acquired three-dimensional data, creates production data for producing a prosthesis suitable for the defective portion (hereinafter, "" Digitally design the prosthesis data) on a computer. Alternatively, the surgeon sends the acquired 3D data to the dental technician, and the dental technician digitally designs the prosthesis data on the computer to create a prosthesis that fits the defect based on the 3D data. do.

However, since the skill level of surgeons and dental technicians varies, it is not always easy to generate appropriate prosthesis data for defective parts based on the acquired 3D data, and it is easier and more appropriate to generate appropriate prostheses. A technique capable of producing an object is desired.

The present invention has been made to solve such a problem, and is a data generation device capable of producing an appropriate prosthesis more easily, a scanner system including the data generation device, a data generation method, and a data generation method. The purpose is to provide a data generation program.

According to an example of the present disclosure, there is provided a data generator that generates prosthesis data for producing a tooth prosthesis. The data generator is a prosthesis that matches the missing part of the missing tooth based on the input section where the three-dimensional data including the missing tooth, which is at least the missing tooth, is input, and the three-dimensional data and the generation model input from the input section. It includes a generation unit that generates prosthesis data for producing an object, and an identification unit that identifies whether or not the prosthesis data generated by the generation unit is appropriate. In the generative model learning stage, the generator generates prosthesis data for producing a prosthesis corresponding to the arbitrary tooth based on the three-dimensional data of the dentition including the tooth other than the arbitrary tooth and the generative model. However, the identification unit estimates the tooth type corresponding to the prosthesis data generated by the generative unit, and is the prosthesis data appropriate based on the estimation result of the tooth type and an arbitrary tooth type? Whether or not it is identified, and the generative model is machine-learned based on the identification result of the identification unit.

According to an example of the present disclosure, a scanner system for acquiring tooth shape information is provided. The scanner system uses a three-dimensional camera to acquire at least three-dimensional data including the missing tooth, which is the missing tooth, and the three-dimensional data acquired by the three-dimensional scanner is used to determine the missing tooth. It is provided with a data generation device that generates prosthesis data for producing a suitable prosthesis. The data generation device generates prosthesis data for producing a prosthesis that matches the defective part based on the input unit in which the three-dimensional data is input, the three-dimensional data input from the input unit, and the generation model. A unit and an identification unit that identifies whether or not the prosthesis data generated by the generation unit is appropriate. In the generative model learning stage, the generator generates prosthesis data for producing a prosthesis corresponding to the arbitrary tooth based on the three-dimensional data of the dentition including the tooth other than the arbitrary tooth and the generative model. However, the identification unit estimates the tooth type corresponding to the prosthesis data generated by the generative unit, and is the prosthesis data appropriate based on the estimation result of the tooth type and an arbitrary tooth type? Whether or not it is identified, and the generative model is machine-learned based on the identification result of the identification unit.

According to an example of the present disclosure, there is provided a data generation method for generating prosthesis data for producing a tooth prosthesis by a computer. The data generation method is a process executed by a computer, in which at least a step of inputting three-dimensional data including a missing tooth, which is a missing tooth, and a missing tooth based on the three-dimensional data and a generation model. It includes a step of generating prosthesis data for producing a prosthesis that fits the site and a step of identifying whether the prosthesis data generated by the generation step is appropriate. In the generative model learning stage, the generation step is to generate prosthesis data for producing a prosthesis corresponding to any tooth based on the three-dimensional data of the dentition including teeth other than any tooth and the generation model. The generation and identification step estimates the tooth type corresponding to the prosthesis data generated by the generation step, and the prosthesis data is based on the estimation result of the tooth type and any tooth type. Is appropriate or not, and the generative model is machine-learned based on the identification result of the identification step.

According to an example of the present disclosure, a data generation program for generating prosthesis data for producing a tooth prosthesis is provided. The data generation program creates a prosthesis that matches the missing part of the missing tooth based on the step of inputting the three-dimensional data including at least the missing tooth, which is the missing tooth, to the computer, and the three-dimensional data and the generation model. A step of generating prosthesis data for the purpose of performing the procedure and a step of identifying whether or not the prosthesis data generated by the step of generating the prosthesis data are appropriate are executed. In the generative model learning stage, the generation step is to generate prosthesis data for producing a prosthesis corresponding to any tooth based on the three-dimensional data of the dentition including teeth other than any tooth and the generation model. The generation and identification step estimates the tooth type corresponding to the prosthesis data generated by the generation step, and the prosthesis data is based on the estimation result of the tooth type and any tooth type. Is appropriate or not, and the generative model is machine-learned based on the identification result of the identification step.

According to the present invention, a suitable prosthesis can be produced more easily.

It is a schematic diagram which shows the application example of the data generation apparatus which concerns on this embodiment. It is a schematic diagram which shows an example of the tooth which is the scan target of the 3D scanner which concerns on this embodiment. It is a schematic diagram for demonstrating the type of the tooth to be scanned by the 3D scanner which concerns on this embodiment. It is a schematic diagram which shows the functional structure in the learning stage of the data generation apparatus which concerns on this embodiment. It is a schematic diagram which shows an example of the prosthesis data generation processing of the prosthesis data generation apparatus which concerns on this embodiment. It is an enlarged view of the defective part which is the prosthesis target of the data generation apparatus which concerns on this embodiment. It is a schematic diagram which shows the functional structure in the practical stage of the data generation apparatus which concerns on this embodiment. It is a schematic diagram which shows the whole structure of the system which concerns on this embodiment. It is a schematic diagram which shows the hardware configuration of the data generation apparatus which concerns on this embodiment. It is a flowchart for demonstrating the learning process executed by the data generation apparatus which concerns on this embodiment. It is a flowchart for demonstrating the prosthesis data generation processing executed by the data generation apparatus which concerns on this embodiment. It is a schematic diagram which shows the functional structure in the learning stage of the data generation apparatus which concerns on a modification.

Embodiments of the present invention will be described in detail with reference to the drawings. The same or corresponding parts in the drawings are designated by the same reference numerals and the description thereof will not be repeated.

[Application example]
FIG. 1 is a schematic diagram showing an application example of the data generation device 100 according to the present embodiment.

As shown in FIG. 1, the user 1 can acquire three-dimensional shape data (three-dimensional data) in the oral cavity including the teeth of the subject 2 by using the scanner system 10. The "user" is any person who uses the scanner system 10, such as a surgeon such as a dentist, a dental assistant, a teacher or student at a dental university, a dental technician, a technician at a manufacturer, or a worker at a manufacturing factory. May be. The "subject" may be any person who is the target of the scanner system 10, such as a patient in a dental clinic or a subject in a dental school. Further, the "target person" is not limited to a living human being, and may be a human body model or a head model.

The scanner system 10 according to the present embodiment includes a three-dimensional scanner 200, a data generation device 100, and a display 300. The three-dimensional scanner 200 acquires three-dimensional data to be scanned by a built-in three-dimensional camera. Specifically, the three-dimensional scanner 200 scans the inside of the oral cavity of the subject 2 to provide position information (for example, lateral direction, depth direction, and height of the tooth) of each of a plurality of points constituting the part to be scanned. The coordinates in the vertical direction) and the color information (for example, the color of the surface of the tooth) are acquired by using an optical sensor or the like. The data generation device 100 generates a three-dimensional image based on the three-dimensional data acquired by the three-dimensional scanner 200, and displays the generated three-dimensional image on the display 300.

Specifically, the user 1 uses the three-dimensional scanner 200 to digitally design the prosthesis data for producing the prosthesis suitable for the defective portion of the defective tooth of the subject 2 by the three-dimensional scanner 200. Image the inside of the oral cavity. Each time the user 1 takes an image of the oral cavity, three-dimensional data is sequentially acquired, and a three-dimensional image of the oral cavity including at least the missing tooth is displayed on the display 300. The user 1 focuses on scanning the missing portion of the three-dimensional data while checking the three-dimensional image displayed on the display 300. The three-dimensional data recorded in this way is used for making a prosthesis.

"Defective tooth" includes teeth whose shape is defective due to caries or cutting during treatment, such as abutment teeth, tooth cavities, and implant bodies. "Prosthesis" includes various known fillings and coverings used in prosthetic dentistry, such as crowns, bridges, implants, inlays and the like.

For example, when prosthesis a defective tooth with a crown, the surgeon first scrapes the carious portion of the tooth with a cutting tool such as a turbine to form an abutment tooth, and then mounts the crown on the abutment tooth. At this time, if the outer edge of the abutment tooth called the margin and the outer edge of the crown are not brought into close contact with each other, it causes secondary caries. Similarly, when prosthesis a defective part with an inlay, if the inlay is not brought into close contact with the tooth cavity after the caries portion of the tooth is scraped off, it causes secondary caries.

Further, in the production of a prosthesis, a prosthesis is made with a tooth around the defective portion (defective tooth) (hereinafter, also referred to as "peripheral tooth"), that is, a tooth adjacent to the defective tooth (hereinafter, also referred to as "adjacent tooth"). It is also important that the distance between the object and the distance between the prosthesis and the tooth facing the defect (defective tooth) (hereinafter, also referred to as “opposite tooth”) is appropriate. In addition, "adjacent" includes being located next to the defective tooth while being in contact with the defective tooth, or being located next to the defective tooth without being in contact with the defective tooth.

Further, as will be described in detail later, the teeth include middle premolars, lateral incisions, dog teeth, first premolars, second premolars, first molars, second molars, and third molars. , There are various types. In addition, the shape is characteristic depending on the type of tooth, and these shapes affect the meshing of teeth and the like. Therefore, it is important to produce a prosthesis of the same type as the defective tooth, that is, a prosthesis having the same shape (characteristic) as the defective tooth as much as possible.

As described above, there are many important points in the production of the prosthesis, but since the technical level of the surgeon and the dental technician who is the user 1 varies, appropriate prosthesis data is generated at the defective portion. That is not always easy.

Therefore, the scanner system 10 according to the present embodiment is suitable for the defective portion based on the three-dimensional data acquired by the three-dimensional scanner 200 by using the AI (Artificial Intelligence) possessed by the data generation device 100. It is configured to generate prosthesis data.

Specifically, when the user 1 scans the oral cavity of the subject 2 using the three-dimensional scanner 200, three-dimensional data including at least the missing tooth is input to the data generation device 100. The data generation device 100 automatically generates prosthesis data that matches the defect location based on the input three-dimensional data and the generation model. The prosthesis data includes position information (coordinates of each axis in the vertical direction, the horizontal direction, and the height direction) of each of a plurality of points constituting the prosthesis as three-dimensional data for producing the prosthesis itself. As the output format of the prosthesis data, a PCD file, an STL file, a PLY file, or the like is applied.

The prosthesis data generated by the data generation device 100 in this way is output to the dental laboratory. At the dental laboratory, a dental technician prepares a prosthesis based on the prosthesis data acquired from the data generation device 100.

Further, when the automatic manufacturing apparatus 600 capable of automatically manufacturing the prosthesis is arranged in the dental clinic, the prosthesis data generated by the data generating apparatus 100 may be output to the automatic manufacturing apparatus 600. In this way, the user 1 can also produce the prosthesis based on the prosthesis data by the automatic manufacturing apparatus 600. Examples of the automatic manufacturing apparatus 600 include a milling machine and a 3D printer.

As described above, according to the scanner system 10 according to the present embodiment, the prosthesis data is automatically generated based on the three-dimensional data acquired by the three-dimensional scanner 200 by using the AI possessed by the data generation device 100. Will be done. By using AI, the scanner system 10 can also find tooth features that cannot be extracted by user 1, which allows user 1 to more easily obtain a suitable prosthesis.

[Example of teeth to be scanned]
FIG. 2 is a schematic diagram showing an example of teeth to be scanned by the three-dimensional scanner 200 according to the present embodiment. In FIG. 2, the teeth to be scanned by the three-dimensional scanner 200 are represented by a diagram.

As shown in FIG. 2, when the tooth to be scanned by the three-dimensional scanner 200 is the maxillary lateral incisor, the obtained three-dimensional image is an image of the upper lip side part, the palatal side part, and the incisor side part. The oral cavity of the subject 2 is scanned by the user 1 so as to include at least. Further, when the teeth to be scanned by the 3D scanner 200 are the canines and molars of the upper jaw, the obtained 3D image includes at least an image of the buccal part, the palatal side part, and the occlusal part. , The oral cavity of the subject 2 is scanned by the user 1. When the tooth to be scanned by the 3D scanner 200 is the incisor of the lower jaw, the obtained 3D image includes at least the image of the lower lip side part, the lingual side part, and the incisor side part. The oral cavity of the subject 2 is scanned by the user 1. When the teeth to be scanned by the 3D scanner 200 are mandibular dog teeth and molars, the user so that the obtained 3D image includes at least an image of the buccal part, the lingual part, and the occlusal part. 1 scans the oral cavity of subject 2.

Generally, the teeth of subject 2 differ in shape and size depending on the type. For example, in the case of maxillary incisors, the surface on the upper lip side is generally U-shaped, whereas in the case of canines on the maxilla, the surface on the buccal side is generally pentagonal. Each tooth is characteristic in shape and size depending on its type. Therefore, digitally designing prosthesis data while identifying the characteristics (types) of each tooth largely depends on the knowledge of the surgeon and dental technician.

[Types of teeth to be scanned]
FIG. 3 is a schematic diagram for explaining the types of teeth to be scanned by the three-dimensional scanner 200 according to the present embodiment.

As shown in FIG. 3, each tooth has a middle premolar, a lateral incisor, a dog tooth, a first premolar, a second premolar, a first molar, and a second molar, depending on the type and position. And the name is given such as the third molar. Further, in the oral cavity, each of the above-mentioned teeth is generally present in each of the right side of the maxilla, the left side of the maxilla, the right side of the mandible, and the left side of the mandible.

Further, each tooth is assigned a predetermined number according to its type and position. For example, the middle premolar is assigned number 1, the lateral incisor is assigned number 2, the dog tooth is assigned number 3, the first premolar is assigned number 4, and the second premolar is assigned number 2. No. 5 is assigned, No. 6 is assigned to the first molar, No. 7 is assigned to the second molar, and No. 8 is assigned to the third molar.

[Functional configuration at the learning stage of the data generator]
FIG. 4 is a schematic diagram showing a functional configuration in the learning stage of the data generation device 100 according to the present embodiment.

As shown in FIG. 4, the data generation device 100 has an input unit 1102, a generation unit 1104, and an identification unit 1106. Each of these functions is realized by the arithmetic unit 130 of the data generation device 100, which will be described later, executing the OS 127, the identification program 120, the learning program, the data generation program 125, and the like.

The three-dimensional data acquired by the three-dimensional scanner 200 is input to the input unit 1102. The three-dimensional data input to the input unit 1102 includes not only the missing tooth (missing part), but also the adjacent tooth adjacent to the missing tooth, the facing tooth facing the missing tooth, the tooth adjacent to the facing tooth, and the dentition of the upper jaw. It contains three-dimensional data of at least one of each tooth in the state where the dentition of the lower jaw and the dentition of the lower jaw are meshed with each other, and the tooth on the opposite side of the missing tooth.

For example, with reference to FIG. 3, when the missing tooth is a canine tooth (No. 3) on the left side of the maxilla, each tooth can be exemplified as follows. For example, the adjacent teeth adjacent to the canine (No. 3) on the left side of the maxilla include the lateral incisor (No. 2), central incisor (No. 1), first premolar (No. 4), or second small on the left side of the maxilla. Examples include molar teeth (No. 5). Examples of the facing tooth facing the canine tooth (No. 3) on the left side of the upper jaw include the canine tooth (No. 3) on the left side of the lower jaw. Examples of the tooth adjacent to the facing tooth facing the canine tooth (No. 3) on the left side of the maxilla include a lateral incisor (No. 2) or a first premolar (No. 4) on the left side of the mandible. The tooth on the opposite side of the defective tooth is the tooth on the left and right opposite sides in the dentition to which the defective tooth belongs. For example, examples of the tooth on the opposite side of the canine tooth (No. 3) on the left side of the maxilla include the canine tooth (No. 3) on the right side of the maxilla. In addition, the input unit 1102 may input not only the actual three-dimensional data of the teeth acquired by the three-dimensional scanner 200 but also a model of the three-dimensional data prepared in advance for learning. Further, in the input unit 1102, the type (name or name) of each tooth included in the three-dimensional data such as the missing tooth, the adjacent tooth, the facing tooth, the tooth adjacent to the facing tooth, and the tooth on the opposite side, which is input by the user. Number) may be entered.

The generation unit 1104 generates prosthesis data for producing a prosthesis that matches the defective portion based on the three-dimensional data input from the input unit 1102 and the generation model 114. At this time, the generation unit 1104 generates the prosthesis data according to the generation conditions specified by the generation condition data 119 described later. The process of generating prosthesis data by the generation unit 1104 is also referred to as "prosthesis data generation process". When the type (name or number) of each tooth included in the three-dimensional data is input to the input unit 1102, the generation unit 1104 receives the type (name) of each tooth included in the three-dimensional data input by the user. Or the prosthesis data is generated with reference to the number).

The identification unit 1106 identifies whether or not the prosthesis data is appropriate based on the prosthesis data generated by the generation unit 1104 and the correct answer data input by the user 1. To identify whether the prosthesis data is appropriate, identify whether the shape of the prosthesis produced based on the prosthesis data matches the shape of the sample tooth input as the correct answer data. Identifying whether or not the similarity between the shape of the prosthesis produced based on the prosthesis data and the shape of the sample tooth input as correct data is equal to or higher than the reference value, and being produced based on the prosthesis data. It is possible to identify whether or not the type (name or number) of the tooth of the prosthesis matches the type (name or number) of the missing tooth input as the correct answer data. The process of identifying whether or not the prosthesis data by the identification unit 1106 is appropriate is also referred to as "identification process".

In this embodiment, the identification unit 1106 is configured to estimate the tooth type (name or number) corresponding to the prosthesis data generated by the generation unit 1104 based on the machine-learned identification model 116. ing. Specifically, the identification unit 1106 estimates the name of the tooth or the number of the tooth shown in FIG. 3 as the type of tooth of the prosthesis, and the estimation result of the type of tooth of the prosthesis is input as correct answer data. Identify whether it matches the type (name or number) of the missing tooth.

For example, when the 6th first molar on the right side of the mandible is missing, the user 1 provides information for identifying the type of the missing tooth such as "6th" or "1st molar" as correct data. Input to the data generation device 100 in advance. In the data generation device 100, when the three-dimensional data in the oral cavity in which the first molar of No. 6 is missing is input, the generation unit 1104 is based on the input three-dimensional data and the generation model 114. As much as possible, an attempt is made to generate prosthesis data for producing a prosthesis having the characteristics of the first molar of No. 6. The identification unit 1106 estimates the type (name or number) of the tooth of the prosthesis produced based on the prosthesis data based on the prosthesis data generated by the generation unit 1104 and the identification model 116, and the tooth of the prosthesis. It is identified whether or not the estimation result of the type of is consistent with the type (name or number) of the missing tooth entered as the correct answer data.

Here, the discriminative model 116 is machine-learned in advance in the preparatory stage before learning the generative model 114. Specifically, the discriminative model 116 includes a neural network (not shown) and parameters used by the neural network.

In the neural network of the discriminative model 116, the intermediate layer has a multi-layer structure, so that processing by deep learning is performed. In this embodiment, for example, VoxNet, 3D ShapeNets, Multi-View CNN, RotationNet, OctNet, FusionNet, PointNet, PointNet ++, SSCNet, MarrNet, and the like are used as programs that perform processing specialized for 3D images. However, other programs may be used. Further, an existing one may be applied to the mechanism of the neural network of the discriminative model 116.

The discriminative model 116 uses the tooth information corresponding to the missing tooth, that is, the tooth type (name or number) associated with the tooth for which the prosthesis needs to be generated, and the three-dimensional data. It is optimized (adjusted) by machine learning based on the identification result of the tooth type (name or number).

For example, in the discriminative model 116, when three-dimensional data in the oral cavity for learning is input, tooth characteristics are extracted by a neural network based on the three-dimensional data, and the tooth type (name) is based on the extracted tooth characteristics. Or number) is estimated. Then, the discriminative model 116 does not update the parameter if both match, based on the tooth type estimated by itself and the tooth type (tooth information) associated with the input three-dimensional data for learning. Then, if they do not match, the parameters are updated so that they match, thereby optimizing the parameters. As a result, the discriminative model 116 is machine learning by optimizing the parameters by using the teacher data including the three-dimensional data which is the input data and the tooth type (name or number) which is the correct answer data. Will be done. By repeating such machine learning in the preparatory stage before learning the generative model 114, the trained discriminative model 116 is obtained. In the discriminative model 116, the parameters are not limited to those updated, and the neural network (for example, the algorithm of the neural network) may be updated.

The identification result obtained by the identification unit 1106 is fed back to the generation unit 1104. The generation model 114 is machine-learned based on the identification result fed back from the identification unit 1106. The process of machine learning such a generation model 114 is also referred to as "learning process".

For example, the generative model 114 includes a neural network (not shown) and parameters used by the neural network. In the neural network of the generative model 114, the intermediate layer has a multi-layer structure, so that processing by deep learning is performed. In this embodiment, as a program that performs processing specialized for 3D images, for example, AAE, “Learning Representations and Generative Models”, ShapeVAE, “Shape Generation using Spatially Partitioned Point Clouds”, FoldingNet, P2P-Net, PCN (Point Completion Network), PPF-FoldingNet, PC-GAN, DeepSDF, etc. are used, but other programs may be used. Further, an existing one may be applied to the mechanism of the neural network of the generative model 114.

In the learning process, in the generation model 114, based on the identification result, the tooth type (name or number) of the prosthesis corresponding to the prosthesis data generated by itself is the type of tooth (name or number) whose correct answer data is. If it is determined that they match, the parameters are not updated, while if it is determined that they do not match, the parameters are updated so that they match, thereby optimizing the parameters. As described above, in the learning process, the generative model 114 is machine-learned by optimizing the parameters. In the generative model 114, the parameters are not limited to those updated, and the neural network (for example, the algorithm of the neural network) may be updated.

In the data generation device 100 configured in this way, the three-dimensional data acquired by the three-dimensional scanner 200 or the three-dimensional data prepared in advance for learning is input. Before learning, the generation unit 1104 cannot generate appropriate prosthesis data that matches the defect location, but first, according to its own prediction, generates prosthesis data based on the three-dimensional data and the generation model 114. Try. The identification unit 1106 estimates the type of tooth corresponding to the prosthesis data generated by the generation unit 1104, and identifies whether or not the estimated tooth type matches the tooth type which is the correct answer data. The identification result is fed back to the generation unit 1104. The generation unit 1104 will generate appropriate prosthesis data so as to be closer to the correct answer data than before the learning by machine learning the generation model 114 based on the feedback identification result. By repeating such machine learning, the generation unit 1104 will soon be able to generate prosthesis data capable of producing an appropriate prosthesis. Further, when the type (name or number) of each tooth included in the three-dimensional data such as the missing tooth, the adjacent tooth, the facing tooth, the tooth adjacent to the facing tooth, and the tooth on the opposite side is input to the input unit 1102, The generation unit 1104 will generate the prosthesis data based on the type (name or number) of each tooth included in the three-dimensional data. In this case, the generation unit 1104 will perform machine learning in consideration of the type (name or number) of each tooth input by the user, and will be able to generate more accurate prosthesis data.

[Example of prosthesis data generation processing]
FIG. 5 is a schematic diagram showing an example of the prosthesis data generation process of the data generation device 100 according to the present embodiment. FIG. 6 is an enlarged view of a defective portion that is a prosthetic target of the data generation device 100 according to the present embodiment. As shown in FIG. 5, the data generation device 100 is based on the three-dimensional data acquired by the three-dimensional scanner 200 and the generation model 114 according to the predetermined generation conditions specified by the generation condition data 119 described later, and the prosthesis data. To generate.

Specifically, first, the three-dimensional data in the oral cavity is acquired by the three-dimensional scanner 200 (STEP 1). For example, with the subject 2 having his mouth open, the teeth located in the upper jaw are scanned, and the teeth located in the lower jaw are scanned. Further, when the subject 2 has the mouth closed, that is, the maxilla and the mandible are in an occlusal state, the teeth located in the maxilla and the mandible are scanned.

In this way, when the oral cavity is scanned by the three-dimensional scanner 200, not only the defective tooth (defective part), but also the adjacent tooth adjacent to the defective tooth, the opposing tooth facing the defective tooth, and the tooth adjacent to the opposing tooth. , At least one of the three-dimensional data of each tooth in the state where the dentition of the upper jaw and the dentition of the lower jaw are meshed with each other, and the tooth on the opposite side (scanner) of the defective tooth is input to the data generator 100. Tooth. At this time, if the missing tooth is an abutment tooth or a tooth having a tooth cavity, the user may specify a margin line on the outer edge of the missing portion. Such designation of the margin line may be realized by the function of detecting the edge line.

Next, the generation unit 1104 of the data generation device 100 defines a spatial grid (three-dimensional grid) in the image embodied based on the three-dimensional data (STEP 2). The spatial lattice is a space that defines the three-dimensional position of the defective tooth and the tooth adjacent to the defective tooth in the three-dimensional space specified by the three-dimensional data of the dentition. More specifically, the spatial lattice is, for example, in a three-dimensional space having a size predetermined times larger than the defective tooth (for example, 1.5 times the size of the defective tooth), and the X-axis (for example, lateral to the tooth). Oriental axes), Y-axis (eg, tooth depth axis), and Z-axis (eg, tooth height axis) are defined, and objects that exist in space on each axis. A space for recording presence / absence information or a space for generating prosthesis data.

For example, FIG. 6 shows a spatial grid when the missing tooth is an abutment tooth. As shown in FIG. 6, a grid-like spatial grid is defined so as to surround the periphery of the abutment tooth which is a missing tooth.

In this way, by making the space lattice larger than the defective tooth, not only the defective tooth but also the adjacent tooth adjacent to the defective tooth, the opposing tooth facing the defective tooth, and the defective tooth in the tooth adjacent to the opposing tooth. The presence / absence information can also be recorded for a part of the side. Therefore, the spatial grid is set centered on the defective tooth to include adjacent teeth, opposed teeth, and a portion of the teeth adjacent to the opposed teeth. Further, by limiting the size of the space grid to a predetermined size, the load of arithmetic processing when the generation model 114 that generates the prosthesis data is machine-learned is reduced as compared with the case where the size of the space grid is not limited. be able to.

Next, the generation unit 1104 identifies adjacent teeth adjacent to the defective tooth corresponding to the defective portion included in the defined spatial lattice, opposed teeth facing the defective tooth, and teeth adjacent to the opposed tooth (STEP 3). .. Specifically, the generation unit 1104 has specific information (for example, "1") at a position corresponding to the contour of each tooth in the XX cross section of the defective tooth, the adjacent tooth, the facing tooth, and the tooth adjacent to the facing tooth. (Numbers such as numbers and specific colors) are linked.

In FIG. 5, the contour of a part of the right side of the adjacent tooth a is shown on the left side of the defective tooth, and the part of the left side of the adjacent tooth b is shown on the right side of the defective tooth, centering on the defective part (defective tooth). The contour of the lower right part of the facing tooth c is shown in the upper left of the missing tooth, and the lower left part of the tooth d adjacent to the facing tooth is shown in the upper right of the missing tooth. .. Then, specific information (for example, a number such as "1" or a specific color) is associated with each other along these contours. Thereby, the generation unit 1104 can specify the shape and position of the defective tooth, the adjacent tooth, the facing tooth, and the tooth adjacent to the facing tooth.

Next, the generation unit 1104 determines the shape of the prosthesis based on the shape and position of the identified defective tooth, adjacent tooth, facing tooth, and tooth adjacent to the facing tooth (STEP 4). Specifically, the generation unit 1104 has specific information (specific information) at a position corresponding to the contour of the prosthesis in the space surrounded by the contours of the defective tooth, the adjacent tooth, the opposing tooth, and the tooth adjacent to the facing tooth. In this example, "1") is associated. Thereby, the generation unit 1104 can determine the shape of the prosthesis based on the shape of the tooth adjacent to or facing the defect portion.

For example, the generation unit 1104 associates the specific information (“1”) so as to be in contact with the contours of the left and right adjacent teeth, and associates the specific information (“1”) so as to be in contact with the contours of the opposite teeth on the upper left and upper right. .. The space surrounded by the specific information associated in this way is formed so as to cover the defective tooth.

Although not shown, the generation unit 1104 can determine the shape of the prosthesis three-dimensionally by repeating STEP3 and STEP4 described above a plurality of times while shifting the XZ cross section in the Y-axis direction at predetermined intervals.

In this way, the generation unit 1104 can determine the shape (particularly the contour and height) of the prosthesis so as to make up for the defect, but since it does not recognize the type of tooth, before performing machine learning. Then, it is not possible to determine the shape suitable for the type of defective tooth. However, as described with reference to FIG. 4, the generation unit 1104 can determine a shape suitable for the type of the defective tooth by repeating machine learning based on the identification result fed back from the identification unit 1106.

For example, when the first molar of No. 6 is missing, the generation unit 1104 does not recognize that the number of the missing tooth is No. 6, so before performing machine learning, the first of No. 6 is performed. It is not possible to determine the shape of a prosthesis that has the characteristics of molars. However, the generation unit 1104 repeats machine learning based on the identification result fed back from the identification unit 1106, and eventually determines the shape of the prosthesis having the characteristics of the sixth first molar suitable for the type of the defective tooth. You will be able to do it.

The size of the prosthesis, the positional relationship between the prosthesis (defective tooth) and the adjacent tooth or the opposite tooth, the contact position between the prosthesis and the peripheral tooth in the meshed state, etc. differ depending on the patient to whom the prosthesis is applied. It is necessary to produce the optimal prosthesis for the patient. In view of this point, the generation unit 1104 according to the present embodiment is positioned based on the contact point between the prosthesis portion (defective tooth) and the peripheral tooth by using the spatial lattice as shown in FIGS. 5 and 6. The relationship can be identified and the optimal prosthesis shape can be determined. Also, areas that have no contact with the prosthesis (eg, labial side, buccal side, lingual side, palatal side, etc.) or areas that should not be contact (eg, occlusal groove, pit, etc.) ) Can be optimized by machine learning of feedback based on the identification result (determination result of tooth type) by the identification unit 1106.

As described above, the generation unit 1104 according to the present embodiment determines the shape of the prosthesis using the space grid, while the identification unit 1106 determines the portion that is difficult to determine only by using the space grid. It is configured to determine the optimum shape by machine learning of feedback based on the identification result. Thereby, the generation unit 1104 can generate the optimum prosthesis data according to the state of the teeth in the oral cavity of the patient.

Although not shown, the generation unit 1104 includes the dentition of the maxilla and the dentition of the mandible in addition to the adjacent tooth adjacent to the defective tooth, the facing tooth facing the defective tooth, and the tooth adjacent to the facing tooth. The shape of the prosthesis may be determined based on the shape and position of each tooth in the meshed state or the tooth on the opposite side of the defective tooth.

[Functional configuration at the practical stage of the data generator]
FIG. 7 is a schematic diagram showing a functional configuration of the data generation device 100 according to the present embodiment at a practical stage.

By the learning process described with reference to FIG. 4, each time the generation model 114 in the generation unit 1104 is machine-learned, the generation model 114 can generate prosthesis data for producing a more appropriate prosthesis. When the generation unit 1104 becomes able to generate prosthesis data for producing an appropriate prosthesis that meets the criteria, the user will use the data generation device 100 in a practical stage. That is, when the scanner system 10 equipped with the trained data generation device 100 is put on the market, the surgeon who is the user 1 acquires the prosthesis data for producing the prosthesis of the actual patient.

As shown in FIG. 7, since machine learning of the generation model 114 is not required at the practical stage, the data generation device 100 does not have to include the identification unit 1106 related to the learning process. When the operator acquires the three-dimensional data in the oral cavity of the actual patient using the three-dimensional scanner 200, the acquired three-dimensional data is input from the input unit 1102. The generation unit 1104 generates prosthesis data based on the three-dimensional data input from the input unit 1102 and the trained generation model 114. The prosthesis data generated by the generator 1104 is transmitted to the dental laboratory or the automated manufacturing apparatus 600. Then, based on the prosthesis data, a prosthesis suitable for the defective portion in the oral cavity of the patient is produced. When the user fine-tunes the generated prosthesis data after the prosthesis data is generated and finally completes the prosthesis, the completed prosthesis data is used as the correct answer data and the data generation model 114 is machine-learned. You may let me.

The data generation device 100 may include the identification unit 1106 even in the practical stage, and may further execute the learning process in the practical stage. In this way, even after the scanner system 10 equipped with the data generation device 100 is put on the market as a product, the generation model 114 is machine-learned based on the three-dimensional data in the oral cavity of an actual patient. be able to. Thereby, in the practical stage, the accuracy of the prosthesis data generated by the generation unit 1104 can be improved.

[Overall system configuration]
FIG. 8 is a schematic diagram showing the overall configuration of the system according to the present embodiment.

As shown in FIG. 8, the scanner system 10 is arranged in each of the plurality of locals A to C. For example, local A and local B are dental clinics, and in the dental clinic, the surgeon who is the user 1 acquires three-dimensional data including the teeth of the patient who is the subject 2 by using the scanner system 10. And generate prosthesis data. Further, the local C is a dental school, and in the dental school, the teacher or the student who is the user 1 acquires the three-dimensional data in the oral cavity of the subject who is the subject 2, and also generates the prosthesis data. The intraoral three-dimensional data and the prosthesis data acquired in each of the locals A to C are transmitted to the dental laboratory, which is the local D, via the network 5.

The three-dimensional data and the prosthesis data in the oral cavity acquired in each of the locals A to C may be output to the server device 500 arranged in the management center via the network 5. In the management center, the server device 500 accumulates and stores the three-dimensional data and the prosthesis data acquired from each of the locals A to C, and holds them as big data.

The server device 500 is not limited to the one arranged in a management center different from the local one such as a dental clinic, and may be arranged in the local one. For example, the server device 500 may be arranged in any one of the locals A to C. Further, a plurality of data generation devices 100 may be arranged in one local, and further, a server device 500 capable of communicating with the plurality of data generation devices 100 may be arranged in the one local. Further, the server device 500 may be realized in the form of a cloud service.

In the dental laboratory, three-dimensional data and prosthesis data in the oral cavity are aggregated from various places such as locals A to C. Therefore, the intraoral three-dimensional data and the prosthesis data held in the dental laboratory may be transmitted to the management center via the network 5, or may be transmitted to the management center via the network 5, or may be transmitted to the management center, or may be CD (Compact Disc) and USB (Universal Serial). Bus) It may be sent to the management center via a removable disk 550 such as a memory.

In addition, the three-dimensional data and the prosthesis data in the oral cavity may be sent to the management center from each of the locals A to C via the removable disk 550 without going through the network 5. In addition, three-dimensional data and prosthesis data in the oral cavity may be sent to each other via the network 5 or the removable disk 550 between each of the locals A to C.

The generation model 114 held by the data generation devices 100 of each local A to C may be shared among the data generation devices 100 of each local A to C.

Further, the server device 500 may have a function of prosthesis data generation processing. For example, each local A to C transmits the acquired three-dimensional data in the oral cavity to the server device 500, and the server device 500 receives each of the three-dimensional data received from each local A to C and the generation held by itself. Prosthesis data for each may be generated based on the model. Then, the server device 500 may transmit the prosthesis data to each local A to C or the dental laboratory. In this way, the data generation devices 100 of each of the locals A to C may share the generation model held by the server device 500 in the form of a cloud service. By doing so, each of the locals A to C can cause the server device 500 to generate the prosthesis data only by transmitting the three-dimensional data to the server device 500.

Further, the data generation devices 100 of the locals A to C may machine-learn the discriminative model 116 based on the three-dimensional data sent to each other.

The discriminative model 116 held by the data generation devices 100 of each local A to C may be shared among the data generation devices 100 of each local A to C.

Further, the server device 500 may have a function of identification processing in the data generation device 100. For example, each local A to C transmits the generated prosthesis data to the server device 500, and the server device 500 uses the prosthesis data received from each local A to C and the discriminative model held by the server device 500. Based on this, the identification result of the tooth type in each may be calculated. Then, the server device 500 may transmit each identification result to each local A to C, and each local A to C may feed back the identification result received from the server device 500 to the generation unit 1104. In this way, the data generation devices 100 of each local A to C may share the identification model held by the server device 500 in the form of a cloud service. By doing so, each local A to C can make the server device 500 identify whether or not the prosthesis data is appropriate only by transmitting the prosthesis data to the server device 500.

[Hardware configuration of data generator]
FIG. 9 is a schematic diagram showing a hardware configuration of the data generation device 100 according to the present embodiment. The data generation device 100 may be realized by, for example, a general-purpose computer or a computer dedicated to the scanner system 10.

As shown in FIG. 9, the data generation device 100 has a scanner interface 102, a display interface 103, a peripheral device interface 105, a network controller 106, a media reader 107, and a PC display 108 as main hardware elements. A memory 109, a storage 110, and an arithmetic unit 130.

The scanner interface 102 is an interface for connecting the three-dimensional scanner 200, and realizes data input / output between the data generation device 100 and the three-dimensional scanner 200.

The display interface 103 is an interface for connecting the display 300, and realizes data input / output between the data generation device 100 and the display 300. The display 300 is composed of, for example, an LCD (Liquid Crystal Display) or an organic ELD (Electroluminescence Display).

The peripheral device interface 105 is an interface for connecting peripheral devices such as a keyboard 601 and a mouse 602, and realizes data input / output between the data generation device 100 and the peripheral devices.

The network controller 106 is a device located in a dental laboratory, a server device 500 located in a management center, an automated manufacturing device 600, and another locally located data generation device 100 via the network 5. Send and receive data to and from each. The network controller 106 supports any communication method such as Ethernet (registered trademark), wireless LAN (Local Area Network), and Bluetooth (registered trademark).

The media reading device 107 writes various data such as three-dimensional data and prosthesis data to the removable disk 550 and reads them from the removable disk 550.

The PC display 108 is a display dedicated to the data generation device 100. The PC display 108 is composed of, for example, an LCD or an organic EL display. In the present embodiment, the PC display 108 is separate from the display 300, but may be shared with the display 300.

The memory 109 provides a storage area for temporarily storing a program code, a work memory, or the like when the arithmetic unit 130 executes an arbitrary program. The memory 109 is composed of, for example, a volatile memory device such as a DRAM (Dynamic Random Access Memory) or a SRAM (Static Random Access Memory).

The storage 110 provides a storage area for storing various data necessary for identification processing, learning processing, prosthesis data generation processing, and the like. The storage 110 is composed of, for example, a hard disk or a non-volatile memory device such as an SSD (Solid State Drive).

The storage 110 includes scan information 112, a generation model 114, an identification model 116, generation condition data 119, an identification program 120, a learning program 121, a data generation program 125, and an OS (Operating System) 127. And store.

The scan information 112 includes the three-dimensional data 122 in the oral cavity acquired by the three-dimensional scanner 200, the identification result 124 by the identification process executed based on the three-dimensional data 122, and the prosthesis generated by the prosthesis data generation process. Includes object data 123. The identification result 124 and the prosthesis data 123 are stored in the storage 110 in association with the three-dimensional data 122.

The identification program 120 is a program for executing the identification process. The learning program 121 is a program for executing the learning process of the generation model 114. The data generation program 125 is a program for executing the prosthesis data generation process.

The generation condition data 119 is data referred to when the prosthesis data is generated in the prosthesis data generation process, and is adjacent to the defective portion specified based on the three-dimensional data in the oral cavity acquired by the three-dimensional scanner 200. Includes data to identify conditions for determining the shape of the prosthesis based on the shape of the matching adjacent tooth, the facing tooth facing the defect, or the facing tooth and the adjacent tooth. For example, as described with reference to FIGS. 5 and 6, the generation condition data 119 is a condition for defining a spatial grid (three-dimensional grid), adjacent teeth, opposed teeth, and adjacent teeth and adjacent teeth. It includes conditions for specifying the shape, conditions for determining the shape of the prosthesis, and the like. It should be noted that the referenced data may include data for identifying the margin of the missing tooth.

The arithmetic unit 130 is an arithmetic unit that executes various processes such as identification processing, learning processing, and prosthesis data generation processing by executing various programs, and is an example of a computer. The arithmetic unit 130 is composed of, for example, a CPU (Central Processing Unit) 132, an FPGA (Field-Programmable Gate Array) 134, a GPU (Graphics Processing Unit) 136, and the like.

[Flowchart of learning process]
FIG. 10 is a flowchart for explaining the learning process executed by the data generation device 100 according to the present embodiment. Each step shown in FIG. 10 is realized by the arithmetic unit 130 of the data generation device 100 executing the OS 127, the identification program 120, the learning program 121, the data generation program 125, and the like.

As shown in FIG. 10, the data generation device 100 determines whether or not the start condition of the learning process is satisfied (S1). The start condition may be, for example, any one that is satisfied when some action for executing the learning process is performed in the data generation device 100. For example, the start condition may be that the learning start icon of the learning application is operated by the user.

When the start condition is not satisfied (NO in S1), the data generation device 100 ends this process. On the other hand, when the start condition is satisfied (YES in S1), the data generation device 100 determines whether or not the three-dimensional data has been input (S2). For example, the data generation device 100 determines whether or not a sufficient amount of three-dimensional data has been input to generate prosthesis data. The data generation device 100 repeats the process of S2 when a sufficient amount of three-dimensional data has not been input (NO in S2).

On the other hand, when a sufficient amount of three-dimensional data is input (YES in S2), the data generation device 100 reads out the generation condition data 119 (S3). After that, the data generation device 100 generates the prosthesis data according to the generation conditions specified by the generation condition data 119 based on the input three-dimensional data and the generation model 114 (S4).

Next, the data generation device 100 estimates the type of teeth of the prosthesis produced based on the generated prosthesis data based on the machine-learned discrimination model 116 (S5). Next, the data generation device 100 compares the estimation result of the tooth type of the prosthesis obtained in S5 with the type of the missing tooth input as the correct answer data (S6).

The data generation device 100 determines whether or not the estimation result of the tooth type of the prosthesis obtained in S5 matches the type of the defective tooth input as the correct answer data (S7). When the estimation result of the tooth type of the prosthesis obtained in S5 matches the type of the defective tooth input as the correct answer data (YES in S7), the data generation device 100 ends this process.

On the other hand, the data generation device 100 adjusts the generation model 114 when the estimation result of the tooth type of the prosthesis obtained in S5 does not match the type of the missing tooth input as the correct answer data (NO in S7). (S8). For example, the data generation device 100 adjusts the neural network or parameters included in the generation model 114 to optimize the generation model 114. After that, the data generation device 100 returns to S4.

[Flowchart of prosthesis data generation process]
FIG. 11 is a flowchart for explaining the prosthesis data generation process executed by the data generation device 100 according to the present embodiment. Each step shown in FIG. 11 is realized by the arithmetic unit 130 of the data generation device 100 executing the OS 127, the identification program 120, and the data generation program 125.

As shown in FIG. 11, the data generation device 100 determines whether or not the start condition of the prosthesis data generation process is satisfied (S11). The start condition may be, for example, any condition that is satisfied when some action for executing the prosthesis data generation process is performed in the data generation device 100. Specifically, the start condition may be satisfied when the power supply of the three-dimensional scanner 200 is turned on, or the mode is switched to the mode corresponding to the prosthesis data generation process after the power supply of the three-dimensional scanner 200 is turned on. It may be established when it is done. Alternatively, the start condition may be satisfied when the start switch is operated after the icon corresponding to the prosthesis data generation process (for example, the AI assist icon) is operated and the icon is in the blinking state.

If the start condition is not satisfied (NO in S11), the data generation device 100 ends this process. On the other hand, when the start condition is satisfied (YES in S11), the data generation device 100 determines whether or not the three-dimensional data has been input (S12). For example, the data generation device 100 determines whether or not a sufficient amount of three-dimensional data has been input to generate prosthesis data. When a sufficient amount of three-dimensional data has not been input (NO in S12), the data generation device 100 repeats the process of S12.

On the other hand, when a sufficient amount of three-dimensional data is input (YES in S12), the data generation device 100 reads out the generation condition data 119 (S13). After that, the data generation device 100 generates the prosthesis data according to the generation conditions specified by the generation condition data 119 based on the input three-dimensional data and the generation model 114 (S14).

Next, the data generation device 100 outputs the generated prosthesis data to the dental laboratory, the automatic manufacturing device 600, or the server device 500 (S15). After that, the data generation device 100 ends this process.

[Main configuration]
As described above, the present embodiment includes the following disclosures.

The data generation device 100 is based on an input unit 1102 to which three-dimensional data including at least a missing tooth, which is a missing tooth, is input, and a three-dimensional data input from the input unit 1102 and a generation model 114. It is provided with a generation unit 1104 for generating prosthesis data for producing a prosthesis suitable for. The generation model 114 is machine-learned based on the discrimination result of whether or not the prosthesis data generated by the generation unit 1104 is appropriate.

As a result, the data generation device 100 generates more appropriate prosthesis data by machine learning the generation model 114 using the identification result of whether or not the prosthesis data generated based on the three-dimensional data is appropriate. You will be able to. Therefore, by using the data generation device 100, the user 1 does not need to digitally design the prosthesis data by himself / herself, and can more easily obtain an appropriate prosthesis.

The data generation device 100 includes an identification unit 1106 that identifies whether or not the prosthesis data generated by the generation unit 1104 is appropriate. The identification unit 1106 estimates the type of tooth corresponding to the prosthesis data generated by the generation unit 1104, and based on the estimation result of the tooth type and the type of tooth corresponding to the defective portion, the prosthesis data. Identify whether is appropriate.

As a result, the data generation device 100 determines whether the prosthesis data is appropriate based on the estimation result of the tooth type corresponding to the prosthesis data generated based on the three-dimensional data and the tooth type corresponding to the defective portion. By identifying the above, the generative model 114 can be machine-learned, so that appropriate prosthesis data suitable for the type of defective tooth can be generated. Therefore, by using the data generation device 100, the user 1 does not have to specify the type of tooth corresponding to the defective portion by himself / herself, and can more easily obtain an appropriate prosthesis.

The identification unit 1106 estimates the type of tooth corresponding to the prosthesis data based on the prosthesis data and the identification model 116 generated by the generation unit 1104, and the identification model 116 uses at least three-dimensional data including the teeth. Machine learning is performed based on the estimation result of the type of tooth that has been present and the type of tooth corresponding to the three-dimensional data.

As a result, the data generation device 100 can machine-learn the discrimination model 116 based on the estimation result of the tooth type using the three-dimensional data and the tooth type corresponding to the three-dimensional data. The accuracy of machine learning of the generative model 114 using the model 116 can be further improved.

In the three-dimensional data input from the input unit 1102, the tooth adjacent to the defective part, the tooth facing the defective part, the tooth adjacent to the tooth facing the defective part, and the dentition of the upper jaw and the dentition of the lower jaw meshed with each other. Further includes three-dimensional data of at least one of each tooth in the state and the tooth on the opposite side of the defective tooth corresponding to the defect site.

As a result, the data generation device 100 is at least one of the adjacent tooth, the opposing tooth, each tooth in the state where the maxillary dentition and the mandibular dentition are in mesh, and the tooth on the opposite side of the defective tooth corresponding to the defective portion. Based on one three-dimensional data, the shape of the prosthesis can be determined in consideration of the shape and position of these teeth. Therefore, the user 1 can obtain a more appropriate prosthesis based on the shape and position of the teeth located around the defective portion.

The position data of the margin in the defective tooth is input to the input unit 1102. As a result, the data generation device 100 can determine the shape of the prosthesis in consideration of the margin of the missing tooth, so that the user 1 can obtain a more appropriate prosthesis.

The generation unit 1104 generates the prosthesis data based on the three-dimensional data input from the input unit 1102 and the generation model 114 according to a predetermined generation condition. Further, the predetermined generation condition includes a condition for determining the shape of the prosthesis based on the shape of the tooth adjacent to or facing the defect portion specified based on the three-dimensional data input from the input unit.

As a result, the data generation device 100 generates the prosthesis data according to the conditions for determining the shape of the prosthesis based on the shape of the teeth adjacent to or facing the defect portion specified based on the input three-dimensional data. Therefore, it is possible to generate prosthesis data more efficiently and more appropriately than determining the shape of the prosthesis without following predetermined conditions.

The three-dimensional data input from the input unit 1102 is three-dimensional data of a tooth row including at least a defective tooth, a tooth adjacent to the defective tooth, and a tooth facing the defective tooth, and the generation unit 1104 is a tooth row. Prosthesis data is generated based on a spatial lattice that defines the three-dimensional positions of the missing tooth, the tooth adjacent to the missing tooth, and the tooth facing the missing tooth in the three-dimensional space specified by the three-dimensional data of.

As a result, the data generation device 100 can generate the prosthesis data based on the spatial lattice that defines the three-dimensional position of the missing tooth and the tooth adjacent to the missing tooth in the three-dimensional space, so that the prosthesis data (missing part) can be generated. The positional relationship can be specified based on the contact point between the tooth) and the surrounding tooth, and the optimum shape of the prosthesis can be determined.

The scanner system 10 uses a three-dimensional camera to acquire at least three-dimensional data including the missing tooth, which is a missing tooth, and the three-dimensional scanner 200, and the scanner system 10 is based on the three-dimensional data acquired by the three-dimensional scanner 200. A data generation device 100 for generating prosthesis data for producing a prosthesis suitable for a defective portion is provided. The data generation device 100 is based on the input unit 1102 to which the three-dimensional data is input, the three-dimensional data input from the input unit 1102, and the generation model 114, and the prosthesis data for producing a prosthesis suitable for the defective portion. The generation unit 1104 and the generation unit 1104 are included. The generation model 114 is machine-learned based on the discrimination result of whether or not the prosthesis data generated by the generation unit 1104 is appropriate.

As a result, the data generation device 100 of the scanner system 10 machine-learns the generation model 114 by using the identification result of whether or not the prosthesis data generated based on the three-dimensional data is appropriate, so that the prosthesis is more appropriate. You will be able to generate data. Therefore, by using the data generation device 100 of the scanner system 10, the user 1 does not need to generate the prosthesis data by himself / herself, and can more easily obtain an appropriate prosthesis.

The data generation method is to prepare a prosthesis suitable for the missing part of the missing tooth based on the step (S12) in which the three-dimensional data including the missing tooth, which is at least the missing tooth, is input, and the three-dimensional data and the generation model 114. It includes a step (S14) of generating prosthesis data for the purpose. The generation model 114 is machine-learned based on the discrimination result of whether or not the prosthesis data generated by the generation step is appropriate.

As a result, according to the data generation method, more appropriate prosthesis data is generated by machine learning the generation model 114 using the identification result of whether or not the prosthesis data generated based on the three-dimensional data is appropriate. You will be able to. Therefore, by using the data generation method, the user 1 does not need to generate the prosthesis data by himself / herself, and can more easily obtain an appropriate prosthesis.

The data generation program 125 is based on the step (S12) in which three-dimensional data including at least the missing tooth, which is the missing tooth, is input to the computer (arithmetic unit) 130, and the three-dimensional data and the generation model 114. The step (S14) of generating the prosthesis data for producing the prosthesis suitable for the defect portion of the above is executed. The generative model 114 is machine-learned based on the discrimination result of whether or not the prosthesis data generated by the generated step is appropriate.

As a result, according to the data generation program 125, more appropriate prosthesis data is obtained by machine learning the generation model 114 by using the identification result of whether or not the prosthesis data generated based on the three-dimensional data is appropriate. Will be able to generate. Therefore, by using the data generation method, the user 1 does not need to generate the prosthesis data by himself / herself, and can more easily obtain an appropriate prosthesis.

[Modification example]
The present invention is not limited to the above examples, and various modifications and applications are possible. Hereinafter, modifications applicable to the present invention will be described.

(Learning process)
As shown in FIG. 4, the data generation device 100 according to the present embodiment inputs three-dimensional data including at least a defective tooth (defective portion), and based on the input three-dimensional data, provides a prosthesis that supplements the defective tooth. It was configured to generate prosthesis data for fabrication. At this time, as shown in FIGS. 5 and 6, the data generation device 100 determines the shape of the prosthesis so as to match the shape and position of the surrounding teeth such as the adjacent tooth and the facing tooth.

That is, the data generation device 100 according to the present embodiment performs machine learning about the shape of the prosthesis without correct answer data. Here, FIG. 12 is a schematic diagram showing a functional configuration in the learning stage of the data generation device according to the modified example. As shown in FIG. 12, the data generation device 100a according to the modified example regards an arbitrary tooth having a predetermined shape as a defective tooth and is based on three-dimensional data of a dentition including a tooth other than the arbitrary tooth. , Prosthesis data for producing a prosthesis corresponding to the arbitrary tooth may be generated. Further, the generative model 114a may be machine-learned using the three-dimensional data of the dentition that does not exclude arbitrary teeth as the correct answer data.

Specifically, as shown in FIG. 12, in the data generation device 100a, in the input unit 1102a, as three-dimensional data, three-dimensional data of a dentition including teeth other than the arbitrary teeth, excluding any teeth. Is entered. The generation unit 1104a generates prosthesis data for producing a prosthesis that fits any tooth removed, based on the three-dimensional data input from the input unit 1102a and the generation model 114a. The three-dimensional data input to the input unit 1102a is not limited to data excluding arbitrary teeth, and may be data in which arbitrary teeth are specified. In this case, the generation unit 1104a generates the prosthesis data based on the adjacent tooth adjacent to the specified arbitrary tooth, the facing tooth facing the arbitrary tooth, or the tooth adjacent to the facing tooth. That is, when designating an arbitrary tooth, the generation unit 1104a does not consider the designated arbitrary tooth, but considers the teeth around it, and generates the prosthesis data of the arbitrary tooth.

The identification unit 1106a identifies whether or not the prosthesis data is appropriate based on the prosthesis data generated by the generation unit 1104a and the correct answer data input by the user 1. Specifically, the identification unit 1106a identifies whether or not the shape of the prosthesis produced based on the prosthesis data generated by the generation unit 1104a matches the shape of any tooth input as correct answer data. do.

The identification result obtained by the identification unit 1106a is fed back to the generation unit 1104a. The generation model 114a is machine-learned based on the identification result fed back from the identification unit 1106a.

For example, the generative model 114a includes a neural network (not shown) and parameters used by the neural network. In machine learning, the generative model 114a does not update the parameter if it is determined based on the discrimination result that the shape of the prosthesis corresponding to the prosthesis data generated by itself matches the shape of any tooth which is the correct answer data. If it is determined that they do not match, the parameters are optimized by updating the parameters so that they match. In this way, the generative model 114a is machine-learned by optimizing the parameters. In the generative model 114a, the parameters are not limited to those updated, and the neural network (for example, the algorithm of the neural network) may be updated.

In the data generation device 100a, the prosthesis data is generated and identified by the generation unit 1104a for each tooth included in the dentition by sequentially changing any tooth as the three-dimensional data input to the input unit 1102a. The identification of the prosthesis data by 1106a and the machine learning of the generative model 114a based on the identification result fed back by the identification unit 1106a are repeated. As a result, the generative model 114a machine-learns the shape of each tooth while considering the shape of each tooth included in the dentition and the shape of the adjacent tooth adjacent to each tooth for each tooth included in the dentition. can do.

As described above, the data generation device 100a includes an identification unit 1106a for identifying whether or not the prosthesis data generated by the generation unit 1104a is appropriate. In the learning stage of the generative model 114a, the generation unit 1104a generates the prosthesis data for producing the prosthesis corresponding to the arbitrary tooth based on the three-dimensional data of the dentition excluding the arbitrary tooth and the generation model 114a. do. The identification unit 1106a identifies whether or not the prosthesis data is appropriate based on the prosthesis data generated by the generation unit 1104a and the three-dimensional data of any tooth.

As a result, the data generation device 100a prosthesis based on the shape of the prosthesis corresponding to the prosthesis data generated based on the three-dimensional data of the tooth row excluding any tooth and the shape of any tooth which is the correct answer data. By identifying whether the object data is appropriate or not, the generation model 114a can be machine-learned, so that the generation ability can generate appropriate prosthesis data suitable for any tooth shape. Can be improved. Therefore, the user 1 can more efficiently machine-learn the generative model 114a based on the shape of the tooth whose shape is predetermined.

In addition, the generation unit 1104a generates prosthesis data for each tooth by sequentially changing any tooth in the dentition. The identification unit 1106a identifies whether the prosthesis data generated by the generation unit 1104a is appropriate for each tooth.

As a result, the data generation device 100a can machine-learn the generation model 114a for the shape of each tooth included in the dentition, and thus can generate appropriate prosthesis data suitable for the shape of each tooth. As such, its generation capacity can be improved.

Further, if a large number of such dentition samples are prepared and machine learning as shown in FIG. 12 is performed for each sample, the data generation device 100a can generate more appropriate prosthesis data.

(Data to be input)
In the data generation device 100, the attribute data of the target person 2 who is the owner of the dentition may be input together with the three-dimensional data of the dentition. The attribute data includes attribute information (profile) regarding the subject 2 such as age, gender, race, height, weight, and place of residence. Further, the data generation device 100 may generate prosthesis data in consideration of the attribute information (profile) regarding the subject 2.

Generally, the shape of a tooth differs in its characteristics depending on heredity or living environment such as age, gender, race, height, weight, and place of residence. For example, in general, adult permanent teeth are larger than children's deciduous teeth, and both differ in shape. Also, in general, male teeth are larger than female teeth, and their shapes are different. Also, in general, Westerners' teeth tend to have a sharp tip so that they can easily bite off hard meat and bread, while Japanese teeth have a tip that makes it easy to grind soft rice and vegetables. Tends to be smooth. Therefore, if the generation model 114 is machine-learned based on the attribute information (profile), a prosthesis for producing a prosthesis suitable for the attribute information (profile) regarding the subject 2 in consideration of heredity or living environment. Data can be generated.

Further, in the data generation device 100, the three-dimensional data of the dentition and the motion data regarding the occlusal motion in at least one of the adjacent tooth and the facing tooth may be input. Occlusal movements include, for example, up and down movements of the lower jaw to grind food, back and forth movements of the lower jaw to grind food, and the like. Further, the data generation device 100 may generate prosthesis data in consideration of the occlusal movement in at least one of the adjacent tooth and the opposite tooth.

In this way, the movement data of the mandible when the mandible moves may be input to the input unit 1102. By doing so, the shape of the prosthesis can be determined in consideration of the mandibular movement data, so that the user 1 can obtain a more appropriate prosthesis.

It should be considered that the embodiments disclosed this time are exemplary in all respects and not restrictive. The scope of the present invention is shown by the scope of claims rather than the above description, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims. The configurations exemplified in this embodiment and the configurations exemplified in the modified examples can be appropriately combined.

1 user, 2 target person, 5 network, 10 scanner system, 100, 100a data generator, 102 scanner interface, 103 display interface, 105 peripheral device interface, 106 network controller, 107 media reader, 108,300 display, 109 memory , 110 storage, 112 scan information, 114, 114a generation model, 116 identification model, 119 generation condition data, 120 identification program, 121 learning program, 122 three-dimensional data, 123 prosthesis data, 124 identification result, 125 data generation. Program, 130 arithmetic unit, 200 three-dimensional scanner, 500 server equipment, 550 removable disk, 600 automatic manufacturing equipment, 601 keyboard, 602 mouse, 1102, 1102a input unit, 1104, 1104a generation unit, 1106, 1106a identification unit.

Claims (11)

A data generator that generates prosthesis data for producing tooth prostheses.
An input section where 3D data including at least the missing tooth, which is the missing tooth, is input,
A generation unit that generates prosthesis data for producing a prosthesis that matches the defect location of the defective tooth based on the three-dimensional data input from the input unit and the generation model.
It is provided with an identification unit for identifying whether or not the prosthesis data generated by the generation unit is appropriate.
In the learning stage of the generative model
The generation unit generates the prosthesis data for producing a prosthesis corresponding to the arbitrary tooth based on the three-dimensional data of the dentition including the tooth other than the arbitrary tooth and the generation model.
The identification unit estimates the type of tooth corresponding to the prosthesis data generated by the generation unit, and the prosthesis data is based on the estimation result of the tooth type and the arbitrary tooth type. Identify whether it is appropriate and
The generation model is a data generation device that is machine-learned based on the identification result of the identification unit. The identification unit estimates the type of tooth corresponding to the prosthesis data based on the prosthesis data and the identification model generated by the generation unit.
The data generation device according to claim 1, wherein the discriminative model is machine-learned based on an estimation result of a tooth type using at least three-dimensional data including teeth and a tooth type corresponding to the three-dimensional data. .. The generation unit generates the prosthesis data for each tooth by sequentially changing the arbitrary tooth in the dentition.
The data generation device according to claim 1 or 2, wherein the identification unit identifies whether or not the prosthesis data generated by the generation unit is appropriate for each tooth. The three-dimensional data input from the input unit includes teeth adjacent to the defect, teeth facing the defect, teeth adjacent to the tooth facing the defect, and dentition of the upper jaw and the dentition of the lower jaw. 13. Data generator. Claims 1 to claim that at least one of data of the position of the margin in the abutment tooth which is the missing tooth and the movement data of the mandible when the mandible moves is input to the input unit. The data generation device according to any one of 4. The one according to any one of claims 1 to 5, wherein the generation unit generates the prosthesis data based on the three-dimensional data input from the input unit and the generation model according to a predetermined generation condition. Data generator. The predetermined generation condition includes a condition for determining the shape of the prosthesis based on the shape of the tooth adjacent to or facing the defect portion specified based on the three-dimensional data input from the input unit. Item 6. The data generation device according to item 6. The three-dimensional data input from the input unit is three-dimensional data of a dentition including at least the defective tooth, the tooth adjacent to the defective tooth, and the tooth facing the defective tooth.
The generation unit is a spatial lattice that defines the three-dimensional positions of the defective tooth, the tooth adjacent to the defective tooth, and the tooth facing the defective tooth in the three-dimensional space specified by the three-dimensional data of the tooth row. The data generation device according to any one of claims 1 to 7, which generates the prosthesis data based on the above. A scanner system that acquires tooth shape information.
A 3D scanner that uses a 3D camera to acquire 3D data including at least the missing teeth, which are the missing teeth.
A data generator for generating prosthesis data for producing a prosthesis suitable for a defective portion of the defective tooth based on the three-dimensional data acquired by the three-dimensional scanner is provided.
The data generator is
An input unit into which the three-dimensional data is input and
A generation unit that generates prosthesis data for producing a prosthesis that matches the defect location based on the three-dimensional data and the generation model input from the input unit.
Includes an identification unit that identifies whether the prosthesis data generated by the generation unit is appropriate.
In the learning stage of the generative model
The generation unit generates the prosthesis data for producing a prosthesis corresponding to the arbitrary tooth based on the three-dimensional data of the dentition including the tooth other than the arbitrary tooth and the generation model.
The identification unit estimates the type of tooth corresponding to the prosthesis data generated by the generation unit, and the prosthesis data is based on the estimation result of the tooth type and the arbitrary tooth type. Identify whether it is appropriate and
The generated model is a scanner system that is machine-learned based on the identification result of the identification unit. It is a data generation method for generating prosthesis data for producing a tooth prosthesis by a computer.
The data generation method is a process executed by the computer.
A step in which 3D data including at least the missing tooth, which is the missing tooth, is input,
Based on the three-dimensional data and the generative model, a step of generating prosthesis data for producing a prosthesis suitable for the defective portion of the defective tooth, and a step of generating prosthesis data.
Including a step of identifying whether the prosthesis data generated by the generating step is appropriate.
In the learning stage of the generative model
The generation step generates the prosthesis data for producing a prosthesis corresponding to the arbitrary tooth based on the three-dimensional data of the dentition including the tooth other than the arbitrary tooth and the generation model.
The identification step estimates the tooth type corresponding to the prosthesis data generated by the generation step, and the prosthesis is based on the estimation result of the tooth type and the arbitrary tooth type. Identify whether the data is appropriate and
The generation model is a data generation method that is machine-learned based on the identification result of the identification step. A data generation program that generates prosthesis data for producing tooth prostheses.
The data generation program is installed in a computer.
A step in which 3D data including at least the missing tooth, which is the missing tooth, is input,
Based on the three-dimensional data and the generative model, a step of generating prosthesis data for producing a prosthesis suitable for the defective portion of the defective tooth, and a step of generating prosthesis data.
The step of identifying whether the prosthesis data generated by the generation step is appropriate is executed, and the step is executed.
In the learning stage of the generative model
The generation step generates the prosthesis data for producing a prosthesis corresponding to the arbitrary tooth based on the three-dimensional data of the dentition including the tooth other than the arbitrary tooth and the generation model.
The identification step estimates the tooth type corresponding to the prosthesis data generated by the generation step, and the prosthesis is based on the estimation result of the tooth type and the arbitrary tooth type. Identify whether the data is appropriate and
The generation model is a data generation program that is machine-learned based on the identification result of the identification step.

Images