JP2020188988A - Data processing device, data generation device, scanner system, data processing method, program for data processing, data generation method, and program for data generation - Google Patents

Abstract

To provide a data processing device, a data generation device, a scanner system, a data processing method, a program for data processing, a data generation method, and a program for data generation, capable of more simply creating an appropriate prosthesis.SOLUTION: A data processing device comprises: an acquisition unit 1141 for acquiring three-dimensional data on a tooth; an extraction unit 1142 that on the basis of an extraction model 1142a including extraction algorithm on which machine learning has been performed for extracting a latent variable from a plurality of pieces of data, extracts a latent variable on a feature of the tooth from the three-dimensional data acquired by the acquisition unit; and a storage unit 1143 for storing the latent variable extracted by the extraction unit.SELECTED DRAWING: Figure 12

Description

The present invention relates to a data processing apparatus, a data generating apparatus, a scanner system, a data processing method, a data processing program, 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.

JP-A-2000-74635

An operator 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 defective 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 so that the dental technician can create a prosthesis that fits the defect based on the 3D data. To do.

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

The present invention has been made to solve such a problem, and is used for a data processing device, a data generating device, a scanner system, a data processing method, and a data processing device that can more easily produce an appropriate prosthesis. It is an object of the present invention to provide a program, a data generation method, and a data generation program.

According to an example of the present disclosure, a data processing device for generating three-dimensional data of teeth is provided. The data processing device is acquired by the acquisition unit based on an acquisition unit that acquires three-dimensional data of teeth and an extraction model that includes a first algorithm that has been machine-learned to extract latent variables from a plurality of data. It includes an extraction unit that extracts latent variables related to tooth characteristics from the three-dimensional data, and a storage unit that stores the latent variables extracted by the extraction unit.

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 an acquisition unit that acquires at least three-dimensional data that includes at least peripheral teeth that are teeth located around the missing teeth that are missing teeth, and machine learning is performed to extract latent variables from multiple data. Based on the extraction model including the first algorithm, the extraction unit that extracts latent variables related to peripheral tooth characteristics from the three-dimensional data acquired by the acquisition unit and a plurality of latent variables related to tooth characteristics are accumulated in advance. A latent variable related to the characteristics of the peripheral teeth extracted by the extraction unit based on the storage unit and a generation model including a second algorithm that has been machine-learned to generate data based on a plurality of latent variables, and the storage unit. It is provided with a generation unit that generates prosthesis data for producing a prosthesis that matches the defective portion of the defective tooth by using the latent variables accumulated by.

According to an example of the present disclosure, a scanner system for acquiring tooth shape information is provided. The scanner system is a 3D scanner that uses a 3D camera to acquire 3D data that includes at least peripheral teeth that are teeth located around the missing tooth, which is a missing tooth, and a 3D scanner that is acquired by the 3D scanner. It is provided with a data generation device that generates prosthesis data for producing a prosthesis that matches the defective portion of the defective tooth based on the data. The data generator is based on an acquisition unit that acquires three-dimensional data including at least peripheral teeth and an extraction model that includes a first algorithm that has been machine-learned to extract latent variables from multiple data. To generate data based on a plurality of latent variables, an extraction unit that extracts latent variables related to peripheral tooth characteristics, and a storage unit that stores multiple latent variables related to tooth characteristics in advance from the three-dimensional data acquired by Based on the generation model including the second algorithm that was machine-learned in, the latent variables related to the characteristics of the peripheral teeth extracted by the extraction unit and the latent variables accumulated by the accumulation unit were used to determine the missing teeth. It includes a generator that generates prosthesis data for producing a prosthesis that fits the defect.

According to an example of the present disclosure, a data processing method for generating three-dimensional data of teeth is provided. The data processing method consists of a step of acquiring three-dimensional data including at least peripheral teeth that are teeth located around any tooth, and a first algorithm in which machine learning is performed to extract latent variables from a plurality of data. A step to extract latent variables related to peripheral tooth characteristics from the acquired three-dimensional data based on an extraction model including, and a second algorithm in which machine learning was performed to generate data based on multiple latent variables. Three-dimensional data of teeth of the same type as any tooth type, using the latent variables related to the extracted peripheral tooth characteristics and the latent variables related to the already accumulated tooth characteristics based on the generation model including And the step of identifying whether the three-dimensional data of the same type of tooth as the generated arbitrary tooth type is appropriate based on the three-dimensional data of any tooth input as the correct answer data. And include. 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 processing program for generating three-dimensional data of teeth is provided. The data processing program is machine-learned to acquire three-dimensional data including at least peripheral teeth, which are teeth located around any tooth, and to extract latent variables from multiple data. Based on the extraction model including the first algorithm, the step of extracting latent variables related to the characteristics of peripheral teeth from the acquired three-dimensional data and machine learning are performed to generate data based on multiple latent variables. Based on the generation model including the second algorithm, the latent variables related to the extracted peripheral tooth characteristics and the latent variables related to the accumulated tooth characteristics are used to obtain the same type of tooth as any type of tooth. Based on the step of generating 3D data and the 3D data of any tooth input as correct answer data, whether or not the 3D data of the same type of tooth as the generated arbitrary tooth type is appropriate. Perform the identification step. The generative model is machine-learned based on the identification result of the identification step.

According to an example of the present disclosure, there is provided a data generation method for generating prosthesis data for producing a tooth prosthesis. The data generation method includes the step of acquiring three-dimensional data including at least the peripheral teeth that are the teeth located around the defective teeth that are the missing teeth, and machine learning to extract the latent variables from multiple data. Based on the extraction model including the first algorithm, the steps of extracting latent variables related to the characteristics of peripheral teeth from the acquired three-dimensional data and machine learning to generate data based on multiple latent variables are performed. Based on the generation model including the second algorithm, the latent variables related to the extracted peripheral tooth characteristics and the latent variables related to the accumulated tooth characteristics are used to obtain a prosthesis suitable for the defective part of the defective tooth. Includes steps to generate prosthesis data for fabrication.

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 is a machine for acquiring three-dimensional data including at least the peripheral teeth of the teeth located around the missing teeth, which are the missing teeth, and extracting latent variables from multiple data. A machine to extract latent variables related to peripheral tooth characteristics from the acquired three-dimensional data based on an extraction model including the first algorithm that has been trained, and to generate data based on multiple latent variables. Based on the generation model including the second algorithm that was trained, the latent variables related to the extracted peripheral tooth characteristics and the latent variables related to the accumulated tooth characteristics are used to fit the defective part of the defective tooth. The step of generating prosthesis data for producing the prosthesis to be performed is executed.

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 processing apparatus which concerns on this embodiment. It is a schematic diagram which shows an example of the tooth to scan 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 processing apparatus which concerns on this embodiment. It is a schematic diagram which shows the functional structure of the data generation part which concerns on this embodiment. It is a schematic diagram which shows the functional structure in the practical stage of the data processing 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 processing apparatus which concerns on this embodiment. It is a schematic diagram for demonstrating the accumulation of latent variable data. It is a schematic diagram for demonstrating the accumulation of latent variable data. It is a schematic diagram which shows an example of the accumulated latent variable data. It is a schematic diagram which shows an example of the generation of prosthesis data in a learning stage. It is a schematic diagram which shows an example of the generation of prosthesis data in a practical stage. It is a flowchart for demonstrating the learning process executed by the data processing apparatus which concerns on this Embodiment. It is a flowchart for demonstrating the data generation processing executed by the data processing apparatus which concerns on this Embodiment.

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 view showing an application example of the data processing apparatus according to the present embodiment.

As shown in FIG. 1, the user 1 can acquire the three-dimensional shape data (three-dimensional data) of 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 school, a dental technician, a technician at a manufacturer, or a worker at a manufacturing factory. It 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 processing 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 oral cavity of the subject 2 to provide position information (for example, lateral direction, depth direction, and height of the teeth) of a plurality of points constituting the part to be scanned. The coordinates in the vertical direction) and color information (for example, the color of the surface of the tooth) are acquired by using an optical sensor or the like. The data processing 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 in the production of the prosthesis.

"Defective teeth" include teeth whose shape has been lost due to caries or therapeutic cutting, such as abutment teeth, tooth cavities, and implant bodies. "Prosthodontic prostheses" include 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 operator 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 carious portion. 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, a secondary caries may occur. Similarly, when the defective portion is prosthesis 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, a secondary caries will occur.

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 to the object and the distance between the tooth facing the defect (defective tooth) (hereinafter, also referred to as “opposite tooth”) and the prosthesis are 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 central incisors, lateral incisors, canines, first premolars, second premolars, first molars, second molars, and third premolars. , 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 prepare 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 is various, the appropriate prosthesis data is generated at the defective part. 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 processing device 100. It is configured to generate various prosthesis data.

Specifically, when the user 1 scans the oral cavity of the subject 2 using the three-dimensional scanner 200, the three-dimensional data including at least the missing teeth is input to the data processing device 100. The data processing device 100 automatically generates prosthesis data that matches the missing portion 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 processing 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 processing 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 processing 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 processing device 100. Will be done. By using AI, the scanner system 10 can also find tooth features that cannot be extracted by the user 1, which allows the user 1 to more easily obtain a suitable prosthesis.

[Example of teeth to be scanned]
FIG. 2 is a schematic view 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 incisor of the maxilla, 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 three-dimensional scanner 200 are dog teeth and molars of the upper jaw, the obtained three-dimensional image should include at least an image of a buccal part, a palatal side part, and an 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 a mandibular incisor, the obtained 3D image includes at least an image of the lower labial part, the lingual 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 lower jaw dog teeth and molars, the user so that the obtained 3D image includes at least images 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 upper labial surface is generally U-shaped, whereas in the case of maxillary canines, the buccal surface 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 central incision, a lateral incision, a canine, a first premolar, a second premolar, a first molar, and a second premolar, depending on the type and position. And the names such as the third molar. Further, in the oral cavity, each of the above-mentioned teeth is generally present on 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 canine is assigned number 3, the first premolar is assigned number 4, and the second premolar is assigned number 2. No. 5 is assigned, the first molar is assigned No. 6, the second molar is assigned No. 7, and the third molar is assigned No. 8.

[Functional configuration at the learning stage of the data processing device]
FIG. 4 is a schematic diagram showing a functional configuration in the learning stage of the data processing device 100 according to the present embodiment. The data processing device 100 may have a function of generating prosthesis data for producing a tooth prosthesis, and is also referred to as a “data generation device”.

As shown in FIG. 4, the data processing device 100 includes an input unit 1102, a data generation unit 1104, and an identification unit 1106. Each of these functions is realized by the arithmetic unit 130 of the data processing device 100, which will be described later, executing the OS 127, the identification program 120, the learning program 121, the data processing program 125, and the like. The data processing program 125 may include a process for generating prosthesis data, and is also referred to as a “data generation program”.

Three-dimensional data of teeth is input to the input unit 1102. The three-dimensional data input to the input unit 1102 is an arbitrary tooth, an adjacent tooth adjacent to the arbitrary tooth, an opposing tooth facing the arbitrary tooth, a tooth adjacent to the opposing tooth, and the opposite of the arbitrary tooth. Includes 3D data of at least one of the lateral teeth.

For example, with reference to FIG. 3, when any tooth is a canine (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 tooth (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 (No. 3) on the left side of the upper jaw include the canine (No. 3) on the left side of the lower jaw. Examples of the tooth adjacent to the opposite tooth facing the canine (No. 3) on the left side of the upper jaw include the lateral incisor (No. 2) or the first premolar (No. 4) on the left side of the lower jaw. Further, the tooth on the opposite side of any tooth is a tooth on the opposite side on the left and right in the dentition to which the arbitrary tooth belongs. For example, examples of the tooth on the opposite side of the canine (No. 3) on the left side of the maxilla include the canine (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) of each tooth included in the three-dimensional data such as an arbitrary tooth, an adjacent tooth, an opposing tooth, a tooth adjacent to the opposing tooth, and a tooth on the opposite side input by the user. Data (for example, the name or number of the tooth) for identifying the (or number) is entered.

As shown in FIG. 4, as an example of the learning stage, the input unit 1102 receives three-dimensional data of each tooth in a dentition in which an arbitrary tooth is omitted, and a type (name or number) of each tooth in the dentition. Data may be entered to identify.

The data generation unit 1104 includes a generation unit 1144 that generates three-dimensional data of teeth. For example, the generation unit 1144 generates three-dimensional data (hereinafter, also referred to as prosthesis data) suitable for any tooth based on the three-dimensional data input from the input unit 1102 and the generation model 1144a. The process of generating prosthesis data by the generation unit 1144 is also referred to as "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 1144 inputs the type (name) of each tooth included in the three-dimensional data input by the user. Or number) further to generate prosthesis data.

Here, the data generation unit 1104 will be specifically described with reference to FIG. FIG. 5 is a schematic diagram showing a functional configuration of the data generation unit 1104 according to the present embodiment. As shown in FIG. 5, the data generation unit 1104 has an acquisition unit 1141, an extraction unit 1142, an accumulation unit 1143, and a generation unit 1144.

The acquisition unit 1141 acquires the three-dimensional data input from the input unit 1102. The extraction unit 1142 extracts latent variables related to tooth characteristics from the three-dimensional data acquired by the acquisition unit 1141 based on the extraction model 1142a.

Specifically, the extraction model 1142a includes an algorithm (corresponding to the "first algorithm") that has been machine-learned to extract latent variables from a plurality of data. For example, the extraction model 1142a includes a neural network (not shown) and parameters used by the neural network. In the neural network of the extraction model 1142a, the intermediate layer has a multi-layer structure, so that processing by deep learning is performed. An existing one may be applied to the mechanism of the neural network of the extraction model 1142a.

The extraction unit 1142 has a function called an encoder, and by analyzing the three-dimensional data of the tooth acquired by the acquisition unit 1141 based on the extraction model 1142a, the characteristics of the tooth can be grasped from various aspects. Based on the results, potential variables that characterize the tooth type are extracted as latent variables from the three-dimensional data of the teeth. For example, the extraction unit 1142 extracts teeth such as tooth shape (overall size, overall shape, edge shape, etc.), tooth position, tooth color, and relationship with surrounding teeth (positional relationship, contact condition, etc.). For each element to be characterized, the characteristic one is extracted as a latent variable. The extraction unit 1142 is not limited to extracting one latent variable for each acquisition of three-dimensional data, but extracts a plurality of latent variables for each acquisition of three-dimensional data. May be good.

The storage unit 1143 stores data for identifying the latent variable extracted by the extraction unit 1142 (hereinafter, also referred to as “latent variable data”). The storage of latent variable data in the storage unit 1143 will be described later with reference to FIGS. 9 and 10.

The generation model 1144a of the generation unit 1144 includes an algorithm (corresponding to the “second algorithm”) in which machine learning is performed to generate data based on a plurality of latent variables. For example, the generative model 1144a includes a neural network (not shown) and parameters used by the neural network. In the neural network of the generative model 1144a, the intermediate layer has a multi-layer structure, so that processing by deep learning is performed. An existing one may be applied to the mechanism of the neural network of the generative model 1144a.

The generation unit 1144 has a function called a decoder, and when the three-dimensional data of each tooth in the tooth row in which the arbitrary tooth is omitted is acquired by the acquisition unit 1141, the arbitrary tooth is based on the generation model 1144a. Regarding the characteristics of peripheral teeth (for example, adjacent teeth adjacent to any tooth, opposing teeth facing any tooth, adjacent teeth adjacent to any tooth, teeth opposite to any tooth), which are teeth located around the Using the latent variable and the latent variable specified by the latent variable data already accumulated by the storage unit 1143, three-dimensional data (prosthesis data) suitable for any tooth is generated. For example, the generation unit 1144 generates three-dimensional data (prosthesis data) of teeth of the same type (name or number) as any tooth type (name or number).

In the data generation unit 1104 described above, as programs that perform 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.

Returning to FIG. 4, the prosthesis data generated by the generation unit 1144 is output to the identification unit 1106. The identification unit 1106 identifies whether or not the prosthesis data is appropriate based on the prosthesis data generated by the generation unit 1144 and the correct answer data input by the user. 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 tooth type (name or number) of the prosthesis matches any tooth type (name or number) input as correct 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 the present embodiment, whether or not the shape of the prosthesis produced based on the prosthesis data generated by the generation unit 1144 and the shape of the sample tooth input as the correct answer data match in the identification unit 1106. To identify.

For example, when the 6th first molar on the right side of the mandible is omitted as an arbitrary tooth, the user 1 inputs the 3D data corresponding to the 6th first molar as the correct answer data to the data processing device 100. Enter in advance. In the data processing device 100, when the intraoral three-dimensional data in which the sixth first molar is omitted is input, the generation unit 1144 is based on the input three-dimensional data and the generation model 1144a. As much as possible, we try to generate prosthesis data for producing a prosthesis with the characteristics of the 6th first molar. The identification unit 1106 compares the prosthesis data generated by the generation unit 1144 with the three-dimensional data corresponding to the sixth first molar pre-input by the user, and identifies whether or not the two match. To do.

The identification result obtained by the identification unit 1106 is fed back to the generation unit 1144. The generative model 1144a is machine-learned based on the identification result fed back from the identification unit 1106. The process of machine learning such a generative model 1144a is also referred to as "learning process".

For example, in the learning process, the generation model 1144a does not update the parameters if it is determined that the prosthesis data generated by the generation unit 1144 matches the correct answer data based on the identification result, but if it is determined that they do not match, both are not updated. The parameters are optimized by updating the parameters so that they match. The generation model 1144a is not limited to the case where the prosthesis data generated by the generation unit 1144 and the correct answer data completely match, and the degree of coincidence between the prosthesis data generated by the generation unit 1144 and the correct answer data is predetermined. If it exceeds the reference value of, it may be judged that the two match. As described above, in the learning process, the generative model 1144a is machine-learned by optimizing the parameters. In the generative model 1144a, 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 processing 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. Prior to learning, the generator 1144 cannot generate appropriate prosthesis data that fits any of the omitted teeth, but first, according to its own predictions, the prosthesis based on the three-dimensional data and the generative model 1144a. Try to generate data. The identification unit 1106 identifies whether or not the prosthesis data generated by the generation unit 1144 matches the correct answer data, and feeds back the identification result to the generation unit 1144. By machine learning the generative model 1144a based on the feedback identification result, the generation unit 1144 will generate appropriate prosthesis data so as to be closer to the correct answer data than before the learning. Further, by repeating such machine learning, the accuracy of prosthesis data generation by the generation unit 1144 is improved.

Further, when the type (name or number) of each tooth included in the three-dimensional data such as an arbitrary tooth, an adjacent tooth, an opposing tooth, a tooth adjacent to the opposing tooth, and a tooth on the opposite side is input to the input unit 1102. , The generation unit 1144 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 1144 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.

[Functional configuration at the practical stage of data processing equipment]
FIG. 6 is a schematic diagram showing a functional configuration of the data processing device 100 according to the present embodiment at a practical stage.

Each time the generation model 1144a in the generation unit 1144 is machine-learned by the learning process described with reference to FIGS. 4 and 5, the generation model 1144a can generate prosthesis data for producing a more appropriate prosthesis. Become. When the generation unit 1144 can generate prosthesis data for producing an appropriate prosthesis that meets the criteria, the user will use the data processing device 100 in a practical stage. That is, when the scanner system 10 equipped with the learned data processing 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. 6, since machine learning of the generative model 1144a is not required in the practical stage, the data processing 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 1144 generates prosthesis data based on the three-dimensional data input from the input unit 1102 and the trained generation model 1144a. The prosthesis data generated by the generator 1144 is transmitted to the dental laboratory or the automatic 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 correct answer data and the generation model 1144a is machine-learned. You may.

The data processing device 100 may include the identification unit 1106 even in the practical stage, and may also execute the learning process in the practical stage. In this way, even after the scanner system 10 equipped with the data processing device 100 is put on the market as a product, the generative model 1144a is machine-learned based on the three-dimensional data in the oral cavity of the actual patient. be able to. Thereby, in the practical stage, the accuracy of generating the prosthesis data by the generation unit 1144 can be improved.

[Overall system configuration]
FIG. 7 is a schematic diagram showing the overall configuration of the system according to the present embodiment.

As shown in FIG. 7, 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 student who is the user 1 acquires the three-dimensional data in the oral cavity of the subject who is the subject 2 and 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 located in any of the locals A to C. Further, a plurality of data processing devices 100 may be arranged in one local, and further, a server device 500 capable of communicating with the plurality of data processing 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 in the oral cavity and prosthesis data are collected from various places such as locals A to C. Therefore, the three-dimensional data and the prosthesis data in the oral cavity 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 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 in the oral cavity and the prosthesis data 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 the locals A to C.

The generation model 1144a held by the data processing devices 100 of each local A to C may be shared among the data processing devices 100 of each local A to C.

Further, the server device 500 may have the function of the data processing device 100. 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 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. As described above, the data processing devices 100 of the locals A to C may share the generation model held by the server device 500 in the form of a cloud service. In this way, each of the locals A to C can cause the server device 500 to generate the prosthesis data simply by transmitting the three-dimensional data to the server device 500.

[Hardware configuration of data processing device]
FIG. 8 is a schematic diagram showing a hardware configuration of the data processing device 100 according to the present embodiment. The data processing 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. 8, the data processing 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 are provided.

The scanner interface 102 is an interface for connecting the three-dimensional scanner 200, and realizes data input / output between the data processing 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 processing 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 processing 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 automatic manufacturing device 600, and another locally located data processing device 100 via a 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 reader 107 writes various data such as three-dimensional data and prosthesis data to the removable disk 550 and reads the data from the removable disk 550.

The PC display 108 is a display dedicated to the data processing 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 required for identification processing, learning processing, 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, an extraction model 1142a, a generation model 1144a, latent variable data 1143a, an identification program 120, a learning program 121, a data processing program (data generation program) 125, and the like. Stores OS (Operating System) 127.

The scan information 112 includes three-dimensional data 122 in the oral cavity acquired by the three-dimensional scanner 200, prosthesis data 123 generated by data generation processing based on the three-dimensional data 122, and identification processing for the prosthesis data 123. Includes the identification result 124 and. The prosthesis data 123 and the identification result 124 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 generative model 1144a. The data processing program 125 is a program for executing data generation processing, and is also referred to as a data generation program.

The latent variable data 1143a is data for identifying the latent variables extracted in the learning stage, and one or more latent variable data are accumulated in the storage 110. Not only in the learning stage, but also in the practical stage, latent variable data for identifying the latent variable may be stored in the storage 110 each time the latent variable is extracted. By doing so, it is possible to increase the latent variable data referred to when generating the prosthesis data not only in the learning stage but also in the practical stage, and it is possible to improve the accuracy of prosthesis data generation.

The arithmetic unit 130 is an arithmetic unit that executes various processes such as identification processing, learning processing, and 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.

[Accumulation of latent variable data]
An example of the accumulation of latent variable data in the learning stage will be described with reference to FIGS. 9 and 10. 9 and 10 are schematic diagrams for explaining the accumulation of latent variable data.

First, the accumulation of latent variable data performed for each tooth will be described with reference to FIG. 9. As shown in FIG. 9, in the learning stage, a latent variable related to the characteristics of the tooth is extracted by the extraction unit 1142 from the three-dimensional data of one arbitrary tooth. The latent variable data for identifying the latent variable extracted by the extraction unit 1142 is accumulated by the storage unit 1143.

For example, latent variables related to the characteristics of the third molar (No. 8) are extracted from the three-dimensional data of the third molar (No. 8) on the right side of the mandible and accumulated in the storage unit 1143. From the second molar (No. 7) on the right side of the mandible, latent variables related to the characteristics of the second molar (No. 7) are extracted and accumulated in the storage unit 1143. From the first molar (No. 6) on the right side of the mandible, latent variables related to the characteristics of the first molar (No. 6) are extracted and accumulated in the storage unit 1143. Latent variables related to the characteristics of the second premolar (No. 5) are extracted from the second premolar (No. 5) on the right side of the mandible and accumulated in the storage unit 1143. Latent variables related to the characteristics of the first premolar (No. 4) are extracted from the first premolar (No. 4) on the right side of the mandible and accumulated in the storage unit 1143.

Similarly, for the other teeth on the right side of the mandible and each tooth on the left side of the mandible, latent variables are extracted for each tooth and accumulated in the storage unit 1143. Further, not only the dental arch of the lower jaw but also the dental arch of the upper jaw, a latent variable is extracted for each tooth and accumulated in the storage unit 1143.

In this way, for each maxillary and mandibular dental arch, each tooth is an arbitrary tooth, and latent variables related to the characteristics of the tooth are accumulated. For example, for each tooth, each element that characterizes the tooth, such as the shape of the tooth (overall size, overall shape, edge shape, etc.), the position of the tooth, and the color of the tooth, is latent. It is extracted as a variable and stored in the storage unit 1143 as latent variable data.

Next, with reference to FIG. 10, the accumulation of latent variable data performed for each of a plurality of teeth will be described. As shown in FIG. 10, in the learning stage, latent variables related to the characteristics of the plurality of teeth are extracted by the extraction unit 1142 from the three-dimensional data of the plurality of teeth. The latent variable data for identifying the latent variable extracted by the extraction unit 1142 is accumulated by the storage unit 1143.

For example, from the three-dimensional data of the first molar (No. 6), the second molar (No. 7), and the third molar (No. 8) on the right side of the mandible, the first molar (No. 6) and the second molar. Latent variables related to the characteristics of the molars (No. 7) and the third molars (No. 8) are extracted and accumulated in the storage unit 1143. From the three-dimensional data of the second premolar (No. 5), the first molar (No. 6), and the second molar (No. 7) on the right side of the mandible, the second premolar (No. 5) and the first molar Latent variables related to the characteristics of (No. 6) and the second molar (No. 7) are extracted and accumulated in the storage unit 1143. From the three-dimensional data of the first premolar (No. 4), the second premolar (No. 5), and the first molar (No. 6) on the right side of the mandible, the first premolar (No. 4) and the second premolar Latent variables related to the characteristics of (No. 5) and the first molar (No. 6) are extracted and accumulated in the storage unit 1143. From the three-dimensional data of the canines (No. 3), first premolars (No. 4), and second premolars (No. 5) on the right side of the mandible, the canines (No. 3), first premolars (No. 4), and Latent variables related to the characteristics of the second premolar (No. 5) are extracted and accumulated in the storage unit 1143. From the three-dimensional data of the lateral incisors (No. 2), canines (No. 3), and first prescription teeth (No. 4) on the right side of the mandible, the lateral incisors (No. 2), canines (No. 3), and No. 1 Latent variables related to the characteristics of the small canine (No. 4) are extracted and accumulated in the storage unit 1143. From the three-dimensional data of the central incision (No. 1), lateral incision (No. 2), and canine (No. 3) on the right side of the mandible, the central incision (No. 1), lateral incision (No. 2), and canine The latent variable related to the feature (No. 3) is extracted and stored in the storage unit 1143.

Similarly, for the other teeth on the right side of the mandible and each tooth on the left side of the mandible, latent variables are extracted for each of the plurality of teeth and accumulated in the storage unit 1143. Further, not only in the dental arch of the lower jaw, but also in the dental arch of the upper jaw, latent variables are extracted for each of a plurality of teeth and accumulated in the storage unit 1143.

In this way, for each of the maxillary and mandibular dental arches, a plurality of teeth are grouped together as an arbitrary tooth, and latent variables related to the characteristics of the plurality of teeth are accumulated. For example, for each of multiple teeth, the shape of each tooth (overall size, overall shape, edge shape, etc.), the position of each tooth, the color of each tooth, and the relationship with surrounding teeth (positional relationship, contact condition). For each element that characterizes the tooth, such as), the characteristic element is extracted as a latent variable and stored in the storage unit 1143 as latent variable data.

It should be noted that the tooth is not limited to any tooth such as one tooth or a plurality of adjacent teeth, but the opposite tooth facing the arbitrary tooth, the tooth adjacent to the opposite tooth, and the opposite side of the arbitrary tooth (Hantaisoku). ), The latent variable may be extracted and accumulated in the storage unit 1143 in the same manner. In this way, the data processing apparatus 100 can generate prosthesis data suitable for the arbitrary tooth by using the latent variable regarding the characteristics of the tooth located around the arbitrary tooth.

[Example of latent variable data]
FIG. 11 is a schematic diagram showing an example of the accumulated latent variable data. For convenience of explanation, FIG. 11 shows the distribution of latent variable data when two latent variables are selected from a plurality of extracted latent variables and mapped in two dimensions. However, if there are many elements that characterize the teeth, The larger the number, the more the distribution of the latent variable data can be represented in many dimensions. In the figure, the latent variable represented by the horizontal axis is "Z (1)", and the latent variable represented by the vertical axis is "Z (2)".

As shown in FIG. 11, when two characteristic latent variables are selected from a plurality of latent variables and the latent variable data is mapped in two dimensions, the arrangement thereof is according to the type of tooth (tooth number). There is a tendency for places to gather. For example, the latent variable data extracted from the first tooth is represented by a white circle, and each data is located at a short distance. The latent variable data extracted from the second tooth is represented by a rhombus, and each data is located at a short distance. The latent variable data extracted from the third tooth is represented by a cross, and each data is located at a short distance. The latent variable data extracted from the 4th tooth is represented by a black circle, and each data is located at a short distance. The latent variable data extracted from the 5th tooth is represented by a star, and each data is located at a short distance. The latent variable data extracted from the 6th tooth is represented by a triangle, and each data is located at a short distance. The latent variable data extracted from the 7th tooth is represented by a white square, and each data is located at a short distance. The latent variable data extracted from the 8th tooth is represented by a black square, and each data is located at a short distance.

As described above, the shape is characteristic depending on the type of tooth, and the teeth of the same type have similar characteristics. Therefore, the latent variable data extracted for each tooth tends to take similar values between teeth of the same type.

[Generation of prosthesis data in the learning stage]
FIG. 12 is a schematic diagram showing an example of generation of prosthesis data in the learning stage. In the example shown in FIG. 12, in the learning stage, the three-dimensional data of each tooth in the dentition in which the three-dimensional data of the fifth tooth is omitted is input from the input unit 1102.

In the learning stage, the extraction unit 1142 extracts latent variables related to tooth characteristics from the three-dimensional data acquired by the acquisition unit 1141 based on the extraction model 1142a. Specifically, the extraction unit 1142 extracts latent variables related to the characteristics of the 4th and 6th teeth adjacent to the 5th tooth.

Here, as described with reference to FIGS. 9 to 11, a plurality of latent variable data have already been accumulated in the storage unit 1143, and for example, two selected characteristic latent variables are two-dimensional. It is mapped as the data distribution of. Based on the generative model 1144a, the generation unit 1144 uses the latent variable data corresponding to the 4th tooth and the latent variable data corresponding to the 6th tooth to generate the latent variable data corresponding to the 5th tooth. Identify and generate prosthesis data corresponding to the omitted 5th tooth based on the latent variable data corresponding to the 5th tooth.

The prosthesis data generated in this way is subjected to identification processing by the identification unit 1106, and the generation model 1144a is machine-learned by the feedback of the identification result.

[Generation of prosthesis data in the practical stage]
FIG. 13 is a schematic diagram showing an example of generation of prosthesis data in the practical stage. In the example shown in FIG. 13, in the practical stage, three-dimensional data of each tooth in the dentition lacking the fifth tooth is input from the input unit 1102.

In the practical stage, the extraction unit 1142 extracts latent variables related to tooth characteristics from the three-dimensional data acquired by the acquisition unit 1141 based on the extraction model 1142a. Specifically, the extraction unit 1142 extracts latent variables related to the characteristics of the 4th and 6th teeth adjacent to the 5th missing tooth.

Based on the generative model 1144a, the generation unit 1144 uses the latent variable data corresponding to the 4th tooth and the latent variable data corresponding to the 6th tooth to generate the latent variable data corresponding to the 5th tooth. Identify and generate prosthesis data corresponding to the 5th missing tooth based on the latent variable data corresponding to the 5th tooth.

In the above-mentioned example, the generation unit 1144 has latent variable data corresponding to the 4th tooth on the right side of the lower jaw as latent variable data corresponding to the "peripheral tooth" of the 5th missing tooth on the right side of the lower jaw to be prosthesis. , And, based on the latent variable data corresponding to the 6th tooth on the right side of the lower jaw, the prosthesis data corresponding to the 5th missing tooth on the right side of the lower jaw is generated, but the latent variable data corresponding to the other peripheral teeth. The prosthesis data corresponding to the 5th missing tooth on the right side of the lower jaw may be generated based on the above. For example, the generation unit 1144 identifies latent variable data corresponding to the 5th tooth on the right side of the upper jaw, which is the opposite tooth facing the 5th missing tooth on the right side of the lower jaw, and corresponds to the 5th tooth on the right side of the upper jaw. Based on the latent variable data, prosthesis data corresponding to the 5th missing tooth on the right side of the mandible may be generated.

In this way, the prosthesis data corresponding to the defective tooth is generated based on the three-dimensional data of the dentition including the defective tooth and the peripheral tooth of the defective tooth acquired by the three-dimensional scanner 200.

[Flowchart of learning process]
FIG. 14 is a flowchart for explaining the learning process executed by the data processing device 100 according to the present embodiment. Each step shown in FIG. 14 is realized by the arithmetic unit 130 of the data processing device 100 executing the OS 127, the identification program 120, the learning program 121, the data processing program (data generation program) 125, and the like. To program.

As shown in FIG. 14, the data processing 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 processing device 100. For example, the start condition may be that the learning start icon of the learning application is operated by the user.

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

On the other hand, when a sufficient amount of three-dimensional data is acquired (YES in S2), the data processing device 100 extracts latent variables of peripheral teeth located around an arbitrary tooth from the three-dimensional data based on the extraction model 1142a. (S3). The three-dimensional data includes at least three-dimensional data of peripheral teeth located around any tooth for which prosthesis data is to be generated.

The data processing device 100 generates three-dimensional data (prosthesis data) corresponding to an arbitrary tooth by using the extracted latent variable and the already accumulated latent variable based on the generative model 1144a (S4).

Next, the data processing device 100 compares the prosthesis data corresponding to the generated arbitrary tooth with the three-dimensional data corresponding to the arbitrary tooth which is the correct answer data (S5). When the two match (YES in S6), the data processing device 100 ends this processing. The data processing device 100 is not limited to the case where the generated prosthesis data and the correct answer data completely match, and when the degree of coincidence between the generated prosthesis data and the correct answer data exceeds a predetermined reference value, both of them You may decide that they match.

On the other hand, when the two do not match (NO in S6), the data processing device 100 adjusts the generation model 1144a (S7). For example, the data processing apparatus 100 adjusts the neural network or parameters included in the generative model 1144a to optimize the generative model 1144a. After that, the data processing device 100 returns to S3.

[Flowchart of data generation process]
FIG. 15 is a flowchart for explaining the data generation process executed by the data processing apparatus according to the present embodiment. Each step shown in FIG. 15 is realized by the arithmetic unit 130 of the data processing device 100 executing the OS 127, the identification program 120, the data processing program (data generation program) 125, and the like.

As shown in FIG. 15, the data processing apparatus 100 determines whether or not the start condition of the data generation processing is satisfied (S11). The start condition may be, for example, any one that is satisfied when some action for executing the data generation process is performed in the data processing 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 data generation processing after the power supply of the three-dimensional scanner 200 is turned on. It may be established at times. Alternatively, the start condition may be satisfied when the start switch is operated after the icon corresponding to the 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 processing device 100 ends this processing. On the other hand, when the start condition is satisfied (YES in S11), the data processing device 100 determines whether or not the three-dimensional data has been acquired (S12). For example, the data processing device 100 determines whether or not a sufficient amount of three-dimensional data has been acquired to generate prosthesis data. When the data processing device 100 has not acquired a sufficient amount of three-dimensional data (NO in S12), the data processing device 100 repeats the processing of S12.

On the other hand, when a sufficient amount of three-dimensional data is acquired (YES in S12), the data processing device 100 extracts latent variables of peripheral teeth located around the missing tooth from the three-dimensional data based on the extraction model 1142a. (S13). The three-dimensional data includes at least three-dimensional data of peripheral teeth located around the defective tooth for which the prosthesis data is to be generated.

The data processing device 100 generates prosthetic data for prosthesis of a defective tooth by using the extracted latent variable and the already accumulated latent variable based on the generation model 1144a (S14).

Next, the data processing 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 processing device 100 ends this processing.

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

The data processing device 100 is based on an acquisition unit 1141 that acquires three-dimensional data of teeth and an extraction model 1142a that includes an algorithm that has been machine-learned to extract latent variables from a plurality of data. It includes an extraction unit 1142 for extracting latent variables related to tooth characteristics from the acquired three-dimensional data, and a storage unit 1143 for accumulating latent variables extracted by the extraction unit 1142.

As a result, the data processing device 100 can extract and accumulate latent variables related to tooth characteristics from the acquired three-dimensional data. Therefore, the accumulated latent variables can be used to three-dimensionalize any tooth such as a defective tooth. Data (prosthesis data) can be generated. Therefore, by using the data processing 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 acquisition unit 1141 is at least one of an arbitrary tooth, a tooth adjacent to the arbitrary tooth, a tooth facing the arbitrary tooth, a tooth adjacent to the opposing tooth, and a tooth opposite to the arbitrary tooth. Acquire one 3D data.

As a result, the data processing device 100 can extract and accumulate latent variables related to tooth characteristics from at least one of three-dimensional data of adjacent teeth, opposing teeth, and teeth on the opposite side of any tooth. Therefore, it is possible to generate prosthesis data suitable for the arbitrary tooth in consideration of the characteristics of the peripheral tooth located around the arbitrary tooth.

The data processing device 100 includes a generation unit 1144 that generates three-dimensional data of an arbitrary tooth. The extraction unit 1142 extracts a latent variable related to the characteristics of the peripheral tooth from the three-dimensional data including at least the peripheral tooth which is a tooth located around the arbitrary tooth. The generation unit 1144 accumulates latent variables related to the characteristics of peripheral teeth extracted by the extraction unit 1142 based on the generation model 1144a including an algorithm in which machine learning is performed to generate data based on a plurality of latent variables. Using the latent variables accumulated by part 1143, three-dimensional data of teeth of the same type as any type of tooth is generated.

As a result, the data processing device 100 uses the latent variables extracted from the three-dimensional data of the peripheral teeth located around the arbitrary teeth and the latent variables already accumulated, and the prosthesis suitable for the arbitrary teeth. Since the data can be generated, the prosthesis data suitable for the arbitrary tooth can be generated in consideration of the characteristics of the peripheral teeth located around the arbitrary tooth.

The data processing device 100 determines whether or not the three-dimensional data of the tooth of the same type as the arbitrary tooth type generated by the generation unit 1144 is appropriate based on the three-dimensional data of any tooth input as the correct answer data. An identification unit 1106 for identifying is provided. The generative model 1144a is machine-learned based on the identification result by the identification unit 1106.

As a result, the data processing device 100 can machine-learn the generation model 1144a by identifying whether or not the generated three-dimensional data (prosthesis data) is appropriate, thus improving the accuracy of prosthesis data generation. Can be made to.

The data generation device (data processing device 100) has an acquisition unit 1141 that acquires at least three-dimensional data including peripheral teeth that are located around the missing tooth, which is a missing tooth, and extracts latent variables from a plurality of data. Based on the extraction model 1142a including the machine learning algorithm, the extraction unit 1142 that extracts the latent variables related to the characteristics of the peripheral teeth from the three-dimensional data acquired by the acquisition unit 1141 and the tooth characteristics in advance. Peripheral teeth extracted by extraction unit 1142 based on a storage unit 1143 that stores multiple latent variables related to and a generation model 1144a that includes an algorithm that has been machine-learned to generate data based on the plurality of latent variables. It is provided with a generation unit 1144 that generates prosthesis data for producing a prosthesis suitable for a defective part of a defective tooth by using a latent variable related to the characteristics of the above and a latent variable accumulated by the storage unit 1143.

As a result, the data generation device (data processing device 100) extracts latent variables related to the characteristics of the peripheral teeth from the acquired three-dimensional data, and uses the extracted latent variables and the already accumulated latent variables to delete the latent variables. Prosthesis data for producing a prosthesis that fits the missing part of the tooth can be generated. Therefore, the user 1 does not need to digitally design the prosthesis data by himself / herself, and can more easily obtain an appropriate prosthesis.

The scanner system 10 is acquired by a three-dimensional scanner 200 and a three-dimensional scanner 200 that acquire three-dimensional data including at least peripheral teeth that are teeth located around the missing tooth, which is a missing tooth, using a three-dimensional camera. It is provided with a data generation device (data processing device 100) that generates prosthesis data for producing a prosthesis that matches the defective portion of the defective tooth based on the three-dimensional data. The data generation device (data processing device 100) includes an extraction model 1142a including an acquisition unit 1141 that acquires three-dimensional data including at least peripheral teeth, and an algorithm that has been machine-learned to extract latent variables from a plurality of data. Extraction unit 1142 that extracts latent variables related to peripheral tooth characteristics from the three-dimensional data acquired by acquisition unit 1141 based on the above, and storage unit 1143 that stores a plurality of latent variables related to tooth characteristics in advance. Based on the generation model 1144a, which includes an algorithm that has been machine-learned to generate data based on the latent variables, the latent variables related to the characteristics of the peripheral teeth extracted by the extraction unit 1142 and the accumulation unit 1143 are accumulated. It includes a generator 1144 that generates prosthesis data for producing a prosthesis that fits the missing part of the missing tooth using a latent variable.

As a result, the data generation device (data processing device 100) of the scanner system 10 extracts latent variables related to the characteristics of the peripheral teeth from the acquired three-dimensional data, and extracts the extracted latent variables and the already accumulated latent variables. It can be used to generate prosthesis data for making a prosthesis that fits the missing part of the missing tooth. Therefore, by using the data generation device (data processing 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 processing method was a step (S2) of acquiring at least three-dimensional data including peripheral teeth that are teeth located around an arbitrary tooth, and machine learning was performed to extract latent variables from a plurality of data. A step (S3) of extracting latent variables related to peripheral tooth characteristics from the acquired three-dimensional data based on the extraction model 1142a including an algorithm, and machine learning to generate data based on a plurality of latent variables. A step to generate three-dimensional data of an arbitrary tooth by using the latent variable related to the extracted peripheral tooth characteristics and the latent variable related to the accumulated tooth characteristics based on the generation model 1144a including the obtained algorithm. Based on (S4) and the three-dimensional data of the tooth of the same type as the arbitrary tooth type input as the correct answer data, whether or not the three-dimensional data of the tooth of the same type as the generated arbitrary tooth type is appropriate. The step (S5) for identifying the data is included. The generative model 1144a is machine-learned based on the identification result of the identification step.

As a result, latent variables related to the characteristics of peripheral teeth are extracted from the acquired three-dimensional data, and prosthesis data suitable for any tooth is generated using the extracted latent variables and the latent variables that have already been accumulated. be able to. Therefore, the user 1 does not need to digitally design the prosthesis data by himself / herself, and can more easily obtain an appropriate prosthesis. Furthermore, more appropriate prosthesis data can be generated by machine learning the generative model 1144a using the identification result of whether or not the prosthesis data generated based on the acquired three-dimensional data is appropriate. Become.

The data processing program has a step (S2) of acquiring at least three-dimensional data including peripheral teeth, which are teeth located around arbitrary teeth, on a computer (computing device 130), and extracting latent variables from a plurality of data. A step (S3) of extracting latent variables related to peripheral tooth characteristics from the acquired three-dimensional data based on an extraction model 1142a including an algorithm that has been machine-learned to perform the data, and data based on a plurality of latent variables. Based on the generation model 1144a, which includes an algorithm that was machine-learned to generate, using the latent variables for the extracted peripheral tooth features and the latent variables for the accumulated tooth features. Based on the step (S4) of generating three-dimensional data of teeth of the same type as the tooth type of, and the three-dimensional data of any tooth input as correct answer data, the same type of any tooth generated. The step (S5) of identifying whether or not the three-dimensional data of the tooth is appropriate is executed. The generative model 1144a is machine-learned based on the identification result of the identification step.

As a result, latent variables related to the characteristics of peripheral teeth are extracted from the acquired three-dimensional data, and prosthesis data suitable for any tooth is generated using the extracted latent variables and the latent variables that have already been accumulated. be able to. Therefore, the user 1 does not need to digitally design the prosthesis data by himself / herself, and can more easily obtain an appropriate prosthesis. Furthermore, more appropriate prosthesis data can be generated by machine learning the generative model 1144a using the identification result of whether or not the prosthesis data generated based on the acquired three-dimensional data is appropriate. Become.

The data generation method includes a step (S12) of acquiring at least three-dimensional data including at least peripheral teeth of teeth located around the missing teeth, which is a missing tooth, and machine learning to extract latent variables from a plurality of data. Step (S13) to extract latent variables related to the characteristics of peripheral teeth from the acquired three-dimensional data based on the extraction model 1142a including the algorithm in which the above was performed, and to generate data based on a plurality of latent variables. Based on the generation model 1144a including the machine-learned algorithm, the latent variables related to the extracted peripheral tooth characteristics and the latent variables related to the accumulated tooth characteristics are used to fit the defective part of the defective tooth. This includes a step (S14) of generating prosthesis data for producing the prosthesis to be produced.

As a result, latent variables related to the characteristics of peripheral teeth are extracted from the acquired three-dimensional data, and the extracted latent variables and the latent variables that have already been accumulated are used to obtain prosthesis data that matches the defective part of the defective tooth. Can be generated. Therefore, 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 program includes a step (S12) of acquiring at least three-dimensional data including at least peripheral teeth, which are teeth located around the defective teeth, which are the missing teeth, on a computer (computing device 130), and from a plurality of data. A step (S13) of extracting latent variables related to peripheral tooth characteristics from the acquired three-dimensional data based on an extraction model 1142a including an algorithm in which machine learning was performed to extract latent variables, and a plurality of latent variables. Based on the generation model 1144a, which includes an algorithm that was machine-learned to generate data based on the variables, we used the extracted latent variables for peripheral tooth characteristics and the accumulated latent variables for tooth characteristics. Then, the step (S14) of generating the prosthesis data for producing the prosthesis suitable for the defective portion of the defective tooth is executed.

As a result, latent variables related to the characteristics of peripheral teeth are extracted from the acquired three-dimensional data, and the extracted latent variables and the latent variables that have already been accumulated are used to obtain prosthesis data that matches the defective part of the defective tooth. Can be generated. Therefore, the user 1 does not need to digitally design 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.

In the data processing device 100 (data generation device), 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 processing device 100 may generate prosthesis data in consideration of the attribute information (profile) regarding the subject 2.

In general, 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 through 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 generative model 1144a is machine-learned based on the attribute information (profile), a prosthesis for producing a prosthesis suitable for the attribute information (profile) related to the subject 2 in consideration of heredity or living environment. Data can be generated.

Further, in the data processing device 100 (data generation device), motion data related to the occlusal motion in at least one of the adjacent tooth and the opposing tooth may be input together with the three-dimensional data of the dentition. 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 processing device 100 may extract a latent variable for each tooth in consideration of the occlusal motion in at least one of the adjacent tooth and the opposing tooth, and the prosthesis data may be extracted by using the extracted latent variable. May be generated.

In this way, the movement data of the jaw when the jaw moves may be input to the input unit 1102. In this way, latent variables that take into account jaw movement data are accumulated in the learning stage. Further, in the practical stage, jaw motion data may be input in addition to the three-dimensional data of the peripheral teeth located around the defective tooth. In this way, the shape of the prosthesis can be determined in consideration of the jaw 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. In addition, the configuration exemplified in this embodiment and the configuration exemplified in the modified example can be appropriately combined.

1 user, 2 subjects, 5 networks, 10 scanner systems, 100 data processors, 102 scanner interfaces, 103 display interfaces, 105 peripherals interfaces, 106 network controllers, 107 media readers, 108,300 displays, 109 memories, 110 Storage, 112 scan information, 120 identification program, 121 learning program, 122 three-dimensional data, 123 prosthesis data, 124 identification result, 125 data processing program, 130 arithmetic unit, 200 three-dimensional scanner, 500 server equipment, 550 Removable disk, 600 automatic manufacturing device, 601 keyboard, 602 mouse, 1102 input unit, 1104 data generation unit, 1106 identification unit, 1141 acquisition unit, 1142 extraction unit, 1142a extraction model, 1143 storage unit, 1143a latent variable data, 1144 generation Part, 1144a generation model.

Claims (10)

It is a data processing device that generates three-dimensional data of teeth.
An acquisition unit that acquires 3D data of teeth,
Extraction to extract latent variables related to tooth features from the three-dimensional data acquired by the acquisition unit based on an extraction model including a first algorithm in which machine learning was performed to extract latent variables from a plurality of data. Department and
A data processing device including a storage unit that stores latent variables extracted by the extraction unit. The acquisition portion is at least one of an arbitrary tooth, a tooth adjacent to the arbitrary tooth, a tooth facing the arbitrary tooth, a tooth adjacent to the opposing tooth, and a tooth opposite to the arbitrary tooth. The data processing apparatus according to claim 1, which acquires one three-dimensional data or jaw movement data. It has a generator that generates 3D data of any tooth.
The extraction unit extracts latent variables related to the characteristics of the peripheral teeth from the three-dimensional data including at least the peripheral teeth that are the teeth located around the arbitrary teeth.
The generator includes latent variables related to the characteristics of the peripheral teeth extracted by the extractor based on a generative model including a second algorithm that has been machine-learned to generate data based on a plurality of latent variables. The data processing apparatus according to claim 1 or 2, wherein the latent variable accumulated by the storage unit is used to generate three-dimensional data of a tooth of the same type as the arbitrary tooth type. An identification unit that identifies whether or not the three-dimensional data of a tooth of the same type as the arbitrary tooth type generated by the generation unit is appropriate based on the three-dimensional data of the arbitrary tooth input as correct answer data. With
The data processing device according to claim 3, wherein the generative model is machine-learned based on the identification result by the identification unit. A data generator that generates prosthesis data for producing a tooth prosthesis.
An acquisition unit that acquires three-dimensional data including at least peripheral teeth that are teeth located around the defective teeth that are missing teeth,
Based on an extraction model including a first algorithm that has been machine-learned to extract latent variables from a plurality of data, latent variables related to the characteristics of the peripheral teeth are extracted from the three-dimensional data acquired by the acquisition unit. Extraction section and
A storage unit that stores multiple latent variables related to tooth characteristics in advance,
Based on a generative model that includes a second algorithm that has been machine-learned to generate data based on a plurality of latent variables, the latent variables related to the characteristics of the peripheral teeth extracted by the extraction unit and the storage unit A data generation device including a generation unit that generates prosthesis data for producing a prosthesis that matches the defective portion of the defective tooth by using the accumulated latent variables. A scanner system that acquires tooth shape information.
A 3D scanner that uses a 3D camera to acquire 3D data that includes at least peripheral teeth that are located around the missing tooth, which is a missing tooth.
A data generating device 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 acquisition unit that acquires three-dimensional data including at least the peripheral teeth, and
Based on an extraction model including a first algorithm that has been machine-learned to extract latent variables from a plurality of data, latent variables related to the characteristics of the peripheral teeth are extracted from the three-dimensional data acquired by the acquisition unit. Extraction section and
A storage unit that stores multiple latent variables related to tooth characteristics in advance,
Based on a generative model that includes a second algorithm that has been machine-learned to generate data based on a plurality of latent variables, the latent variables related to the characteristics of the peripheral teeth extracted by the extraction unit and the storage unit A scanner system including a generator that uses the accumulated latent variables to generate prosthesis data for producing a prosthesis that fits the defective portion of the defective tooth. It is a data processing method that generates three-dimensional data of teeth.
A step to acquire 3D data including at least peripheral teeth that are teeth located around any tooth, and
A step of extracting latent variables related to the characteristics of the peripheral teeth from the acquired three-dimensional data based on an extraction model including a first algorithm in which machine learning was performed to extract latent variables from a plurality of data.
Based on a generative model including a second algorithm that was machine-learned to generate data based on multiple latent variables, the extracted latent variables related to the characteristics of the peripheral teeth and the accumulated characteristics of the teeth. A step of generating three-dimensional data of a tooth of the same type as the above-mentioned arbitrary tooth type using a latent variable, and
Including a step of identifying whether or not the three-dimensional data of the same type of tooth as the generated arbitrary tooth type is appropriate based on the three-dimensional data of the arbitrary tooth input as the correct answer data.
The generative model is a data processing method that is machine-learned based on the identification result of the identification step. A data processing program that generates three-dimensional data for teeth.
The data processing program is installed in a computer.
A step to acquire 3D data including at least peripheral teeth that are teeth located around any tooth, and
A step of extracting latent variables related to the characteristics of the peripheral teeth from the acquired three-dimensional data based on an extraction model including a first algorithm in which machine learning was performed to extract latent variables from a plurality of data.
Based on a generative model including a second algorithm that was machine-learned to generate data based on multiple latent variables, the extracted latent variables related to the characteristics of the peripheral teeth and the accumulated characteristics of the teeth. A step of generating three-dimensional data of a tooth of the same type as the above-mentioned arbitrary tooth type using a latent variable, and
Based on the three-dimensional data of the arbitrary tooth input as the correct answer data, the step of identifying whether or not the three-dimensional data of the same type of tooth as the generated arbitrary tooth type is appropriate is executed.
The generative model is a data processing program that is machine-learned based on the identification result of the identification step. It is a data generation method for generating prosthesis data for producing a tooth prosthesis.
The step of acquiring three-dimensional data including at least the peripheral teeth that are the teeth located around the defective teeth that are the missing teeth, and
A step of extracting latent variables related to the characteristics of the peripheral teeth from the acquired three-dimensional data based on an extraction model including a first algorithm in which machine learning was performed to extract latent variables from a plurality of data.
Based on a generative model including a second algorithm that was machine-learned to generate data based on multiple latent variables, the extracted latent variables related to the characteristics of the peripheral teeth and the accumulated characteristics of the teeth. A data generation method including a step of generating prosthesis data for producing a prosthesis suitable for a defective portion of the defective tooth using a latent variable. A data generation program that generates prosthesis data for producing tooth prostheses.
The data generation program is installed in a computer.
The step of acquiring three-dimensional data including at least the peripheral teeth that are the teeth located around the defective teeth that are the missing teeth, and
A step of extracting latent variables related to the characteristics of the peripheral teeth from the acquired three-dimensional data based on an extraction model including a first algorithm in which machine learning was performed to extract latent variables from a plurality of data.
Based on a generative model including a second algorithm that has been machine-learned to generate data based on multiple latent variables, the extracted latent variables related to the characteristics of the peripheral teeth and the accumulated characteristics of the teeth. A data generation program that executes a step of generating prosthesis data for producing a prosthesis that matches the defective portion of the defective tooth by using a latent variable.