KR102250314B1 - Aligner apparatus manufacturing system using artificial intelligence and method using the same - Google Patents

Abstract

Provided are an orthodontic device manufacturing system and a method thereof using artificial intelligence. The orthodontic device manufacturing system using artificial intelligence according to an embodiment of the present invention comprises: a scanning unit which acquires a patient's dental structure as 3D image data; a data processing unit inputting the 3D image data and outputting image data in which gums and teeth are separately displayed; a database unit storing a plurality of pieces of clinical data; an image analysis unit outputting clinical data having the highest similarity by performing similarity determination between a result value of the data processing unit and the pieces of clinical data of the database unit; and an output unit manufacturing an orthodontic device on the basis of an output value of the image analysis unit. An optimized orthodontic device can be provided.

Description

Calibration device manufacturing system and calibration device manufacturing method using artificial intelligence {ALIGNER APPARATUS MANUFACTURING SYSTEM USING ARTIFICIAL INTELLIGENCE AND METHOD USING THE SAME}

The present invention relates to a calibration device manufacturing system and a calibration device manufacturing method using artificial intelligence.

The orthodontic device refers to a device that makes the patient's irregular teeth evenly. Since the calibration period is long and the existing calibration devices are not good in terms of aesthetics, transparent calibration devices have recently been in the spotlight.

Unlike general orthodontic devices, the transparent orthodontic device has no conspicuous structure, such as a metal wire or prosthesis, and thus has a transparent color and is superior in aesthetics compared to a general orthodontic device. Due to these advantages, it can be a good alternative for those who want to receive orthodontic treatment but avoid school treatment because they are concerned about adversely affecting their confidence in social life or interpersonal relationships.

In addition, it is possible to minimize discomfort in daily life due to the characteristic that can be pinched and removed. Because of these advantages, the market size related to transparent orthodontic devices is continuously expanding.

However, the patient's tooth condition is different, and there is a need to manufacture an optimized orthodontic device suitable for each tooth condition, and various technical attempts have been made for this.

Prior art, etc. related to a method of manufacturing a transparent orthodontic device are disclosed in Korean Patent Publication No. 2020-0109273.

Therefore, it is important to achieve the treatment purpose to reduce discomfort during wearing so that the user can wear the orthodontic device for a sufficient time.

The problem to be solved by the present invention is to provide a system for manufacturing an orthodontic device optimized for a patient's tooth condition.

Another problem to be solved by the present invention is to provide a system for manufacturing a customized orthodontic device suitable for a patient's treatment course.

The problem to be solved by the present invention is to provide a method of manufacturing an orthodontic device optimized for a patient's tooth condition.

Another problem to be solved by the present invention is to provide a method of manufacturing a customized orthodontic device suitable for a patient's treatment course.

The problems of the invention are not limited to the technical problems mentioned above, and other technical problems that are not mentioned will be clearly understood by those skilled in the art from the following description.

The orthodontic device manufacturing system using artificial intelligence according to an embodiment of the present invention for solving the above problems includes a scanning unit that acquires a patient's dental structure as 3D image data, and the gums and teeth are separated by inputting the 3D image data. Clinical data with the highest similarity by performing a similarity determination between a data processing unit that outputs image data that is displayed separately, a database unit that stores a plurality of clinical data, and a result value of the data processing unit and the plurality of clinical data of the database unit It includes an image analysis unit for outputting and an output unit for manufacturing a calibration device based on the output value of the image analysis unit.

In addition, the data processing unit converts the 3D image data into a point cloud object including a plurality of point objects, a weight setting unit that sets weights to the plurality of point objects, and the plurality of point objects. It may include a determination unit that samples by reflecting the set weight, and outputs the separate and outputs the gum and the tooth based on this.

In addition, the weight setting unit may set a relatively high weight of the point object disposed near the boundary between the gum and the tooth, the boundary between the tooth and the tooth, and a curve formed on the surface of the tooth.

Further, the image analysis unit may include an input unit for receiving a result value of the data processing unit and a plurality of clinical data stored in the database unit; And a similarity determination unit configured to output clinical data having the highest similarity by performing a similarity determination between the result value of the data processing unit and the plurality of clinical data of the database unit.

In addition, the similarity determination unit includes a first sub determination unit and a second sub determination unit, and the input unit quantitatively distributes the plurality of point objects and provides them to the first sub determination unit and the second sub determination unit, The first sub-determining unit and the second sub-determining unit may further include a synchro module that matches a result value of the second sub-determining unit.

The method of manufacturing an orthodontic device using artificial intelligence according to an embodiment of the present invention for solving the above problem includes the steps of obtaining a patient's dental structure as 3D image data, and separating the gums and teeth by inputting the 3D image data. Outputting the displayed image data, determining the similarity between the result value of the data processing unit and a plurality of clinical data stored in the database unit, and outputting the clinical data having the highest similarity, and the output value of the image analysis unit Including the step of outputting an orthodontic device as a basis, wherein the step of inputting the 3D image data and outputting the image data displayed by separating the gums and the teeth comprises converting the 3D image data to a point cloud including a plurality of point objects. Converting into an object, setting weights to the plurality of point objects; And sampling the plurality of point objects by reflecting the set weight, and separately outputting the gum and the tooth based on the sample, and a result value of the data processing unit and a plurality of clinical data stored in the database unit. The step of performing the similarity determination for and outputting the clinical data with the highest similarity may include quantitatively distributing the plurality of point objects, and dividing the distributed plurality of point objects into a first sub-determining unit and a second sub-determining unit. It may include determining the degree of similarity and matching a result value of the first sub-determining unit and the second sub-determining unit.

The means for solving the problem is not limited thereto, and more specific means are dealt with in more detail in the specification.

According to embodiments of the present invention, it is possible to provide an orthodontic device optimized for a patient's tooth condition.

Using artificial intelligence, it is possible to quickly and accurately manufacture calibration devices.

The effects according to the present invention are not limited by the contents exemplified above, and more various effects are included in the present specification.

1 is a block diagram of a system for manufacturing a calibration apparatus using artificial intelligence according to an embodiment of the present invention.
2 is a schematic diagram illustrating a system for manufacturing a calibration device using artificial intelligence according to an embodiment of the present invention.
3 is a partial block diagram of a system for manufacturing a calibration apparatus using artificial intelligence according to an embodiment of the present invention.
4 is a schematic diagram illustrating a system for manufacturing a calibration device using artificial intelligence according to an embodiment of the present invention.
5 is a schematic diagram illustrating a system for manufacturing a calibration device using artificial intelligence according to an embodiment of the present invention.
6 is a partial block diagram of a system for manufacturing a calibration apparatus using artificial intelligence according to an embodiment of the present invention.
7 is a partial block diagram of a system for manufacturing a calibration apparatus using artificial intelligence according to an embodiment of the present invention.
8 is a block diagram of a method of manufacturing a calibration device using artificial intelligence according to an embodiment of the present invention.

Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various forms different from each other, and only these embodiments make the disclosure of the present invention complete, and common knowledge in the technical field to which the present invention pertains. It is provided to completely inform the scope of the invention to the possessor, and the invention is only defined by the scope of the claims.

When elements or layers are referred to as “on” or “on” of another element or layer, it is possible to interpose other layers or other elements in the middle as well as directly above other elements or layers. All inclusive. On the other hand, when a component is referred to as "directly on" or "directly on", it means that no other components or layers are interposed therebetween.

The spatially relative terms "below", "beneath", "lower", "above", "on", "on", "top ( upper)" or the like may be used to easily describe a correlation between one component or components and another component or components, as shown in the drawings. Spatially relative terms should be understood as terms including different directions of a configuration during use or operation in addition to the directions shown in the drawings. For example, when the configuration shown in the drawing is reversed, the configuration described as "below" of the other configuration may be placed on the "top" of the other configuration. In addition, a configuration described as being located on the "left" side of another configuration based on the drawing may be located on the "right side" of another configuration depending on the viewpoint. Accordingly, the exemplary term “below” may include both directions below and above. The composition may be oriented in other directions, and in this case, terms that are spatially relative may be interpreted according to the orientation.

Although the first, second, and the like are used to describe various components, it goes without saying that these components are not limited by these terms. These terms are only used to distinguish one component from another component. Therefore, it goes without saying that the first component mentioned below may be the second component within the technical idea of the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In addition, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, one or more other features or numbers, The possibility of the presence or addition of steps, actions, components, parts, or combinations thereof is not precluded.

The same reference numerals are used for the same or similar parts throughout the specification.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

1 is a block diagram of a system for manufacturing a calibration device using artificial intelligence according to an embodiment of the present invention.

Referring to FIG. 1, a calibration device manufacturing system 300 using artificial intelligence according to an embodiment of the present invention includes a control unit 310, a communication unit 320, a database unit 330, a scan unit 340, and a data processing unit. 350, an image analysis unit 360 and an output unit 370 may be included.

The controller 310 may collectively control the calibration device manufacturing system 300 and/or a sub-configuration of the system using artificial intelligence.

That is, a lower configuration of the calibration device manufacturing system 300 using artificial intelligence or the calibration device manufacturing system 300 using artificial intelligence may be driven according to a control signal from the controller 310.

To this end, the control unit 310 may be physically and/or conceptually connected to all components included in the calibration device manufacturing system 300 using artificial intelligence.

In the present specification, "connection" may mean that data or signals are exchanged between them. That is, the connection may include a wireless and/or wired connection.

In one embodiment, the control unit 310 may be entirely hardware, partially hardware, or partially software. That is, the control unit may be understood as a concept collectively referring to a device for sending and receiving data of a specific format and content through an electronic communication method and software related thereto.

In an embodiment, when the controller 310 includes hardware, the controller 310 may include at least one processor. In an embodiment, the processor may include at least one selected from a central processing unit (CPU), a graphic processing unit (GPU), and a tensor processing unit (TPU). However, this is exemplary, and the type of processor is not limited thereto.

In addition, the control unit 310 may include a processor for deep learning. Specifically, the controller 310 may perform calculations for learning a neural network. That is, the controller 310 may perform calculations for learning a neural network, such as processing data for learning in deep learning, extracting features from input data, calculating errors, and updating weights of the neural network using backpropagation.

The communication unit 320 may provide a wired and/or wireless connection between each component and each component.

As a means for achieving this, the communication unit 320 may include a wired communication module for supporting wired communication and/or a wireless communication module for supporting wireless communication.

The wired communication module is, for example, in a wired communication network built according to technical standards or communication methods (Ehternet, PLC (Power Line Communication), home PNA, IEEE 1394, etc.) for wired communication. access point) and a communication interface for transmitting and receiving wired signals.

The wireless communication module includes technical standards or communication methods for wireless communication (e.g., WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), DLNA (Digital Living Network Alliance)), GSM (Global System for Mobile communication). ), Code Division MultiAccess (CDMA), Wideband CDMA (WCDMA), Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), etc.) It may include a communication interface for transmitting and receiving a radio signal with at least one of the. However, this is exemplary, and the configuration of the communication unit 320 is not limited thereto. That is, if it is a means for enabling data transmission and reception, it may be adopted as the communication unit 320.

The database unit 330 may store information required by the system.

In an embodiment, the database unit 330 may include an internal memory. More specifically, the database unit 330 is a volatile memory (for example, dynamic RAM (DRAM), static RAM (SRAM), synchronous dynamic RAM (SDRAM), etc.)) or non-volatile memory (for example, , OTPROM (one time programmable ROM), PROM (programmable ROM), EPROM (erasable and programmable ROM), EEPROM (electrically erasable and programmable ROM), mask ROM, flash ROM, NAND flash memory, NOR flash memory, etc.), SSD ( Solid State Drive).

Meanwhile, the database unit 330 may include an external memory according to an embodiment. More specifically, the database unit 330 is a flash drive, for example, CF (compact flash), SD (secure digital), Micro-SD (micro secure digital), Mini-SD (mini secure digital), xD (extreme digital) or Memory Stick may be further included.

The database unit 330 may store information that is based on the determination of the control unit 310. The information stored by the database unit 330 may be previously input information, or may be information provided from the server 300 or the external server 400 or other computing device using the communication unit 320.

In an embodiment, the database unit 330 may store clinical data of an existing orthodontic patient. This will be described in detail later.

The scanning unit 340 may acquire 3D image data of the user's teeth. To this end, the scan unit 340 may include an image acquisition means including a camera or the like.

2 is an example of image data of a user's dentition scanned by the scanning unit 340.

As illustrated in FIG. 2, the scanning unit 340 may acquire the user's dental structure as a three-dimensional image.

In one embodiment, the scanning unit 340 may obtain image data by scanning at least one selected from the user's maxillary oral structure 101, the mandibular oral structure 102, and the maxillary combined oral structure 103.

Referring back to FIG. 1, the calibration device manufacturing system 300 using artificial intelligence may include a data processing unit 350. The data processing unit 350 may process the image data of the user's teeth provided by the scanning unit 340.

For a detailed description of this, reference is made to FIG. 3.

3 is a partial block diagram of a system for manufacturing a calibration device using artificial intelligence according to an embodiment of the present invention.

Referring to FIG. 3, in an embodiment, the data processing unit 350 may include an object conversion unit 351, a weight setting unit 352, and a determination unit 353.

In one embodiment, the data processing unit 350 may be entirely hardware, partially hardware, or partially software. That is, the data processing unit 350 may be understood as a concept collectively referring to a device for sending and receiving data of a specific format and content in an electronic communication method and software related thereto.

In an embodiment, when the data processing unit 350 includes hardware, the data processing unit 350 may include at least one processor. In an embodiment, the processor may include at least one selected from a central processing unit (CPU), a graphic processing unit (GPU), and a tensor processing unit (TPU). However, this is exemplary, and the type of processor is not limited thereto.

In addition, the data processing unit 350 may include a processor for deep learning. In more detail, the data processing unit 350 may perform calculations for learning a neural network. That is, the data processing unit 350 may perform calculations for learning a neural network, such as processing data for learning in deep learning, extracting features from input data, calculating errors, and updating weights of the neural network using backpropagation. .

The lower configuration of the data processing unit 350 may also be hardware and/or software as described above. However, in this specification, the functions performed by each component will be classified and described.

The object conversion unit 351 may convert image data provided by the scan unit 340. Specifically, it is possible to process image data so that it is advantageous to be used for deep learning in the background.

In an embodiment, the object conversion unit 351 may convert image data provided by the scan unit 340 into point cloud object data. The point cloud object data may mean a group consisting of a plurality of point objects.

In general, since a tooth model is a three-dimensional object, it is not easy to apply segmentation deep learning optimized for a two-dimensional object.

When the object conversion unit 351 converts the image data provided by the scan unit 340 into point cloud object data, deep learning may be applied using a point net model.

Details about this are disclosed in the paper Dynamic Graph CNN for Learning on Point Clouds (ACM Transactions on GraphicsOctober 2019 Article No.: 146), etc., and some embodiments of the present invention may utilize at least some of the contents of the paper.

The object conversion unit 351 may convert 3D image data of the user's teeth into a plurality of point objects.

4 is a schematic diagram illustrating a system for manufacturing a calibration device using artificial intelligence according to an embodiment of the present invention.

Referring to FIG. 4, in order to improve the accuracy of determination, the point object conversion unit 351 may generate 200,000 or more point objects.

The weight setting unit 352 may set different weights for a plurality of point objects. The number of point objects generated by the object conversion unit 351 is too large, and thus, computing resources are consumed enormously in order to process all point objects, resulting in a decrease in production efficiency.

Accordingly, a step of sampling a part from a plurality of point objects may be performed.

The weight setting unit 352 may set different weights of the plurality of point objects. If the weight of the point object is set differently, the possibility of preferentially selecting a point having a high weight during the sampling process may increase.

In one embodiment, the weight setting unit 352 is relative to the boundary between a tooth and a gum in the user's dentition, a boundary portion between one tooth and another adjacent tooth, and a point object disposed in a curve disposed on the surface of one tooth. It can be given a high weight.

The sampled point object is later used as a basis for performing similarity analysis with existing clinical data. As described above, a portion having a high weight may be a factor that can significantly improve accuracy in determining the similarity of the dentition.

Referring back to FIG. 3, the determination unit 353 may sample a plurality of point objects. In an embodiment, the determination unit 353 may sample 18,000 to 22,000 point objects. As described above, among 18,000 to 22,000 point objects, a point object having a high weight may be included.

The determination unit 353 may separate and output a gum and a tooth and/or a tooth and a tooth based on image data including the sampled point object.

To this end, the determination unit 353 may include a neural network model that is trained by using image data of a tooth row converted into a plurality of point objects as a training data set.

In an embodiment, the neural network model included in the determination unit 353 may include a convolutional neural network (CNN).

When the determination unit 353 learns from the above-described learning data and inputs image data including the sampled point object, the gum and the tooth may be separated and output. Specifically, the gum and the tooth may be separated and displayed image data may be output.

5 illustrates a result image output by the determination unit 353.

Referring back to FIG. 1, as described above, the database unit 330 may store clinical data of existing patients.

In the present specification, the clinical data may include 3D image data showing the dentition of patients who have previously undergone correction and 3D image data of the dentition that changes according to the progress of the correction. In other words, the clinical data may include image data of multiple viewpoints or converted image data for one patient.

In addition, the clinical data may include three-dimensional data of the shape of the calibration device used in correspondence with the time when the calibration has elapsed, that is, the shape of the calibration device used at a certain time point in the course of the calibration.

In one embodiment, clinical data of existing patients may be stored through the processing process described above. Specifically, the clinical data of the 3D image data may be stored in the database unit 330 in a state that is converted into point cloud object data as described above.

In addition, clinical data stored in the database unit 330 may be processed by the data processing unit 350 and converted into point cloud object data.

The data processing unit 350 may output data in which the gums and teeth are separated and displayed using clinical data (three-dimensional image data) converted into point cloud object data.

The image analysis unit 360 may determine similarity between clinical data stored in the database unit 330 and image data (image data displayed by separating the gums and teeth) output from the data processing unit 350.

6 is a partial block diagram of a system for manufacturing a calibration device using artificial intelligence according to an embodiment of the present invention.

Referring to FIG. 6, the image analysis unit 360 may include an input unit 361 and a similarity determination unit 362.

In one embodiment, the image analysis unit 360 may be entirely hardware, partially hardware, or partially software. That is, the image analysis unit 360 may be understood as a concept collectively referring to a device for sending and receiving data of a specific format and content in an electronic communication method and software related thereto.

In an embodiment, when the image analysis unit 360 includes hardware, the image analysis unit 360 may include at least one processor. In an embodiment, the processor may include at least one selected from a central processing unit (CPU), a graphic processing unit (GPU), and a tensor processing unit (TPU). However, this is exemplary, and the type of processor is not limited thereto.

In addition, the image analysis unit 360 may include a processor for deep learning. Specifically, the image analysis unit 360 may perform calculations for learning a neural network. That is, the image analysis unit 360 can perform calculations for learning a neural network, such as processing data for learning in deep learning, extracting features from input data, calculating errors, and updating weights of the neural network using backpropagation. have.

The lower configuration of the data processing unit 350 may also be hardware and/or software as described above. However, in this specification, for convenience of description, functions performed by each component will be classified and described.

The input unit 361 may receive a result value of the data processing unit 350 and a plurality of clinical data stored in the database unit 330.

As described above, the result value of the data processing unit 350 may be image data that is displayed by separating the gums and teeth into a point cloud object.

In an embodiment, the clinical data input to the input unit 361 may be data having the same form as the result value of the data processing unit 350, that is, image data that has been converted into a point cloud object.

When the result value of the data processing unit 350 and clinical data are input to the input unit 361, the similarity determination unit 362 may determine the similarity by comparing the sampled point objects. To this end, the similarity determination unit 362 may include at least one neural network model. The neural network model included in the similarity determination unit 362 may include a Dynamic Graph CNN (DGCNN) model. In the case of using the DGCNN model, it is possible to very accurately determine the similarity of the transformed 3D image data.

The similarity determination unit 362 may find and output clinical data that is most similar to a result value of the data processing unit 350 from among a plurality of clinical data.

As described above, the clinical data may include dental image data at multiple times (according to the course of correction) of one patient. The image analysis unit 360 may not only find the clinical data of the patient most similar to the result value of the data processing unit 350, but also output the clinical data of the most similar time point among the patient's dentition change time points.

7 is a partial block diagram of a system for manufacturing a calibration device using artificial intelligence according to another embodiment of the present invention.

Referring to FIG. 7, in an embodiment, the similarity determination unit 362 of the image analysis unit 360 includes a first sub determination unit 363, a second sub determination unit 364, and a synchro module 365. I can.

In an exemplary embodiment, the input unit 361 may distribute the result value of the data processing unit 350 and provide it to the first and second sub-determiners 363 and 364, respectively.

The first sub-determining unit 363 and the second sub-determining unit 364 may include one or more processors. In an embodiment, the first sub-determining unit 363 and the second sub-determining unit 364 may include a GPU.

Specifically, the sampled point object can be quantitatively divided and distributed. In an exemplary embodiment in which the number of sampled point objects is 20,000, the input unit 361 provides 10,000, which is half of the point objects, to the first sub-determining unit 363, and the remaining 10,000 are provided to the second sub-determining unit 364 ) Can be provided. However, this is illustrative and is not limited thereto. In another embodiment, the number of point objects allocated to both may be differently applied according to the processing capability of the processor. That is, the number of point objects allocated according to the computing power of the first sub-determining unit 363 and the second sub-determining unit 364 may be differently applied. That is, if the first sub-determining unit 363 has a relatively higher computing power than the second sub-determining unit 364, the first sub-determining unit 363 has more points than the second sub-determining unit 364 You can allocate objects.

The first sub-determining unit 363 and the second sub-determining unit 364 may determine similarity to clinical data based on image data including point objects allocated to each of them.

In an embodiment, the similarity determination unit 365 may further include a synchro module 365. The synchro module may serve to determine an output value of the similarity determination unit 365 as one. For example, if the result values of the first sub-determining unit 363 and the second sub-determining unit 364 are different, the synchro module 365 redistributes the point object to determine again until the result values are the same, or It is possible to independently compare the similarity of the result values and select and output only one clinical data with high similarity.

The output unit 370 may output a calibration device corresponding to the corresponding clinical data based on a result value output from the image analysis unit 360. To this end, the output unit 370 may include a 3D printer.

In one embodiment, the calibration device output by the output unit 370 may be a transparent calibration device. In one embodiment, the transparent calibration device may refer to a calibration device that has light transmission or semi-transmission, and is made of a transparent resin and is not easily recognized from the outside. In an embodiment, the output unit 370 may output a calibration device corresponding to a corresponding result value based on the result value of the image analysis unit 360.

However, this is exemplary, and the method of manufacturing the calibration device by the output unit 370 is not limited thereto. That is, it should be understood that the output unit 370 includes all methods of implementing a physical entity based on the modeled image data.

When manufacturing the orthodontic device through the above-described method, it is possible to provide the most optimized orthodontic device to the patient by utilizing a plurality of clinical data. That is, the efficiency of orthodontic treatment can be improved by finding a case most similar to the patient's dental structure among a plurality of clinical data and applying the orthodontic device in the same manner as the case. In addition, it is possible to reduce the time required for orthodontic treatment by quickly providing the most suitable orthodontic device to the patient through the above-described data processing method and output method.

Hereinafter, a method of manufacturing a calibration device using artificial intelligence according to an embodiment of the present invention will be described. The method of manufacturing a calibration device using artificial intelligence may be substantially the same as the operation method of the calibration device manufacturing system using artificial intelligence described above. Therefore, duplicate explanations are omitted.

8 is a block diagram illustrating a method of manufacturing a calibration device using artificial intelligence according to an embodiment of the present invention.

Referring to FIG. 8, a method of manufacturing an orthodontic device using artificial intelligence according to an embodiment of the present invention includes the step of obtaining 3D image data by scanning a patient's dental structure (S01), preprocessing the 3D image data to The step of outputting image data in which the teeth and the teeth are separated (S02), the step of performing a similarity determination on the image data displayed by separating the gums and teeth and a plurality of clinical data stored in the database (S03), and the most similar And outputting the calibration device based on the clinical data (S04).

The step S01 of obtaining 3D image data by scanning the patient's dental structure may be performed by the scanning unit 340 as described above. The acquired patient's dentition structure can be preprocessed in the next step.

Subsequently, a step (S02) of preprocessing the 3D image data and outputting image data in which the gums and the teeth are separated and displayed may be performed.

Pre-processing the 3D image data to output image data in which the gums and teeth are separated and displayed (S02) is the step of converting the 3D image data into a point cloud object including a plurality of point objects, the plurality of point objects The step of setting a weight to the point cloud object may include sampling the point cloud object and outputting image data that is displayed by separating the gum and the tooth. Converting 3D image data to a point cloud object including a plurality of point objects, setting weights to the plurality of point objects, sampling the point cloud object to separate and display image data of gums and teeth The outputting step may be substantially the same as the operation method of the data processing unit 350 above.

Subsequently, a step (S03) of determining the degree of similarity with respect to the image data displayed by separating the gum and the tooth and a plurality of clinical data stored in the database may proceed. The step (S03) of determining the similarity between the image data displayed by separating the gums and the teeth and the plurality of clinical data stored in the database may be substantially the same as the operation method of the image analysis unit 360 described above.

Subsequently, the step of outputting the orthodontic device may proceed based on the output value of the step (S03) of performing similarity determination on image data displayed by separating the gums and teeth and a plurality of clinical data stored in the database. The output step may be performed in the output unit 370 described above. That is, the operation method of the output unit 370 may be substantially the same.

The operations according to the embodiments described above may be implemented at least partially as a computer program and recorded on a computer-readable recording medium. The recording medium in which a program for implementing the operation of the embodiments is recorded and the computer-readable recording medium includes all kinds of recording devices in which data that can be read by a computer is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tapes, floppy disks, and optical data storage devices. In addition, the computer-readable recording medium may be distributed over a computer system connected through a network, and computer-readable codes may be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing this embodiment may be easily understood by those of ordinary skill in the art to which this embodiment belongs.

In this specification, the term'~' may be understood as a concept including all units realized by hardware, units realized by software, or units partially realized by hardware and partially realized by software. .

Further, one unit may be realized by two or more hardware and/or software, and two or more units may be realized by one hardware and/or software.

In addition, the'~ unit' is not meant to be limited to hardware or software, and the'~ unit' may be configured to be in an addressable storage medium, or may be configured to reproduce one or more processors. Thus, for example,'~ unit' refers to components and processes such as software components, object-oriented software components, class components, and task components, functions, properties, procedures, subroutines, segments of program code, and drivers. , Firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables.

In addition, the components and functions provided in the'~ units' may be combined or separated into a smaller number of elements and the'~ units'. In addition, the components and the'~ unit' may be implemented to reproduce one or more processors (including CPU, GPU, etc.) of the device.

The embodiments of the present invention have been described above, but these are only examples and are not intended to limit the present invention, and those of ordinary skill in the field to which the present invention pertains should not depart from the essential characteristics of the embodiments of the present invention. It will be appreciated that various modifications and applications not illustrated above are possible. For example, each component specifically shown in the embodiment of the present invention can be modified and implemented. And differences related to these modifications and applications should be construed as being included in the scope of the present invention defined in the appended claims.

310: control unit
320: communication department
330: database unit
340: scan unit
350: data processing unit
360: image analysis unit
370: output

Claims (7)

A scanning unit for acquiring 3D image data by scanning at least one selected from the patient's maxillary oral structure, mandibular oral structure, and maxillary combined oral structure;
A data processing unit that inputs the 3D image data and outputs image data in which the gums and teeth are separated and displayed;
A database unit for storing a plurality of clinical data;
An image analysis unit for outputting clinical data having the highest similarity by determining a similarity between the result value of the data processing unit and the plurality of clinical data of the database unit; And
Including an output unit for manufacturing a calibration device based on the output value of the image analysis unit,
The data processing unit includes an object conversion unit for converting the 3D image data into a point cloud object including a plurality of point objects;
A weight setting unit for setting weights to the plurality of point objects; And
And a determination unit configured to sample the plurality of point objects by reflecting the set weight, and to separate and output the gum and the tooth based on this,
The weight setting unit is a calibration device manufacturing system using artificial intelligence that sets a relatively high weight of some point objects among the plurality of point objects. The method of claim 1,
The image analysis unit includes a similarity determination unit that compares the sampled point objects to determine a similarity, and the similarity determination unit includes a DGCNN model. The system of claim 1, wherein the determination unit samples 18,000 to 22,000 point objects, and the sampled point object includes a point object whose weight is set to be relatively high. The method of claim 1,
Orthodontic device manufacturing system using artificial intelligence to set a relatively high weight of the point object disposed near the boundary between the gum and the tooth, the boundary between the tooth and the tooth, and the curve formed on the surface of the tooth. The method of claim 2,
The image analysis unit further includes an input unit for receiving a result value of the data processing unit and a plurality of clinical data stored in the database unit, and the similarity determination unit includes a first sub determination unit and a second sub determination unit, wherein the input unit The plurality of point objects are quantitatively distributed and provided to the first sub-determining unit and the second sub-determining unit, and further comprising a synchro module configured to match result values of the first sub-determining unit and the second sub-determining unit Calibration device manufacturing system using artificial intelligence. Acquiring the patient's dental structure as 3D image data;
Inputting the 3D image data to output image data in which the gums and teeth are separated and displayed;
Outputting clinical data having the highest similarity by determining similarity between the image data and a plurality of clinical data stored in the database; And
Including the step of outputting a calibration device based on the clinical data having the highest similarity,
The step of inputting the 3D image data and outputting image data in which the gums and teeth are separated and displayed may include converting the 3D image data into a point cloud object including a plurality of point objects;
Setting weights to the plurality of point objects; And sampling the plurality of point objects by reflecting the set weight, and separately outputting the gum and the tooth based on the sample, and the similarity between the image data and a plurality of clinical data stored in the database. The step of performing the determination and outputting clinical data having the highest similarity may include quantitatively distributing the plurality of point objects; An artificial intelligence comprising the step of dividing the plurality of distributed point objects into a first sub-determining unit and a second sub-determining unit, determining a similarity, and matching result values of the first sub-determining unit and the second sub-determining unit Method of manufacturing a calibration device used. A computer program stored in a medium to execute the method of manufacturing a calibration device using the artificial intelligence of claim 6 in combination with hardware.

Images