Method and apparatus for generating dental alignment data

Abstract

A method for generating dental alignment data according to one embodiment of the present disclosure may include the steps of acquiring oral cavity scan images of a patient's dental region, the oral cavity scan images including an upper jaw scan image and a lower jaw scan image, acquiring CT scan images including the patient's dental region, generating first sub-alignment data by aligning the upper jaw scan image with the CT scan image, generating first alignment data by aligning the lower jaw scan image with the first sub-alignment data, generating second sub-alignment data by aligning the lower jaw scan image with the CT scan image, and generating second alignment data by aligning the first sub-alignment data with the second sub-alignment data.

Description

[Technical Field]

[0001] Method for generating dental alignment data

[0002] The present disclosure relates to a method for generating dental alignment data, and more particularly to a method for generating dental alignment data by aligning intraoral scan images and CT images to more intuitively indicate the dental condition of a dental patient. [Background technology]

[0003] In dental consultations and treatments, there are limitations to relying solely on oral explanations from dentists, so there is a need for a method to more intuitively show patients the current dental condition and the dental condition after treatment.

[0004] Meanwhile, with the development of digital imaging technology, various types of image data are increasingly being used in dental treatment or consultation. The use of such various image data enables improved dental diagnosis, establishment of treatment plans, patient management, etc. Typical image data used in dental consultation or treatment include CT images obtained using a dental CT (Computerized Tomography) device, facial images obtained by photographing the patient's face using a facial imaging device, and oral scan images obtained by scanning the inside of the patient's oral cavity using a 3D oral scanner.

[0005] However, in the case of CT scans, the patient must hold certain parts of the CT scanner (e.g., a mouthpiece or bite block) in their mouth to fix the patient's position, and the CT image obtained in this way is taken with the oral cavity slightly open, which may differ from the actual state of oral occlusion under normal circumstances. Therefore, it can be cumbersome for users such as dentists to appropriately load and use image data with different uses according to the purpose of treatment or consultation.

[0006] For example, when determining the implant placement position and designing a surgical guide for implant surgery, it is important to accurately confirm the position of the neural canal, so an oral scan image aligned with a CT scan image in the CT occlusion state may be required. On the other hand, when planning prosthetic treatment such as a crown, it is necessary to confirm the contact point between the tooth to be treated and the tooth on the opposite side, so an oral scan image aligned with a CT scan image in the oral scan occlusion state may be required.

[0007] In response, there exists a need for a method for generating and displaying matching data appropriate for the type of treatment desired, whether for dental treatment or consultation purposes. Summary of the Invention [Problem to be solved by the invention]

[0008] In contrast, one object of the present disclosure is to provide a method for generating and displaying appropriate matching data depending on the type of treatment desired, whether for dental treatment or consultation purposes.

[0009] According to an embodiment of the present disclosure, when the maxillary scan image and the mandibular scan image are aligned with the CT image, the mandibular scan image can be aligned based on the maxillary scan image aligned with the CT image. In this case, a set of oral cavity scan images aligned with the CT can be obtained in an oral cavity scan occlusion state.

[0010] According to an embodiment of the present disclosure, when the maxillary scan image and the mandibular scan image are registered (or aligned) with the CT image, the maxillary scan image registered with the CT image and the mandibular scan image registered with the CT image can be registered with each other. In this case, a set of oral cavity scan images aligned with the CT can be obtained in a CT occlusion state.

[0011] According to an embodiment of the present disclosure, a technical problem is to provide at least one of matching data indicating an oral scan occlusion state and matching data indicating a CT occlusion state according to the purpose of treatment.

[0012] However, the problem to be solved by the present disclosure is not limited to those mentioned above, and may include objectives that have not been mentioned but can be clearly understood by a person having ordinary skill in the art to which the present disclosure pertains from the following description. [Means for solving the problem]

[0013] Specific means for achieving the object of the present disclosure will be described below.

[0014] A method for generating dental alignment data according to one embodiment of the present disclosure includes the steps of acquiring oral cavity scan images of a patient's dental region, the oral cavity scan images including an upper jaw scan image and a lower jaw scan image, acquiring CT scan images including the patient's dental region, generating first sub-alignment data by aligning the upper jaw scan image with the CT scan image, generating first alignment data by aligning the lower jaw scan image with the first sub-alignment data, generating second sub-alignment data by aligning the lower jaw scan image with the CT scan image, and generating second alignment data by aligning the first sub-alignment data with the second sub-alignment data.

[0015] The above-mentioned method for generating dental alignment data may further include a step of receiving a user input for selecting one of the first alignment data and the second alignment data, and a step of displaying the selected one of the alignment data in response to receiving the user input.

[0016] The above-mentioned method for generating dental matching data may further include the steps of receiving a user input regarding a treatment method for the patient's tooth portion, selecting one matching data corresponding to the user input from the first matching data and the second matching data, and displaying the selected one matching data.

[0017] The above-described method for generating dental alignment data may further include a step of acquiring a CT segmentation image in which at least one of maxillary teeth, mandibular teeth, maxilla, mandible, and mandibular nerve canal is segmented by image processing the CT image.

[0018] In the above-mentioned method for generating dental alignment data, the step of generating the first sub-alignment data may include a step of generating the first sub-alignment data by aligning the maxillary scan image to the CT segmentation image, and the step of generating the second sub-alignment data may include a step of generating the second sub-alignment data by aligning the mandibular scan image to the CT segmentation image.

[0019] In the above-mentioned method for generating dental alignment data, the step of generating the first alignment data may include the steps of: calculating a transformation matrix between the first alignment data and the second sub-alignment data; and applying an inverse transformation matrix of the transformation matrix to at least one of the segmented mandibular teeth, mandible, and mandibular nerve canal.

[0020] The above-described method for generating dental alignment data may further include the steps of: acquiring a 3D facial image of the patient's face including the dental region; and aligning the 3D facial image with one of the CT image, the first alignment data, and the second alignment data to generate a dental 3D avatar as final alignment data.

[0021] In the above-mentioned method for generating dental alignment data, the step of generating the first sub-alignment data includes a step of generating the first sub-alignment data from the maxillary scan image and the CT image using a first deep learning model, and the first deep learning model may be an artificial intelligence model constructed based on a deep learning algorithm, using a plurality of maxillary scan images and a plurality of CT image sets for a plurality of patients as input data, and a plurality of sub-alignment data sets in which each of the plurality of maxillary scan images is aligned with each of the plurality of CT images as output data, and modeling the correlation between the input data and the output data.

[0022] In the above-mentioned method for generating dental alignment data, the step of generating the second sub-alignment data includes a step of generating the second sub-alignment data from the mandibular scan image and the CT image using a second deep learning model, and the second deep learning model may be an artificial intelligence model constructed based on a deep learning algorithm, using a plurality of mandibular scan images and a plurality of CT image sets for a plurality of patients as input data, and a plurality of sub-alignment data sets in which each of the plurality of mandibular scan images is aligned with each of the plurality of CT images as output data, and modeling the correlation between the input data and the output data.

[0023] In the above-described method for generating dental alignment data, the first sub-alignment data and the second sub-alignment data are generated based on at least three landmarks of the patient's three-dimensional data, and the at least three landmarks are extracted by an application for generating dental alignment data. The at least three landmarks are extracted using an artificial neural network module built into the application or connected via a network, and the artificial neural network module may be pre-trained using pre-training data.

[0024] An apparatus for generating dental alignment data according to one embodiment of the present disclosure may include a communication circuit, a memory, and a processor, wherein the processor is configured to acquire oral cavity scan images of a patient's dental site, the oral cavity scan images including an upper jaw scan image and a lower jaw scan image, acquire CT scan images including the patient's dental site, generate first sub-alignment data by aligning the upper jaw scan image to the CT scan image, generate first alignment data by aligning the lower jaw scan image to the first sub-alignment data, generate second sub-alignment data by aligning the lower jaw scan image to the CT scan image, and generate second alignment data by aligning the first sub-alignment data to the second sub-alignment data.

[0025] The above-mentioned device for generating dental alignment data may further include an input device and a display, and the processor may be configured to receive user input for selecting one of the first alignment data and the second alignment data via the input device, and to display the selected one of the alignment data via the display in response to receiving the user input.

[0026] The above-mentioned apparatus for generating dental alignment data may further include an input device and a display, and the processor may be configured to receive user input regarding a treatment method for the patient's dental site via the input device, select one of the first alignment data and the second alignment data corresponding to the user input, and display the selected one of the first alignment data and the second alignment data via the display.

[0027] In the above-mentioned apparatus for generating dental alignment data, the processor may be configured to perform image processing on the CT image to obtain a CT segmentation image in which at least one of the maxillary teeth, mandibular teeth, maxilla, mandible, and mandibular nerve canal is segmented.

[0028] In the above-mentioned apparatus for generating dental alignment data, the processor may be configured to generate the first sub-alignment data by aligning the maxilla scan image to the CT segmentation image, and to generate the second sub-alignment data by aligning the mandible scan image to the CT segmentation image.

[0029] In the above-mentioned apparatus for generating dental alignment data, the processor may calculate a transformation matrix between the first alignment data and the second sub-alignment data in the step of generating the first alignment data, and apply an inverse transformation matrix of the transformation matrix to at least one of the segmented mandibular teeth, mandible, and mandibular nerve canal.

[0030] In the above-described apparatus for generating dental alignment data, the processor may be configured to acquire a 3D facial image of the patient's face including dental regions, and align the 3D facial image with one of the CT image, the first alignment data, and the second alignment data to generate a dental 3D avatar as final alignment data.

[0031] In the above-mentioned apparatus for generating dental alignment data, the processor is configured to generate the first sub-alignment data from the maxillary scan images and the CT images using a first deep learning model, and the first deep learning model may be an artificial intelligence model constructed based on a deep learning algorithm, using multiple maxillary scan images and multiple CT image sets for multiple patients as input data, and multiple sub-alignment data sets in which each of the multiple maxillary scan images is aligned with each of the multiple CT images as output data, and modeling the correlation between the input data and the output data.

[0032] In the above-mentioned apparatus for generating dental alignment data, the processor is configured to generate the second sub-alignment data from the mandibular scan image and the CT image using a second deep learning model, and the second deep learning model may be an artificial intelligence model constructed based on a deep learning algorithm, using a plurality of mandibular scan images and a plurality of CT image sets for a plurality of patients as input data, and a plurality of sub-alignment data sets in which each of the plurality of mandibular scan images is aligned with each of the plurality of CT images as output data, and modeling the correlation between the input data and the output data.

[0033] In the above-mentioned device for generating dental alignment data, the first sub-alignment data and the second sub-alignment data are generated based on at least three landmarks of the patient's three-dimensional data, and the at least three landmarks are extracted by an application for generating dental alignment data, but the at least three landmarks are extracted using an artificial neural network module built into the application or connected via a network, and the artificial neural network module may be pre-trained using pre-training data. [Effects of the Invention]

[0034] According to an embodiment of the present disclosure, at least one of matching data indicating an intraoral scan occlusion state and matching data indicating a CT occlusion state can be provided depending on the purpose of treatment.

[0035] However, the effects obtained by the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by a person having ordinary skill in the art to which the present disclosure pertains from the description below. [Brief explanation of the drawings]

[0036] The following drawings attached to this specification illustrate preferred embodiments of the present disclosure and, together with the detailed description of the invention, serve to further understand the technical concepts of the present disclosure, and therefore the present disclosure should not be interpreted as being limited solely to the matters depicted in such drawings. [Figure 1] FIG. 1 is a diagram for illustrating a schematic basic configuration of an apparatus for generating dental alignment data according to one embodiment of the present disclosure. [Figure 2] FIG. 1 is a block diagram of an apparatus for generating dental alignment data according to one embodiment of the present disclosure. [Figure 3] FIG. 2 is a diagram for schematically explaining the principle of generating dental alignment data by an alignment module according to an embodiment of the present disclosure. [Figure 4] 1 is an operational flowchart illustrating a method for generating dental alignment data according to one embodiment of the present disclosure. [Figure 5a] 1 is a CT scan image according to an embodiment of the present disclosure. [Figure 5b] 1 is a diagram illustrating an upper jaw scan image among oral cavity scan images according to one embodiment of the present disclosure. [Figure 5c] 10 is a first sub-matching data according to one embodiment of the present disclosure. [Figure 6a] 1 is a lower jaw scan image among oral cavity scan images according to one embodiment of the present disclosure. [Figure 6b] 1 is a diagram illustrating first matching data according to an embodiment of the present disclosure. [Figure 7] 10 is second sub-match data according to one embodiment of the present disclosure. [Figure 8] 10 is a diagram illustrating second matching data according to an embodiment of the present disclosure. [Figure 9] 1 is an operational flowchart illustrating a method for generating dental alignment data according to one embodiment of the present disclosure. [Figure 10a] 1 is a CT segmentation image according to one embodiment of the present disclosure. [Figure 10b] 1 is a CT segmentation image according to one embodiment of the present disclosure. [Figure 11]1 is a diagram illustrating first matching data according to an embodiment of the present disclosure. [Figure 12] 10 is a diagram illustrating second matching data according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0037] The various examples described herein are provided for the purpose of clearly explaining the technical idea of ​​the present disclosure and are not intended to limit the technical idea to specific embodiments. The technical idea of ​​the present disclosure includes various modifications, equivalents, alternatives, and embodiments that selectively combine all or part of the examples described herein. Furthermore, the scope of the technical idea of ​​the present disclosure is not limited to the various examples and their specific descriptions provided below.

[0038] Terms used herein, including technical or scientific terms, may have the meaning commonly understood by one of ordinary skill in the art to which this disclosure belongs, unless otherwise defined.

[0039] As used herein, terms such as "include," "may include," "includes," "may comprise," "have," "could have," and the like mean the presence of a target feature (e.g., a function, operation, or component) and do not exclude the presence of other additional features. In other words, such terms should be understood as open-ended terms that include the possibility of including a second embodiment.

[0040] In this specification, the singular expression includes the plural expression unless the context clearly dictates otherwise. Furthermore, the plural expression includes the singular expression unless the context clearly dictates otherwise. Throughout the specification, when a part includes a certain element, this does not mean that other elements are excluded, but that other elements may also be included, unless specifically stated to the contrary.

[0041] Furthermore, the terms "module" or "module" as used herein refer to a software or hardware component, and the "module" or "module" performs a certain function. However, the term "module" or "module" is not limited to software or hardware. A "module" or "module" may be configured to reside on an addressable storage medium or to execute on one or more processors. Thus, by way of example, a "module" or "module" may include components such as software components, object-oriented software components, class components, and task components, as well as at least one of processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The components and functionality provided within a "module" or "module" may be combined into fewer components and "modules" or "modules," or further separated into additional components and "modules" or "modules."

[0042] According to one embodiment of the present disclosure, a "module" or "unit" may be embodied with a processor and memory. "Processor" should be broadly interpreted to include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, etc. In some environments, "processor" may also refer to an application-specific semiconductor (ASIC), a programmable logic device (PLD), a field-programmable gate array (FPGA), etc. "Processor" may also refer to a combination of processing devices, such as, for example, a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors in conjunction with a DSP core, or any other such configuration. Additionally, "memory" should be broadly interpreted to include any electronic component capable of storing electronic information. "Memory" may refer to various types of processor-readable media such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage devices, registers, etc. Memory is said to be in electronic communication with a processor if the processor can read information from and / or write information to the memory. Memory that is integrated into a processor is in electronic communication with the processor.

[0043] As used herein, unless the context indicates otherwise, the terms "first," "second," "primary," "secondary," and the like are used to distinguish one object from another when referring to multiple similar objects, and do not limit the order or importance of those objects.

[0044] As used herein, phrases such as "A, B, and C," "A, B, or C," "A, B, and / or C," or "at least one of A, B, and C," "at least one of A, B, or C," "at least one of A, B, and / or C," "at least one selected from A, B, and C," "at least one selected from A, B, and / or C," and the like, can refer to each listed item or all possible combinations of the listed items. For example, "at least one selected from A and B" can refer to (1) A, (2) at least one of A, (3) B, (4) at least one of B, (5) at least one of A and at least one of B, (6) at least one of A and B, (7) at least one of B and A, or (8) both A and B.

[0045] As used herein, the phrase "based on" is used to describe one or more factors that influence the decision, judgment, act, or behavior described in the phrase or sentence in which the phrase appears, and does not exclude additional factors that influence the decision, judgment, act, or behavior.

[0046] As used in this specification, the expression "coupled" or "connected" to a component (e.g., a first component) to another component (e.g., a second component) may mean not only that the component is directly coupled or connected to the other component, but also that the component is coupled or connected via a new component (e.g., a third component).

[0047] As used herein, the expression "configured to" may have meanings such as "set to," "capable of," "modified to," "made to," or "capable of," depending on the context. The expression is not limited to the meaning of "specially designed in hardware." For example, a processor configured to perform a specific operation may refer to a generic-purpose processor that can perform the specific operation by executing software.

[0048] Hereinafter, various embodiments of the present disclosure will be described with reference to the accompanying drawings. In the accompanying drawings and the description of the drawings, identical or substantially equivalent components may be assigned the same reference numerals. Furthermore, in the following description of various embodiments, duplicated descriptions of identical or corresponding components may be omitted, but this does not mean that the components are not included in the embodiments.

[0049] Basic structure of the device for generating dental alignment data

[0050] FIG. 1 is a diagram for schematically explaining the basic configuration of an apparatus for generating dental alignment data according to one embodiment of the present disclosure.

[0051] Referring to FIG. 1, an apparatus (100) for generating dental alignment data can include a memory (110) and a processor (120).

[0052] The memory 110 can store various applications, including personal information and treatment data for each patient, and an application for generating dental alignment data. According to one embodiment, the patient's treatment data can include at least one of an intraoral scan (IOS) image 15, a three-dimensional (3D) facial image 25, and a computed tomography (CT) image 35.

[0053] The processor 120 can execute an application for generating dental alignment data stored in the memory 110. According to one embodiment, the acquisition module 130, the alignment module 140, and the display module 150 can be implemented in software in response to the execution of the application for generating dental alignment data. However, depending on the design of the device, some modules may be implemented in hardware, and this is not limiting.

[0054] According to one embodiment, the intraoral scan (IOS) image 15 may be obtained by scanning the patient's dental region, i.e., the inside of the oral cavity, using a 3D oral scanner 10. The 3D oral scanner 10 is a non-contact scanner that collects surface data of the patient's intraoral structure and generates the 3D intraoral scan (IOS) image using a confocal method or optical triangulation method based on the data. When the 3D intraoral scan (IOS) image is obtained as a digital impression using the 3D oral scanner 10, it is advantageous in that it does not require the cumbersome procedure of physically capturing the patient's intraoral structure by performing an impression process (mold-taking process) using impression material placed in a tray. The intraoral scan (IOS) image 15 may be obtained using various types of commercially available 3D oral scanners, but is not limited to these.

[0055] The oral cavity scan image may include an upper jaw scan image and a lower jaw scan image. The upper jaw scan image may be obtained by scanning the patient's upper jaw teeth, and the lower jaw scan image may be obtained by scanning the patient's lower jaw teeth.

[0056] The 3D facial image 25 may be obtained by photographing the patient's face using a 3D facial photographing device 20. According to one embodiment, the 3D facial photographing device 20 may include multiple cameras, and may be operated in a manner in which the multiple cameras photograph the patient's face in one shot to obtain the 3D facial image 25. However, the 3D facial photographing device 20 may be operated in a manner in which the patient's face is photographed at different times while the patient's face is fixed or moved, and is not limited to this.

[0057] According to one embodiment, the multiple cameras of the 3D face imaging device 20 may include at least one dental imaging camera for capturing images of the patient's dental region, in addition to the multiple facial imaging cameras. The facial imaging cameras may be installed on the front, left, right, and bottom of the 3D face imaging device 20 to capture images of the front, left, right, and bottom of the patient's face. According to one embodiment, the dental imaging camera may be different from the facial imaging camera, for example, with a different lens magnification. The dental imaging cameras may be installed on the left and right sides of the 3D face imaging device 20, for example, to capture images of both the left and right sides of the patient's dental region, but the number and installation locations of the dental imaging cameras are not limited. The provision of a separate dental imaging camera not only allows for more accurate representation and presentation of the patient's teeth, but also facilitates more precise and smooth matching with other data (e.g., CT images or oral scan (IOS) images) when generating matching data. This will be described in more detail below.

[0058] According to one embodiment, the 3D facial image (25) may be captured with the patient's dental region exposed. That is, when capturing a patient's face using the 3D facial imaging device (20), the patient may be guided to fix their face in a fixed position and expose their dental region before capturing the image. For this reason, the 3D facial imaging device (20) may be designed with a guide function. This allows the patient's face as well as their dental region to be captured more accurately to generate the 3D facial image (25). However, in some cases, it may not be necessary to capture the 3D facial image (25) with the patient's dental region exposed. In such cases, the 3D facial image (25) may or may not have exposed teeth.

[0059] According to one embodiment, the 3D face photographing device 20 may capture a plurality of images of a patient's face using a plurality of cameras while irradiating the patient's face with a structured light pattern, and acquire a 3D face image 25 based on the captured images. However, the method of acquiring the 3D face image 25 may include, but is not limited to, a laser scanning method, a depth sensor method, or a method of reconstructing a 3D face image using artificial intelligence (AI), in addition to a method using structured light.

[0060] The CT image 35 may be obtained by imaging a facial region including a patient's dental region using a CT device 30. The CT device 30 may be a dental CT device, such as a cone beam CT device. A cone beam CT device has the advantage of being able to acquire a CT image of a patient's dental region while minimizing radiation exposure to the patient by scanning with a cone-shaped X-ray beam. However, the CT device 30 may also be a fan beam CT device that scans with a fan-shaped X-ray beam. In other words, the CT image 35 according to the embodiment of the present disclosure may be obtained using various CT devices, and is not limited thereto.

[0061] According to one embodiment, the acquisition module 130 of the dental alignment data generation apparatus 100 can acquire the aforementioned intraoral scan (IOS) images 15, 3D facial images 25, and CT scan images 35 from the 3D intraoral scanner 10, 3D facial imaging device 20, and CT scanner 30, respectively. However, at least one of the intraoral scan (IOS) images 15, 3D facial images 25, and CT scan images 35 may also be acquired by the acquisition module 130 in the form of downloading images stored on other storage media or the cloud.

[0062] The intraoral scan (IOS) images 15, 3D facial images 25, and CT scan images 35 acquired by the acquisition module 130 may be stored in the memory 110 of the device 100 for generating dental registration data. The intraoral scan (IOS) images 15, 3D facial images 25, and CT scan images 35 may be stored in the memory 110 by patient, or, if multiple copies of the same type of data are taken at different times, they may be stored by time. In addition, the memory 110 may store each patient's personal information, treatment data such as dentist comments, and various applications, including an application for generating dental registration data.

[0063] FIG. 2 is a block diagram of an apparatus for generating dental alignment data (hereinafter referred to as dental alignment data generating apparatus) 100 according to one embodiment of the present disclosure.

[0064] Referring to FIG. 2 , according to one embodiment, the dental registration data generation device 100 may be a device for registering intraoral scan images and CT images. The dental registration data generation device 100 according to one embodiment may include a memory 110, a processor 120, and a communication circuit 160. The processor 120 of the dental registration data generation device 100 may execute software (e.g., a program) to control at least one other component (e.g., a hardware component, a software component) of the dental registration data generation device 100 connected to the processor 120, and perform various data processing or calculations. As at least part of the data processing or calculations, the processor 120 may load instructions or data received from other components into the memory 110, process the instructions or data stored in the memory 110, and store the resulting data in the non-volatile memory 110. The memory 110 of the dental alignment data generating device 100 can store information related to the above-described method or a program implementing the above-described method. The memory 110 can be a volatile memory or a non-volatile memory.

[0065] The processor 120 of the dental registration data generation device 100 according to one embodiment can execute a program and control the dental registration data generation device 100. The code of the program executed by the processor 120 can be stored in the memory 110. The dental registration data generation device 100 can be connected to and exchange data with external devices (e.g., the 3D oral scanner 10, the 3D face image capture device 20, and the CT image capture device 30) via an input / output device (not shown). The processor 120 can be operatively connected to components of the dental registration data generation device 100. The processor 120 can load instructions or data received from other components of the dental registration data generation device 100 into the memory 110, process the instructions or data stored in the memory 110, and store the resulting data.

[0066] The communication circuitry 160 of the dental alignment data generation device 100 according to one embodiment can establish a communication channel with an external device (e.g., the 3D oral scanner 10, the 3D face scanner 20, or the CT scanner 30) and transmit and receive various data to and from the external device. According to various embodiments, the communication circuitry 160 can include a cellular communication module and be configured to connect to a cellular network (e.g., 3G, LTE, 5G, Wibro, or Wimax). According to various embodiments, the communication circuitry 160 can include a short-range communication module and can transmit and receive data to and from the external device using short-range communication (e.g., but not limited to, Wi-Fi, Bluetooth, Bluetooth Low Energy (BLE), or UWB).

[0067] According to one embodiment, the dental alignment data generating device 100 may further include an input device (not shown). The input device may receive commands or data from an external device for use by components of the server device. The input device may include, for example, a microphone, a mouse, or a keyboard.

[0068] According to one embodiment, the dental alignment data generating device 100 may further include a display (not shown), which may display various screens under the control of the processor 120.

[0069] FIG. 3 is a diagram for schematically explaining the principle of generating dental alignment data according to an embodiment of the present disclosure.

[0070] 1 and 2, the registration module 140 can generate registration data by registering the intraoral scan (IOS) image 15 and the CT scan image 35. The intraoral scan image can include a maxillary (upper teeth) scan image and a mandibular (lower teeth) scan image. The registration module 140 can generate two types of registration data in two ways depending on the purpose of treatment. Specific methods for generating the two types of registration data will be described later.

[0071] The alignment module 140 may also align the 3D facial image 25 with the CT image 35 or the alignment data to generate a dental 3D avatar as final alignment data. According to one embodiment, a method for performing this alignment may be used in which landmarks are extracted from the patient's 3D data (e.g., facial and / or dental data) and used to perform image alignment. However, other methods may be used in addition to the method using landmarks, and the present invention is not limited to this method.

[0072] According to one embodiment, the alignment module 140 can extract three or more landmarks from the patient's three-dimensional data. The intraoral scan (IOS) image 15, the 3D facial image 25, and the CT scan image 35 according to the embodiment of the present disclosure are all three-dimensional, or at least three or more three-dimensional data. By utilizing three or more landmarks, the x, y, and z axes of the three-dimensional data can all be aligned.

[0073] According to a method for generating dental registration data according to one embodiment of the present disclosure, landmark extraction may be manually specified by a user, such as a dentist or laboratory manager. For example, the user may specify landmarks using a pointer, such as a mouse, via a user interface of the application for generating dental registration data, which is presented to the user by the display module 150. According to another embodiment, three or more landmarks may be extracted by the application for generating dental registration data.

[0074] Meanwhile, according to another embodiment, the application for generating dental alignment data may incorporate an artificial neural network module that has been pre-trained through a large amount of data, or may be connected to such an artificial neural network module via a network, thereby extracting landmarks based on artificial intelligence.

[0075] According to one embodiment, an intraoral scan (IOS) image (15) corresponds to a 3D image generated by scanning the patient's oral cavity and does not include facial data, so dental landmarks can be used when aligning with other images (25, 35). In addition, when aligning a 3D facial image (25) with a CT scan image (35), landmarks in the patient's facial area excluding the dental area can be used, or both the dental landmarks and the facial landmarks can be used.

[0076] The display module 150 may display the alignment data generated by the alignment module 140 on a display. The display module 150 may display the dental 3D avatar generated by the alignment module 140 on a display of the device 100. According to one embodiment, the display module 150 may display the alignment data on a user interface provided by an application for generating dental alignment data. The display module 150 may also adjust the transparency of some of the three images 15, 25, and 35 constituting the dental 3D avatar or select whether or not to display them, allowing users such as dentists and laboratory managers to view appropriate representations as needed. In addition, the display module 150 may allow users to adjust the position and shape of some data, such as the oral cavity scan image 15, in the dental 3D avatar displayed via the display module 150.

[0077] Method for generating dental alignment data - Patent application

[0078] FIG. 4 is a flowchart illustrating a method for generating dental alignment data according to one embodiment of the present disclosure.

[0079] First, referring to FIG. 4 , in a method for generating dental alignment data according to one embodiment of the present disclosure, the processor 120 of the dental alignment data generation device 100 may acquire intraoral scan (IOS) images of a patient's dental region in step S410. The intraoral scan images may include an upper jaw scan image and a lower jaw scan image. For example, a user (e.g., a dentist or dental technician) may use a 3D oral scanner 20 to acquire intraoral scan images of the patient's dental region. The user may use the 3D oral scanner 20 to acquire an upper jaw scan image of the patient's upper dental region. The user may use the 3D oral scanner 20 to acquire a lower jaw scan image of the patient's lower dental region.

[0080] The dental alignment data generating device 100 can acquire the upper jaw scan image and the lower jaw scan image acquired from the 3D oral cavity scanner 20. Alternatively, the dental alignment data generating device 100 can acquire the upper jaw scan image and the lower jaw scan image by downloading them from other storage media or the cloud. The dental alignment data generating device 100 can generate an oral cavity scan image by aligning the upper jaw scan image and the lower jaw scan image with each other. The oral cavity scan image in which the upper jaw scan image and the lower jaw scan image are aligned with each other represents the state in which the patient bites the oral cavity under normal circumstances, and the bite state of such an oral cavity scan image (the state in which the patient bites the teeth) can be called the oral cavity scan bite state (or oral bite state).

[0081] According to an embodiment, the processor 120 may acquire a CT image including a dental region of a patient in step S420. For example, a user may acquire a CT image including a dental region of a patient using the CT imaging device 30. The patient may perform the CT imaging by holding the mouthpiece (or bite block) of the CT imaging device 30 in their mouth. The occlusal state of the oral cavity during the CT imaging may be referred to as a CT occlusion state.

[0082] In one embodiment, the processor 120 may generate first sub-alignment data by aligning the maxillary scan image to the CT image in step S430. The first sub-alignment data is necessary to generate both the first alignment data corresponding to the oral scan bite state and the second alignment data corresponding to the CT bite state. A method for generating the first sub-alignment data will be described with reference to Figures 5a to 5c.

[0083] FIG. 5a is a CT image including a patient's dental region. The CT image may be a three-dimensional CT image. Image 510a in FIG. 5a may be a CT image viewed from the front, and image 510b may be a CT image viewed from the side. FIG. 5b is a maxillary scan image of the patient's maxillary dental region. The maxillary scan image may be a three-dimensional oral cavity scan image. Image 520a in FIG. 5b may be a maxillary scan image viewed from the front, and image 520b in FIG. 5b may be a maxillary scan image viewed from the side. FIG. 5c is first sub-alignment data obtained by aligning the maxillary scan image with the CT image. FIG. 5c may be three-dimensional data generated by aligning the three-dimensional maxillary scan image with the three-dimensional CT image. Image 530a in FIG. 5c may be first sub-alignment data viewed from the front, and image 530b may be first sub-alignment data viewed from the side.

[0084] Referring to FIGS. 5a to 5c, according to one embodiment, the processor 120 can generate first sub-alignment data by aligning the maxilla scan image and the CT image based on at least three landmarks. Because each image corresponds to three-dimensional data, the number of landmarks used to generate the first sub-alignment data can be three or more, and they can be extracted from the patient's face and / or dental regions. For example, the processor 120 can extract three landmarks from the CT image and three corresponding landmarks from the maxilla scan data. The landmarks can refer to points located on the maxilla teeth and gums, for example. However, the above-mentioned landmark locations are merely exemplary, and the landmarks can also be extracted from various locations, such as the middle of the front teeth or points located at the interdental boundary. Since precise alignment of dental regions is important for generating alignment data useful in dental treatment, it is necessary to accurately extract landmarks from the patient's dental regions. Therefore, if possible, precise alignment can be achieved using only landmarks from the patient's dental regions, which would be more effective because it would eliminate the need to extract additional landmarks from areas of the patient's face other than the teeth.

[0085] According to an embodiment, the processor 120 may generate first sub-alignment data from the maxillary scan images and the CT images using a first deep learning model. The first deep learning model may be an artificial intelligence model constructed based on a deep learning algorithm, using input data including a plurality of maxillary scan images and a plurality of CT image sets for a plurality of patients, and output data including a plurality of sub-alignment data sets in which each of the plurality of maxillary scan images is aligned with each of the plurality of CT images, and modeling the correlation between the input data and the output data.

[0086] In this disclosure, a deep learning algorithm may refer to computer software improving its data processing capabilities through learning using data and experience processing the data. Deep learning may be performed by a deep learning model. A deep learning model is constructed by modeling correlations between data, and the correlations may be expressed by multiple parameters. A deep learning model extracts and analyzes features from given data to derive correlations between data. Deep learning can be said to involve repeating this process to optimize the parameters of the deep learning model. For example, when data is provided as input and output pairs to a deep learning model, the deep learning model can learn the mapping (correlation) between the input and output. Alternatively, when only input data is provided, the learning model can derive regularities between the given data and learn the relationships. In one embodiment, the deep learning algorithm may be at least one selected from a deep neural network, a recurrent neural network, a convolutional neural network, a machine learning model for classification-regression analysis, a reinforcement learning model, a decision tree learning method, an association rule learning method, genetic programming, inductive logic programming, a support vector machine, clustering, a Bayesian network, or an identity measurement learning method.

[0087] Through the above process, the upper jaw scan image disclosed in Figure 5b can be aligned with the CT image disclosed in Figure 5a to generate the first sub-alignment data disclosed in Figure 5c.

[0088] According to one embodiment, the processor 120 may generate first alignment data by aligning the mandibular scan image to the first sub-alignment data in step S440. The first alignment data may refer to alignment data based on the oral cavity scan bite state. Specifically, the processor 120 may generate the first alignment data by aligning the mandibular scan image to the maxillary scan image in the first sub-alignment data. For example, the processor 120 may align the mandibular scan image and the maxillary scan image in the first sub-alignment data so that they are in an oral cavity scan bite state. The processor 120 may align the mandibular scan image to the first sub-alignment data by moving the mandibular scan image by an amount corresponding to the alignment of the maxillary scan image with the CT image.

[0089] 6a and 6b are diagrams illustrating a method for generating first alignment data. Specifically, FIG. 6a is a mandibular scan image obtained by scanning the patient's mandibular dental region, and FIG. 6b is a diagram illustrating first alignment data. Image 610a in FIG. 6a is a mandibular scan image viewed from the front, and image 610b is a mandibular scan image viewed from the side. Image 620a in FIG. 6b is first alignment data viewed from the front, and image 620b is first alignment data viewed from the side.

[0090] 6a and 6b, the processor 120 can generate first alignment data by aligning the mandibular scan image of FIG. 6a with the first sub-alignment data of FIG. 5c. The processor 120 can generate the first alignment data by aligning the mandibular scan image and the maxillary scan image in the first sub-alignment data so that they are in an oral scan occlusion state. Because the first alignment data is generated by aligning the mandibular scan image based on the maxillary scan image of the first sub-alignment data, the first alignment data can indicate the oral scan occlusion state. Therefore, the first alignment data can be used in dental treatments (e.g., prosthetic treatments such as crowns) that require confirmation of the oral scan occlusion state.

[0091] In one embodiment, the processor 120 can generate second sub-alignment data by aligning the mandibular scan image with the CT image in step S450. The second sub-alignment data is necessary to generate second alignment data corresponding to the CT bite state. A method for generating second sub-alignment data will be described with reference to FIGS. 5a, 6a, and 7. As described above, FIG. 5a is a CT image including a patient's dental region, and FIG. 6a is a mandibular scan image obtained by scanning the patient's mandibular dental region. FIG. 7 is a diagram showing second sub-alignment data. Image 710a in FIG. 7 is second sub-alignment data viewed from the front, and image 710b is second sub-alignment data viewed from the side.

[0092] 5a, 6a, and 7, the processor 120 can generate second sub-alignment data by aligning the mandibular scan image of FIG. 6a with the CT image of FIG. 5a. According to one embodiment, the processor 120 can generate second sub-alignment data by aligning the mandibular scan image and the CT image based on at least three landmarks. For example, the processor 120 can extract three landmarks from the CT image and three corresponding landmarks from the mandibular scan data. The landmarks can refer to predetermined points related to the mandibular teeth and gums, for example. However, the above-mentioned landmark locations are merely exemplary, and the landmarks can also be extracted from various locations, such as the middle of the front teeth or points located at the interdental boundary.

[0093] According to an embodiment, the processor 120 may generate second sub-alignment data from the mandibular scan images and the CT scan images using a second deep learning model. The second deep learning model may be an artificial intelligence model constructed based on a deep learning algorithm, using a plurality of mandibular scan images and a plurality of CT scan image sets for a plurality of patients as input data, and a plurality of sub-alignment data sets in which each of the plurality of mandibular scan images is aligned with each of the plurality of CT scan images as output data, and modeling the correlation between the input data and the output data.

[0094] In this disclosure, a deep learning algorithm may refer to computer software improving its data processing capabilities through learning using data and experience processing the data. Deep learning may be performed by a deep learning model. A deep learning model is constructed by modeling correlations between data, and the correlations may be expressed by multiple parameters. A deep learning model extracts and analyzes features from given data to derive correlations between data. Deep learning can be said to involve repeating this process to optimize the parameters of the deep learning model. For example, when data is provided as input and output pairs to a deep learning model, the deep learning model can learn the mapping (correlation) between the input and output. Alternatively, when only input data is provided, the learning model can derive regularities between the given data and learn the relationships. In one embodiment, the deep learning algorithm may be at least one selected from a deep neural network, a recurrent neural network, a convolutional neural network, a machine learning model for classification-regression analysis, a reinforcement learning model, a decision tree learning method, an association rule learning method, genetic programming, inductive logic programming, a support vector machine, clustering, a Bayesian network, or an identity measurement learning method.

[0095] Through the above process, the mandibular scan image disclosed in FIG. 6a can be aligned with the CT image disclosed in FIG. 5a to generate the second sub-alignment data disclosed in FIG. 7.

[0096] According to an embodiment, the processor 120 may generate second alignment data by aligning the first sub-alignment data with the second sub-alignment data in step S460. The second alignment data may refer to alignment data based on a CT occlusion state. Specifically, since the CT images of the first sub-alignment data and the second sub-alignment data are identical, the processor 120 may perform alignment based on the CT images of the first sub-alignment data and the second sub-alignment data. That is, the processor 120 may align the first sub-alignment data and the second sub-alignment data to form a CT occlusion state.

[0097] FIG. 8 is a diagram showing the second matching data. Image 810a in FIG. 8 is the second matching data viewed from the front, and image 810b is the second matching data viewed from the side. The process of generating the second matching data will be described using FIGS. 5c, 7, and 8. The processor 120 can generate the second matching data of FIG. 8 by matching the first sub-matching data of FIG. 5c with the second sub-matching data of FIG. 7. The processor 120 can generate the second matching data by matching the CT image of the first sub-matching data with the CT image of the second sub-matching data so that they overlap.

[0098] A user can select and use the necessary matching data from the first matching data and the second matching data according to the purpose of treatment. In one embodiment, the processor 120 of the dental matching data generating device 100 can receive a user input for selecting one of the first matching data and the second matching data via the input device 100. In response to receiving the user input, the processor 120 can display the selected matching data via a display. In another embodiment, the processor 120 of the dental matching data generating device 100 can receive a user input regarding a treatment method for a patient's tooth region via the input device 100. The processor 120 can select one of the first matching data and the second matching data corresponding to the user input. The processor 120 can also display the selected matching data via a display.

[0099] According to an embodiment, the processor 120 can store the first and second matching data in the memory 110. Alternatively, the processor 120 can store the first and second matching data in the cloud.

[0100] According to one embodiment, the processor 120 can acquire a 3D facial image of a patient's face, including dental regions. The processor 120 can align the 3D facial image with one of a CT image, the first alignment data, and the second alignment data to generate a dental 3D avatar as final alignment data. For example, the processor 120 can align the 3D facial image with a CT image, the 3D facial image with the first alignment data, or the 3D facial image with the second alignment data. To generate the dental 3D avatar, the processor 120 can extract landmarks from the 3D facial image that correspond to the landmarks extracted to generate the first alignment data. For example, the processor 120 can extract landmarks from the 3D facial image that correspond to at least three landmarks extracted to generate the first sub-alignment data.

[0101] As described above, according to the method for generating dental alignment data in accordance with another embodiment of the present disclosure, it is possible to generate first sub-alignment data generated based on aligning the maxillary scan image among the oral cavity scan images with the CT image acquired in the patient's intraoral occlusion state, and first alignment data generated based on aligning the mandibular scan image. Also, according to the method for generating dental alignment data in accordance with another embodiment of the present disclosure, it is possible to generate first sub-alignment data generated based on aligning the maxillary scan image among the oral cavity scan images with the CT image acquired in the patient's intraoral occlusion state, and second alignment data generated based on aligning the second sub-alignment data generated based on aligning the mandibular scan image with the CT image.

[0102] In other words, since two matching data based on two occlusion conditions are generated together, the user can selectively use the data required according to the patient's dental treatment purpose, and the dental condition when the patient maintains an intraoral occlusion condition can be more effectively expressed.

[0103] More specifically, depending on the treatment method, the first matching data may be more appropriate, the second matching data may be more appropriate, or both may be necessary. For example, when designing prosthetics such as crowns, inlays, or onlays, the occlusal relationship with other teeth is more important, so the first matching data based on the oral scan occlusion state can be used. On the other hand, when designing a surgical guide, it is necessary to confirm the patient's tooth roots and nerve positions, so the second matching data, which is data on the patient's dental occlusion state based on a CT image (i.e., CT occlusion state), may be more appropriate. In addition, when designing prosthetics and a surgical guide simultaneously, both sets of data (i.e., a first dental 3D avatar and a second dental 3D avatar) may be required.

[0104] 9 is a flowchart showing the operation of the dental alignment data generating device 100 according to an embodiment of the present disclosure. Content that overlaps with the content explained in FIG. 4 will be omitted.

[0105] Referring to the operational flowchart 900, the processor 120 of the dental alignment data generation device 100 according to one embodiment can acquire an intraoral scan image of the patient's dental region in step S910. The processor 120 according to one embodiment can acquire a CT scan image including the patient's dental region in step S920.

[0106] According to an embodiment, the processor 120 performs image processing on the CT image in step S930 to obtain a CT segmentation image in which at least one of the maxillary teeth, mandibular teeth, maxilla, mandible, and mandibular nerve canal is segmented. The processor 120 can identify and extract at least one of the maxillary teeth, mandibular teeth, maxilla, mandible, and mandibular nerve canal from the CT image. When the mesh-type data is generated, each part can be segmented while maintaining the CT occlusion state.

[0107] 10a and 10b are diagrams showing CT segmentation images. Image 1010a in FIG. 10a is a CT segmentation image viewed from the front, and image 1010b is a CT segmentation image viewed from the side. Image 1010c in FIG. 10b is a semi-transparent version of image 1010a in FIG. 10a.

[0108] 10a to 10c, the CT segmentation image may include the tooth 1011, the maxilla 1013, the mandible 1015, and the mandibular nerve canal 1017. That is, the processor 120 can identify and extract the tooth 1011, the maxilla 1013, the mandible 1015, and the mandibular nerve canal 1017 from the CT image.

[0109] Returning to Figure 9 again, in step S940, the processor 120 according to one embodiment can generate first sub-alignment data by aligning the maxilla scan image to the CT segmentation image. In step S950, the processor 120 according to one embodiment can generate first alignment data by aligning the mandible scan image to the first sub-alignment data. The method of Figure 9 differs from the method disclosed in Figure 4 in that the method does not use the CT scan image as is, but uses a CT segmentation image in which the teeth, maxilla, mandible, and / or mandibular nerve canal are segmented for alignment.

[0110] FIG. 11 is a diagram showing first alignment data according to one embodiment. Image 1110a in FIG. 11 is the first alignment data viewed from the front, and image 1110b is the first alignment data viewed from the side. That is, the processor 120 can sequentially align the upper jaw scan image and the lower jaw scan image with the CT segmentation image. At this time, the processor 120 can align the lower jaw scan image based on the upper jaw scan image of the first sub-alignment data. That is, the processor 120 can generate the first alignment data by shifting the lower jaw scan image by the amount by which the upper jaw scan data is aligned with the CT segmentation image. Therefore, the first alignment data can indicate the bite condition of the oral cavity scan.

[0111] According to one embodiment, the segmented mandible, mandibular teeth, and mandibular nerve canal may be aligned to the bite state of the oral cavity scan. The processor 120 may calculate a transformation relationship between the first alignment data and the second sub-alignment data. For example, the processor 120 may register the mandibular scan image of the first alignment data to the CT segmentation image to generate the second sub-alignment data. The processor 120 may calculate a transformation matrix from the first alignment data to the second sub-alignment data. The processor 120 may calculate an inverse transformation matrix of the transformation matrix. By applying the inverse transformation matrix to the segmented mandible, mandibular teeth, and mandibular nerve canal, the processor 120 may accurately calculate and represent the positions of the segmented mandible, mandibular teeth, and mandibular nerve canal in the bite state of the oral cavity scan.

[0112] 9, in one embodiment, the processor 120 can generate second sub-alignment data by aligning the mandibular scan image with the CT segmentation image in step S960. In one embodiment, the processor 120 can generate second alignment data by aligning the first sub-alignment data with the second sub-alignment data in step S970. The method of FIG. 9 differs from the method of FIG. 4 in that the method of FIG. 9 does not use the CT scan image as is, but uses a CT segmentation image in which the teeth, maxilla, mandible, and / or mandibular nerve canal are segmented for alignment.

[0113] FIG. 12 is a diagram showing second alignment data according to one embodiment. Image 1210a in FIG. 12 is second alignment data viewed from the front, and image 1210b is first alignment data viewed from the side. That is, the processor 120 can generate first sub-alignment data by aligning the maxillary scan image with the CT segmentation image, and generate second sub-alignment data by aligning the mandibular scan image with the CT segmentation image. At this time, the processor 120 can align the first sub-alignment data and the second sub-alignment data based on the CT segmentation image. Therefore, the second alignment data can indicate the CT occlusion state.

[0114] Computer-readable recording medium

[0115] It is apparent that each step or operation of the method according to the embodiments of the present disclosure can be performed by a computer including one or more processors in response to execution of a computer program stored in a computer-readable recording medium.

[0116] The computer-executable instructions stored in the recording medium can be implemented as a computer program programmed to perform the corresponding steps. Such a computer program can be stored in a computer-readable recording medium and executed by a processor. The computer-readable recording medium can be a non-transitory readable medium. A non-transitory readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, the programs for performing the various methods described above can be stored and provided in a non-transitory readable medium, such as a semiconductor memory device, such as an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory device; a magnetic disk, such as an internal hard disk or a removable disk; a magneto-optical disk; and a non-volatile memory, including a CD-ROM or DVD-ROM disk.

[0117] Methods according to various examples disclosed herein may be provided in a computer program product. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact discreet only memory (CD-ROM)) or online via an application store (e.g., Play Store™). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily generated in a storage medium such as memory on a manufacturer's server, an application store server, or an intermediary server.

[0118] As described above, those skilled in the art to which the present disclosure pertains will understand that the present disclosure may be embodied in other specific forms without changing the technical spirit or essential characteristics thereof. Therefore, the above-described embodiments should be understood to be illustrative in all respects and not limiting. The scope of the present disclosure is defined by the claims below rather than the detailed description, and all modifications and variations derived from the meaning and scope of the claims and equivalent concepts should be construed as being within the scope of the present disclosure.

[0119] The features and advantages described herein are not all-inclusive, and many additional features and advantages will become apparent to those skilled in the art, particularly in view of the drawings, specification, and claims. Furthermore, it should be noted that the language used in this specification has been chosen primarily for ease of reading and for instructional purposes, and may not be chosen to delineate or limit the subject matter of the present disclosure.

[0120] The above description of embodiments of the present disclosure has been presented for purposes of illustration. It is not intended to limit the disclosure to the precise form disclosed or to be exhaustive. Those skilled in the art will recognize that many modifications and variations are possible in light of the above disclosure.

[0121] Accordingly, the scope of the present disclosure is not limited by this detailed description, but rather by any claims in an application based thereon. Accordingly, the disclosure of embodiments of the present disclosure is illustrative and does not limit the scope of the present disclosure, which is set forth in the following claims. [Explanation of symbols]

[0122] 10: 3D oral scanner 15: Oral scan (IOS) image 20: 3D face capture device 25:3D facial image 30: Dental CT equipment 35:CT scan image 100: Dental alignment data generating device 110: Memory 120: Processor 130: Acquisition module 140: Matching module 150: Display module

Claims

1. 1. A method for generating dental alignment data, comprising: acquiring oral scans of the patient's dental region, the oral scans including an upper jaw scan and a lower jaw scan; obtaining a CT image including a dental region of the patient; generating first sub-alignment data by aligning the maxillary scan image to the CT image; generating first alignment data by aligning the mandibular scan image to the first sub-alignment data; generating second sub-alignment data by aligning the mandibular scan image with the CT image; and generating second alignment data by aligning the first sub-alignment data with the second sub-alignment data.

2. receiving a user input for selecting one of the first and second matching data; The method of claim 1 , further comprising the step of: displaying the selected one of the alignment data in response to receiving the user input.

3. receiving user input for a treatment regime for the patient's dental site; selecting one of the first matching data and the second matching data corresponding to the user input; The method of claim 1 , further comprising the step of: displaying the selected one of the alignment data.

4. The method for generating dental alignment data according to claim 1, further comprising the step of obtaining a CT segmentation image in which at least one of maxillary teeth, mandibular teeth, maxilla, mandible, and mandibular nerve canal is segmented by image processing the CT image.

5. The step of generating the first sub-match data includes: generating the first sub-alignment data by aligning the maxillary scan image to the CT segmentation image; The step of generating the second sub-match data includes: The method for generating dental alignment data according to claim 4 , further comprising the step of generating the second sub-alignment data by aligning the mandibular scan image to the CT segmentation image.

6. The step of generating the first alignment data includes: calculating a transformation matrix from the first matching data to the second sub-matching data; and applying an inverse transformation matrix of the transformation matrix to at least one of the segmented mandibular teeth, mandible, and mandibular nerve canal.

7. acquiring a three-dimensional facial image of the patient's face including a dental region; 2. The method of claim 1, further comprising: aligning the 3D facial image with one of the CT image, the first alignment data, and the second alignment data to generate a dental 3D avatar as final alignment data.

8. The step of generating the first sub-match data includes: generating the first sub-alignment data from the maxillary scan image and the CT image using a first deep learning model; 2. The method for generating dental alignment data according to claim 1, wherein the first deep learning model is an artificial intelligence model constructed based on a deep learning algorithm, using a plurality of maxillary scan images and a plurality of CT image sets for a plurality of patients as input data, and a plurality of sub-alignment data sets in which each of the plurality of maxillary scan images is aligned with each of the plurality of CT images as output data, and modeling the correlation between the input data and the output data.

9. The step of generating the second sub-match data includes: generating the second sub-alignment data from the mandibular scan image and the CT image using a second deep learning model; 2. The method for generating dental alignment data according to claim 1, wherein the second deep learning model is an artificial intelligence model constructed based on a deep learning algorithm, using a plurality of mandibular scan images and a plurality of CT image sets for a plurality of patients as input data, and a plurality of sub-alignment data sets in which each of the plurality of mandibular scan images is aligned with each of the plurality of CT images as output data, and modeling the correlation between the input data and the output data.

10. the first sub-alignment data and the second sub-alignment data are generated based on at least three landmarks in the three-dimensional data of the patient; The at least three landmarks are extracted by an application for generating dental registration data, 2. The method for generating dental alignment data according to claim 1, wherein the at least three landmarks are extracted using an artificial neural network module built into the application or connected via a network, and the artificial neural network module is pre-trained using pre-training data.

11. 1. An apparatus for generating dental alignment data, comprising: A communication circuit; Memory and a processor, The processor: acquiring oral scans of the patient's dental region, the oral scans including an upper jaw scan and a lower jaw scan; obtaining a CT image including a dental region of the patient; generating first sub-alignment data by aligning the maxillary scan image to the CT image; generating first alignment data by aligning the mandibular scan image to the first sub-alignment data; generating second sub-alignment data by aligning the mandibular scan image with the CT image; An apparatus configured to generate second matched data by matching the first sub-matched data with the second sub-matched data.

12. An input device; a display; and The processor: receiving a user input via the input device to select one of the first and second matching data; 12. The apparatus of claim 11, configured to display the selected piece of matching data via the display in response to receiving the user input.

13. An input device; a display; and The processor: receiving a user input regarding a treatment method for the patient's dental site via the input device; selecting one of the first matching data and the second matching data corresponding to the user input; The device of claim 11, configured to display the selected matching data via the display.

14. The processor: The device according to claim 11, configured to perform image processing on the CT image to obtain a CT segmentation image in which at least one of maxillary teeth, mandibular teeth, maxilla, mandible, and mandibular nerve canal is segmented.

15. The processor: generating the first sub-alignment data by aligning the maxillary scan image to the CT segmentation image; The apparatus of claim 14 , configured to generate the second sub-alignment data by aligning the mandibular scan image to the CT segmentation image.

16. The processor: Calculating a transformation matrix from the first matching data to the second sub-matching data; 16. The apparatus of claim 15, configured to apply an inverse transformation matrix to the transformation matrix to at least one of the segmented mandibular teeth, mandible, and mandibular nerve canal.

17. The processor: obtaining a three-dimensional facial image of the patient's face including a dental region; 12. The apparatus of claim 11, further configured to align the 3D facial image with one of the CT image, the first alignment data, and the second alignment data to generate a dental 3D avatar as final alignment data.

18. The processor: The method is configured to generate the first sub-alignment data from the maxillary scan image and the CT image using a first deep learning model; 12. The device of claim 11, wherein the first deep learning model is an artificial intelligence model constructed based on a deep learning algorithm, using input data consisting of a plurality of maxillary scan images and a plurality of CT image sets for a plurality of patients, and output data consisting of a plurality of sub-aligned data sets in which each of the plurality of maxillary scan images is aligned with each of the plurality of CT images, and modeling the correlation between the input data and the output data.

19. The processor: The method is configured to generate the second sub-alignment data from the mandibular scan image and the CT image using a second deep learning model; 12. The device of claim 11, wherein the second deep learning model is an artificial intelligence model constructed based on a deep learning algorithm, using input data consisting of a plurality of mandibular scan images and a plurality of CT image sets for a plurality of patients, and output data consisting of a plurality of sub-aligned data sets in which each of the plurality of mandibular scan images is aligned with each of the plurality of CT images, and modeling the correlation between the input data and the output data.

20. the first sub-alignment data and the second sub-alignment data are generated based on at least three landmarks in the three-dimensional data of the patient; The at least three landmarks are extracted by an application for generating dental registration data, 12. The device of claim 11, wherein the at least three landmarks are extracted using an artificial neural network module that is built into the application or connected via a network, and the artificial neural network module is pre-trained using pre-training data.

21. 1. A method for generating dental alignment data, comprising: acquiring oral scans of the patient's dental region, the oral scans including an upper jaw scan and a lower jaw scan; obtaining a CT image including a dental region of the patient; obtaining a CT segmentation image in which at least one of maxillary teeth, mandibular teeth, maxilla, mandible, and mandibular nerve canal is segmented by image processing the CT image; generating first sub-alignment data by aligning the maxillary scan image to the CT image; generating first alignment data by aligning the mandibular scan image to the first sub-alignment data; generating second sub-alignment data by aligning the mandibular scan image with the CT image; generating second matched data by matching the first sub-matched data with the second sub-matched data; The step of generating the first alignment data includes: calculating a transformation matrix from the first matching data to the second sub-matching data; applying an inverse transformation matrix to the transformation matrix to at least one of the segmented mandibular teeth, mandible, and mandibular nerve canal.

22. 1. An apparatus for generating dental alignment data, comprising: A communication circuit; Memory and a processor, The processor: acquiring oral scans of the patient's dental region, the oral scans including an upper jaw scan and a lower jaw scan; obtaining a CT image including a dental region of the patient; The CT image is image-processed to obtain a CT segmentation image in which at least one of the maxillary teeth, the mandibular teeth, the maxilla, the mandible, and the mandibular nerve canal is segmented; generating first sub-alignment data by aligning the maxillary scan image to the CT image; generating first alignment data by aligning the mandibular scan image to the first sub-alignment data; generating second sub-alignment data by aligning the mandibular scan image with the CT image; configured to generate second matched data by matching the first sub-matched data with the second sub-matched data; The processor: Calculating a transformation matrix from the first matching data to the second sub-matching data; The apparatus is further configured to apply an inverse transformation matrix to the transformation matrix to at least one of the segmented mandibular teeth, mandible, and mandibular nerve canal.

Images