Electronic device and method for generating dental data information
The use of generative AI models for dental data generation addresses the accuracy and efficiency issues in existing dental charting methods, providing objective and efficient dental data processing.
Patent Information
- Application Number
- PCT/KR2025/001323
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-08-01
- Filing Date
- 2025-01-23
- Publication Date
- 2025-09-04
AI Technical Summary
Existing dental charting methods based on panoramic images suffer from low accuracy in recognizing and separating tooth regions, requiring manual correction, which is labor-intensive and time-consuming.
An electronic device and method using generative artificial intelligence models to infer and generate dental data information from X-ray and oral image information, including preprocessing, inference, and generation of customized dental data in various formats.
Improves the objectivity and efficiency of dental data generation, enhancing the quality of dental treatment by providing accurate and personalized dental information.
Smart Images

Figure KR2025001323_04092025_PF_FP_ABST
Abstract
Description
Electronic device and method for generating dental data information
[0001] The present disclosure relates to artificial intelligence (AI) technology, and more specifically, to an electronic device and method for generating dental data information based on individual oral information of a patient through a generative artificial intelligence model.
[0002] As the pace of AI technology development accelerates, it is being utilized in a variety of fields. AI models are expected to become a key tool in the medical field, where analyzing vast amounts of patient and raw medical information is crucial for more accurate diagnoses and treatment plans. With the recent digital transformation of dentistry, the rapid advancement of digital dentistry technology is attracting attention as a tool to support and enhance the work of medical professionals.
[0003] Dental institutions must use electronic medical records (EMR) formats appropriate for the dental specialty to input patient dental examination and treatment information into electronic charts when providing dental care. Medical professionals must objectively communicate the patient's current dental and oral condition and explain any necessary treatment plans. In the past, medical professionals manually entered information about the patient's dental condition onto paper or electronic charts based on individual patient X-rays and visual examinations of the oral cavity. However, this method was labor-intensive and time-consuming. To address this, charting methods based on panoramic images of the teeth have been proposed. However, this method suffers from low accuracy in recognizing and separating tooth regions, requiring subsequent correction of designated tooth regions.
[0004] In relation to this, reference may be made to Korean Patent Publication No. 10-2024-0003371A and Korean Patent Registration No. 10-2634835B1.
[0005] The present disclosure aims to provide an electronic device and method for generating dental data information based on individual oral information of a patient through a generative artificial intelligence model.
[0006] The present disclosure aims to provide an electronic device and method for generating customized dental data information for a patient based on input information in various formats.
[0007] The problems to be solved by the present disclosure are not limited to the problems described above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.
[0008] In a method for generating dental data information performed by an electronic device according to one embodiment of the present disclosure, the method for generating dental data information may include a step of obtaining input information including X-ray image information of a patient from an external terminal, a step of inferring dental information for each tooth type of the patient based on the input information through a first artificial intelligence model, and a step of generating dental data information based on the dental information for each tooth type through a second artificial intelligence model.
[0009] As an example, the method for generating dental data information may further include a step of obtaining a request for modification of the dental data information from the external terminal and a step of modifying the dental data information based on the modification request.
[0010] For example, the input information further includes oral image information of the patient, and the step of inferring tooth information for each tooth type of the patient may include a step of recognizing the first tooth of the patient for each of the X-ray image and the oral image information through the first artificial intelligence model, a step of extracting first tooth condition information related to the first tooth based on the X-ray image information through the first artificial intelligence model, a step of extracting second tooth condition information related to the first tooth based on the oral image information through the first artificial intelligence model, and a step of inferring first tooth information for the first tooth based on the first tooth information and the second tooth information through the first artificial intelligence model.
[0011] For example, the input information may further include dental treatment-related information including at least a portion of the patient's treatment history information, dental management information, and prior medical examination information, and the step of inferring the patient's tooth information by type may include a step of recognizing the patient's second tooth with respect to each of the X-ray image, the oral image information, and the dental treatment-related information through the first artificial intelligence model, a step of extracting third tooth condition information related to the second tooth based on the X-ray image information through the first artificial intelligence model, a step of extracting fourth tooth condition information related to the second tooth based on the oral image information through the first artificial intelligence model, a step of extracting fifth tooth condition information related to the second tooth based on the dental treatment-related information through the first artificial intelligence model, and a step of inferring second tooth information for the second tooth based on the first tooth information, the second tooth information, and the third tooth information through the first artificial intelligence model.
[0012] As an example, the step of inferring the patient's dental information by type may further include the step of performing preprocessing on each of the X-ray image and the oral image information to recognize the first tooth for each of the X-ray image and the oral image information.
[0013] For example, the dental data information may include information in at least one form of video, image, text, and voice.
[0014] For example, the first artificial intelligence model may perform an update based on the patient's dental information inferred in response to the input information, and the second artificial intelligence model may perform an update based on dental data information generated in response to the dental information in response to the dental information inferred in response to the input information.
[0015] As an example, the method for generating dental data information may further include a step of providing the dental data information to the external terminal.
[0016] An electronic device for generating dental data information according to one embodiment of the present disclosure comprises a transceiver, a memory for storing commands, and a processor, wherein the processor connected to the transceiver and the memory obtains input information including X-ray image information of a patient from a first terminal, infers dental information for each tooth type of the patient based on the input information through a first artificial intelligence model, and generates dental data information based on the dental information for each tooth type through a second artificial intelligence model.
[0017] In one embodiment of the present disclosure, a computer program stored in a computer-readable storage medium for executing a method for generating dental data information, combined with hardware, the method for generating dental data information may include a step of acquiring input information including X-ray image information of a patient from a first terminal, a step of inferring dental information for each tooth type of the patient based on the input information through a first artificial intelligence model, and a step of generating dental data information based on the dental information for each tooth type through a second artificial intelligence model.
[0018] According to an embodiment of the present disclosure, by generating dental data information based on individual oral information of a patient through a generative artificial intelligence model, the objectivity of the derived dental data information and the efficiency of dental treatment can be improved.
[0019] According to an embodiment of the present disclosure, the quality of dental treatment can be improved by generating customized dental data information for a patient based on input information in various formats.
[0020] The effects according to the present disclosure are not limited to the effects described above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.
[0021] FIG. 1 is a block diagram illustrating a dental data information generation system according to an embodiment of the present disclosure.
[0022] FIG. 2 is a block diagram illustrating an electronic device according to an embodiment of the present disclosure.
[0023] FIG. 3 is a block diagram illustrating a dental data information generation unit according to an embodiment of the present disclosure.
[0024] FIGS. 4A and 4B are diagrams for explaining information input to an electronic device according to an embodiment of the present disclosure.
[0025] FIGS. 5A and 5C are drawings for explaining dental data information output from an electronic device according to an embodiment of the present disclosure.
[0026] FIG. 5d is a drawing for explaining a page provided from an electronic device according to an embodiment of the present disclosure.
[0027] FIG. 6 is a flowchart illustrating a method for generating dental data information according to an embodiment of the present disclosure.
[0028] FIG. 7 is a block diagram illustrating an electronic device according to an embodiment of the present disclosure.
[0029] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the contents described in the attached drawings. However, the present invention is not limited or restricted by the exemplary embodiments. Unless otherwise defined, all terms (including technical and scientific terms) used in this specification shall be used with meanings that can be commonly understood by those of ordinary skill in the technical field to which this disclosure pertains. However, this may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc.
[0030] Additionally, terms defined in commonly used dictionaries should not be interpreted ideally or excessively unless explicitly and specifically defined otherwise. In certain cases, terms may be arbitrarily selected by the applicant, in which case their meanings will be described in detail in the relevant description. Therefore, the terms used in this disclosure should be defined based on their meaning and the overall content of this disclosure, rather than simply their names.
[0031] Throughout this specification, when a part is said to "include" a certain component, this does not mean that other components may be included, but rather that other components may be excluded, unless specifically stated otherwise. Furthermore, the singular forms used herein also include plural forms unless specifically stated otherwise. Furthermore, the expression "at least one of a, b, and / or c" used throughout this specification can encompass "a alone," "b alone," "c alone," "a and b," "a and c," "b and c," or "all of a, b, and c."
[0032] Meanwhile, terms such as "first and / or second" used in this specification may be used to describe various components, but are only used to distinguish one component from another and are not intended to be limited to the components referred to by those terms. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and the second component may also be referred to as the first component.
[0033] In addition, terms such as “unit”, “module”, etc. described in this specification mean a unit that processes at least one function or operation, which may be implemented by hardware or software, or a combination of hardware and software. In addition, embodiments of the present disclosure in this specification may be represented by functional block configurations and various processing steps. These functional blocks may be implemented by various numbers of hardware or / and software configurations that execute specific functions. For example, embodiments of the present disclosure may employ direct circuit configurations such as memory, processing, logic, look-up tables, etc. that may execute various functions under the control of one or more microprocessors or other control devices.
[0034] Meanwhile, the "electronic device" or "terminal" described in this specification may be implemented as a computer or portable terminal that can connect to a server or other terminal via a network. Here, the computer includes a notebook, desktop, laptop, etc. equipped with a web browser, and the portable terminal is a wireless communication device that ensures portability and mobility, and may include all types of handheld-based wireless communication devices such as communication-based terminals such as IMT (International Mobile Telecommunication), CDMA (Code Division Multiple Access), W-CDMA (W-Code Division Multiple Access), LTE (Long Term Evolution), smartphones, tablet PCs, etc. In addition, the "electronic device" or "terminal" in this specification may also include a processor, a memory that stores and executes program data, a permanent storage such as a disk drive, a communication port that communicates with an external device, a user interface device such as a touch panel, a key, a button, etc.
[0035] In embodiments according to the present disclosure, functions related to artificial intelligence may be implemented through a processor and memory. In this case, the processor may be any one of a general-purpose processor such as a CPU (Center Processing Unit), an AP (Application Processor), a DSP (Digital Signal Processor), a graphics-only processor such as a GPU (Graphics Processing Unit), a VPU (Vision Processing Unit), and an AI-only processor such as an NPU (Neural Network Processing Unit). The processor may process input data according to predefined operation rules or AI models stored in the memory. Alternatively, if the processor is an AI-only processor, the AI-only processor may be designed with a hardware structure specialized for processing a specific AI model. In some embodiments according to the present disclosure, functions related to artificial intelligence may be implemented through a plurality of processors.
[0036] In embodiments of the present disclosure, predefined operating rules or artificial intelligence models may be configured to perform machine learning. Here, "configured to perform machine learning" means that the predefined operating rules or artificial intelligence models are trained using a learning algorithm and a plurality of learning data sets to perform a desired characteristic (or purpose). This learning may be performed within the device itself implementing the artificial intelligence according to the present disclosure, or may be performed through a separate server and / or system.
[0037] Artificial intelligence models can be implemented as neural networks (or artificial neural networks) and operate based on statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network can refer to a general model in which artificial neurons (nodes) form a network by combining synapses, and through learning, the strength of the synaptic connections changes, thereby achieving problem-solving capabilities. A neural network can be composed of multiple neural network layers. For example, a neural network can include an input layer, a hidden layer, and an output layer. Each of the multiple neural network layers can include at least one node and at least one weight, and can perform neural network operations through operations between the computational results of the previous (precious) layer and the weights. At least one weight of the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, at least one weight can be updated during the learning process to reduce or minimize the loss or cost values obtained from the artificial intelligence model. Neural networks can infer the desired outcome from arbitrary input.
[0038] The learning methods of artificial intelligence models can be categorized into supervised learning, where input and output data are provided as training data, and the correct answer (output data) corresponding to the problem (input data) is determined, unsupervised learning, where only input data is provided without output data, and the correct answer (output data) corresponding to the problem (input data) is not determined, and reinforcement learning, where a reward is given whenever an action is taken in the current state, and learning progresses in the direction of maximizing this reward. Alternatively, they can be categorized according to the architecture, which is the structure of the learning model.
[0039] In an embodiment of the present disclosure, the artificial intelligence model is a CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, etc., R-CNN (Region with Convolution Neural Network), RPN (Region Proposal Network), RNN (Recurrent Neural Network), S-DNN (Stacking-based deep Neural Network), S-SDNN (State-Space Dynamic Neural Network), Deconvolution Network, DBN (Deep Belief Network), RBM (Restrcted Boltzman Machine), Fully Convolutional Network, LSTM (Long Short-Term Memory) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT for natural language processing, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet for data intelligence, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization, At least one of various artificial intelligence structures and algorithms, such as Recommendation, Data Creation, etc., may be used, and the above-described examples are merely listing examples of artificial intelligence structures and algorithms used according to embodiments of the present disclosure, and do not limit the artificial intelligence structures and algorithms used according to embodiments of the present disclosure.
[0040] Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In describing the embodiments, descriptions of technical details that are well known in the technical field to which the present invention pertains and are not directly related to the present invention will be omitted. This is to convey the gist of the present invention more clearly without obscuring unnecessary explanation. For the same reason, some components in the accompanying drawings are exaggerated, omitted, or schematically depicted. Furthermore, the size of each component does not entirely reflect the actual size. Throughout this specification, the same reference numerals may refer to the same or corresponding components.
[0041] FIG. 1 is a block diagram illustrating a dental data information generation system (10) according to an embodiment of the present disclosure.
[0042] Referring to FIG. 1, a dental data information generation system (10) according to an embodiment of the present disclosure may include a photographing device (110), a first terminal (120_1), a second terminal (120_2), and an electronic device (130). In the dental data information generation system (10) according to an embodiment of the present disclosure, the photographing device (110) may communicate with the first terminal (120_1) through a network or a physically implemented electrical connection structure and provide information. In addition, the first terminal (120_1) may communicate with the electronic device (130) through a network or a physically implemented electrical connection structure and exchange information. In addition, the first terminal (120_1) may communicate with the second terminal (120_2) through a network or a physically implemented electrical connection structure and provide information.
[0043] According to an embodiment of the present disclosure, the network may include at least one of a Personal Area Network (PAN), a Local Area Network (LAN), a Campus Area Network (CAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Broad Band Network (BBN), and the Internet. In addition, the network may include at least one of network topologies including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree, or a hierarchical network. In an embodiment of the present disclosure, the communication method performed is not limited to the types of the above-described networks, and may include not only a communication method utilizing a communication network that the network may include, but also short-range wireless communication between devices.
[0044] In an embodiment of the present disclosure, the electronic device (130) may include a transceiver, a memory, and a processor. In addition, the electronic device (130) may refer to a unit that processes at least one function or operation, which may be implemented by hardware, software, or a combination of hardware and software. In an embodiment, the electronic device (130) may include at least one of a plurality of computer systems and computer software implemented as network servers. For example, the electronic device (130) may refer to at least one of a computer system and computer software that is connected to a lower device that can communicate with another network server through a computer network such as an intranet or the Internet, receives a task execution request, performs the task accordingly, and provides the execution result.
[0045] Meanwhile, although the first terminal (120_1) and the electronic device (130) are mentioned in this specification as being physically separate components, this is only some embodiments according to the present disclosure, and according to another embodiment of the present disclosure, the electronic device (130) may be implemented by being included in the first terminal (120_1) or combined with the first terminal (120_1) to execute the method for generating dental data information according to the embodiment of the present disclosure. In other words, the first terminal (120_1) and the electronic device (130) may be logically separate structures and may be implemented by separate functions. In addition, the electronic device (130) may be understood as a broad concept including a series of application programs that can operate on a network server and various databases built inside. For example, the electronic device (130) may be implemented using a network server program that is provided in various ways according to an operating system such as DOS, Windows, Linux, Unix, or MacOS.
[0046] In an embodiment of the present disclosure, the photographing device (110) is a device for photographing a patient's teeth, and may include at least some of a dental X-ray device, a dental Cone-Beam Computed Tomography (CBCT) device, and a camera. In the embodiment, images and image information (e.g., patient's teeth X-ray image information, oral image information, etc.) of the patient's teeth photographed by the photographing device (110) may be provided to the first terminal (120_1).
[0047] In an embodiment of the present disclosure, the first terminal (120_1) may be a terminal used by a specialist (medical staff) and may refer to a terminal to which the specialist has been granted access authority. In an embodiment, the first terminal (120_1) may store at least a portion of the patient's dental X-ray image information and oral image information provided from the photographing device (110). In addition, the first terminal (120_1) may store the patient's dental treatment-related information, and the dental treatment-related information may include at least a portion of the patient's treatment history information, dental management information, and prior medical examination information. Each of the dental X-ray image information, the oral image information, and the dental treatment-related information may be in the form of at least one of a video, an image, text, and a voice. The first terminal (120_1) may provide at least a portion of the patient's dental X-ray image information and the oral image information to the electronic device (130) as first input information, and in some embodiments, the first input information may further include treatment-related information.
[0048] An electronic device (130) according to an embodiment of the present disclosure may generate dental data information based on at least a portion of the first input information acquired from a first terminal (120_1). The electronic device (130) may generate dental data information using an artificial intelligence model, and in an embodiment, the dental data information may include at least a portion of chart draft information, consultation data information, and virtual treatment result information. A method for generating dental data information according to an embodiment of the present disclosure will be described in detail with reference to FIGS. 2 to 6 to be described later. Meanwhile, at least a portion of the dental data information generated by the electronic device (130) may be provided to the first terminal (120_1) as first output information, and the first terminal (120_1) may provide at least a portion of the first output information to the second terminal (120_2). The second terminal (120_2) is a terminal used by a patient, and may refer to a terminal of a patient to which access rights have been granted by a specialist.
[0049] Meanwhile, in some embodiments, the electronic device (130) may perform communication with the photographing device (110) through a network and obtain information from the photographing device (110). As a specific example, the electronic device (130) may obtain at least a portion of the patient's dental X-ray image information and oral image information photographed by the photographing device (110). In addition, in some embodiments, the electronic device (130) may perform communication with the second terminal (120_1) through a network and exchange information. In an embodiment, the second input information provided to the electronic device (130) from the second terminal (120_2) may be the patient's dental treatment-related information stored or input in the second terminal (120_2), and the second output information provided to the second terminal (120_2) from the electronic device (130) may correspond to at least a portion of the dental data information provided from the electronic device (130) selected by an expert.
[0050] The dental data information system (10) according to an embodiment of the present disclosure can increase the objectivity of the derived dental data information and the efficiency of dental treatment by generating dental data information based on individual oral information of a patient through a generative artificial intelligence model. In addition, the dental data information system (10) according to an embodiment of the present disclosure can improve the quality of dental treatment by generating customized dental data information for a patient based on input information in various formats. In addition, the dental data information system (10) according to an embodiment of the present disclosure can be applied to any purpose that performs generation or judgment using dental information other than generating chart draft information, generating consultation data information, and generating virtual treatment result information.
[0051] Meanwhile, in FIG. 1, the photographing device (110), the first terminal (120_1), and the second terminal (120_2) are each illustrated as one configuration, but this is only one embodiment presented for the convenience of explanation, and does not limit the configuration of the dental data information system (10) according to the present disclosure. According to another embodiment of the present disclosure, the dental data information system (10) may include at least one photographing device (110), at least one first terminal (at least one terminal for a professional) (120_1), and at least one second terminal (at least one terminal for a patient) (120_2).
[0052] FIG. 2 is a block diagram illustrating an electronic device (200) according to an embodiment of the present disclosure.
[0053] The electronic device (200) illustrated in FIG. 2 may correspond to the electronic device (130, see FIG. 1) of FIG. 1 described above, and referring to FIG. 2, the electronic device (200) according to an embodiment of the present disclosure may include a data input unit (210), a dental data information generation unit (220), and a storage and communication unit (230). The configuration of the electronic device (200) illustrated in FIG. 2 illustrates a configuration according to a function performed by the electronic device (200), and may mean a logical or physical configuration.
[0054] A data input unit (210) according to an embodiment of the present disclosure may obtain input information provided from a first terminal (120_1, see FIG. 1) and perform information processing on the obtained input information. In an embodiment, the input information may include at least a portion of the patient's X-ray image information and oral image information captured by a photographing device (110, see FIG. 1), and in some embodiments, may further include dental treatment-related information including at least a portion of the patient's treatment history information, dental care information, and prior medical examination information.
[0055] In some embodiments, the data input unit (210) may perform preprocessing on input information obtained from the first terminal (120_1), and the preprocessing on the input information may be performed to optimize the input information for subsequent information processing. For example, the preprocessing operation on the input information may include at least some of a first operation of classifying the input information based on at least one of the type and format of the input information, a second operation of performing resizing on the input information, a third operation of performing resolution correction on the input information, and a fourth operation of performing cropping on the input information. The data input unit (210) may provide the input information or the preprocessed input information to the dental data information generation unit (220).
[0056] The dental data information generation unit (220) according to an embodiment of the present disclosure can generate dental data information based on input information obtained from the data input unit (210) or preprocessed input information, and in an embodiment, the dental data information can include at least some of chart draft information, consultation data information, and virtual treatment result information. Specifically, the dental data information generation unit (220) can infer tooth information by type based on input information through an artificial intelligence model, and generate dental data information based on the inferred tooth information by type. A specific method of inferring tooth information by type and generating dental data information according to an embodiment of the present disclosure will be described in detail with reference to FIG. 3 below. The dental data information generation unit (220) can provide the generated dental data information to the storage and communication unit (230).
[0057] The storage and communication unit (230) according to an embodiment of the present disclosure may store the tooth information by tooth type derived in the process of generating dental data information obtained from the dental data information generation unit (220) and the finally derived dental data information, or provide them to a first terminal (120_1) to which a specialist is granted access. In some embodiments, the storage and communication unit (230) may provide at least a part of the tooth information by tooth type derived in the process of generating dental data information and the finally derived dental data information to a second terminal (120_2) to which a patient is granted access. The tooth information by tooth type derived in the process of generating dental data information stored in the storage and communication unit (230) and the finally derived dental data information may be used to update the artificial intelligence model included in the dental data information generation unit (220).
[0058] FIG. 3 is a block diagram illustrating a dental data information generation unit (300) according to an embodiment of the present disclosure.
[0059] The dental data information generation unit (300) illustrated in FIG. 3 may correspond to the dental data information generation unit (220, see FIG. 2) of FIG. 2 described above, and referring to FIG. 3, the dental data information generation unit (300) may include an inference unit (310), a chart draft information generation unit (320), a consultation data information generation unit (330), a virtual treatment result information generation unit (340), and a modification unit (350). The configuration of the dental data information generation unit (300) illustrated in FIG. 3 illustrates a configuration according to a function performed by the dental data information generation unit (300), and may mean a logical or physical configuration.
[0060] According to an embodiment of the present disclosure, the inference unit (310) can infer tooth information for each tooth type from input information or preprocessed input information through a first artificial intelligence model corresponding to an inference-type artificial intelligence model. Specifically, when the input information includes X-ray image information, the inference unit (310) can recognize a first tooth from the X-ray image information through the first artificial intelligence model and infer first tooth condition information for the recognized first tooth. The first tooth condition information for the first tooth is information indicating the condition of the first tooth that can be inferred from the X-ray image information, and may include at least a part of information on whether the first tooth has caries, whether it has undergone root canal treatment, whether it has periapical inflammation, whether it has been implanted, and whether it has been extracted. The inference unit (310) can derive first tooth condition information corresponding to each of the second to Nth teeth (N corresponds to the number of teeth of the patient) other than the first tooth in series or in parallel with the inference of the first tooth condition information for the first tooth.
[0061] Alternatively, when the input information includes X-ray image information and oral image information, the inference unit (310) can recognize the first tooth from the X-ray image information through the first artificial intelligence model, infer first tooth condition information for the recognized first tooth, recognize the first tooth from the oral image information, and infer second tooth condition information for the recognized first tooth. The second tooth condition information for the first tooth is information indicating the condition of the first tooth that can be inferred from the oral image information, and can include at least some of information on whether the first tooth is restored, the restoration material, and the restoration range. The inference unit (310) can derive the first tooth condition information and the second tooth condition information corresponding to each of the second to Nth teeth other than the first tooth in series or in parallel with the inference of the first tooth condition information and the second tooth condition information for the first tooth.
[0062] Alternatively, when the input information further includes dental treatment-related information, the inference unit (310) can recognize the first tooth from the dental treatment-related information through the first artificial intelligence model and infer third tooth condition information for the recognized first tooth. The third tooth condition information for the first tooth is information indicating the condition of the first tooth that can be inferred from the dental treatment-related information, and may include at least some of the treatment history information, dental management information, and prior medical examination information of the first tooth. The inference unit (310) can derive the first tooth condition information, the second tooth condition information, and the third tooth condition information corresponding to the second to Nth teeth other than the first tooth, respectively, serially or in parallel with the inference of the first tooth condition information, the second tooth condition information, and the third tooth condition information for the first tooth.
[0063] The inference unit (310) can derive tooth information by type, including at least a part of the first tooth condition information, the second tooth condition information, and the third tooth condition information corresponding to each of the first to Nth teeth, and can provide the derived tooth information by type to at least one of the chart draft information generation unit (320), the consultation data information generation unit (330), and the virtual treatment result information generation unit (340). Meanwhile, the tooth condition information and tooth information by type corresponding to each tooth derived from the inference unit (310) can be stored in the storage and communication unit (230, see FIG. 2) described above in FIG. 2, and the first artificial intelligence model included in the inference unit (310) can be updated based on at least a part of the tooth condition information and tooth information by type corresponding to each tooth stored in the storage and communication unit (230).
[0064] The chart draft information generation unit (320) according to an embodiment of the present disclosure can generate chart draft information from tooth information by tooth type through a second artificial intelligence model corresponding to a generative artificial intelligence model. In an embodiment, the chart draft information may refer to a medical record for recording the dental condition and treatment process of a patient. According to an embodiment of the present disclosure, the chart draft information generation unit (320) adaptively generates chart draft information based on the tooth information by individual tooth type of the patient, and thus can generate customized chart draft information for each patient. In other words, the chart draft information generation unit (320) can provide an optimized medical record by generating chart draft information by reflecting the number of teeth, tooth shape, treatment history, etc. based on the tooth information by individual tooth type of the patient. The specific form of the chart draft information derived according to an embodiment of the present disclosure will be described in detail with reference to FIG. 5A, which will be described later.
[0065] The consultation data information generation unit (330) according to an embodiment of the present disclosure can generate consultation data information from tooth information by type through a second artificial intelligence model corresponding to a generative artificial intelligence model. In the embodiment, the consultation data information may mean data for intuitively explaining to the patient the patient's current dental condition, treatment process, and expected treatment results. According to an embodiment of the present disclosure, the consultation data information generation unit (330) adaptively generates consultation data information based on the patient's individual tooth information by type, and thus can generate customized consultation data for each patient. The specific form of the consultation data information derived according to an embodiment of the present disclosure will be described in detail with reference to FIG. 5b, which will be described later.
[0066] The virtual treatment result information generation unit (340) according to an embodiment of the present disclosure can generate virtual treatment result information from tooth information for each tooth type through a second artificial intelligence model corresponding to a generative artificial intelligence model. In the embodiment, the virtual treatment result information may mean simulation data including the patient's current dental condition and expected treatment result. According to an embodiment of the present disclosure, the virtual treatment result information generation unit (340) adaptively generates consultation data information based on the patient's individual tooth information for each tooth type, and thus can generate customized simulation data for each patient. The specific form of the virtual treatment result information derived according to an embodiment of the present disclosure will be described in detail with reference to FIG. 5c, which will be described later.
[0067] According to an embodiment of the present disclosure, at least some of the chart draft information, consultation material information, and virtual treatment result information may be provided to a modification unit (350), and the modification unit (350) may modify (correct) at least some of the chart draft information, consultation material information, and virtual treatment result information based on a modification request obtained through a first terminal (120_1, see FIG. 1). The modification request obtained through the first terminal (120_1) may be based on an expert's user input for the first terminal (120_1), and may include any information related to matters to be omitted or supplemented in generating dental material information. If a request for modification through the first terminal (120_1) is confirmed, the modification unit (350) can provide the finally modified dental data information to the external terminal, and if a separate request for modification through the first terminal (120_1) is not confirmed, dental data information derived from at least one of the chart draft information generation unit (320), the consultation data information generation unit (330), and the virtual treatment result information generation unit (340) can be provided to the external terminal without modification.
[0068] As described above, the first operation of inferring dental information by type based on input information is performed through a first artificial intelligence model corresponding to an inferential artificial intelligence model, and the second operation of generating dental data information based on dental information by type is described as being performed through a second artificial intelligence model corresponding to a generative artificial intelligence model, and thus using separate artificial intelligence models. However, this is only one embodiment according to the present disclosure presented for convenience of explanation, and does not limit the form and number of artificial intelligence models used in the present disclosure. In other words, in the embodiment of the present disclosure, artificial intelligence models of any form and number capable of inferring and generating operations may be used.
[0069] In addition, although each of the chart draft information generation unit (320), the consultation data information generation unit (330), and the virtual treatment result information generation unit (340) is described as generating information through a second artificial intelligence model corresponding to the generative artificial intelligence model and thus using the same artificial intelligence model, this is only one embodiment of the present disclosure presented for convenience of explanation, and does not limit the form and number of artificial intelligence models used in generating dental data information. In other words, in another embodiment of the present disclosure, the chart draft information generation unit (320), the consultation data information generation unit (330), and the virtual treatment result information generation unit (340) may generate dental data information corresponding to each configuration through independent artificial intelligence models.
[0070] FIGS. 4A and 4B are diagrams for explaining information input to an electronic device (130, see FIG. 1) according to an embodiment of the present disclosure.
[0071] Specifically, FIG. 4a illustrates X-ray image information (IN1) input to the electronic device (130), and as described above in FIG. 3, the inference unit (310, see FIG. 3) of the electronic device (130) can infer first tooth condition information for each tooth based on the X-ray image information (IN1). Meanwhile, FIG. 4b illustrates oral cavity image information (IN2) input to the electronic device (130), and as described above in FIG. 3, the inference unit (310) of the electronic device (130) can infer second tooth condition information for each tooth based on the oral cavity image information (IN2).
[0072] The inference unit (310) can recognize the first tooth (TX) on the X-ray image information (IN1) from the X-ray image information (IN1), and infer the first tooth state information for the first tooth (TX). Meanwhile, the inference unit (310) can recognize the first tooth (TI) on the oral image information (IN2) from the oral image information (IN2), and infer the second tooth state information for the first tooth (TI). Here, the first tooth (TX) on the X-ray image information (IN1) and the first tooth (TI) on the oral image information (IN2) may correspond. The inference unit (310) can infer the tooth information for the first tooth (TX, TI) based on the first tooth state information and the second tooth state information, and can derive the tooth information for each tooth type based on the tooth information corresponding to each of the first to Nth teeth.
[0073] Meanwhile, although not shown, if the input information for the electronic device (130) further includes dental treatment-related information, the inference unit (310) can infer third tooth status information corresponding to each of the first to Nth teeth based on the dental treatment-related information, and derive tooth information for each tooth type by reflecting the inferred third tooth status information.
[0074] FIGS. 5A and 5C are drawings for explaining dental data information output from an electronic device (130, see FIG. 1) according to an embodiment of the present disclosure.
[0075] Specifically, FIG. 5A illustrates chart draft information (OUT1) generated from an electronic device (130). As described above with reference to FIG. 3, the chart draft information generation unit (320, see FIG. 3) of the electronic device (130) can generate chart draft information (OUT1) based on the tooth information for each tooth type derived from the inference unit (310, see FIG. 3). The chart draft information (OUT1) can be adaptively generated for the tooth information for each tooth type of the patient, and thus can be generated in an individualized (or personalized) form for each patient. The chart draft information (OUT1) generated from the electronic device (130) can include information in at least one form of video, image, text, and voice. The generated chart draft information (OUT1) can be used for chart preparation work by an expert.
[0076] Meanwhile, FIG. 5b illustrates consultation data information (OUT2) generated from an electronic device (130). As described above in FIG. 3, the consultation data information generation unit (330, see FIG. 3) of the electronic device (130) can generate consultation data information (OUT2) based on the tooth information for each tooth type derived from the inference unit (310). The consultation data information (OUT2) can also be adaptively generated for the tooth information for each tooth type of the patient, and thus can be generated in an individualized (or personalized) form for each patient, and can include information in at least one form of video, image, text, and voice. The generated consultation data information (OUT2) can be used to facilitate easier treatment through illustration images or explanatory information that are easy for the patient to understand.
[0077] Meanwhile, FIG. 5c illustrates virtual treatment result information (OUT3) generated from the electronic device (130). As described above in FIG. 3, the virtual treatment result information generation unit (340, see FIG. 3) of the electronic device (130) can generate virtual treatment result information (OUT3) based on the tooth information for each tooth type derived from the inference unit (310). The virtual treatment result information (OUT3) can also be adaptively generated for the tooth information for each tooth type of the patient, and thus can be generated in an individualized (or personalized) form for each patient, and can include information in at least one form of video, image, text, and voice. The generated virtual treatment result information (OUT3) can be used to explain the treatment result to the patient.
[0078] The output information of FIGS. 5A to 5C illustrated in this specification is merely an example of output information that can be derived according to some embodiments of the present disclosure, and does not limit the types of output information that can be derived from the present disclosure. For example, according to an embodiment of the present disclosure, a determination as to whether a person is the same can be made based on dental information for each tooth identification, and in addition, the electronic device (130) can also be used for any purpose that generates or determines using dental information.
[0079] Meanwhile, FIG. 5d is a drawing for explaining a page (PAGE) provided from an electronic device (130, see FIG. 1) according to an embodiment of the present disclosure.
[0080] The page (PAGE) illustrated in FIG. 5d may be provided through a dental data information processing program provided from an electronic device (130) according to an embodiment of the present disclosure to a first terminal (120_1, see FIG. 1), and may be configured to include output information selected according to a user input. In the embodiment illustrated in FIG. 5d, the page (PAGE) provided to the first terminal (120_1) may include patient X-ray image information (510), chart draft information (520), and tooth information (530) by type. In the embodiment, the tooth information (530) by type may include tooth information of a type selected in response to a user input for the page (PAGE). For example, a user may select at least one dental formula from the chart draft information (520) on a page (PAGE) provided for the first terminal (120_1), and the electronic device (130) may provide a page (PAGE) including dental information of the selected dental formula to the first terminal (120_1). The page (PAGE) illustrated in FIG. 5d merely illustrates a page (PAGE) provided according to an embodiment of the present disclosure, and does not limit the page form of a program provided according to the present disclosure. A page provided from a program provided according to an embodiment of the present disclosure may be configured to include at least some of the output information (OUT1, OUT2, OUT3) described in FIGS. 5a to 5c described above, and the type of information included in the page (PAGE) may be determined in response to a user's request to the electronic device (130).
[0081] FIG. 6 is a flowchart illustrating a method for generating dental data information according to an embodiment of the present disclosure.
[0082] In step S610, an electronic device (130, see FIG. 1) according to an embodiment of the present disclosure may obtain input information from a first terminal (120_1, see FIG. 1). In an embodiment, the input information may include at least a portion of the patient's X-ray image information and oral image information captured by a photographing device (110, see FIG. 1), and in some embodiments, may further include dental treatment-related information including at least a portion of the patient's treatment history information, dental care information, and prior medical examination information. In some embodiments, the electronic device (130) may perform preprocessing on the input information obtained from the first terminal (120_1), and the preprocessing on the input information may be performed to optimize the input information for subsequent information processing.
[0083] In step S620, the electronic device (130) according to an embodiment of the present disclosure can infer tooth information for each tooth type of the patient based on input information or preprocessed input information. Specifically, the electronic device (130) can perform tooth recognition on the input information or preprocessed input information and infer tooth information for each tooth type of the patient based on the inferred state information corresponding to each tooth. A specific method for inferring tooth information for each tooth type of the patient based on the input information or preprocessed input information can be based on the operation of the inference unit (310, see FIG. 3) described through FIG. 3 described above.
[0084] In step S630, the electronic device (130) according to the embodiment of the present disclosure may generate dental data information based on the tooth information for each tooth type inferred in step S620 through the second artificial intelligence model. In the embodiment, the dental data information generated by the electronic device (130) may include at least some of chart draft information, consultation data information, and virtual treatment result information. A specific method for generating dental data information based on the tooth information for each tooth type may be based on the operations of the chart draft information generating unit (320, see FIG. 3), the consultation data information generating unit (330, see FIG. 3), and the virtual treatment result information generating unit (340, see FIG. 3) described through the above-described FIG. 3.
[0085] At step S640, the electronic device (130) according to an embodiment of the present disclosure can check whether a modification request has been received from the first terminal (120_1). In an embodiment, the modification request may be a modification request based on user input from an expert regarding any information related to matters that are missing or need to be supplemented when generating dental data information. If it is confirmed that a modification request has been received from the first terminal (120_1), the procedure may proceed to step S650, and if it is confirmed that a modification request has not been received from the first terminal (120_1), the procedure may proceed to step S660.
[0086] In step S650, the electronic device (130) according to the embodiment of the present disclosure may modify the dental data information generated in step S630 based on the modification request obtained in step S640. For example, if the modification request includes a request for adjusting the spacing between the first tooth and the second tooth, the electronic device (130) may modify the dental data information so that the spacing between the first tooth and the second tooth is adjusted in response to the request. Alternatively, if the modification request includes a request for deleting the first tooth (e.g., scheduled for extraction) or adding a tooth (e.g., scheduled for implant), the electronic device (130) may modify the dental data information so that the first tooth is deleted or the dental data information so that the additional tooth is included in response to the request.
[0087] At step S660, the electronic device (130) according to an embodiment of the present disclosure may provide the finally derived dental data information as output information to an external terminal. The output information provided to the external terminal may be in the form of at least one of video, image, text, and voice. In some embodiments, there may be no restrictions on the provision of output information to a first terminal (120_1) to which access rights are granted to a specialist, but only some information permitted by the specialist among the output information may be provided to a second terminal (120_2) to which access rights are granted to a patient.
[0088] FIG. 7 is a block diagram illustrating an electronic device (700) according to an embodiment of the present disclosure.
[0089] The electronic device (700) illustrated in FIG. 7 may correspond to the electronic device (130, see FIG. 1) of FIG. 1 described above. Referring to FIG. 7, the electronic device (700) according to an embodiment of the present disclosure may include a transceiver (710), a processor (720), and a memory (630).
[0090] The electronic device (700) can be connected to at least one of an external terminal and an external device through a transceiver (710) and exchange data. For example, the electronic device (700) can be connected to at least one of a photographing device (110, see FIG. 1), a first terminal (120_1, see FIG. 1), and a second terminal (120_2, see FIG. 2) through the transceiver (710).
[0091] The processor (720) can perform at least one operation by the device and at least one method described through the above-described FIGS. 1 to 6. In addition, the processor (720) can execute a program for performing at least one operation by the device and at least one method described through the above-described FIGS. 1 to 6, and can process information and control the electronic device (700) to perform at least one operation by the device and at least one method described through the above-described FIGS. 1 to 6.
[0092] The memory (730) can store information for performing operations and at least one method by at least one device described through FIGS. 1 to 6. In addition, the memory (730) can store the code of a program executed by the processor (720). In an embodiment, the memory (730) can be a volatile memory or a non-volatile memory.
[0093] Meanwhile, the embodiments disclosed in this specification may be implemented in the form of a recording medium that stores computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium. The computer-readable recording medium may include any type of recording medium that stores instructions that can be deciphered by a computer. Examples thereof include ROM, RAM, magnetic tape, magnetic disk, flash memory, and optical data storage devices.
[0094] The above-described embodiments are specific examples for implementing the present disclosure. The present disclosure will encompass not only the above-described embodiments, but also embodiments that can be simply designed or easily modified. Furthermore, the present disclosure will encompass techniques that can be easily modified and implemented using the above-described embodiments. Therefore, the scope of the present disclosure should not be limited to the above-described embodiments, but should be defined not only by the claims set forth below, but also by equivalents of the claims of the present disclosure.
[0095] Meanwhile, this disclosure is derived from research conducted as part of the research on early diagnosis and prognosis of dental diseases, and derivation of customized prevention and treatment methods through development of a deep learning-based dental medical twin system by the Ministry of Education of the Republic of Korea (Project Identification Number: 1345364914, Project Number: 2022R1I1A1A01069188, Project Management (Specialized) Organization Name: National Research Foundation of Korea, Research Project Name: Creative Challenge Research Base Support, Project Performing Organization Name: Korea University Industry-Academic Cooperation Foundation, Research Period: 2022.06.01~2025.05.31). Korea Information, the project provider, has no property interests in any aspect of this disclosure.
Claims
1. In a method for generating dental data information performed by an electronic device, A step of acquiring input information including patient X-ray image information from an external terminal; A step of inferring dental information for each patient based on the input information through the first artificial intelligence model; and A method for generating dental data information, comprising a step of generating dental data information based on the dental information for each tooth type through a second artificial intelligence model.
2. In paragraph 1, A step of obtaining a request for modification of the dental data information from the external terminal; and A method for generating dental data information, further comprising a step of modifying the dental data information based on the modification request.
3. In paragraph 1, The above input information further includes oral image information of the patient, The steps for inferring dental information for each patient's teeth are: A step of recognizing the first tooth of the patient for each of the X-ray image and the oral image information through the first artificial intelligence model; A step of extracting first tooth condition information related to the first tooth based on the X-ray image information through the first artificial intelligence model; A step of extracting second tooth condition information related to the first tooth based on the oral image information through the first artificial intelligence model; and A method for generating dental data information, comprising a step of inferring first tooth information for the first tooth based on the first tooth information and the second tooth information through the first artificial intelligence model.
4. In paragraph 3, The above input information further includes dental treatment-related information including at least some of the patient's treatment history information, dental care information, and prior medical examination information, The steps for inferring dental information for each patient's teeth are: A step of recognizing the second tooth of the patient for each of the X-ray image, the oral image information, and the dental treatment-related information through the first artificial intelligence model; A step of extracting third tooth condition information related to the second tooth based on the X-ray image information through the first artificial intelligence model; A step of extracting fourth tooth condition information related to the second tooth based on the oral image information through the first artificial intelligence model; A step of extracting fifth tooth condition information related to the second tooth based on the dental treatment-related information through the first artificial intelligence model; and A method for generating dental data information, comprising a step of inferring second tooth information for the second tooth based on the first tooth information, the second tooth information, and the third tooth information through the first artificial intelligence model.
5. In paragraph 3, A method for generating dental data information, wherein the step of inferring dental information for each of the patient's teeth further includes the step of performing preprocessing on each of the X-ray image and the oral image information to recognize the first tooth for each of the X-ray image and the oral image information.
6. In paragraph 1, A method for generating dental data information, wherein the dental data information includes information in the form of at least one of video, image, text, and voice.
7. In paragraph 1, The above first artificial intelligence model performs an update based on the patient's dental information inferred in response to the input information, A method for generating dental data information in which the second artificial intelligence model performs an update based on dental data information generated in response to the dental information for each tooth type.
8. In paragraph 1, A method for generating dental data information further comprising a step of providing the dental data information to the external terminal.
9. An electronic device that generates dental data information, It includes a transceiver, a memory for storing instructions, and a processor, The processor connected to the transceiver and the memory, Obtain input information including patient X-ray image information from the first terminal, Inferring the patient's dental information based on the input information through the first artificial intelligence model, An electronic device that generates dental data information based on the above-mentioned dental information by using a second artificial intelligence model.
10. A computer program stored in a computer-readable storage medium for executing a method of generating dental data information in combination with hardware, How to create the above dental data information: A step of obtaining input information including patient X-ray image information from a first terminal; A step of inferring dental information for each patient based on the input information through the first artificial intelligence model; and A computer program comprising a step of generating dental data information based on the dental information for each tooth type through a second artificial intelligence model.
Citation Information
Patent Citations
Integrated personal information protection system
KR1020240114894A
The Method that Infer Medical Prediction Information, and The System and Computer-readable Medium for Performing The Same
KR1020240167309A
System and method and of learning english while driving using large language model
KR1020250084662A
Dental diagnosis system using big data-based artificial intelligence
KR102284579B1
Smart interior system for space monitoring and maintenance
KR102740880B1