WO2023054876A1

WO2023054876A1 - Apparatus and method for dental diagnosis

Info

Publication number: WO2023054876A1
Application number: PCT/KR2022/011200
Authority: WO
Inventors: 이상화; 감세훈
Original assignee: 가톨릭대학교 산학협력단
Priority date: 2021-09-29
Filing date: 2022-07-29
Publication date: 2023-04-06
Also published as: KR20230045838A; KR102652766B1

Abstract

The present disclosure relates to an apparatus and a method for dental diagnosis and, in particular, can provide an apparatus and a method for dental diagnosis, the apparatus and the method enabling dental age determination by applying, to dental panoramic image data, at least one technique including an artificial intelligence technique. In addition, provided are an apparatus and a method for dental diagnosis, the apparatus and the method allowing an optimum technique to be recommended according to the age, sex and race of a patient by comparing each of the techniques for dental age determination.

Description

Dental diagnosis apparatus and method

The present embodiments provide a dental diagnosis apparatus and method.

In situations where identification is difficult, such as in a disaster, age assessment is required. In particular, in forensic dentistry, if the age of an unidentified deceased can be known, the range of subjects for investigation can be reduced, so age assessment is essential. In addition, due to various social and economic problems among living people, the date of birth is incorrectly recorded in the family register, and accurate age estimation is required to correct it. In addition, age emotion may provide a guideline for determining the degree of growth according to the state of development. There are various methods for such age assessment, but among them, the method using teeth has the most suitable characteristics for age assessment. In other words, compared to the development and growth process of other organs, teeth have much less individual differences and diversity, and as the strongest tissue among human tissues, they hardly decay even after a long time, and are stable even in extreme environments such as high temperature, high pressure, and high heat. It has the characteristics of maintaining its original form.

Accordingly, a dental panoramic image of a dental condition is used as a tool for assessing a patient's age. Such a dental panoramic image is an image captured by a device for photographing the inside of the oral cavity of a human body by introducing a panoramic imaging technique. In addition, the dental panoramic image is the most basic radiographic image taken when a patient visits the hospital for the first time. However, there is a problem in that there are many limitations in accurate age estimation because the tooth age estimated using the dental panoramic image is often not the same as the actual age depending on the patient's gender, age, race, etc.

Therefore, there is a need for a dental diagnosis technology capable of accurately determining the tooth age from a dental panoramic image using the latest artificial intelligence (AI) as well as the existing tooth age appraisal technology. In addition, there is a need for a dental diagnosis technology that can select and apply an age assessment technology that can most accurately determine tooth age according to the patient's gender, age, and race.

Against this background, an object of the present embodiments is to provide a dental diagnosis apparatus and method for determining tooth age by applying at least one technique, including an artificial intelligence technique, to dental panoramic image data.

In order to achieve the above object, in one aspect, in the present embodiment, in the dental diagnosis apparatus, panoramic image data of dental conditions are collected and selected according to at least one patient information among age information, gender information, and race information. a data selection unit that determines the patient's tooth age by applying at least one of an artificial intelligence technique and a preset judgment technique to the patient's panoramic image data; and a specific technique with high accuracy according to patient information. Accordingly, it is possible to provide a dental diagnosis apparatus comprising a technique recommendation unit recommended as an optimization technique for determining the patient's tooth age.

In another aspect, in the present embodiment, in the dental diagnosis method, a data selection step of collecting panoramic image data of dental conditions and selecting according to at least one patient information among age information, gender information, and race information, a patient's panorama An age determination step of determining the patient's tooth age by applying at least one of an artificial intelligence technique and a preset judgment technique to image data, and determining a specific technique with high accuracy according to patient information to determine the patient's tooth age It is possible to provide a dental diagnosis method comprising the step of recommending a technique as an optimization technique.

1 is a diagram exemplarily illustrating a system to which a dental diagnosis apparatus according to an embodiment of the present disclosure may be applied.

2 is a diagram showing the configuration of a dental diagnosis apparatus according to an embodiment of the present disclosure.

3 is a flowchart illustrating an operation of determining a tooth age and recommending an optimization technique of the dental diagnosis apparatus according to an embodiment of the present disclosure.

4 is a flowchart illustrating a determination technique applied when a patient is an adult in a dental diagnosis apparatus according to an embodiment of the present disclosure.

5 is a flowchart illustrating a determination technique applied when a patient is a child in a dental diagnosis apparatus according to an embodiment of the present disclosure.

6 is a diagram illustrating an example of an artificial intelligence technique applied in a dental diagnosis apparatus according to an embodiment of the present disclosure.

7 is a flowchart of a dental diagnosis method according to an embodiment of the present disclosure.

The present disclosure relates to dental diagnostic devices and methods.

DETAILED DESCRIPTION Some embodiments of the present disclosure are described in detail below with reference to exemplary drawings. In adding reference numerals to components of each drawing, the same components may have the same numerals as much as possible even if they are displayed on different drawings. In addition, in describing the present embodiments, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present technical idea, the detailed description may be omitted. When "comprises", "has", "consists of", etc. mentioned in this specification is used, other parts may be added unless "only" is used. In the case where a component is expressed in the singular, it may include the case of including the plural unless otherwise explicitly stated.

Also, terms such as first, second, A, B, (a), and (b) may be used in describing the components of the present disclosure. These terms are only used to distinguish the component from other components, and the nature, sequence, order, or number of the corresponding component is not limited by the term.

In the description of the positional relationship of components, when it is described that two or more components are "connected", "coupled" or "connected", the two or more components are directly "connected", "coupled" or "connected". ", but it will be understood that two or more components and other components may be further "interposed" and "connected", "coupled" or "connected". Here, other components may be included in one or more of two or more components that are “connected”, “coupled” or “connected” to each other.

In the description of the temporal flow relationship related to components, operation methods, production methods, etc., for example, "after", "continued to", "after", "before", etc. Alternatively, when a flow sequence relationship is described, it may also include non-continuous cases unless “immediately” or “directly” is used.

On the other hand, when a numerical value or corresponding information (eg, level, etc.) for a component is mentioned, even if there is no separate explicit description, the numerical value or its corresponding information is not indicated by various factors (eg, process factors, internal or external shocks, noise, etc.) may be interpreted as including an error range that may occur.

Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings.

Referring to FIG. 1 , a system to which a dental diagnosis apparatus 100 according to an embodiment of the present disclosure may be applied may be implemented by including a server 110 and a network 120 .

The dental diagnosis apparatus 100 is a device capable of performing a dental diagnosis method according to an embodiment of the present disclosure, and may be implemented as hardware such as an electronic device capable of executing programs, software executed by a processor, or a combination thereof. can

According to one example, when the dental diagnosis apparatus 100 is implemented as hardware, it includes a general PC such as a general desktop or laptop, and mobile devices such as smart phones, tablet PCs, PDAs (Personal Digital Assistants), and mobile communication terminals. A terminal may be included. However, this is an example, and any electronic device capable of communicating with the server 110 and inputting data is not limited to its name or type and can be widely interpreted. Also, according to an example, the dental diagnosis apparatus 100 may be implemented as an application capable of inputting information according to a user's manipulation and performing a dental diagnosis method according to an embodiment of the present disclosure. For example, it may be a dental diagnosis application or program, but it may be widely interpreted without being limited to its name or type.

The server 110 may be connected to an unspecified number of clients (including the device 100) and/or other servers through the network 120. Accordingly, the server 110 may refer to a computer system that receives a request for performing a task from a client or another server, derives and provides a result of the task, or refers to computer software (server program) installed for such a computer system. there is.

According to an example, the server 110 may store and manage patient panoramic image data. Also, the server 110 may transmit corresponding data according to a request of the dental diagnosis apparatus 100 . For example, the server 110 may provide environmental data to the dental diagnosis apparatus 100 through an application corresponding to a dental diagnosis service.

In addition, the server 110 is understood as a broad concept including, in addition to the above-described server program, a series of application programs that operate on the server 110 and, in some cases, various databases built inside or outside. It should be. Here, the server 110 may refer to an aggregate of data in which data such as information or data is structured and managed for the purpose of being used by a server or other device, and may also refer to a storage medium for storing such an aggregate of data. there is.

In addition, the server 110 may include a plurality of databases classified according to a data structure method, management method, and type. In some cases, the server 110 may include a database management system (DBMS), which is software that allows information or data to be added, modified, deleted, and the like.

On the other hand, the network 120 is a network that connects the dental diagnosis device 100 and the server 110, and may be a closed network such as a local area network (LAN) or a wide area network (WAN), but the Internet It may be an open network such as (Internet). Here, the Internet refers to the TCP/IP protocol and various services existing in its upper layer, namely HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), It refers to a worldwide open computer network structure that provides Simple Network Management Protocol (SNMP), Network File Service (NFS), and Network Information Service (NIS).

The briefly described dental diagnosis apparatus and method according to an embodiment of the present disclosure will be described in more detail below.

Referring to FIG. 2 , the dental diagnosis apparatus 100 according to an embodiment of the present disclosure collects panoramic image data of dental conditions and selects them according to at least one patient information among age information, gender information, and race information. A data selector 210 that determines the patient's tooth age by applying at least one of an artificial intelligence technique and a preset judgment technique to the patient's panoramic image data, and an age determination unit 220 that determines the patient's tooth age and accuracy according to patient information Provided is a dental diagnosis apparatus 100 including a technique recommendation unit 230 that determines a specific technique with a high value and recommends it as an optimization technique for determining the patient's tooth age.

According to an embodiment, the data selector 210 may collect panoramic image data of dental conditions and select according to at least one patient information among age information, gender information, and race information. For example, the data selector 210 may collect panoramic image data of a tooth state from a photographing device or server interlocked through communication. In detail, the data selector 210 may transmit and collect the panoramic image captured by the photographing device to a medical image storage and transmission system (PACS) according to the DICOM standard. In addition, the collected panoramic image data may include the patient's tooth shape, jawbone, bone structure, and the like. For another example, the data selection unit 210 may select collected panoramic image data using at least one patient information among age information, gender information, and race information. Specifically, patient information may be an important factor for determining the age of teeth because the dental condition has various characteristics depending on the age, gender, or race of the patient.

According to an embodiment, the age determination unit 220 may determine the patient's tooth age by applying at least one of an artificial intelligence technique and a preset determination technique to panoramic image data of the patient. For example, the age determination unit 220 may determine the patient's tooth age by applying an artificial intelligence technique to the patient's panoramic image data. For example, the age determination unit 220 performs classification to determine tooth age by training with training data selected for each age based on age information from the panoramic image data, and compares the panoramic image data that are not selected for each age with similarity. It is possible to apply an artificial intelligence technique that performs clustering by grouping based on criteria. In this case, the applied artificial intelligence technique may be a semi-supervised learning technique. Details of the artificial intelligence technique will be described later with reference to FIG. 6 .

For another example, the age determination unit 220 selects training data by using the age as a first unit when the specific age is less than a specific age, and sets the age as a second unit when the specific age is greater than or equal to the specific age. to select the training data. For example, the age determination unit 220 selects training data based on the age of 1 year when the patient is less than 20 years of age, and selects training data based on the age of 5 years when the patient is 20 years of age or older. can be selected In addition, the age determination unit 220 may select training data by dividing the age by 10 years if the patient is 40 years of age or older. However, the specific age and age unit are examples, and are not limited thereto. Also, for another specific example, the age determination unit 220 may randomly select 100 pieces of image data for each age from 6 to 90 years old. In addition, the age determination unit 220 may perform classification by selecting 100 pieces of basic training data according to each age and gender.

As another example, the age determination unit 220 may determine whether the patient is an adult or a child based on a preset age, and select and apply at least one of preset determination techniques according to a result of the determination. Here, at least one technique applied to adults may be different from at least one technique applied to children. For example, the age determination unit 220 may set a specific age in advance to determine whether the patient is an adult or a child. Specifically, the age determination unit 220 may set a specific age based on 20 years of age, determine that the patient is an adult if the patient is 20 years of age or older, and determine the patient as a child if the patient is less than 20 years of age. However, the age of 20 is not limited thereto as an example. Accordingly, the age determination unit 220 may determine the patient's tooth age by determining whether the patient is an adult or a child based on the patient's age information, and applying a preset determination technique according to the determination result. For another example, when determining that the patient is an adult, the age determination unit 220 may apply a determination technique set to at least one of a Gustafson technique and a tooth-coronal index (TCI) technique. As another example, if the age determination unit 220 determines that the patient is a child, a determination technique set to at least one of the Demirjian technique, the Willems technique, and the Nolla technique may be applied. Specifically, there are various methods using a tooth eruption time, a degree of calcification of a tooth, a degree of attrition of a tooth, a size of a pulp cavity, and the like as a determination technique for determining the age of a tooth. However, there is a difference in that it is efficient to use attrition as a physiological synergistic change for adults, and for children, it is efficient to use the eruption time and degree of calcification of teeth corresponding to the growth period. Accordingly, each of the above-described techniques is an example of a technique for determining the tooth age according to distinguishing characteristics of adults and children, but is not limited thereto. Details of the determination technique will be described later with reference to FIGS. 4 and 5 .

According to an embodiment, the technique recommendation unit 230 may determine a specific technique with high accuracy according to patient information and recommend it as an optimization technique for determining the patient's tooth age. For example, the technique recommendation unit 230 may determine a technique with high accuracy as a specific technique by comparing the degree of agreement between the actual age of the patient and the tooth age determined by each technique. Also, the technique recommendation unit 230 may recommend the determined specific technique as an optimization technique. For example, the technique recommendation unit 230 may recommend different techniques as optimization techniques to each patient according to different combinations of age information, gender information, and race information for each patient. This is because if even one of the age information, gender information, and race information of the patient is different, the determined tooth age of the patient may be different even if the same determination technique is applied. Therefore, the technique recommendation unit 230 may determine a technique that determines the patient's tooth age most similar to the actual age among each technique according to the patient's age information, gender information, and ethnicity information, and recommend it as an optimization technique.

Referring to FIG. 3 , the data selection unit 210 of the dental diagnosis apparatus according to an embodiment of the present disclosure may select panoramic image data obtained by photographing dental conditions according to patient information (S310). For example, the data selector 210 may collect panoramic image data of a specific region including the patient's tooth shape, jaw bone, bone structure, and the like. The data selector 210 may select the collected panoramic image data according to at least one patient information among age information, gender information, and race information of the patient. For example, the data selector 210 may select the panoramic image data by age from 6 to 90 years old according to age information of the patient, and may classify the panoramic image data into men and women according to gender information. In addition, the data selection unit 210 may classify the panoramic image data into Asians, Europeans, Africans, etc., or by country, according to the patient's race information.

The age determination unit 220 of the dental diagnosis apparatus according to an embodiment may determine the patient's tooth age by applying at least one of an artificial intelligence technique and a preset determination technique (S320). For example, the age determination unit 220 may apply an artificial intelligence technique by performing pre-processing on each panoramic image data selected according to patient information. For example, the age determination unit 220 may perform preprocessing of converting each panoramic image data into a consistent format according to a criterion through operations such as rotation, enlargement, reduction, and removal of unnecessary regions. Also, for example, the age determination unit 220 may label each panoramic image data using at least one patient information among age information, gender information, and race information. In addition, the age determination unit 220 may perform analysis using an artificial intelligence technique using minimum labeled panoramic image data and unlabeled panoramic image data.

As another example, the age determination unit 220 may determine whether the patient is an adult or a child based on a preset age, and apply a preset determination technique according to the determination result. Here, at least one technique applied to adults may be different from at least one technique applied to children. For example, when determining that the patient is an adult, the age determination unit 220 may apply a determination technique set to at least one of a Gustafson technique and a tooth-coronal index (TCI) technique. Specifically, the age determination unit 220 may preset a Gustafson technique and a TCI technique using ointment as a physiological augmentation change to determine tooth age in the case of an adult as a determination technique. Here, the degree of attrition of the teeth may be measured using Percentages of Dentine Exposure (PDE) of the occlusal surface as a result of friction of the tooth surfaces due to friction between the upper and lower teeth and contact with food. In general, the shape of attrition is irreversibly changed mainly by temporal factors, and may be suitable as a technique for determining the age of an adult's teeth. However, the judgment technique is an example of a classic judgment technique, and is not limited to the Gustafson technique and the TCI technique.

For another example, when determining that the patient is a child, the age determination unit 220 may apply a determination technique set to at least one of the Demirjian technique, the Willems technique, and the Nolla technique. Specifically, the age determining unit 220 may preset a Demirjian technique, a Willems technique, and a Nolla technique using the eruption time and degree of calcification of teeth to determine the tooth age in the case of a child. The timing of tooth eruption and the degree of calcification may be suitable as a technique for determining the age of teeth mainly for infants, children, and adolescents whose teeth have not yet fully developed. However, the judgment technique is an example of a classic judgment technique, and is not limited to the Demirjian technique, the Willems technique, and the Nolla technique.

For another example, when it is unclear whether the patient is an adult or a child, the age determination unit 220 may determine the age through an artificial intelligence technique. Also, the age determination unit 220 may determine whether the patient is an adult or a child using the determined age, and determine the age using a preset determination technique according to the determination result.

The technique recommendation unit 230 of the dental diagnosis apparatus according to an embodiment may determine a specific technique with high accuracy according to patient information (S330). For example, the technique recommendation unit 230 may determine a specific technique with high accuracy from among techniques including an artificial intelligence technique and a preset judgment technique according to patient information. For example, the technique recommendation unit 230 may use a preset judgment technique as a control group and an artificial intelligence technique as an experimental group and compare the patient's tooth age determined by each technique. At this time, the technique recommendation unit 230 may form a control group by applying a judgment technique set to a different technique depending on whether the patient is an adult or a child. For another example, the technique recommendation unit 230 uses the general supervised learning technique as a control group and the semi-supervised learning technique as an experimental group, and the tooth age of the patient determined by each artificial intelligence technique can be compared. Accordingly, the technique recommendation unit 230 may determine a technique with high accuracy as a specific technique by comparing the degree of matching between the tooth age of the patient determined by each technique and the actual age. Alternatively, the technique recommendation unit 230 may determine a technique with high accuracy as a specific technique by comparing the patient's tooth age determined by the artificial intelligence technique with the patient's tooth age determined by a preset determination technique.

The technique recommendation unit 230 of the dental diagnosis apparatus according to an embodiment may recommend the determined specific technique as an optimization technique (S340). For example, the technique recommendation unit 230 may determine a specific technique having high accuracy as a result of the comparison and recommend it to the user as an optimization technique. For example, the user may be recommended and select at least one of an artificial intelligence technique and a preset determination technique in order to determine the patient's tooth age. Therefore, the technique recommendation unit 230 may determine a specific technique with high accuracy and recommend it as an optimization technique so that the user can select a more accurate judgment technique.

Referring to FIG. 4 , the data selection unit 210 of the dental diagnosis apparatus according to an embodiment of the present disclosure may select panoramic image data obtained by photographing dental conditions according to patient information (S310). For example, the data selection unit 210 may select panoramic image data of a patient corresponding to an adult from among collected panoramic image data based on age information. For example, the data selector 210 may select panoramic image data of a patient aged 20 or older and use it as training data for an adult patient in an artificial intelligence technique. In addition, the selected panoramic image data may be used to evaluate a judgment technique compared to an artificial intelligence technique when the patient is an adult. However, the age of 20 is an example for distinguishing an adult among patients, but is not limited thereto.

When new panoramic image data is input, the age determination unit 220 of the dental diagnosis apparatus according to an embodiment may determine whether the image data is of an adult patient (S410). For example, the age determination unit 220 may determine whether the patient is an adult based on the input panoramic image data of the patient. Alternatively, the age determination unit 220 may determine whether the patient of the panoramic image data is an adult based on the patient's age information. For example, the age determination unit 220 may determine whether the patient is an adult according to the degree of development of a wisdom tooth or a neural tube included in the input patient's panoramic image data. Alternatively, the age determination unit 220 may determine whether the patient of the panoramic image data is an adult based on the approximate age of the patient. For another example, the age determination unit 220 may determine the age of the patient by applying an artificial intelligence technique to the patient's panoramic image data, and determine whether the patient is an adult based on the determined age. Accordingly, when it is determined that the patient is an adult, the age determination unit 220 may re-determine the tooth age by applying a preset determination technique.

The age determination unit 220 of the dental diagnosis apparatus according to an embodiment may apply an artificial intelligence technique to the patient's panoramic image data (S420). For example, the age determination unit 220 trains the panoramic image data with training data selected by age based on age information to determine the age of the teeth and group the panoramic image data that are not selected by age based on similarity. Artificial intelligence techniques that perform clustering can be applied. For example, the age determination unit 220 may select training data by classifying age into units based on a specific age in order to perform classification. As a specific example, if the patient is 20 years of age or older, the age determination unit 220 may select training data by dividing the age by 5 years. In addition, the age determination unit 220 may select training data by dividing the age by 10 years if the patient is 40 years of age or older. However, the specific age and age unit are examples, and are not limited thereto. Also, for another specific example, the age determination unit 220 may randomly select 100 pieces of image data for each age from 20 to 90 years old. In addition, the age determination unit 220 may perform classification by selecting 100 pieces of basic training data according to each age according to gender. However, the number of copies of the selected image data is an example, and is not limited thereto.

For another example, the age determiner 220 may perform clustering on image data that has not been selected according to age and classify the image data into a plurality of subgroups. Each group may be composed of image data having a similarity. In addition, the age determination unit 220 may select each image data included in the same group as the same age information and use it as training data. Accordingly, the age determination unit 220 may determine the patient's tooth age through a learning model to which the above-described artificial intelligence technique is applied to the newly input panoramic image data.

If the age determination unit 220 of the dental diagnosis apparatus according to an embodiment determines that the patient is an adult, the Gustafson technique may be applied to the panoramic image data (S430). For example, the age determination unit 220 observes six microstructure changes from the polished specimen of the patient's teeth, assigns a 4-level score to each change item, and then determines the age of the patient's teeth according to the sum of the Gustafson technique. can be applied. Specifically, the Gustafson technique may be a technique based on decreasing the length of the pulp cavity with increasing age. In addition, the six microstructural changes observed in the Gustafson technique are tooth incisal and occlusal wear, alveolar bone resorption or periodontal pocket depth, secondary dentin addition amount, cementum deposition amount, root resorption, and amount of dentin clear layer. can Accordingly, the age determination unit 220 may determine the age of the patient's teeth by applying the Gustafson technique to the newly input panoramic image data.

If the age determination unit 220 of the dental diagnosis apparatus according to an embodiment determines that the patient is an adult, a tooth-coronal index (TCI) technique may be applied to the panoramic image data (S440). For example, the age determination unit 220 calculates a tooth-coronal index (TCI) by measuring the coronal height (CH) and the coronal pulp cavity height (CPCH) of the patient's teeth. TCI technique can be applied. Specifically, the TCI technique may be a technique based on changes in the size of the pulp cavity according to the accumulation of secondary dentin with increasing age. Here, the crown height may be a value obtained by measuring a vertical distance from the cervical line to the highest cusp apex, and the height of the dental pulp cavity may be a value obtained by measuring the vertical distance from the cervical line to the highest dental pulp angle. Accordingly, the age determination unit 220 may determine the age of the patient's teeth by applying the TCI technique to the newly input panoramic image data.

The technique recommendation unit 230 of the dental diagnosis apparatus according to an embodiment may determine a specific technique among artificial intelligence techniques and judgment techniques and recommend it as an optimization technique for determining the patient's tooth age (S450). For example, the accuracy of the tooth age may be determined to be high in a specific technique according to age information, gender information, and race information of the patient. Therefore, the technique recommendation unit 230 may determine a specific technique determined to be highly accurate according to patient information and recommend it as an optimization technique for determining the patient's tooth age. For example, the technique recommendation unit 230 compares the degree of matching between the patient's tooth age determined by each of the artificial intelligence techniques, the Gustafson technique, and the TCI technique, and the actual age of the patient, and selects a specific technique with the highest accuracy as an optimization technique. can recommend Alternatively, the technique recommendation unit 230 may determine a specific technique by comparing the patient's tooth age determined by each technique and recommend it as an optimization technique. That is, different optimization techniques may be recommended according to different combinations of age information, gender information, and race information for each patient.

Referring to FIG. 5 , the data selector 210 of the dental diagnosis apparatus according to an embodiment of the present disclosure may select panoramic image data obtained by photographing dental conditions according to patient information (S310). For example, the data selector 210 may select panoramic image data of a patient corresponding to a child based on age information from among the collected panoramic image data. For example, the data selection unit 210 may select panoramic image data of a patient under the age of 20 and use it as training data for a child patient in an artificial intelligence technique. In addition, the selected panoramic image data may be used to evaluate a judgment technique compared to an artificial intelligence technique when the patient is a child. However, the age of 20 is an example for classifying children among patients, but is not limited thereto.

The age determination unit 220 of the dental diagnosis apparatus according to an embodiment may determine whether the input panoramic image data is image data of a child patient (S510). For example, the age determination unit 220 may determine whether the patient is a child based on the input panoramic image data of the patient. Alternatively, the age determination unit 220 may determine whether the patient of the corresponding panoramic image data is a child based on the patient's age information. For another example, the age determination unit 220 may determine the age of the patient by applying an artificial intelligence technique to panoramic image data of the patient, and determine whether the patient is a child based on the determined age. Accordingly, when it is determined that the patient is a child, the age determination unit 220 may re-determine the tooth age by applying a preset determination technique.

The age determination unit 220 of the dental diagnosis apparatus according to an embodiment may apply an artificial intelligence technique to the patient's panoramic image data (S520). For example, the age determination unit 220 may select training data by classifying age into units based on a specific age in order to perform classification. As a specific example, if the patient is less than 20 years of age, the age determination unit 220 may select training data based on the age of the patient on a yearly basis. Alternatively, the age determination unit 220 may randomly select image data for each age from 6 to 20 years old, and perform classification by selecting 100 pieces of each age as basic training data according to gender. However, the artificial intelligence technique may be applied in the same way as the artificial intelligence technique applied when the patient is an adult.

If the age determination unit 220 of the dental diagnosis apparatus according to an embodiment determines that the patient is a child, the Demirjian technique may be applied to the panoramic image data (S530). For example, the age determination unit 220 may apply the Demirjian technique for evaluation by dividing the grade according to the degree of development of the crown and root of the patient's tooth. Specifically, the Demirjian technique may be a technique for classifying into 8 stages, starting with stage 1 when calcification starts in the crown and ending with stage 8 when the apical end is closed. In addition, the Demirjian technique can determine tooth age by summing the scores differentiated by tooth and gender. Accordingly, the age determination unit 220 may determine the age of the patient's teeth by applying the Demirjian technique to newly input panoramic image data.

If the age determination unit 220 of the dental diagnosis apparatus according to an embodiment determines that the patient is a child, the Willems technique may be applied to the panoramic image data (S540). For example, the age determination unit 220 may apply the Demirjian technique to the Willems technique that compensates for the difference generated by race. Accordingly, the age determination unit 220 may determine the tooth age of the patient by applying the Willems technique to the newly input panoramic image data.

If the age determination unit 220 of the dental diagnosis apparatus according to an embodiment determines that the patient is a child, the Nolla technique may be applied to the panoramic image data (S550). For example, the age determination unit 220 may apply the Nolla technique for determining based on the degree of tooth development and calcification. Specifically, the Nolla technique may be a technique for evaluating the tooth calcification level of the left upper and lower permanent teeth, excluding the third molar, on a scale of 11 from 0 to 10. Accordingly, the age determination unit 220 may determine the age of the patient's teeth by applying the Nolla technique to the newly input panoramic image data.

The technique recommendation unit 230 of the dental diagnosis apparatus according to an embodiment may determine a specific technique among artificial intelligence techniques and judgment techniques and recommend it as an optimization technique for determining the patient's tooth age (S450). For example, the technique recommendation unit 230 compares the degree of matching between the patient's tooth age and the patient's actual age determined by each of the artificial intelligence techniques, Demirjian techniques, Willems techniques, and Nolla techniques, and selects a specific technique with the highest accuracy. It can be recommended as an optimization technique. Alternatively, the technique recommendation unit 230 may determine a specific technique by comparing the patient's tooth age determined by each technique and recommend it as an optimization technique.

Referring to FIG. 6 , the age of a patient's teeth may be determined by applying an artificial intelligence technique to panoramic image data of the age determination unit 220 of the dental diagnosis apparatus according to an embodiment of the present disclosure. However, the panoramic image data may be of poor image quality, such as when the quality of the image is deteriorated due to the patient's movement, or image data of a patient with completely edentulous jaws, maxillary bones, and severe dental deformities may be excluded.

For example, the age determination unit 220 may apply an artificial intelligence technique corresponding to a semi-supervised learning technique combining supervised learning and unsupervised learning. That is, the age determination unit 220 may use some of the panoramic image data in the form of data for supervised learning and some of the panoramic image data in the form of data for unsupervised learning. For example, the age determination unit 220 may perform a classification technique 610 of determining a tooth age using data selected for each age based on age information from panoramic image data as training data. In addition, the age determination unit 220 may perform a clustering technique 620 to group the panoramic image data 630 that are not selected by age based on similarity. In addition, the age determination unit 220 may perform a semi-supervised learning technique in which retraining is performed using the inferred age after inferring the age of data not selected by age. This semi-supervised learning technique can solve the problem of deterioration of learning effect due to indiscriminately massive data processing as well as errors in accuracy due to insufficient learning.

Here, the classification technique 610 is a type of supervised learning, and may be a technique of grasping a category relationship of existing data and automatically determining and classifying a category of newly observed data. Specifically, the classification technique 610 may include a k-nearest neighbor algorithm (KNN) algorithm, a decision tree algorithm, a random forest algorithm, a support vector machine algorithm, and the like. can Also, the clustering technique 620 is a kind of unsupervised learning and may be a technique of grouping undefined categories in consideration of characteristics of data. Specifically, the clustering technique 620 may include a K-Means algorithm, a Mean Shift algorithm, a Gaussian Mixture Model (GMM) algorithm, and the like. However, the above algorithm is not limited to this as an example.

Hereinafter, a dental diagnosis method that can be performed by the dental diagnosis apparatus described with reference to FIGS. 1 to 6 will be described. However, detailed descriptions of some embodiments or some operations described in FIGS. 1 to 6 may be omitted below, but this is only to prevent duplication of description, so the dental diagnosis method uses the same dental diagnosis device as described above. can provide

Referring to FIG. 7 , the dental diagnosis method according to an embodiment of the present disclosure may include a data selection step of collecting panoramic image data obtained by photographing dental conditions and selecting data according to patient information (S710). For example, the dental diagnosis apparatus may collect panoramic image data obtained by photographing dental conditions, and select the patient according to at least one patient information among age information, gender information, and race information. For example, the dental diagnosis apparatus may collect panoramic image data of a tooth condition from a photographing apparatus or a server interlocked through communication. In addition, the collected panoramic image data may include the patient's tooth shape, jawbone, bone structure, and the like. For another example, the dental diagnosis apparatus may label and select collected panoramic image data with at least one patient information among age information, gender information, and race information. Specifically, patient information may be an important factor for determining the age of teeth because the dental condition has various characteristics depending on the age, gender, or race of the patient.

The dental diagnosis method according to an embodiment may include a data selection step of collecting panoramic image data of dental conditions and selecting the data according to at least one patient information among age information, gender information, and race information (S710). For example, the dental diagnosis apparatus may determine the patient's tooth age by applying at least one of an artificial intelligence technique and a preset determination technique to panoramic image data of the patient. For example, a dental diagnosis apparatus performs classification for determining tooth age by training with training data selected for each age based on age information from panoramic image data and using panoramic image data that is not selected for age as a basis for similarity. An artificial intelligence technique that performs grouping and clustering can be applied. In addition, the dental diagnosis apparatus is trained with training data selected by age based on age information from panoramic image data to determine tooth age and group panoramic image data that are not selected by age based on similarity Artificial intelligence techniques that perform clustering can be applied.

As another example, the dental diagnosis apparatus may determine whether the patient is an adult or a child based on a preset age, and select and apply at least one of preset determination techniques according to a result of the determination. Here, at least one technique applied to adults may be different from at least one technique applied to children. For example, the dental diagnosis apparatus may preset a specific age to determine whether a patient is an adult or a child. Also, the dental diagnosis apparatus may determine whether the patient is an adult or a child based on the age information of the patient, and may determine the age of the patient's teeth by applying a preset determination technique according to the determination result. For another example, when determining that the patient is an adult, the dental diagnosis apparatus may apply a determination technique set to at least one of a Gustafson technique and a tooth-coronal index (TCI) technique. For another example, when determining that the patient is a child, the dental diagnosis apparatus may apply a determination technique set to at least one of the Demirjian technique, the Willems technique, and the Nolla technique. However, each technique is not limited thereto as long as it corresponds to, for example, a determination technique for determining the age of a tooth according to distinguishing characteristics of an adult and a child.

The dental diagnosis method according to an embodiment may include a technique recommendation step of recommending an optimization technique for determining the patient's tooth age (S730). For example, the dental diagnosis apparatus may determine a specific technique with high accuracy according to patient information and recommend it as an optimization technique for determining the patient's tooth age. For example, the dental diagnosis apparatus may determine a technique with high accuracy as a specific technique by comparing the degree of matching between the patient's actual age and the tooth age determined by each technique. And, the dental diagnosis apparatus may recommend the determined specific technique as an optimization technique. In addition, the dental diagnosis apparatus may recommend different techniques as optimization techniques to each patient according to different combinations of age information, gender information, and race information for each patient.

As described above, according to the present disclosure, it is possible to provide a dental diagnosis apparatus and method for determining tooth age by applying at least one or more techniques including an artificial intelligence technique to dental panoramic image data. In addition, it is possible to provide a dental diagnosis apparatus and method for recommending an optimization technique according to the patient's age, sex, and race by comparing each technique for determining the patient's tooth age.

The above description is merely an example of the technical idea of the present disclosure, and various modifications and variations may be made to those skilled in the art without departing from the essential characteristics of the present disclosure. Therefore, the embodiments disclosed in this disclosure are not intended to limit the technical spirit of the present disclosure, but to explain, and the scope of the technical spirit of the present disclosure is not limited by these embodiments. The protection scope of the present disclosure should be construed by the claims below, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present disclosure.

CROSS-REFERENCE TO RELATED APPLICATIONCROSS-REFERENCE TO RELATED APPLICATION

This patent application claims priority in accordance with US Patent Act Article 119 (a) (35 U.S.C § 119 (a)) for Patent Application No. 10-2021-0128620 filed in Korea on September 29, 2021, and All contents are incorporated into this patent application by reference. In addition, if this patent application claims priority for the same reason as above for countries other than the United States, all the contents are incorporated into this patent application as references.

Claims

a data selection unit that collects panoramic image data of dental conditions and selects them according to at least one patient information among age information, gender information, and race information;

an age determination unit determining the patient's tooth age by applying at least one of an artificial intelligence technique and a preset determination technique to panoramic image data of the patient; and

and a technique recommendation unit that determines a specific technique with high accuracy according to the patient information and recommends it as an optimization technique for determining the patient's tooth age.
According to claim 1,

The age determination unit,

Based on a preset age, the patient is determined as an adult or a child, and according to the determination result, at least one technique is selected and applied from among the preset determination techniques,

The dental diagnosis apparatus according to claim 1 , wherein the at least one technique applied to adults and the at least one technique applied to children are different from each other.
According to claim 2,

The age determination unit,

If it is determined that the patient is an adult, the dental diagnosis apparatus characterized by applying the determination technique set to at least one of a Gustafson technique and a tooth-coronal index (TCI) technique.
According to claim 2,

The age determination unit,

If it is determined that the patient is a child, the dental diagnosis apparatus, characterized in that for applying the determination technique set to at least one of the Demirjian technique, the Willems technique and the Nolla technique.
According to claim 1,

The age determination unit,

Classification for determining tooth age by training with training data selected for each age based on the age information from the panoramic image data and clustering for grouping the panoramic image data that are not selected for each age based on similarity Dental diagnosis device, characterized in that for applying the artificial intelligence technique to perform.
According to claim 5,

The age determination unit,

Characterized in that, based on a specific age, if the age falls below the specific age, the training data is selected using the age as a first unit, and if the specific age is greater than or equal to the specific age, the training data is selected using the age as a second unit. A dental diagnostic device made with
According to claim 1,

The technique recommendation unit,

The dental diagnosis apparatus according to claim 1 , wherein the specific technique is determined by comparing a degree of matching between the actual age of the patient and the tooth age determined by each technique, and the specific technique is recommended as the optimization technique.
According to claim 7,

The technique recommendation unit,

The dental diagnosis apparatus, characterized in that a different technique is recommended to each patient as the optimization technique according to a different combination of the age information, the gender information, and the race information for each patient.
A data selection step of collecting panoramic image data of dental conditions and selecting them according to at least one patient information among age information, gender information, and race information;

an age determination step of determining the age of the patient's teeth by applying at least one of an artificial intelligence technique and a preset determination technique to panoramic image data of the patient; and

and a technique recommendation step of determining a specific technique with high accuracy according to the patient information and recommending it as an optimization technique for determining the patient's tooth age.
According to claim 9,

The age determination step,

Based on a preset age, the patient is determined as an adult or a child, and according to the determination result, at least one technique is selected and applied from among the preset determination techniques,

The dental diagnosis method, characterized in that the at least one technique applied to the adult and the at least one technique applied to the child are different from each other.
According to claim 10,

The age determination step,

If it is determined that the patient is an adult, the dental diagnosis method, characterized in that for applying the determination technique set to at least one of a Gustafson technique and a tooth-coronal index (TCI) technique.
According to claim 10,

The age determination step,

If it is determined that the patient is a child, the dental diagnosis method, characterized in that for applying the determination technique set to at least one of the Demirjian technique, the Willems technique and the Nolla technique.
According to claim 9,

The age determination step,

Classification for determining tooth age by training with training data selected for each age based on the age information from the panoramic image data and clustering for grouping the panoramic image data that are not selected for each age based on similarity Dental diagnosis method, characterized in that for applying the artificial intelligence technique to perform.
According to claim 13,

The age determination step,

Characterized in that, based on a specific age, if the age falls below the specific age, the training data is selected using the age as a first unit, and if the specific age is greater than or equal to the specific age, the training data is selected using the age as a second unit. dental diagnosis method.
According to claim 9,

In the step of recommending the technique,

The dental diagnosis method, characterized in that the specific technique is determined by comparing the degree of matching between the actual age of the patient and the tooth age determined by each technique, and the specific technique is recommended as the optimization technique.
According to claim 15,

In the step of recommending the technique,

and recommending a different technique to each patient as the optimization technique according to a different combination of the age information, the gender information, and the race information for each patient.