KR102330069B1 - Method for determining sex and age of subject from dental image and apparatus using the same - Google Patents

Abstract

The present disclosure relates to a method for determining the sex and age of a subject from a dental image of the subject, and an apparatus using the same. Specifically, according to the method according to the present disclosure, the computing device acquires the dental image, detects an effective area from the dental image using an effective area model, and based on the effective area using a gender model While calculating the gender of the subject, the age of the subject is calculated based on the effective region using an age model.

Description

Method for determining the sex and age of a subject from a dental image and a device using the same

The present disclosure relates to a method for determining the sex and age of a subject from a dental image of the subject, and an apparatus using the same. Specifically, according to the method according to the present disclosure, the computing device acquires the dental image, detects an effective area from the dental image using an effective area model, and based on the effective area using a gender model While calculating the gender of the subject, the age of the subject is calculated based on the effective region using an age model.

A dental image refers to an image in which the maxilla and mandibula, which are anatomical structures of the oral cavity, are photographed in the dental field. Specifically, the dental image may be a dental panoramic X-ray image. In situations where identification is difficult, such as a disaster, gender and age are estimated using dental images. Especially in forensic medicine, in the case of unidentified dead people, knowing the age group can reduce the range of subjects to be investigated, so it is essential to assess the age of the unidentified deceased. In addition, among living people, due to the chaotic modern history of the Republic of Korea and various social and economic problems, the birth date is incorrectly recorded in the family register, so there is a need for age assessment to correct it.

'Age' includes bone age, age, and full age. Bone age refers to the age determined by looking at the skeleton, age refers to the age determined by looking at the teeth, and the full age refers to the actual age. There may be some differences between them.

There are various methods for estimating age. As forensic anthropology, there are methods to analyze the degree of ossification of the skeleton, fusion of epiphyseal growth plates, and occlusion of cranial sutures. How to analyze, etc. The age estimation method using teeth more specifically analyzes tooth eruption time, degree of calcification of teeth, degree of bite, size of pulp cavity, specific gravity and hardness, changes in tooth microstructure, and racemization reaction rate of amino acid components in teeth. method and so on.

The method using teeth has many advantages compared to other methods. First, the tooth-making process has the most suitable characteristics for age estimation because there is much less individual difference and diversity compared to the development and growth process of other organs. In addition, as the most durable tissue in the human body, the tooth hardly decays even after a long period of time, and it maintains its original shape stably even in extreme environments such as high temperature, high pressure, and high temperature, and still has the above-mentioned characteristics even when it is removed. There is also the advantage of being able to estimate the age of only one of the 32 teeth including the wisdom tooth. Of course, in the case of a dead person, all of the above methods can be used, but for a living person, there is a limitation in that only a non-invasive test method that does not damage the human body should be used due to a medical ethical problem. Clinically, for adolescents in the growth phase, the method of determining the eruption period and the degree of calcification of teeth is the most used, and for adults, the method of analyzing the degree of dentition is the most used.

As such, among the conventional techniques for estimating age using teeth, there is a Demirjian's method. According to this Demirjian method, there is a limit to first knowing the information of the gender in order to estimate the age, as well as the Demirjian method. The method is to judge the age, and there is a big difference with the age of the elderly, and it is mainly made based on Europeans, and it is not well applied to the case of different races because it is not suitable for East Asians. Such a conventional statistical method estimated the age through a complicated procedure such as time-consume, but the statistical method often showed inaccurate results according to race and environment.

However, since the method using the dental panoramic X-ray image has the advantage of being a non-invasive and ethical method, it would be desirable if the disadvantages of the prior art could be solved by using the latest artificial intelligence technology.

That is, in order to overcome the limitations of the conventional method, the present inventor extracts image features of a dental image by machine learning, in particular, deep learning, and utilizes them for estimating gender and age, so that accuracy compared to the conventional method We intend to propose a method that not only improves the estimation, but also supports the final judgment of experts by visualizing the areas that acted as important factors for estimation.
Related prior art literature may be Korean Patent Laid-Open Publication No. 10-2018-0070365.

An object of the present invention is to accurately predict both gender and age for identification of an individual in forensic medicine and the like.

In particular, the present invention overcomes the limitations of gender and age prediction of conventional statistical methods, extracts image features (shape, texture, global location, structural features, etc.) of dental images with an artificial neural network and utilizes them to predict gender and age. It aims to improve its accuracy and efficiency.

The characteristic configuration of the present invention for achieving the object of the present invention as described above and for realizing the characteristic effects of the present invention to be described later is as follows.

According to one aspect of the present invention, there is provided a method of determining the sex and age of the subject from a dental image of the subject, the method comprising: (a) a computing device acquiring the dental image or supporting another device linked to the computing device to acquire the dental image; (b) detecting, by the computing device, an effective area from the dental image using an effective area model or supporting the other device to detect the effective area; and (c) a process in which the computing device calculates the gender of the subject based on the effective region using (i) a gender model and (ii) the subject based on the valid region using an age model. and performing a process of calculating the age of , or supporting the other device to perform the process (i) and the process (ii).

According to another aspect of the present invention, there is also provided a computer program, stored in a machine-readable non-transitory recording medium, comprising instructions implemented to perform a method according to the present invention.

According to another aspect of the present invention, there is provided a computing device for determining the sex and age of the subject from a dental image of the subject, the apparatus comprising: a communication unit for obtaining the dental image; and (i) a process of detecting a valid area from the dental image via a valid area detection module comprising a valid area model; (ii) a process of calculating the sex of the subject based on the effective area through a gender determination module including a gender model; and (iii) a process of calculating the sex of the subject based on the effective area through an age determination module including an age model. and a processor that performs a process of calculating the age of a sample or supports another device interworking through the communication unit to perform the processes (i) to (iii).

According to the present invention, since there is an effect of accurately and efficiently estimating gender and age using a dental image, it can be utilized to identify an individual's identity in forensic medicine. In particular, according to the present invention, when a dental image is input, unlike the conventional Demirian method, gender and age can be derived very quickly and accurately within 1 second.

In addition, according to the present invention, there is an advantage in that it is possible to quickly grasp the main factors when estimating gender and age by providing visualization.

The accompanying drawings for use in the description of the embodiments of the present invention are only a part of the embodiments of the present invention, and for those of ordinary skill in the art to which the present invention pertains (hereinafter referred to as "a person skilled in the art"), Other drawings may be obtained based on these drawings without an effort leading to the invention.
1 is a conceptual diagram schematically illustrating an exemplary configuration of a computing device for performing a method of determining the sex and age of a subject from a dental image of the subject (hereinafter referred to as a "gender-age determination method") according to the present invention; am.
2 is an exemplary block diagram illustrating hardware or software components of a computing device for performing the method for determining gender and age of the present invention.
3 is a flowchart exemplarily illustrating a method for determining gender and age according to the present invention.
4 is a diagram conceptually illustrating a semantic segmentation model as an example of an effective region model that can be used to derive an effective region from a dental image in the method for determining gender and age of the present invention.
5 is a diagram conceptually illustrating a gender model used to calculate a gender from a dental image in the method for determining gender and age of the present invention.
6 is a diagram conceptually illustrating an age model used to calculate an age from a dental image in the method for determining gender and age of the present invention.
7 is a view exemplarily showing visualization made with respect to a dental image in the method for determining gender and age of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following detailed description of the present invention refers to the accompanying drawings, which show by way of illustration a specific embodiment in which the present invention may be practiced, in order to clarify the objects, technical solutions and advantages of the present invention. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention.

The term "image" or "image data" as used throughout the present description and claims refers to multidimensional data composed of discrete image elements (eg, pixels in a two-dimensional image), in other words, ( For example, a term that refers to a visible object (eg, displayed on a video screen) or a digital representation of the object (eg, a file corresponding to a pixel output of a CT, MRI detector, etc.). For example, “image” or “image” means X-ray imaging, computed tomography (CT), magnetic resonance imaging (MRI), ultrasound or any other medical treatment known in the art. It may be a medical image of a subject collected by an imaging system. The image does not necessarily have to be provided in a medical context, but may be provided in a non-medical context, for example, there may be X-ray imaging for security screening.

In the present disclosure, in the drawings presented for convenience of description, it is shown that a dental panoramic image taken with X-rays is an exemplary image modality. However, those skilled in the art will know that the image formats used in various embodiments of the present invention are 2D, 3D, such as CT, positron emission tomography (PET), PET-CT, SPECT, SPECT-CT, MR-PET, and 3D ultrasound image. It will be appreciated that the formats include, but are not limited to, examples listed as such.

Throughout the detailed description and claims of the present invention, the 'DICOM (Digital Imaging and Communications in Medicine)' standard is a generic term for various standards used for digital image representation and communication in medical devices, DICOM Standards are published by a joint committee formed by the American Society of Radiological Medicine (ACR) and the National Electrical Engineers Association (NEMA).

In addition, throughout the detailed description and claims of the present invention, 'Picture Archiving and Communication System (PACS)' is a term that refers to a system that stores, processes, and transmits in accordance with the DICOM standard, X-ray, CT , medical imaging images acquired using digital medical imaging equipment such as MRI are stored in DICOM format and can be transmitted to terminals inside and outside the hospital through a network, to which reading results and medical records can be added.

And throughout the detailed description and claims of the present invention, 'learning' or 'learning' is a term referring to performing machine learning through computing according to a procedure, and a mental action such as human educational activity. It is not intended to be a reference, and training is used in the generally accepted sense of machine learning. For example, 'deep learning' refers to machine learning using deep artificial neural networks.

Further, throughout the description and claims of the present invention, the word 'comprise' and variations thereof are not intended to exclude other technical features, additions, components or steps. In addition, 'one' or 'an' is used to mean more than one, and 'another' is limited to at least a second or more.

Other objects, advantages and characteristics of the present invention will appear to a person skilled in the art, in part from this description, and in part from practice of the present invention. The following illustrations and drawings are provided by way of illustration and are not intended to limit the invention. Therefore, the details disclosed herein with respect to a specific structure or function are not to be construed in a limiting sense, but merely representative should be interpreted as basic data.

Moreover, the invention encompasses all possible combinations of the embodiments indicated herein. It should be understood that various embodiments of the present invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in relation to one embodiment. In addition, it should be understood that the position or arrangement of individual components in each disclosed embodiment may be changed without departing from the spirit and scope of the present invention. Accordingly, the detailed description set forth below is not intended to be taken in a limiting sense, and the scope of the invention, if properly described, is limited only by the appended claims, along with all scope equivalents to those claimed. Like reference numerals in the drawings refer to the same or similar functions throughout the various aspects.

Unless otherwise indicated herein or otherwise clearly contradicted by context, items referred to in the singular encompass the plural unless the context requires otherwise. In addition, in describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description thereof will be omitted.

Hereinafter, in order to enable those skilled in the art to easily practice the present invention, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a conceptual diagram schematically illustrating an exemplary configuration of a computing device that performs a method for determining gender and age according to the present invention.

Referring to FIG. 1 , a computing device 100 according to an embodiment of the present invention includes a communication unit 110 and a processor 120 , and is directly or indirectly connected to an external computing device (not shown) through the communication unit 110 . can communicate effectively.

Specifically, the computing device 100 includes typical computer hardware (eg, a computer processor, memory, storage, input device and output device, device that may include other components of a conventional computing device; router, switch, etc.) Electronic communication devices; electronic information storage systems, such as network-attached storage (NAS) and storage area networks (SANs)) and computer software (i.e., that enable the computing device to function in a particular way). instructions) to achieve the desired system performance.

The communication unit 110 of such a computing device may transmit and receive a request and a response to and from another computing device that is interlocked. As an example, such a request and a response may be made by the same transmission control protocol (TCP) session. , but is not limited thereto, and may be transmitted and received as, for example, a user datagram protocol (UDP) datagram. In addition, in a broad sense, the communication unit 110 may include a keyboard, a mouse, other external input devices, printers, displays, and other external output devices for receiving commands or instructions.

In addition, the processor 120 of the computing device may include a micro processing unit (MPU), a central processing unit (CPU), a graphics processing unit (GPU), a neural processing unit (NPU) or a tensor processing unit (TPU), and a cache memory. ), and may include a hardware configuration such as a data bus. In addition, it may further include an operating system, a software configuration of an application for performing a specific purpose.

2 is an exemplary block diagram illustrating hardware or software components of a computing device for performing the method for determining gender and age of the present invention.

First, a brief overview of the configuration of the method and apparatus according to the present invention with reference to FIG. 2 , the computing device 100 may include an image acquisition module 210 as a component thereof. The image acquisition module 210 is configured to acquire data of a dental image to which the method according to the present invention is applied. The individual modules shown in FIG. 2 include, for example, the communication unit 110 included in the computing device 100 . Those of ordinary skill in the art will understand that the processor 120 or the communication unit 110 and the processor 120 may be implemented by interworking.

The dental image, for example, may be obtained from an external image storage system, such as a photographing device or a medical image storage and transmission system (PACS) interlocked through the communication unit 110, but is not limited thereto. For example, the dental image may be acquired by the image acquisition module 210 of the computing device 100 after the image captured by the dental imaging device is transmitted to the PACS according to the DICOM standard. Preferably, the dental image may be a panoramic X-ray image.

Next, the acquired dental image may be transmitted to the effective area detection module 220 , and the effective area model, which is an artificial neural network model included in the effective area detection module 220 , is obtained from the entire dental image of maxilla, mandible, and temporomandibular mandible. It is configured to extract an effective region including a temporomandibular joint (TMJ).

When the extraction of the effective region is completed, the gender determination module 230 extracts gender and dental image feature information (encoding information) from the valid region through the gender model, and the age determination module 240 uses the age model to extract the effective area. Age is extracted from the feature information extracted from the region and the gender model. That is, the age model increases the accuracy of age determination according to gender by reflecting the characteristic information from the gender model.

Then, the output module 250 may provide the gender and age information to an external entity. The information on gender and age may be provided together with visualization information of a part corresponding to a major factor in the calculation of gender and visualization information of a part corresponding to a major factor in calculating age. Here, the external entity includes a user of the computing device 100 performing the method according to the present invention, an administrator, a medical professional in charge of the subject, and the like, but in addition to this, the gender and age determined from the dental image Any subject that requires such information should be understood as being included. When the external entity is a human, the output module 250 may provide gender information and age information to the external entity through a predetermined output device, for example, a user interface displayed on a display.

Detailed functions and effects of each component schematically described with reference to FIG. 2 will be described later in detail with reference to FIGS. 3 to 6 . Although the components shown in FIG. 2 are exemplified as being realized in one computing device for convenience of description, it will be understood that the computing device 100 for performing the method of the present invention may be configured as a plurality of devices interworking with each other. .

3 is a flowchart exemplarily illustrating a method for determining gender and age according to the present invention.

Referring to FIG. 3 , in the method for determining gender and age according to the present invention, first, the image acquisition module 210 implemented by the computing device 100 acquires a dental image of a subject or a communication unit of the computing device 100 . It includes a step (S100) of supporting another device to be linked through 110 to acquire a dental image. It will be understood that the present invention is not limited to the dental panoramic X-ray image and may be applied to other image formats in which the corresponding area is photographed.

Next, in the method for determining gender and age according to the present invention, the effective area detection module 220 implemented by the computing device 100 detects the effective area from the dental image or causes the other device to detect the effective area It further includes a step (S200) of supporting to do so.

4 is a diagram conceptually illustrating a semantic segmentation model as an example of an effective region model that can be used to derive an effective region from a dental image in the method for determining gender and age of the present invention.

The deep neural network automatically learns the characteristics of each image by learning a large amount of data in a structure consisting of a multi-layered artificial neural network, and through this, the learning proceeds in a way that minimizes the error of the objective function, that is, the classification accuracy. It is a machine learning model, and it is in the spotlight because it can extract and classify features of various levels from low-level features such as points, lines, and planes to complex and meaningful high-level features.

In particular, the semantic segmentation models 410 to 450 illustrated in FIG. 4 are encoders 410, 420, and 430 for compressing and extracting features from an original image, and a decoder 440 for restoring them to an output value of the model. , 450) may be configured to include.

The panoramic X-ray image 460 used in the present disclosure has a wide range of areas to be photographed including not only the maxilla and mandible, but also the cervical spine, nasal cavity, etc. 470) can be extracted and used as refined input data to ultimately enable accurate prediction of gender and age.

For example, the effective region may be a region excluding the cervical spine from the dental image 460 or a region excluding a nasal cavity.

Next, in the method for determining gender and age according to the present invention, a process ( S300a ) in which the gender determination module 230 implemented by the computing device 100 calculates the gender of the subject based on the effective area ( S300a ) and the computing device The age determination module 240 implemented by ( 100 ) performs the process ( S300b ) of calculating the age of the subject based on the effective area or causes the other device to perform the processes ( S300a ) and ( S300b ) It further includes a step (S300) of supporting to perform.

5 is a diagram conceptually illustrating a gender model included in the gender determination module 230 used to calculate the gender from the dental image 510 in the method for determining age and gender of the present invention.

Referring to FIG. 5 , a dental image 530 reconstructed using an effective area 520 that is an output value of the effective area detection module 220 is used as an input value of the gender model.

The gender model may be an artificial neural network model, and specifically, a convolutional layer (eg, 541 to 544) for extracting features from the reconstructed dental image 530, and a precoupling layer for predicting gender from them. (a fully-connected layer; for example, 545 ), information on the subject's gender and feature information (encoding information) of the dental image may be extracted from the gender model.

The gender model may be trained using, as a training dataset, data of valid regions detected for a plurality of subjects and corresponding sex data of the subject. For example, the gender model may be trained in a direction to reduce the difference between the cross entropy of the model's output value (ie, predicted value) and the actual value (ie, correct answer).

6 is a diagram conceptually illustrating an age model used to calculate an age from a dental image in the method for determining age and gender of the present invention.

Referring to FIG. 6 , a dental image 610 reconstructed using an effective area that is an output value of the effective area detection module 220 is used as an input value of the age model.

The age model may be an artificial neural network model, and specifically, a convolutional layer (eg, 621 to 624) for extracting features from the reconstructed dental image 610, and a precoupling layer (eg, 625) for predicting age from them. ), and information on the subject's age may be extracted from this age model. In order to increase the accuracy of age prediction, feature information (encoding information) 626 calculated in the gender model may be concatenated with the feature information calculated in the age model and used to generate an output value by the precoupling layer 625 .

This is because teeth and skeletons have different developmental rates according to gender, so when estimating age, using the gender information derived using a trained gender model as an additional input value can be helpful in estimating age more accurately. because there is

The age model may be trained using data of valid regions detected for a plurality of subjects and corresponding age data of the subject as a training dataset. Here, the training dataset may further include feature information (encoding information) of the dental image extracted from the gender model.

For example, the age model may be trained in a direction to reduce the difference between an output value of the model (ie, predicted age) and a distance measurement function (eg, L2 distance, etc.) between an actual value (ie, actual age).

When gender and age are calculated in step S300, in the method for determining gender and age according to the present invention, the output module 250 implemented by the computing device 100 outputs the determination result including the gender and age to an external entity. It may further include a step (S400) of providing to or supporting the other device to provide it.

In an embodiment of step S400, a process of visualizing a first part corresponding to a major factor in calculating the age using a first activation map in the age model and providing it to the external entity; and At least one of a process of visualizing a second portion corresponding to a major factor in calculating the gender using the second activity map in the gender model and providing it to the external entity may be performed.

Specifically, a method for calculating the activity map is as follows.

7 is a diagram exemplarily showing visualization made with respect to the dental image 710 in the method for determining gender and age of the present invention.

Referring to FIG. 7 , a latent convolutional layer 720 is shown among the convolutional layers included in the artificial neural network model that can be employed in the gender model and the age model.

Now, c is the class of age or gender, y is the output value, i is the width of the latent convolutional layer, j is the height of the latent convolutional layer, and Z is the product of the width and height of the latent convolutional layer. , Let A ^{k be} the k-th feature map of the latent convolutional layer,

, the active map is expressed as Equation 2 below.

Examples of visualization of the gender model are as indicated by reference numbers 730 and 740 of FIG. 7 , and examples of visualization of the age model are indicated by reference numbers 750 and 760 of FIG. 7 .

As described above with reference to FIGS. 1 to 7 , the present invention is capable of accurately and efficiently estimating gender and age using a dental image in all embodiments and modifications thereof, and at the same time providing visualization, When estimating the age, it has the effect of being able to quickly grasp the main factors.

Based on the description of the above embodiments, those skilled in the art will recognize that the method and/or processes of the present invention, and the steps thereof, may be implemented in hardware, software, or any combination of hardware and software suitable for a particular application. point can be clearly understood. The hardware may include general purpose computers and/or dedicated computing devices or specific computing devices or special features or components of specific computing devices. The processes may be realized by one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors or other programmable devices, having internal and/or external memory. Additionally, or alternatively, the processes may be configured to process an application specific integrated circuit (ASIC), programmable gate array, programmable array logic (PAL) or electronic signals. It may be implemented with any other device or combination of devices. Moreover, the objects of the technical solution of the present invention or parts contributing to the prior arts may be implemented in the form of program instructions that can be executed through various computer components and recorded in a machine-readable recording medium. The machine-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the machine-readable recording medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software. Examples of the machine-readable recording medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as CD-ROM, DVD, Blu-ray, and a magneto-optical medium such as a floppy disk (magneto-optical media), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include any one of the devices described above, as well as heterogeneous combinations of processors, processor architectures or combinations of different hardware and software, or stored and compiled or interpreted for execution on a machine capable of executing any other program instructions. can be created using a structured programming language such as C, an object-oriented programming language such as C++, or a high-level or low-level programming language This includes not only bytecode, but also high-level language code that can be executed by a computer using an interpreter or the like.

Accordingly, in one aspect according to the present invention, when the method and combinations thereof described above are performed by one or more computing devices, the methods and combinations of methods may be implemented as executable code for performing respective steps. In another aspect, the method may be implemented as systems that perform the steps, the methods may be distributed in various ways across devices or all functions may be integrated into one dedicated, standalone device or other hardware. In another aspect, the means for performing the steps associated with the processes described above may include any of the hardware and/or software described above. All such sequential combinations and combinations are intended to fall within the scope of this disclosure.

For example, the hardware device may be configured to operate as one or more software modules to perform processing in accordance with the present invention, and vice versa. The hardware device may include a processor such as an MPU, CPU, GPU, TPU coupled with a memory such as ROM/RAM for storing program instructions and configured to execute instructions stored in the memory, and an external device and signal It may include a communication unit that can send and receive. In addition, the hardware device may include a keyboard, a mouse, and other external input devices for receiving commands written by developers.

In the above, the present invention has been described with specific matters such as specific components and limited embodiments and drawings, but these are only provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments, Those of ordinary skill in the art to which the present invention pertains can make various modifications and variations from these descriptions.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and not only the claims described below, but also all modifications equivalently or equivalently to the claims described below belong to the scope of the spirit of the present invention. will do it

Such equivalent or equivalent modifications shall include, for example, logically equivalent methods capable of producing the same results as practiced by the methods according to the present invention, the spirit and scope of the present invention. should not be limited by the above examples, and should be understood in the broadest sense permitted by law.

Claims (8)

In the method of determining the sex and age of the subject from the dental image of the subject,
acquiring, by the computing device, the dental image;
detecting, by the computing device, an effective area from the dental image using an effective area model; and
performing, by the computing device, a process of calculating the gender of the subject based on the valid region using a gender model and a process of calculating the age of the subject based on the valid region using an age model;
including,
The age model is
Gender age for calculating the age of the subject based on gender-age characteristic information, in which the gender characteristic information extracted from the effective region through the gender model and the age characteristic information extracted from the effective region through the age model are connected Judgment method. delete According to claim 1,
providing, by the computing device, a determination result including the calculated gender and the age to an external entity;
further comprising,
In the step of providing to the external entity,
A process in which the computing device visualizes a first part corresponding to a major factor in calculating the age using a first activation map in the age model and provides it to the external entity, and in the gender model and performing a process of visualizing a second part corresponding to a major factor in calculating the gender using a second activity map and providing the second part to the external entity. According to claim 1,
The effective region is a region excluding cervical vertebrae from the dental image. According to claim 1,
The gender model is an artificial neural network model trained using effective regions detected for a plurality of subjects and data of the subject's corresponding sex as a training dataset. According to claim 1,
The age model is an artificial neural network model trained using data of valid regions detected for a plurality of subjects and age of the subject corresponding thereto as a training dataset. A computer program, stored in a machine-readable non-transitory recording medium, comprising instructions implemented to cause a computing device to perform the method of any one of claims 1 to 6 . A computing device for determining the sex and age of the subject from a dental image of the subject, the computing device comprising:
a communication unit for acquiring the dental image; and
a process of detecting a valid area from the dental image via a valid area detection module comprising a valid area model; calculating the age of the subject based on the valid region through a process for calculating the gender of the subject based on the effective region through a gender determining module including a gender model and an age determination module including an age model the processor that performs the process
including,
The age model is
A computing device for calculating the age of the subject based on gender-age characteristic information in which the gender characteristic information extracted from the effective region through the gender model and age characteristic information extracted from the effective region through the age model are connected.

Images