KR102518493B1 - Electronic apparatus and method for detecting at least one cervical vertebrae point included in cervical vertebrae using artificial intelligence model in x-ray image including cervical vertebrae - Google Patents

Abstract

Disclosed are a device and method for detecting at least one cervical vertebrae point included in cervical vertebrae in an X-ray image including the cervical vertebrae by using an artificial intelligence model. According to one embodiment of the present disclosure, the device comprises a memory including at least one instruction, and at least one processor executing the at least one instruction stored in the memory. The at least one processor may acquire an X-ray image including cervical vertebrae, detect a cervical vertebrae region including the cervical vertebrae from the X-ray image, calculate a degree of detection reliability of each of a plurality of point regions included in the detected cervical vertebrae region, and detect at least one cervical vertebrae point in at least one point region having a degree of detection reliability equal to or greater than a preset threshold among the plurality of point regions.

Description

An electronic device and method for detecting at least one cervical vertebrae point included in the cervical vertebrae using an artificial intelligence model in an X-ray image including the cervical vertebrae VERTEBRAE USING ARTIFICIAL INTELLIGENCE MODEL IN X-RAY IMAGE INCLUDING CERVICAL VERTEBRAE}

The present disclosure relates to an electronic device and method for detecting cervical points. More specifically, the present disclosure relates to an electronic device and method for detecting at least one cervical vertebrae point included in the cervical vertebrae using an artificial intelligence model in an X-ray image including the cervical vertebrae.

In general, a medical imaging apparatus is equipment for acquiring an image of an internal structure of a target object. Medical imaging devices include a magnetic resonance imaging (MRI) device for providing magnetic resonance images, a computed tomography (CT) device, an X-ray device, and an ultrasound diagnosis device. etc. Based on the medical image obtained from the medical imaging device, structural details of the patient's body can be grasped to diagnose the patient's health condition and disease.

Patent Publication No. KR 10-2402221 B1 (published date: May 23, 2022) Patent Publication US 2011-0058720 A1 (published on March 10, 2011) Published Patent Publication JP 3234668 U (published date: October 06, 2021)

In the disclosed embodiments, after detecting a cervical spine region using an artificial intelligence model in an X-ray image including the cervical spine, calculating detection reliability for each of a plurality of point regions included in the detected cervical region, - It is possible to provide an electronic device and method for detecting cervical vertebrae points in at least one point area having detection reliability greater than or equal to a set threshold.

The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

According to one aspect of the present disclosure for achieving the above technical problem, an electronic device for detecting at least one cervical vertebrae point included in the cervical vertebrae using an artificial intelligence model in an X-ray image including the cervical vertebrae is provided. can The electronic device may include a memory including at least one instruction and at least one processor executing the at least one instruction stored in the memory. The at least one processor may acquire an X-ray image including the cervical vertebrae and detect a cervical vertebrae region including the cervical vertebrae from the X-ray image. The at least one processor may calculate detection reliability for each of a plurality of point regions included in the detected cervical region. The at least one processor may detect at least one cervical vertebrae point from at least one point region having a detection reliability greater than or equal to a preset threshold among a plurality of point regions.

The at least one processor may not detect at least one cervical vertebrae point in at least one point region having a detection reliability smaller than a preset threshold among a plurality of point regions.

The at least one cervical vertebrae point may include a plurality of cervical vertebrae points. The at least one processor may detect at least one of an angle and a distance between a plurality of cervical vertebrae points based on the plurality of cervical vertebrae points.

The at least one processor may calculate detection reliability based on at least one of the size of the detected cervical vertebrae region, the number of a plurality of point regions, the arrangement between the plurality of point regions, or the shape of the cervical spine included in the detected cervical region. there is.

The at least one processor may increase the resolution of at least one point area having a detection reliability greater than or equal to a preset threshold among a plurality of point areas from a first resolution to a second resolution higher than the first resolution. there is. The at least one processor may detect at least one cervical vertebrae point in at least one point region having a second resolution.

The electronic device may further include a camera that captures an X-ray image including the cervical vertebrae. The at least one processor may obtain an X-ray image including the cervical vertebrae through a camera.

The at least one processor may increase the resolution of each of the plurality of point areas from a first resolution to a third resolution higher than the first resolution before calculating the detection reliability. The at least one processor may calculate detection reliability for each of a plurality of point areas having a third resolution.

The at least one processor may calculate detection reliability for each of a plurality of point areas using a pre-trained artificial intelligence model. The at least one processor may detect at least one cervical vertebrae point in at least one point region having a detection reliability greater than or equal to a pre-set threshold, using a pre-trained artificial intelligence model.

According to one aspect of the present disclosure for achieving the above technical problem, a method for detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae is provided. The method may include obtaining an X-ray image including the cervical vertebrae and detecting a cervical vertebrae region including the cervical vertebrae in the X-ray image. The method may include calculating detection reliability for each of a plurality of point regions included in the detected cervical region. The method may include detecting at least one cervical vertebrae point in at least one point region having a detection reliability greater than or equal to a preset threshold value among a plurality of point regions.

In addition to this, a computer program stored in a computer readable recording medium for executing the method of detecting cervical vertebrae points provided in the present disclosure may be further provided.

In addition to this, a computer readable recording medium recording a computer program for executing the method for detecting cervical vertebrae points provided in the present disclosure may be further provided.

Other specific details of the invention are included in the detailed description and drawings.

According to the above-mentioned problem solving means of the present disclosure, it is possible to detect at least one cervical vertebrae point included in the cervical vertebrae from an X-ray image including the cervical vertebrae using an artificial intelligence model. In this case, according to the present disclosure, when detecting a cervical vertebrae point in an X-ray image, a detection reliability for each of point regions to be detected is calculated, and a point region having a detection reliability equal to or greater than a preset threshold value. cervical vertebrae points can be detected. Therefore, the reliability of the cervical vertebrae points detected according to the present disclosure can be increased, and the patient's health status and disease diagnosis can be performed using the highly reliable cervical vertebrae points.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram for explaining an electronic device and method for detecting cervical vertebrae points according to an embodiment of the present disclosure.
2 is a block diagram illustrating the configuration of an electronic device according to an embodiment of the present disclosure.
3 is a flowchart for explaining a method of detecting cervical vertebrae points according to an embodiment of the present disclosure.
4 is a diagram for explaining an operation of detecting a cervical vertebrae region including cervical vertebrae in an X-ray image according to an embodiment of the present disclosure.
5 is a diagram for explaining an operation of detecting at least one cervical vertebrae point in at least one point area according to an embodiment of the present disclosure.
6 is a diagram for explaining an operation of detecting at least one of an angle and a distance between a plurality of cervical vertebrae points based on a plurality of cervical vertebrae points according to an embodiment of the present disclosure.
7 is a diagram for explaining a method of detecting a cervical vertebrae point according to a comparison between a calculated detection reliability and a preset threshold according to an embodiment of the present disclosure.

Like reference numbers designate like elements throughout this disclosure. The present disclosure does not describe all elements of the embodiments, and general content or overlapping content between the embodiments in the technical field to which the present disclosure belongs is omitted. The term 'unit, module, member, or block' used in the specification may be implemented as software or hardware, and according to embodiments, a plurality of 'units, modules, members, or blocks' may be implemented as one component, It is also possible that one 'part, module, member, block' includes a plurality of components.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case of being directly connected but also the case of being indirectly connected, and indirect connection includes being connected through a wireless communication network. do.

In addition, when a certain component is said to "include", this means that it may further include other components without excluding other components unless otherwise stated.

Throughout the specification, when a member is said to be located “on” another member, this includes not only a case where a member is in contact with another member, but also a case where another member exists between the two members.

Terms such as first and second are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

Expressions in the singular number include plural expressions unless the context clearly dictates otherwise.

In each step, the identification code is used for convenience of description, and the identification code does not explain the order of each step, and each step may be performed in a different order from the specified order unless a specific order is clearly described in context. there is.

In this specification, the 'electronic device according to the present disclosure' includes all various devices capable of providing results to users by performing calculation processing. For example, an electronic device according to the present disclosure may include a computer, a server device, and a portable terminal, or may be in any one form.

Here, the computer may include, for example, a laptop computer, a desktop computer, a laptop computer, a tablet PC, a slate PC, and the like equipped with a web browser.

The server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

The portable terminal is, for example, a wireless communication device that ensures portability and mobility, and includes a Personal Communication System (PCS), a Global System for Mobile communications (GSM), a Personal Digital Cellular (PDC), a Personal Handyphone System (PHS), and a PDA. (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, smart phone ) and wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted-devices (HMDs). can include

Hereinafter, the working principle and embodiments of the present disclosure will be described with reference to the accompanying drawings.

1 is a diagram for explaining an electronic device and method for detecting cervical vertebrae points according to an embodiment of the present disclosure. 2 is a block diagram illustrating the configuration of an electronic device according to an embodiment of the present disclosure.

Referring to FIGS. 1 and 2 , the electronic device 1000 according to the present disclosure may obtain an X-ray image 100 including the cervical spine. In one embodiment, the X-ray image 100 may be an X-ray image 100 obtained by photographing the whole lateral side of the patient. However, the present disclosure is not limited thereto, and the X-ray image 100 may be an X-ray image of the upper body including the patient's cervical spine.

In an embodiment, the electronic device 1000 may detect the cervical region 200, which is a region including the cervical spine, from the X-ray image 100 including the cervical spine. In one embodiment, when the X-ray image 100 is an X-ray image 100 of the side of the whole body including the cervical vertebrae, the electronic device 1000 detects and detects the cervical vertebrae in the X-ray image 100. The cervical region 200 including the cervical vertebrae may be detected from the X-ray image 100 . In one embodiment, the electronic device 1000 compares the pre-learned cervical spine image with the acquired X-ray image 100 to detect the cervical region 200 including the cervical spine in the X-ray image 100. You may. The electronic device 1000 may detect a region including an image similar to the learned cervical spine image in the X-ray image 100 as the cervical spine region 200 . In one embodiment, the electronic device 1000 may include an artificial intelligence (AI) model. The artificial intelligence model may be a model learned to detect a cervical spine region in an X-ray image. The artificial intelligence model may implement various algorithms for detecting cervical vertebrae in an X-ray image. For example, the artificial intelligence model may be implemented as a convolutional neural network (CNN), a recurrent neural network (RNN), or a combination thereof, but is not limited thereto.

In one embodiment, the detected cervical region 200 may include a plurality of point regions. Each of the plurality of point regions may correspond to a cervical vertebra included in the cervical vertebrae. The electronic device 1000 may detect a plurality of point regions included in the detected cervical region 200 based on the positions and arrangements of cervical vertebrae included in the pre-learned cervical spine image. In one embodiment, the artificial intelligence model of the electronic device 1000 may be a model learned to detect a plurality of point regions in the cervical spine region 200 .

In an embodiment, the electronic device 1000 may calculate detection reliability for each of the plurality of point regions based on the detected cervical region 210 including the plurality of point regions. As an embodiment, the electronic device 1000 may calculate reliability of a result detected as including a plurality of point areas. In an embodiment, the electronic device 1000 may detect a plurality of point regions from the cervical spine region 200 using an artificial intelligence model, and calculate reliability of the detected result for each of the plurality of detected point regions. can

In an embodiment, the electronic device 1000 may compare the detection reliability calculated for each of the plurality of points with a preset threshold value. The electronic device 1000 determines at least one cervical vertebrae point 300 based on at least one point area having a detection reliability equal to or greater than a preset threshold among a plurality of points. can be detected. In one embodiment, the cervical vertebrae point 300 is a point corresponding to the cervical vertebrae, and may serve as a kind of landmark representing the cervical vertebrae.

In addition, when there are a plurality of detected cervical vertebrae points 300, the electronic device 1000 may detect an angle 400 between the plurality of cervical vertebrae points 300 based on the plurality of cervical vertebrae points 300. .

The electronic device 1000 of the present disclosure obtains a plurality of cervical vertebrae points 300 having high detection reliability and an angle 400 between the plurality of cervical vertebrae points 300 in an X-ray image 100 including the cervical vertebrae. can do. Therefore, through the electronic device 1000 and method of the present disclosure, it is possible to accurately diagnose the patient's health condition, the presence or absence of disease, and the type of disease.

Referring to FIG. 2 , an electronic device 1000 according to an embodiment may include a communication interface 1100, a memory 1200, at least one processor 1300, a camera 1400, and a display 1500. . However, not all components shown in FIG. 2 are essential components. The electronic device 1000 may be implemented with more components than those shown in FIG. 2 , or the electronic device 1000 may be implemented with fewer components. The communication interface 1100, memory 1200, at least one processor 1300, camera 1400, and display 1500 may be electrically and/or physically connected to each other.

The communication interface 1100 may perform data communication with external electronic devices (eg, user devices, external servers, etc.) under the control of at least one processor 1300 .

The communication interface 1100, for example, wired LAN, wireless LAN, Wi-Fi, Bluetooth, Zigbee, Wi-Fi Direct (WFD), infrared communication (IrDA) , infrared Data Association), BLE (Bluetooth Low Energy), NFC (Near Field Communication), WiBro (Wireless Broadband Internet, Wibro), WiMAX (World Interoperability for Microwave Access, WiMAX), SWAP (Shared Wireless Access Protocol), WiGi Data communication between the electronic device 1000 and an external electronic device may be performed using at least one of WiGig (Wireless Gigabit Alliances) and data communication methods including RF communication.

The communication interface 1100 according to an embodiment may receive an X-ray image 100 including the cervical spine from an external electronic device. Also, the communication interface 1100 transmits information on at least one of a plurality of cervical vertebrae points detected from the X-ray image 100 including the cervical vertebrae using the electronic device 1000 and angles and distances between the cervical vertebrae points. It can also be provided as an external electronic device.

The memory 1200 may store instructions, data structures, and program codes readable by at least one processor 1300 . In the disclosed embodiments, operations performed by at least one processor 1300 may be implemented by executing instructions or codes of a program stored in the memory 1200 .

The memory 1200 includes a flash memory type, a hard disk type, a multimedia card micro type, and a card type memory (eg SD or XD memory). Non-volatile memory including at least one of ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk and volatile memory such as RAM (Random Access Memory) or SRAM (Static Random Access Memory).

According to an embodiment, the memory 1200 determines whether the electronic device 1000 uses an artificial intelligence model in an X-ray image including the cervical vertebrae, among a plurality of cervical vertebrae points included in the cervical vertebrae and angles and distances between the cervical vertebrae points. At least one instruction or program for detecting at least one may be stored. For example, the memory 1200 includes various types of images for detecting at least one of a plurality of cervical vertebrae points included in the cervical vertebrae and angles and distances between the cervical vertebrae points using an artificial intelligence model in an X-ray image including the cervical vertebrae. Software modules and/or data may be stored. The memory 1200 may include an image acquisition module 1210, a cervical region detection module 1220, a detection reliability calculation module 1230, a cervical spine point detection module 1240, and a resolution conversion module 1250.

At least one processor 1300 may control overall operations of the electronic device 1000 . For example, the at least one processor 1300 executes one or more modules stored in the memory 1200 so that the electronic device 1000 can determine the cervical vertebrae in an X-ray image including the cervical vertebrae using an artificial intelligence model. Overall operations for detecting at least one of a plurality of included cervical vertebrae points and angles and distances between the cervical vertebrae points may be controlled.

The at least one processor 1300 may include, for example, a central processing unit, a microprocessor, a graphic processing unit, application specific integrated circuits (ASICs), and digital signal processors (DSPs). , DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), Application Processors, Neural Processing Units, or hardware structures specialized in the processing of artificial intelligence models. It may be configured with at least one of the designed artificial intelligence dedicated processors, but is not limited thereto.

In one embodiment, the camera 1400 may be configured to take an X-ray image 100 including the cervical vertebrae. At least one processor 1300 may be a component for taking an X-ray image 100 including the cervical vertebrae using the camera 1400 . In one embodiment, the camera 1400 may be an X-ray device. However, the present disclosure is not limited thereto. The electronic device 1000 may not include the camera 1400 and may receive the X-ray image 100 including the cervical vertebrae captured by the external electronic device through the communication interface 1100 .

In one embodiment, the display 1500 detects at least one of a plurality of cervical vertebrae points included in the cervical vertebrae and angles and distances between the cervical vertebrae points in an X-ray image including the cervical vertebrae using the electronic device 1000. Each of the images 100, 200, 300, and 400 appearing in the process may be displayed. In addition, according to an embodiment of the present disclosure, the display 1500 displays an X-ray image 100 including the cervical vertebrae, a plurality of cervical vertebrae points 300 detected using the electronic device 1000, and a plurality of cervical vertebrae points. It is also possible to display only the angle (400) between them.

3 is a flowchart for explaining a method of detecting cervical vertebrae points according to an embodiment of the present disclosure. 4 is a diagram for explaining an operation of detecting a cervical vertebrae region including cervical vertebrae in an X-ray image according to an embodiment of the present disclosure. 5 is a diagram for explaining an operation of detecting at least one cervical vertebrae point in at least one point area according to an embodiment of the present disclosure. 6 is a diagram for explaining an operation of detecting at least one of an angle and a distance between a plurality of cervical vertebrae points based on a plurality of cervical vertebrae points according to an embodiment of the present disclosure.

Referring to FIGS. 1, 2 and 3 , in an embodiment, a method of detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae includes: It may include obtaining (100) (S100).

In one embodiment, in the step of acquiring the X-ray image 100 (S100), at least one processor 1300 executes the image acquisition module 1210 to capture the patient's body using the camera 1400. An X-ray image 100 may be obtained by photographing. In one embodiment, the electronic device 1000 may obtain an X-ray image 100 taken from an external electronic device.

Referring to FIGS. 3 and 4 , in an embodiment, a method for detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae includes the cervical vertebrae in the X-ray image 100. It may include a step (S200) of detecting the cervical region 200 to be. In one embodiment, at least one processor 1300 may execute the cervical region detection module 1220 to detect the cervical region 200 in the X-ray image 100 . The step of detecting the cervical region 200 including the cervical vertebrae in the X-ray image 100 ( S200 ) will be described later with reference to FIG. 5 .

In one embodiment, a method of detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae, which corresponds to each of a plurality of cervical vertebrae points 300 among the detected cervical vertebrae regions 200. A step of calculating detection reliability for each of a plurality of point areas (S300) may be included. In an embodiment, at least one processor 1300 may execute the detection reliability calculation module 1230 to calculate detection reliability for each of a plurality of point areas.

In one embodiment, at least one processor 1300 may calculate detection reliability for each of a plurality of point regions based on the size of the detected cervical spine region 200 . Specifically, when the size of the cervical spine region 200 included in the X-ray image 100 is smaller than a preset size, the at least one processor 1300 determines the size of the cervical spine region 200 having the corresponding size. Reliability of a corresponding detection result may be calculated with respect to a plurality of detected point areas.

In one embodiment, at least one processor 1300 may calculate the detection reliability for each of the plurality of point regions based on the number of the plurality of point regions included in the detected cervical spine region 200 . In detail, at least one processor 1300 may detect a plurality of point regions by using a pre-learned artificial intelligence model to classify cervical vertebrae included in the cervical vertebrae into 13 parts. In this case, when the number of the plurality of point areas included in the X-ray image 100 is less than 13, the at least one processor 1300 may calculate low reliability of the detection result for the plurality of point areas. there is. At least one processor 1300 controls the reliability of the detection result for the plurality of point areas to decrease as the difference between the number of point areas included in the X-ray image 100 and the set number of 13 increases. can be calculated

In one embodiment, at least one processor 1300 may calculate detection reliability for each of the plurality of point regions based on the arrangement between the plurality of point regions included in the detected cervical spine region 200 . Specifically, the at least one processor 1300 may detect a plurality of point regions by using a pre-learned artificial intelligence model based on a plurality of cervical vertebrae images including 13 cervical vertebrae. In this case, 13 cervical vertebrae included in each of the plurality of cervical vertebrae images are similarly arranged in terms of the human body structure. Accordingly, the at least one processor 1300 determines whether a plurality of point regions are formed as the difference between the arrangement between the plurality of point regions included in the X-ray image 100 and the arrangement between the pre-learned 13 cervical vertebrae increases. It can be calculated so that the reliability of the corresponding detection result for .

In one embodiment, at least one processor 1300 may calculate detection reliability for each of a plurality of point regions based on the shape of the cervical spine included in the detected cervical region 200 . Specifically, the at least one processor 1300 may detect a plurality of point regions by using a pre-learned artificial intelligence model based on a plurality of cervical spine images including the cervical spine. In this case, the shapes of the cervical vertebrae respectively included in the plurality of cervical vertebrae images are similar to each other in view of the human body structure. Accordingly, as the difference between the shape of the cervical spine included in the X-ray image 100 and the shape of the cervical spine included in the pre-learned X-ray images increases, the at least one processor 1300 generates a plurality of point regions. It can be calculated so that the reliability of the corresponding detection result for .

In an embodiment, a method for detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae includes a detection reliability calculated for each of a plurality of points and a size of a preset threshold value. It may include a step of comparing. In one embodiment, the pre-set threshold value can trust the plurality of cervical vertebrae points 300 detected by the at least one processor 1300 and the angle 400 between the plurality of cervical vertebrae points 300, Based on this, it may be a set value because it is determined that it is possible to accurately diagnose the patient's health status, presence or absence of a disease, type of disease, and the like. In one embodiment, when the detection reliability calculated by the at least one processor 1300 has a value between 0 and 1 and the threshold value is set to 0.75, the at least one processor 1300 determines each of the plurality of points. 0.75 can be compared with the magnitude of the detection reliability calculated for .

In one embodiment, in order to adjust the accuracy of the electronic device 1000 and the method for detecting at least one cervical vertebrae point included in the cervical vertebrae from an X-ray image including the cervical vertebrae, different sizes of the threshold values may be set. In one embodiment, in order to increase the accuracy of the detected plurality of cervical vertebrae points 300 and the angle 400 between the cervical vertebrae points 300, as the magnitude of the threshold value increases, the point area that does not include the cervical vertebrae bones but detection can be prevented.

Including FIGS. 3 and 5 , in one embodiment, at least one processor 1300 may include a pre-learned artificial intelligence model to detect 13 cervical vertebrae points 300 . In one embodiment, the at least one processor 1300 is included in a seventh cervical vertebra (Vertebra Prominens, C7), a second cervical vertebra (Axis, C2), a first thoracic vertebrae (T1), and an occipital bone (Occipital). A pre-learned artificial intelligence model may be included to detect Foramen magnum (FM), Odontoid (ODT), Forehad, and Jaw. At this time, the at least one processor 1300 includes the center C7 of the 7th cervical vertebra, the front vertex C7_1 of the lower endplate of the 7th cervical vertebra, and the rear vertex C7_2 of the lower endplate of the 7th cervical vertebra. ), the posterior vertex of the upper endplate of the 7th cervical vertebra (C7_3), the anterior vertex of the lower endplate of the 2nd cervical vertebra (C2_1), the posterior vertex of the lower endplate of the 2nd cervical vertebra (C2_2), the anterior vertex of the upper endplate of the 1st thoracic vertebra ( T1_1), the posterior vertex of the upper endplate of the first thoracic vertebrae (T1_2), the anterior vertex of the foramen included in the occipital bone (FM_1), the anterior vertex of the foramen included in the occipital bone (FM_2), the odontoid process (ODT), forehead and chin. It is possible to detect 13 bones including 13 bones and 13 cervical vertebrae points 300 corresponding to each bone.

However, the present disclosure is not limited thereto, and bones that can be detected by at least one processor 1300 and cervical vertebrae points corresponding to the bones are determined according to images and parameter settings used in the learning process of the artificial intelligence model. It can vary.

In one embodiment, in the X-ray image 100 including the cervical spine, the method of detecting at least one cervical spine point 300 included in the cervical spine is equal to or equal to a preset threshold among a plurality of point regions. , detecting at least one cervical vertebrae point 300 in at least one point area having high detection reliability.

In one embodiment, a method of detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae has detection reliability equal to or greater than a preset threshold among a plurality of point regions. It may include increasing the resolution of at least one point area from the first resolution to a second resolution higher than the first resolution ( S350 , see FIG. 4 ). In one embodiment, the at least one processor 1300 uses a method capable of converting the resolution of the first resolution of each of the at least one point region by interpolation, etc., so that the second resolution is higher than the first resolution. can be improved with However, the present disclosure is not limited thereto, and at least one processor 1300 may improve resolution of each of a plurality of point regions through a resolution restoration algorithm using artificial intelligence in addition to interpolation.

In this case, the at least one processor 1300 may include detecting at least one cervical vertebrae point 300 in at least one point area having a second resolution higher than the first resolution (S400).

3 and 6, in one embodiment, at least one processor 1300 may include a pre-learned artificial intelligence model to detect angles 400 between 13 cervical vertebrae points 300. can In one embodiment, at least one processor 1300 may include an angle between a first cervical vertebra (Atlas, C1) and a second cervical vertebrae C2, and a gap between a second cervical vertebra C2 and a seventh cervical vertebra C7. Includes a pre-trained artificial intelligence model to detect the angle of the cervical vertebrae, the angle between the 1st cervical vertebrae (C1) and the 7th cervical vertebrae (C7), and the Chin Brow Vertical Angle (CBVA). can do. However, the present disclosure is not limited thereto, and the at least one processor 1300 is configured to detect another angle between the cervical vertebrae points 300 necessary for diagnosing the patient's health condition, presence or absence of disease, type of disease, and the like. -May be learned.

In one embodiment, a method for detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae includes at least one of an angle and a distance between a plurality of cervical vertebrae points, based on a plurality of cervical vertebrae points. It may further include detecting one.

In addition, the at least one processor 1300 determines the angle 400 between the plurality of cervical vertebrae points 300 and the plurality of cervical vertebrae points 300 in at least one point area having a second resolution higher than the first resolution. It may also include a detection step. In this case, it is possible to detect a plurality of cervical vertebrae points 300 and an angle 400 between the plurality of cervical vertebrae points 300 in a high-resolution X-ray image, and the arrangement of the detected cervical vertebrae points 300 and Accuracy of the size of the angle 400 between the plurality of cervical vertebrae points 300 may be improved.

In an embodiment, a method of detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae may include, prior to the step of calculating detection reliability for each of a plurality of point regions, a first resolution and increasing the resolution of each of the plurality of point areas having a third resolution higher than the first resolution. In this case, the at least one processor 1300 may increase the accuracy of the detection reliability by calculating the detection reliability for each of the plurality of point areas having the third resolution higher than the first resolution.

7 is a diagram for explaining a method of detecting a cervical vertebrae point according to a comparison between a calculated detection reliability and a preset threshold according to an embodiment of the present disclosure. Hereinafter, the same reference numerals are assigned to the same steps as those described in FIG. 3, and descriptions thereof will be omitted.

Referring to FIGS. 2, 3, and 7 , a method for detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae includes calculating detection reliability for each of a plurality of point regions. After step S300, a step of comparing the detection reliability calculated for each of the plurality of points with the size of a preset threshold may be included.

In one embodiment, when the pre-set threshold is 0.75, the detection reliability has a value of 0.75 or the detection reliability has a value greater than 0.75, the at least one processor 1300 determines that the calculated detection reliability is It may be determined that it is equal to or greater than the threshold value.

In this case, in an embodiment, a method for detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae has a detection reliability equal to or greater than a preset threshold among a plurality of point regions. It may include increasing the resolution of at least one point area from the first resolution to a second resolution higher than the first resolution (S350).

Thereafter, a method for detecting at least one cervical vertebrae point included in the cervical vertebrae from an X-ray image including the cervical vertebrae includes a plurality of cervical vertebrae points from at least one point having a detection reliability greater than or equal to a preset threshold value. Detecting (300) may include a step (S410). In one embodiment, in the step of detecting the plurality of cervical vertebrae points 300 ( S410 ), at least one cervical vertebrae point 300 may be detected in at least one point area having a second resolution.

In addition, a method for detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae is a plurality of detected cervical vertebrae points 300 based on the plurality of cervical vertebrae points 300 . Detecting the angle 400 between the cervical vertebrae points 300 of (S420) may be included.

In one embodiment, after calculating the detection reliability for each of a plurality of point areas (S300), in the step of comparing the detection reliability calculated for each of the plurality of points with the size of a preset threshold When the detection reliability has a value smaller than 0.75, the at least one processor 1300 may determine that the calculated detection reliability is smaller than a threshold value. In this case, the at least one processor 1300 may not detect at least one cervical vertebrae point in at least one point region having a detection reliability smaller than a preset threshold (S500).

According to the present disclosure, an electronic device 1000 and method for detecting at least one cervical spine point 300 included in the cervical spine in an X-ray image 100 including the cervical spine include a group- At least one cervical vertebrae point 300 and an angle 400 between the cervical vertebrae points 300 are calculated based on at least one point area having detection reliability greater than or equal to a set threshold, and among a plurality of point areas The at least one cervical vertebrae point 300 and the angle 400 between the cervical vertebrae points 300 are not calculated based on the at least one point region having a detection reliability smaller than a preset threshold.

Therefore, according to the present disclosure, it is prevented from detecting the cervical vertebrae point 300 and the angle 400 between the cervical vertebrae points 300 based on a region having low detection reliability, that is, a region that does not include a cervical vertebrae but is detected as a point region. can do. Accordingly, based on the incorrectly detected cervical vertebrae points 300 and the angle 400 between the cervical vertebrae points 300, the patient's state of health, presence or absence of a disease, diagnosis of a disease, etc. are prevented, and an accurate diagnosis can be made. can do.

Meanwhile, the disclosed embodiments may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the medium may be those specially designed and configured for the present invention or those known and usable to those skilled in computer software. Examples of computer readable media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. Included are hardware devices specially configured to store and execute program instructions, such as magneto-optical media and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. A computer readable medium may be provided in the form of a non-transitory recording medium. Here, the non-transitory recording medium only means that it is a tangible device and does not contain a signal (eg, electromagnetic wave), and this term refers to the case where data is semi-permanently stored in the recording medium and temporarily stored does not discriminate between cases For example, a 'non-temporary storage medium' may include a buffer in which data is temporarily stored.

Although the embodiments have been described in detail above, the scope of the present disclosure is not limited thereto, and various modifications and improvements of those skilled in the art using the basic concepts of the present disclosure defined in the following claims are also within the scope of the present invention. belongs to

Claims (10)

An electronic device for detecting at least one cervical vertebrae point included in the cervical vertebrae using an artificial intelligence model in an X-ray image including the cervical vertebrae, comprising:
a memory containing at least one instruction; and
at least one processor to execute the at least one instruction stored in the memory;
The at least one processor,
Obtaining the X-ray image including the cervical vertebrae;
Detecting a cervical spine region including the cervical spine in the X-ray image;
Calculate detection reliability for each of a plurality of point regions included in the detected cervical spine region;
Converting a resolution of at least one point area having a detection reliability equal to or greater than a preset threshold among the plurality of point areas based on a preset method;
An electronic device for detecting the at least one cervical vertebrae point in the at least one point area having a converted resolution. According to claim 1,
The at least one processor,
The electronic device does not detect the at least one cervical vertebrae point in at least one point area having a detection reliability smaller than a predetermined threshold among the plurality of point areas. According to claim 1,
The at least one cervical point includes a plurality of cervical points,
The at least one processor,
An electronic device that detects at least one of an angle and a distance between the plurality of cervical vertebrae points based on the plurality of cervical vertebrae points. According to claim 1,
The at least one processor,
Electronics for calculating the detection reliability based on at least one of the size of the detected cervical spine region, the number of the plurality of point regions, the arrangement between the plurality of point regions, or the shape of the cervical spine included in the detected cervical spine region Device. According to claim 1,
The at least one processor,
When converting the resolution of the at least one point area based on a preset method,
Increasing the resolution of at least one point area having a detection reliability greater than or equal to a preset threshold among the plurality of point areas from a first resolution to a second resolution higher than the first resolution;
An electronic device for detecting the at least one cervical vertebrae point in the at least one point area having the second resolution. According to claim 1,
Further comprising a camera for taking an X-ray image including the cervical vertebrae,
The at least one processor,
An electronic device for obtaining the X-ray image including the cervical vertebrae through the camera. According to claim 1,
The at least one processor,
Before calculating the detection reliability,
Increasing the resolution of each of the plurality of point areas from a first resolution to a third resolution higher than the first resolution;
The electronic device that calculates the detection reliability for each of the plurality of point areas having the third resolution. According to claim 1,
The at least one processor,
Calculate detection reliability for each of the plurality of point areas using a pre-trained artificial intelligence model;
An electronic device for detecting the at least one cervical vertebrae point in at least one point region having a detection reliability greater than or equal to the preset threshold by using the artificial intelligence model. A method of detecting at least one cervical vertebrae point included in the cervical vertebrae in an X-ray image including the cervical vertebrae, performed by an electronic device, includes:
obtaining the X-ray image including the cervical vertebrae;
detecting a cervical spine region including the cervical spine in the X-ray image;
calculating a detection reliability for each of a plurality of point regions included in the detected cervical region; and
converting a resolution of at least one point area having a detection reliability greater than or equal to a preset threshold among the plurality of point areas based on a preset method; and
and detecting the at least one cervical vertebrae point in the at least one point area having a transformed resolution. A computer-readable recording medium recording a program for executing the method of claim 9 on a computer.

Images