KR102527376B1 - Apparatus and method for auto labeling using thresholding of medical image - Google Patents

Abstract

According to the present invention, a method for auto labeling using thresholding of medical images can be provided. The method for auto labeling comprises the steps of: receiving a medical image through an image receiving unit; displaying at least three sectional views related to the medical image through a screen processing unit; displaying a first area determined through a user input by labeling the same on any one sectional view among the three sectional views through a labelling processing unit; and in response to an activation selection of a thresholding function through a user terminal, displaying an expanded second area containing the first area based on a range of pixel values related to the first area set through the labeling processing unit. The three sectional views contain a transverse sectional view, a sagittal sectional view, and a coronal sectional view. Accordingly, the method can complete labeling of medical images more rapidly.

Description

Automatic labeling method using threshold processing of medical image and apparatus therefor

The present invention relates to an automatic labeling method using threshold processing of medical imaging images and an apparatus therefor. More specifically, the present invention relates to a method and apparatus capable of setting an automatic labeling region with minimal user input through threshold processing and connected region filtering of a medical imaging image.

Recently, through active research on artificial intelligence, interest in medical image processing using artificial neural networks is growing in academia, companies, and research institutes. Neural networks using deep learning have already been applied to the field of medical image analysis and their effectiveness has been proven. In terms of understanding medical images, recent advances in machine learning are contributing to the study of identifying, classifying, and quantifying patterns in medical images in deep learning. In particular, as CNN (Convolutional Neural Network) algorithms based on artificial neural networks have begun to be used in earnest for medical image analysis, cases of various disease analysis studies are rapidly increasing.

Data labeling refers to the process of processing source data so that computers can understand it. In particular, in order to perform deep learning analysis based on image data built with big data, a region of interest (ROI) to be analyzed must be set in the image data. For example, when analyzing medical image data to analyze characteristics of a tumor in a specific body part, a medical staff directly draws an outline of a tumor, which is a region of interest, in each medical image constructed with big data.

However, since a large amount of image data is included in the big data built to perform deep learning analysis, the labeling task of drawing a region of interest in each image data requires a lot of manual work and takes a long time, so it takes a lot of time to build data. and costs. Therefore, a technique for reducing the time required to label a region of interest in an image built with big data is required.

In addition, technologies to semi-automatically perform these labeling tasks using artificial intelligence have been proposed, but if the accuracy of artificial intelligence is insufficient or the label desired by the user is not generated, a situation in which the user's manual work is still required is generated. .

In addition, in the case of conventional semi-automatic labeling technologies, they only deal with labeling of a wide area such as a bounding box rather than precise labeling in pixel units, so if accurate and fast labeling in pixel units is required for a specific shape within a medical image, There are problems with using it.

Accordingly, a new method capable of more quickly and accurately automatically labeling a region of interest through a minimum user input is required.

Republic of Korea Patent Publication No. 10-2021-0020618

An object of the present invention is to provide an automatic labeling method using threshold processing of medical imaging images and an apparatus therefor.

In addition, the present invention can automatically and conveniently label the entire region of interest including the corresponding region based on pixel value differences and connectivity based on a simple labeling task for setting a minimum region of a point or plane for a portion of a user's region. It is an object of the present invention to provide a method and apparatus capable of

In addition, an object of the present invention is to provide a UX/UI of a medical image labeling tool capable of more quickly completing a labeling task of a medical image image in accordance with a user's intention.

Solving problems of the present invention are not limited to the contents mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

In one embodiment of the present invention, an automatic labeling method using thresholding of a medical imaging image includes receiving a medical imaging image through an image receiving unit; displaying at least three cross-sectional views related to the medical imaging image through a screen processing unit; labeling and displaying a first area determined through a user input in any one of the three cross-sectional views through a labeling processing unit; Displaying an expanded second area including the first area based on a range of pixel values related to the first area set through the labeling processing unit in response to activation selection of the threshold processing function through the user terminal. Including, it is possible to provide an automatic labeling method, wherein the three cross-sectional views include a transverse cross-sectional view, a sagittal cross-sectional view and a coronal cross-sectional view.

Here, the medical imaging image may include a computed tomography (CT) image.

Also, changing a range of pixel values related to the first area through the user's input; and displaying an extended second area including the first area based on the changed pixel value range.

In addition, in response to activation selection of the connection region filtering function through the user's input, a third region directly connected to the first region among the second regions is determined, only the third region is activated and displayed, and the third region is displayed. The method may further include inactivating and removing regions other than the third region among the two regions.

Also, the third area may be composed of only a set of pixels connected to each other while expanding in three dimensions without being disconnected from at least one pixel among a plurality of pixels belonging to the first area among a plurality of areas included in the second area.

The method may further include additionally displaying a 3D rendered image in which a 3D area corresponding to the third area is labeled.

In addition, in another embodiment of the present invention, a computer readable recording medium storing a program for implementing the method described above may be provided.

In addition, in another embodiment of the present invention, an automatic labeling apparatus using thresholding of a medical imaging image includes an image receiving unit configured to receive a medical imaging image; a screen processing unit configured to display at least three cross-sectional views related to the medical imaging image; and labeling and displaying a first area determined through an input through a user terminal in any one of the three cross-sectional views, and in response to activation selection of a threshold processing function through the user terminal, the set through the labeling processing unit. and a labeling processing unit configured to display an extended second area including the first area based on a range of pixel values related to the first area, wherein the three cross-sectional views include a transverse cross-sectional view, a sagittal cross-sectional view, and a coronal cross-sectional view. That is, it is possible to provide an automatic labeling device.

According to the present invention, it is possible to provide an automatic labeling method using threshold processing of a medical imaging image and an apparatus therefor.

In addition, according to the present invention, based on a simple labeling task for setting the minimum area of a point or plane for a user's partial area, the entire area of interest including the corresponding area is automatically and conveniently based on pixel value differences and connectivity. A labeling method and apparatus may be provided.

In addition, according to the present invention, it is possible to provide a UX/UI of a medical image labeling tool capable of more quickly completing a labeling task of a medical image image in accordance with a user's intention.

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

1 is a block diagram for explaining the configuration of an apparatus for automatically labeling medical imaging images according to an embodiment of the present invention.
2A to 2C are screen views illustrating a threshold processing function of a medical imaging image according to an embodiment of the present invention.
3A to 3D are screen views illustrating an automatic labeling method through a threshold processing function and a connection region filtering function of a medical imaging image according to an embodiment of the present invention.
4 is a flowchart illustrating a method of automatically labeling medical imaging images according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail so that those skilled in the art can easily practice with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the embodiment of the present invention in the drawings, parts irrelevant to the description are omitted.

Terms used in this specification are only used to describe specific embodiments and are not intended to limit the present invention. Singular expressions may include plural expressions unless the context clearly dictates otherwise.

In this specification, terms such as "include", "have" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, and one Or it may be understood that it does not exclude in advance the possibility of the existence or addition of other features, numbers, steps, operations, components, parts, or combinations thereof.

In addition, the components appearing in the embodiments of the present invention are shown independently to represent different characteristic functions, and it does not mean that each component is made of separate hardware or a single software component unit. That is, each component is listed and described as each component for convenience of description, and at least two components of each component may be combined to form one component, or one component may be divided into a plurality of components to perform a function. An integrated embodiment and a separate embodiment of each of these components are also included in the scope of the present invention unless departing from the essence of the present invention.

In addition, the following embodiments are provided to more clearly explain to those with average knowledge in the art, and the shapes and sizes of elements in the drawings may be exaggerated for clearer explanation.

Hereinafter, preferred embodiments according to the present invention will be described with reference to the accompanying drawings.

1 is a block diagram for explaining the configuration of an apparatus for automatically labeling medical imaging images according to an embodiment of the present invention.

An automatic labeling apparatus using thresholding of medical image images according to the present invention includes an image receiving unit 110, a screen processing unit 120, a labeling processing unit 130, a user input unit 140, and a display unit 150. In addition to these components, additional components composed of software or hardware may be included as needed.

For example, the apparatus for automatically labeling medical image images according to the present invention may be configured as a terminal capable of receiving, processing, and displaying various data via a wired/wireless communication network according to input/output operations of a user, for example, a desktop computer. , laptop computers, notebooks, smart phones, tablet computers, workstations, PDAs (Personal Digital Assistants), portable computers, wireless phones, mobile phones (mobile phone), e-book, portable multimedia player (PMP), portable game console, navigation device, black box, digital camera, television, wearable It may be one of a wearable device, a voice recognition speaker, a smart speaker, and an artificial intelligence (AI) speaker, but is not limited thereto.

In addition, the apparatus for automatically labeling medical imaging images according to the present invention may include a program or program module that can be executed by one or more processors, and may receive a user input in conjunction with the user input unit 140, A processed result may be output in association with the display unit 150 . In particular, the programs or program modules included in the screen processing unit 120 and the labeling processing unit 130 may be configured in the form of an operating system, application program or program, and various types of widely used may be physically stored on a storage device of Such a program or program module includes one or more routines, subroutines, programs, objects, components, instructions, data structures, and specific tasks ( It may include various forms for performing tasks) or executing specific data types, but is not limited to these forms.

First, the image receiving unit 110 is configured to receive a medical imaging image. The image receiving unit 110 may receive a plurality of medical imaging images by directly or indirectly communicating with an external device through a communication unit. Also, the medical imaging image received by the image receiving unit 210 may be transmitted to the screen processing unit 120 and the labeling processing unit 130, and the medical imaging image may include black and white images such as 3D images and 2D images. In addition, the medical imaging image may include, for example, a computed tomography (CT) image. First of all, unlike a general RGB image in which each pixel has a value of 0 to 255, the pixel value of the CT is Hounsfield Unit HU), HU is a unit representing the degree of attenuation when X-rays pass through the body. In the present invention, a pixel value of a pixel may be expressed based on such a HU unit.

The screen processing unit 120 displays at least three cross-sectional views related to the medical imaging image through the display unit 150, and includes three cross-sectional views corresponding to each other, wherein the three cross-sectional views are a transverse cross-sectional view, a sagittal cross-sectional view, and a coronal cross-sectional view. It may include, and may further include a 3D rendered image that is additionally rendered in three dimensions. In addition, the screen processing unit 120 displays a user tool for labeling through the display unit 150. For example, the user tool activates a threshold processing function activation selection button and a connection area filtering function linked with the threshold processing function. A user input according to the user input unit 140 may be received by displaying a selection button and an apply button for these functions on the screen.

In addition, the screen processing unit 120 interlocks with the threshold processing function through the display unit 150 to easily change the input window for inputting the maximum and minimum range of the pixel value of the pixel and the standard range by changing the left and right arrows. It can be configured to provide a histogram graph.

The labeling processing unit 130 labels and displays the first area determined through the input through the user terminal in any one of the three cross-sectional views, and responds to activation selection of the threshold processing function through the user terminal through the labeling processing unit. An extended second area including the first area may be displayed based on a range of pixel values related to the set first area. Here, image thresholding is a filtering method of binarizing one pixel value in an image matrix using a threshold specified by a user. In the present invention, image thresholding is used to perform medical image A region may be automatically segmented by using comparative analysis of a pixel value of a corresponding pixel in an image with a reference range (reference value). Here, the labeling of the first region may be a selection of a dot of a specific size including a plurality of pixels or a surface of a specific shape and size, for example, selection of a position of a circular region of a specific size.

Here, the labeling processing unit 130 analyzes the pixel value range of pixels included in the selected original area, sets the pixel value range of the corresponding area as a reference range, and sets the area having pixel values belonging to the reference range as the second area. It can be set as an area, set as a second area 330 in each of the three cross-sectional views, and displayed on the screen through the display unit 150.

In addition, the range of pixel values set in relation to the first area may be directly changed to a desired range through a user input through the user input unit 140, and the labeling processing unit 130 may set the first area based on the changed range of pixel values. It may be configured to redetermine the extended second area included therein and display it through the display unit 150 .

In addition, in response to activation selection of the connection region filtering function through the user input through the user input unit 140, the labeling processing unit 130 filters and determines only the third region directly connected to the first region among the expanded second regions, , it may be configured to activate and display only the third region, deactivate and remove regions other than the third region of the second region, and display them through the display unit 150 . Here, the third area is composed of only a set of pixels connected to each other while expanding in three dimensions without being disconnected from at least one pixel among a plurality of pixels belonging to the first area among a plurality of areas included in the second area, and is inputted through a user input. This refers to an area that is adjacent to the selected first area and is continuously connected without being disconnected.

In addition, the labeling processing unit 130 may generate a 3D rendering image in which a 3D area corresponding to the third area is labeled in response to a user's 3D rendering update input, and display the updated 3D rendering image on the screen. Through the processing unit 120, it can be additionally displayed on the display unit 150 by arranging it together with three cross-sectional views.

The user input unit 140 uses a touch pad, a touch panel, a key pad, a mouse, a keyboard, and a dome switch to receive various inputs for user manipulation and selection. (dome switch), a physical button, a jog shuttle (jog shuttle) and a sensor (sensor) may include an input unit composed of at least one, but is not limited thereto.

The display unit 150 serves to show output results to a user, and the display unit 150 may be, for example, a liquid crystal display (LCD), a light emitting diode (LED) display, or an organic light emitting diode (OLED) display. organic LED) displays, micro LEDs, micro electro mechanical systems (MEMS) displays, and electronic paper displays, but is not limited thereto. Also, such a display unit 150 may be combined with the user input unit 140 and implemented in the form of a touch screen.

2A to 2C are screen views illustrating a threshold processing function of a medical imaging image according to an embodiment of the present invention.

Referring to FIG. 2A , three cross-sectional views 201, 202, and 203 are displayed on the user screen displayed through the display unit 150, for example, as a transverse cross-section 201, a sagittal cross-section 202, and a coronal cross-section 203. , and additionally, a 3D rendering image 204 may be included.

In addition, as a user tool 210 for labeling, one side of the screen includes a drawing with a pencil, a fill function, and the like. In particular, according to the present invention, the user tool 210 activates the threshold processing function. A user input according to the user input unit 140 may be received by displaying a selection button, an activation selection button of a connection region filtering function linked with a threshold processing function, and an apply button of these functions on the screen.

Referring to FIG. 2B , an activation selection button 211 of a threshold processing function is selected among user tools 210 by a user input, and according to the setting of a threshold processing function setting item 212 that appears accordingly, a pixel is selected. The standard range of pixel values can be set using an input window for inputting the maximum (max) range and minimum (min) range, or a histogram graph that can easily change the standard range of pixel values by changing the left and right arrows. For this, a preset function may be provided to provide a preset range of pixel values suitable for each tissue, such as bone, lung, liver, blood, water, and fat. In FIG. 2B, when the standard range of the pixel value of a pixel is set from a minimum of 400 to a maximum of 1,000, it can be seen that the area belonging to the standard range is automatically labeled and displayed within the three cross-sectional views 201, 202, and 203. there is.

Referring to FIG. 2C, according to the setting of the threshold processing function setting item 212, when the standard range of the pixel value of a pixel is widened and set from a minimum of 300 to a maximum of 2,000, within three cross-sections 201, 202, and 203 It can be seen that the region belonging to the reference range is automatically labeled and displayed, and it can be confirmed that the range of the corresponding region has been widened to include the region of the bone more extensively than in FIG. 2B.

However, in the case of using only the threshold processing function in this way, there is an advantage in that only a desired tissue can be automatically filtered and labeled based on the reference range setting of the pixel value of a pixel corresponding to the tissue, but a more specific location within the tissue, for example, There is a limitation in that the right lung and the left lung or a specific right joint and a specific left joint cannot be labeled separately.

3A to 3D are screen views illustrating an automatic labeling method through a threshold processing function and a connection region filtering function of a medical imaging image according to an embodiment of the present invention.

Referring to FIG. 3A , three cross-sectional views, for example, a transverse cross-sectional view 301, a sagittal cross-sectional view 302, and a coronal cross-sectional view 303, may be displayed on the user's screen displayed through the display unit 150. The rendered image 304 may be displayed together.

At this time, the user uses a point or plane of a specific size including a plurality of pixels to select a specific region or position in any one of the three cross-sectional views, for example, a circle region 320 of a specific size, that is, the first region. A location of the circle is selected and labeled, and the location of the selected circle may be displayed on at least one cross-sectional view and the 3D rendering image 304 .

Referring to FIG. 3B , when the activation selection button 311 of the threshold processing function is selected through a user input through the user input unit 140, pixels of pixels included in the circle area 320 selected based on simple labeling by the user The range of values is analyzed, the range of pixel values in the corresponding area is set as a reference range, and the area having pixel values belonging to the corresponding reference range is set as the second area 330 in each of the three cross-sections, and it is all on the screen. can be displayed At this time, the range of pixel values may be automatically set based on the range of pixel values of pixels belonging to the region selected by the user input, but if the range of pixel values needs to be changed by looking at the screen of FIG. 3B, it is restricted by the user input. A range of pixel values related to area 1 may be changed, and the labeling processing unit 130 resets an extended second area including the first area based on the changed range of pixel values, and displays this through the display unit 150. It can be configured to display.

Referring to FIG. 3C , when an activation selection button 312 of the connection area filtering function is selected through a user input through the user input unit 140, in response to this, the labeling processing unit 130 selects an expanded second area 330. Only the third area 340 directly connected to the first area 320 is determined by filtering, only the third area 340 is activated and displayed, and areas other than the third area 340 among the second area 330 are determined by filtering. It may be configured to be deactivated and removed from display, and configured to be displayed through the display unit 150 . Here, the third area 340 is a set of pixels connected to each other while expanding in three dimensions without being disconnected from at least one pixel among the plurality of pixels belonging to the first area 320 among the plurality of areas included in the second area 330. It is composed of only, and refers to an area adjacent to the first area 320 selected through a user input and continuously connected without being disconnected.

In this way, based on the user's simple labeling task for setting the minimum region, the entire region of interest including the corresponding region is automatically and conveniently labeled based on the pixel value difference and whether there is connectivity, thereby more quickly meeting the user's intention. It is possible to provide a method and apparatus capable of completing a labeling task of an image.

Referring to FIG. 3D , by selecting the rendering update button displayed on the 3D rendering image 304, a 3D rendering image in which the 3D area corresponding to the third area 340 is labeled is additionally displayed, thereby making the corresponding labeling area 3D. You can easily check it on the screen as well.

4 is a flowchart illustrating a method of automatically labeling medical imaging images according to an embodiment of the present invention.

First, a medical imaging image may be received through the image receiver 110 (S410). The corresponding imaging image may be a black and white image, and may include, for example, a computed tomography (CT) image.

The screen processing unit 120 may display at least three cross-sectional views related to the medical imaging image, a transverse cross-sectional view, a sagittal cross-sectional view, and a coronal cross-sectional view through the display unit 150 (S420).

The user may view the screen and label and display the first area by inputting the user (S430). Here, the labeling display of the first area is a dot of a specific size including a plurality of pixels or a surface of a specific shape and size. It may be a selection of, for example, it may be to select the location of a circular area of a specific size.

The user may select activation of the threshold processing function (S440). At this time, the labeling processor 130 analyzes the pixel value range of the labeling display area of the first area and sets the pixel value range of the corresponding area as the reference range. Thus, such a range of pixel values can be displayed on the screen.

The labeling processing unit 130 may display an extended second area including the first area based on the range of pixel values related to the first area (S450). Based on this, an extended second area including the first area may be set and displayed through the display unit 150 .

A connection region filtering function linked with the threshold processing function may be activated through a user input (S460).

In response to this, the labeling processing unit 130 filters and determines only the third region directly connected to the first region among the extended second regions, activates and displays only the third region, and displays the regions other than the third region among the second regions. It is configured to be deactivated and removed from display, and can be displayed through the display unit 150 (S470).

Various embodiments described in this specification may be implemented by hardware, middleware, microcode, software, and/or combinations thereof. For example, various embodiments may include one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), ), processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions presented herein, or combinations thereof.

Also, for example, various embodiments may be embodied or encoded in a computer-readable medium containing instructions. Instructions embodied or encoded on a computer-readable medium can cause a programmable processor or other processor to perform a method, for example when the instructions are executed. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage medium may be any available medium that can be accessed by a computer. For example, such computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage medium, magnetic disk storage medium or other magnetic storage device, or instructions or data accessible by a computer that contains desired program code. Any other medium that can be used to transport or store in the form of structures.

Such hardware, software, firmware, etc. may be implemented within the same device or within separate devices to support the various operations and functions described herein. Additionally, components, units, modules, components, etc., described as "-units" in the present invention may be implemented together or separately as separate but interoperable logic devices. Depiction of different features for modules, units, etc. is intended to highlight different functional embodiments and does not necessarily mean that they must be realized by separate hardware or software components. Rather, functionality associated with one or more modules or units may be performed by separate hardware or software components or integrated within common or separate hardware or software components.

Also, while actions are shown in the drawings in a specific order herein, it is necessary that these actions be performed in the specific order shown, or in a sequential order, or that all depicted actions need to be performed to achieve a desired result. should not be understood as In some circumstances, multitasking and parallel processing may be advantageous. Moreover, the division of various components in the above-described embodiments should not be understood as requiring such division in all embodiments, and the described components may generally be integrated together into a single software product or packaged into multiple software products. It should be understood that it is possible

Although the present invention has been described with reference to the embodiments shown in the drawings, this is only exemplary, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

110: image receiver
120: screen processing unit
130: labeling processing unit
140: user input unit
150: display unit

Claims (8)

In the automatic labeling method using thresholding of medical image images,
Receiving a medical imaging image through an image receiver of an automatic medical imaging image labeling device;
displaying at least three cross-sectional views related to the medical imaging image through a screen processing unit of the automatic medical imaging image labeling apparatus;
labeling and displaying a first area determined through a user's input in any one of the three cross-sectional views through a labeling processing unit of the automatic medical image labeling apparatus; and
In response to activation selection of the threshold processing function through the user's input, displaying an expanded second area including the first area based on a range of pixel values related to the first area through the labeling processing unit.
Including, wherein the three cross-sections include a transverse cross-section, a sagittal cross-section and a coronal cross-section,
In response to activation selection of the connection region filtering function through the user's input, a third region directly connected to the first region among the second regions is determined through the labeling processor, and only the third region is activated and displayed; , deactivating and removing regions other than the third region from among the second region,
The third region is composed of only a set of pixels connected to each other while expanding in three dimensions without being disconnected from at least one pixel among a plurality of pixels belonging to the first region among a plurality of regions included in the second region. method. The method of claim 1, wherein the medical imaging image includes a computed tomography (CT) image. The method of claim 1 , further comprising: changing a range of pixel values associated with the first area through the user's input; and
Displaying an expanded second area including the first area based on the changed pixel value range through the labeling processing unit
Automatic labeling method further comprising a. delete delete The automatic labeling method of claim 1, further comprising additionally displaying a 3D rendered image in which the 3D area corresponding to the third area is labeled through the screen processing unit. A computer-readable recording medium storing a program for implementing the method according to any one of claims 1, 2, 3, and 6. In the automatic labeling device using thresholding of medical image images,
an image receiver configured to receive a medical imaging image;
a screen processing unit configured to display at least three cross-sectional views related to the medical imaging image; and
In any one of the three cross-sectional views, a first area determined through an input through a user terminal is labeled and displayed, and a pixel value related to the first area is displayed in response to activation selection of a threshold processing function through the user terminal. A labeling processor configured to display an extended second area including the first area based on a range of
Including, wherein the three cross-sections include a transverse cross-section, a sagittal cross-section and a coronal cross-section,
The labeling processor determines a third region directly connected to the first region among the second regions in response to activation selection of the connection region filtering function through the user's input, activates and displays only the third region, and , configured to inactivate and remove regions other than the third region among the second regions,
The third region is composed of only a set of pixels connected to each other while expanding in three dimensions without being disconnected from at least one pixel among a plurality of pixels belonging to the first region among a plurality of regions included in the second region. Device.

Images