Blood vessel classification method and electronic device

Abstract

To provide a blood vessel classification method and an electronic device achieved by at least one processor.SOLUTION: A blood vessel classification method may include: a step of acquiring a video capturing cardiac blood vessels of a subject and angle information of a video acquisition device with respect to the subject; and a step of identifying the type of at least one cardiac blood vessel contained in the video on the basis of the angle information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a blood vessel classification method and an electronic device.

Background Art

[0002] The coronary artery (or cardiovascular) is an artery that surrounds the heart and can supply oxygen and nutrients to the myocardium, which is the muscle of the heart. That is, the function of the heart can be performed by continuously supplying oxygen and nutrients from the coronary artery to the myocardium. Along with this, if an abnormal phenomenon (e.g., disease) occurs in the coronary artery and oxygen and nutrients are not properly supplied to the myocardium, cardiovascular diseases such as myocardial infarction can develop.

[0003] Such a coronary artery is located in a coronary form around the heart and can be classified into detailed types based on the arranged position. For example, the coronary artery can be classified into the right coronary artery (RCA, Right Coronary Artery) that starts from the right side of the entrance of the ascending aorta and mainly runs on the right side of the heart, and the left coronary artery (LCA, Left Coronary Artery) that starts from the left side of the entrance of the ascending aorta and mainly runs on the left side of the heart. Further, the left coronary artery can be more detailedly classified into the left main coronary artery (LMCA, Left Main Coronary Artery) (hereinafter referred to as LM) that starts from the upper left end of the left side of the heart, the left anterior descending coronary artery (LAD, Left Anterior Descending coronary artery) branched from the left main coronary artery, and the left circumflex coronary artery (LCX, Left Circumflex coronary artery).

[0004] As described above, depending on the form in which the coronary artery is located, the coronary artery can supply oxygen and nutrients to the adjacent myocardium. Along with this, when an abnormal phenomenon occurs in a part of the coronary artery, it is possible to determine in which region of the coronary artery the abnormal phenomenon has occurred, and thus identify the region of the myocardium related to the region of the coronary artery where the abnormal phenomenon has occurred, and more precisely diagnose cardiovascular diseases.

[0005] On the one hand, coronary angiography (CAG) can be used to observe whether abnormal phenomena occur in the coronary arteries. CAG refers to an examination in which coronary arteries are imaged using an X-ray imaging device (e.g., a C-arm X-ray imaging device) with a contrast agent injected into the blood vessels of a subject (e.g., a patient), and the condition of the coronary arteries is confirmed through CAG images to diagnose cardiovascular diseases.

[0006] Previously, it was inevitable that physicians or analysts had to rely on their experience to confirm the condition of the coronary arteries through CAG images. However, recently, technologies have been developed in which electronic devices can receive inputs of CAG images and diagnose cardiovascular diseases through the analysis of CAG images through machine learning. However, due to the diversity of blood vessel types and forms, the development of technologies for accurately classifying blood vessels is required for more precise analysis.

Prior Art Documents

Patent Documents

[0007]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0008] The present disclosure provides a blood vessel classification method and an electronic device for solving the above problems.

Means for Solving the Problems

[0009] The present disclosure can be implemented in various ways including a method, an apparatus (system), and / or a computer program.

[0010] According to an embodiment of the present disclosure, a blood vessel classification method performed by at least one processor may include obtaining an image including a cardiovascular system of a subject and angle information of an image acquisition device with respect to the subject, and identifying at least one type of cardiovascular system included in the image based on the angle information.

[0011] According to an embodiment of the present disclosure, a blood vessel classification method performed by at least one processor may include obtaining an image including a cardiovascular system of a subject and identifying at least one type of cardiovascular system included in the image through a machine learning model that takes the image as an input.

[0012] According to an embodiment of the present disclosure, an electronic device includes a memory and at least one processor coupled to the memory and configured to execute at least one computer-readable program included in the memory. The at least one program may include instructions for obtaining an image including a cardiovascular system of a subject and angle information of an image acquisition device with respect to the subject, and identifying at least one type of cardiovascular system included in the image based on the angle information.

[0013] According to an embodiment of the present disclosure, a computer program for executing the above-described blood vessel classification method on a computer can be provided.

Advantages of the Invention

[0014] According to some embodiments of the present disclosure, by identifying at least one type of cardiovascular system included in an image of a subject's cardiovascular system based on the angle information of the image acquisition device with respect to the subject, the accuracy of blood vessel classification can be increased, and thereby more precise analysis of the image may be possible.

[0015] 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 of ordinary skill in the technical field to which the present disclosure belongs (referred to as "ordinary technicians") from the description of the claims.

Brief Description of the Drawings

[0016] Examples of the present disclosure will be described with reference to the accompanying drawings described below, where like reference numerals indicate like elements, but are not limited thereto.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

DETAILED DESCRIPTION OF THE INVENTION

[0017] <Summary of the Invention> According to one embodiment, the angular information can include first rotation angle information of the imaging device about a first axis in the vertical direction of the subject, and second rotation angle information of the imaging device about a second axis in the left - right direction of the subject.

[0018] According to one embodiment, the step of identifying at least one type of cardiovascular can include the step of identifying at least one type of cardiovascular included in the image based on the angular information and information regarding the type of cardiovascular matched with the angular information.

[0019] According to one embodiment, the machine - learning model can be trained to limit the types of cardiovascular that can be identified in the image based on the angular information of the imaging device with respect to the subject.

[0020] According to one embodiment, the step of identifying at least one type of cardiovascular can further include the step of correcting the identified at least one type of cardiovascular based on the angular information of the imaging device with respect to the subject.

[0021] According to one embodiment, the method for classifying blood vessels further includes training a machine - learning model to identify a view corresponding to each of a plurality of input images of the cardiovascular based on class information in which view information classified by the angular information of the imaging device and the type of blood vessel matched with the view information are designated to one class. The step of identifying at least one type of cardiovascular can include the step of identifying the view corresponding to the image based on the machine - learning model and the step of identifying at least one type of cardiovascular included in the image based on the identified view.

[0022] According to one embodiment, the class information can include at least one of a class that enables blood - vessel classification for other images other than CAG images among the plurality of images or a dummy class that includes only the type of blood vessel without view information.

[0023] According to one embodiment, the step of identifying at least one cardiovascular type can further include the step of restricting the cardiovascular types that can be identified in the video based on the identified view.

[0024] According to one embodiment, the step of identifying the view corresponding to the video can include the steps of generating weighted values based on a predetermined number of points in the video, extracting at least one representative frame in the video based on the generated weighted values, inputting the at least one representative frame into a machine learning model, and identifying the view corresponding to the video based on the inference result for the at least one representative frame through the machine learning model.

[0025] According to one embodiment, the step of identifying the view corresponding to the video based on the inference result for at least one representative frame includes, when the at least one representative frame includes a plurality of representative frames, determining the final result through a voting method for the inference results for the plurality of representative frames through a machine learning model. The step of determining the final result includes: when a valid view is selected as the result of voting on the inference results for the plurality of representative frames, determining, as the final result, the class including the type of blood vessel corresponding to the selected valid view and the view information; when an invalid view is selected as the result of voting, voting again on the remaining part excluding the invalid views in the inference results for the plurality of representative frames, and when a valid view is selected as the result of the re-voting, determining, as the final result, the class including the type of blood vessel corresponding to the selected valid view and the view information; when an invalid view is selected as the result of voting, voting again on the remaining part excluding the invalid views in the inference results for the plurality of representative frames, and when all of the results of the re-voting are invalid views, voting again with the second confidence level, and when a valid view is selected as the result of the re-voting, determining, as the final result, the class including the type of blood vessel corresponding to the selected valid view and the view information; and when an invalid view is selected as the result of voting, voting again on the remaining part excluding the invalid views in the inference results for the plurality of representative frames, and when all of the results of the re-voting are invalid views, voting again with the second confidence level, and when the result of the re-voting is an invalid view or a video that is not a CAG video, voting again with the first confidence level only on the view information of the class including the type of blood vessel in the first inference result, and the step of determining the final result can be included.

[0026] According to one embodiment, the electronic device can include a main body with a built-in driving unit for lifting, a lifting unit fixed to the upper end of the driving unit for lifting and lifted in a first direction, a rotating unit having one end rotatably connected about a first axis in a second direction perpendicular to the first direction and a curved surface formed at the other end, a C-shaped frame unit slidably connected to the curved surface and provided in a "C" shape, an X-ray generating device disposed at one end of the C-shaped frame unit, and a video acquisition device disposed at the other end of the C-shaped frame unit.

[0027] According to one embodiment, the angle information can include first rotation angle information of the image acquisition device formed when the rotating part rotates about the first axis, and second rotation angle information of the image acquisition device about the second axis in the third direction perpendicular to the first direction and the second direction, which is formed when the C-shaped frame part slides.

[0028] <Detailed Description of the Invention> Hereinafter, specific contents for implementing the present disclosure will be described in detail with reference to the accompanying drawings. However, in the following description, when there is a risk of unnecessarily obscuring the gist of the present disclosure, specific descriptions regarding widely known functions and configurations will be omitted.

[0029] In the accompanying drawings, the same or corresponding components are given the same reference numerals. Also, in the following description of the embodiments, the description of the same or corresponding components may be omitted from being repeated. However, even if the technology related to the components is omitted, such components are not intended to be excluded from any of the embodiments.

[0030] The advantages and features of the disclosed embodiments, and the methods for achieving them, will become clear by referring to the embodiments described later together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and can be embodied in various different forms. However, this embodiment is only provided to make the present disclosure complete and to fully inform those of ordinary skill in the art of the scope of the invention.

[0031] The terms used in this specification will be briefly explained, and the disclosed embodiments will be specifically described. When selecting the terms used in this specification, general terms that are currently widely used have been chosen as much as possible while considering their functions in this disclosure. However, this may change due to the intentions or precedents of those skilled in the relevant art, the emergence of new technologies, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in such cases, the meaning will be described in detail in the part explaining the corresponding invention. Therefore, the terms used in this disclosure should be defined based not on the simple names of the terms but on the meanings they have and the overall content of this disclosure.

[0032] In this specification, the singular forms include the plural forms unless the context clearly dictates otherwise. Also, the plural forms include the singular form unless the context clearly dictates otherwise. When a certain part of the specification states that it includes a certain component, this means that it may further include other components rather than excluding other components unless otherwise stated to the contrary.

[0033] Also, the terms "module" or "section" used in the specification mean software or hardware components, and the "module" or "section" performs some role. However, the "module" or "section" is not meant to be limited to software or hardware. The "module" or "section" may be configured to be in an addressable storage medium or may be configured to cause one or more processors to execute. Thus, by way of example, the "module" or "section" can include components such as software components, object-oriented software components, class components, and task components, and at least one of a process, a function, an attribute, a processor, a subroutine, a segment of program code, a driver, firmware, microcode, a circuit, data, a database, a data structure, a table, an array, or a variable. The functions provided within the components and the "module" or "section" can be combined with a smaller number of other components and "module" or "section" or further separated into additional components and "module" or "section".

[0034] According to an embodiment of the present disclosure, a "module" or "unit" may be implemented by a processor and a memory. The "processor" should be broadly construed to include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, etc. In some environments, the "processor" may refer to an application-specific semiconductor (ASIC), a programmable logic device (PLD), a field-programmable gate array (FPGA), etc. The "processor" may refer to a combination of processing devices such as, for example, a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors coupled with a DSP core, or a combination of any other such configuration. Also, the "memory" should be broadly construed to include any electronic component capable of storing electronic information. The "memory" may refer to various types of processor-readable media such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable-programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, magnetic or marking data storage devices, registers, etc. The memory is said to be in electronic communication with the processor if the processor can read information from the memory and / or record information in the memory. Memory integrated with the processor is in electronic communication with the processor.

[0035] Also, terms such as first, second, A, B, (a), (b), etc. used in the following embodiments are merely used to distinguish one component from another component, and the essence, order, or sequence of the corresponding components is not limited by such terms.

[0036] Also, in the following embodiments, when it is described that a certain component is “connected”, “coupled” or “attached” to another component, that component can be directly connected or attached to the other component, but it should be understood that other components can be further “connected”, “coupled” or “attached” between each component.

[0037] Also, “comprises” and / or “comprising” used in the following embodiments do not exclude the presence or addition of one or more other components, steps, operations and / or elements.

[0038] Hereinafter, various embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings.

[0039] FIG. 1 is a diagram exemplarily showing an electronic device 100 for classifying blood vessels according to an embodiment of the present disclosure. Referring to FIG. 1, the electronic device 100 for classifying blood vessels can provide blood vessel information 120 based on video 112 and angle information 114. For example, the electronic device 100 can acquire the video 112 and the angle information 114, identify at least one type of blood vessel included in the video 112 based on the angle information 114, and provide blood vessel information 120 for the identified at least one blood vessel. Here, the angle information 114 can indicate the angle information of the video acquisition device that captured the video 112 with respect to the subject (e.g., patient).

[0040] According to an embodiment, the video 112 can include a video (e.g., CAG video) of the cardiovascular system (or coronary artery) of the subject being imaged. For example, the video 112 can include a video of the cardiovascular system of the subject taken using an X-ray imaging device (e.g., a C-arm X-ray imaging device) with a contrast agent injected into the subject's blood vessels. In this case, the angle information 114 can indicate the angle information of the imaging device included in the X-ray imaging device with respect to the subject, and the blood vessel information 120 can include information about at least one cardiovascular system identified in the video 112. Information about the cardiovascular system can include, for example, the type of the cardiovascular system. In the following description, for the sake of convenience of explanation, the case where the video 112 is a CAG video and the angle information 114 is the angle information of the imaging device included in the X-ray imaging device with respect to the subject will be described, but the type of the video 112 and the type of the device for acquiring the video 112 are not limited thereto.

[0041] According to an embodiment, after the cardiovascular system of the subject is imaged through the imaging device, the video 112 (e.g., cardiovascular angiography video) of the imaged cardiovascular system can be input into the electronic device 100. As an example, the electronic device 100 can be connected to the imaging device through wired or wireless communication, and the video 112 can be provided from the imaging device to the electronic device 100 through the communication module. In an embodiment, the electronic device 100 can be provided integrally with the imaging device. As another example, the electronic device 100 can receive the video 112 from an external electronic device (e.g., an external storage device) connected through the communication module. The manner in which the electronic device 100 acquires the video 112 is not limited to the examples described above, and any manner can be used.

[0042] According to one embodiment, the angle information 114 of the imaging device (or the video acquisition device included in the imaging device) with respect to the subject can be input into the electronic device 100 together with the video 112 of the cardiovascular system of the subject or at regular time intervals. As an example, when the electronic device 100 is connected to the imaging device by wired or wireless communication, the imaging device acquires the angle information 114 of the imaging device (or the video acquisition device included in the imaging device) with respect to the subject at the time when the video 112 is captured, and can provide the acquired angle information 114 to the electronic device 100 through the communication module together with the captured video 112. As another example, when the electronic device 100 is provided integrally with the imaging device, the electronic device 100 can acquire the angle information 114 of the imaging device (or the video acquisition device included in the imaging device) with respect to the subject together with the captured video 112 at the time when the imaging device captures the video 112. As yet another example, the electronic device 100 can receive the angle information 114 together with the video 112 from an external electronic device (e.g., an external storage device) connected through the communication module.

[0043] According to one embodiment, the electronic device 100 can identify at least one type of cardiovascular system in the video 112 of the cardiovascular system of the subject, correct the identified at least one type of cardiovascular system based on the angle information 114, and then provide the vascular information 120 for the at least one cardiovascular system. For example, after classifying the blood vessels in the video 112, the electronic device 100 can verify an error in the blood vessel classification based on the angle information 114, and if there is an error in the blood vessel classification, the incorrect classification can be corrected.

[0044] According to one embodiment, the electronic device 100 can limit (or set) the types of cardiovascular vessels that can be identified in the video 112 based on the angle information 114, identify at least one type of cardiovascular vessel in the video 112 based on the limited types of cardiovascular vessels, and provide vascular information 120 for the identified at least one cardiovascular vessel. For example, before classifying blood vessels in the video 112, the electronic device 100 can limit (or set) the types of cardiovascular vessels that can be identified in the video 112 based on the angle information 114. Thereafter, the electronic device 100 can identify at least one type of cardiovascular vessel included in the video 112 so as not to deviate from the limited (or set) types of cardiovascular vessels.

[0045] FIG. 2 is a drawing showing the internal configuration of the electronic device 100 according to an embodiment of the present disclosure. Referring to FIG. 2, the electronic device 100 may include a memory 210, a processor 220, a communication module 230, and an input / output interface 240. However, the configuration of the electronic device 100 is not limited thereto. According to various embodiments, the electronic device 100 may omit at least one of the foregoing components and may further include at least one other component. As an example, the electronic device 100 may further include a display. In this case, the electronic device 100 can display at least one of the video of the captured cardiovascular vessels (e.g., video 112 in FIG. 1) or the vascular information for the cardiovascular vessels identified in the video (e.g., vascular information 120 in FIG. 1) on the display.

[0046] The memory 210 can store various data used by at least one other component (e.g., processor 220) of the electronic device 100. The data may include, for example, software (or programs) and input data or output data for related instructions.

[0047] Memory 210 can include any non-transitory computer-readable recording medium. According to one embodiment, memory 210 can include a non-volatile mass storage device such as a disk drive, SSD (solid state drive), flash memory, etc. As another example, non-volatile mass storage devices such as ROM, SSD, flash memory, disk drive, etc. can be included in electronic device 100 as a separate permanent storage device distinct from memory 210. Also, an operation system and at least one program code (e.g., instruction words such as video analysis and object recognition processing installed and driven in electronic device 100) can be stored in memory 210. In FIG. 2, memory 210 is illustrated as a single memory, but this is merely for convenience of explanation, and memory 210 can include multiple memories and / or buffer memories.

[0048] Software components can be loaded from a computer-readable recording medium separate from memory 210. Such a separate computer-readable recording medium can include a recording medium directly connectable to electronic device 100, and can include, for example, computer-readable recording media such as a floppy drive, disk, tape, DVD / CD-ROM drive, memory card, etc. As another example, software components can be loaded into memory 210 through communication module 230 rather than from a computer-readable recording medium. For example, at least one program can be loaded into memory 210 based on a computer program (e.g., a program for data transmission such as for contrast images of the cardiovascular system) installed by a file provided by a file distribution system that distributes developer or application installation files through communication module 230.

[0049] The processor 220 can execute software (or a program) to control at least one other component (e.g., a hardware or software component) of the electronic device 100 connected to the processor 220, and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operation, the processor 220 can load instructions or data received from other components (e.g., the communication module 230) into the volatile memory, process the instructions or data stored in the volatile memory, and store the resulting data in the non-volatile memory.

[0050] The processor 220 can be configured to process the instructions of a computer program by performing basic arithmetic, logic, and input / output operations. The instructions can be provided to the electronic device 100 or other external systems by the memory 210 or the communication module 230. For example, the processor 220 can identify at least one type of cardiovascular vessel included in the contrast image of the cardiovascular system. Thereafter, the processor 220 can store the vascular information for the identified at least one cardiovascular vessel in the memory 210, output or display it on the display of the electronic device 100, or transmit it to an external electronic device through the communication module 230. In FIG. 2, the processor 220 is illustrated as a single processor, but this is for convenience of explanation only, and the processor 220 can include a plurality of processors.

[0051] The communication module 230 can assist in establishing a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device 100 and an external electronic device, and in performing communication through the established communication channel. For example, the communication module 230 can provide a configuration or function for the electronic device 100 and an external electronic device (e.g., a user terminal or a cloud server) to communicate with each other through a network. As an example, control signals, instructions, data, etc. provided under the control of the processor 220 of the electronic device 100 can be transmitted to the external electronic device through the communication module 130 and the communication module of the external electronic device via the network. For example, the electronic device 100 can receive, through the communication module 230, a video of the cardiovascular system of a subject taken by an external electronic device and angle information of the video acquisition device with respect to the subject.

[0052] The input / output interface 240 can be a means for interfacing with a device (not shown) for input or output that can be connected to the electronic device 100 or included in the electronic device 100. For example, the input / output interface 240 can include, but is not limited to, a PCI express interface, an ethernet interface, etc. In FIG. 2, the input / output interface 240 is illustrated as an element configured separately from the processor 220, but is not limited thereto, and the input / output interface 240 can be configured to be included in the processor 220.

[0053] According to one embodiment, the processor 220 can perform functions related to blood vessel classification. To perform functions related to blood vessel classification, the processor 220 can execute at least one computer-readable program included in the memory 210. Here, the at least one program can acquire an image of the cardiovascular system of the subject (e.g., image 112 in FIG. 1) and angle information of the image acquisition device with respect to the subject (e.g., angle information 114 in FIG. 1), and can include instruction words for identifying at least one type of cardiovascular system included in the image based on the angle information. Here, the angle information of the image acquisition device with respect to the subject can include first rotation angle information of the image acquisition device centered on a first axis in the vertical direction (or longitudinal direction) of the subject (e.g., the direction connecting the head and feet), and second rotation angle information of the image acquisition device centered on a second axis in the left-right direction (or width direction) of the subject (e.g., the direction connecting the shoulders on both sides or the arms on both sides). The angle information will be described in detail with reference to FIGS. 3 and 4. Also, in the following description, for the sake of convenience of explanation, it can be described that the processor 220 executes at least one program to perform functions related to blood vessel classification as the processor 220 performing functions related to blood vessel classification. For example, the fact that the at least one program includes instruction words related to functions for blood vessel classification can be an explanation corresponding to the processor 220 performing the blood vessel classification function.

[0054] According to one embodiment, the processor 220 can identify at least one type of cardiovascular system included in the image based on the angle information and information regarding the type of cardiovascular system matched with the angle information. The information regarding the type of cardiovascular system matched with the angle information can be, for example, information defining (or setting) the types of cardiovascular systems that can be identified in the captured image according to the shooting angle of the image acquisition device. According to one embodiment, the angle information and the information regarding the type of cardiovascular system matched with the angle information can be pre-stored in the memory 210 in the data structure of a table. The angle information and the information regarding the type of cardiovascular system matched with the angle information will be described in detail with reference to FIGS. 6 and 7.

[0055] According to an embodiment, the processor 220 can identify at least one cardiovascular type included in the video through a machine learning model that takes the video as input. Here, the machine learning model can be included in any memory accessible by the processor 220 (for example, the memory 210, etc.). Also, the machine learning model can include any model used to infer a solution for a given input. According to an embodiment, the machine learning model can include an artificial neural network model including an input layer, a plurality of hidden layers, and an output layer. Here, each layer can include one or more nodes. Also, the machine learning model can include weight values associated with a plurality of nodes included in the machine learning model. Here, the weight values can include any parameters associated with the machine learning model. The machine learning model of the present disclosure can be a model learned using various learning methods. For example, various learning methods such as supervised learning, semi-supervised learning, unsupervised learning (or self-learning), reinforcement learning, etc. can be used in the present disclosure. In the present disclosure, the machine learning model can refer to an artificial neural network model, and the artificial neural network model can refer to the machine learning model. The artificial neural network model will be described in detail with reference to FIG. 11.

[0056] FIG. 3 is a perspective view of an electronic device 300 including a video acquisition device according to an embodiment of the present disclosure. The electronic device 300 illustrated in FIG. 3 is a device including a video acquisition device 352 for photographing the cardiovascular of a subject to acquire a video (e.g., the video 112 in FIG. 1), and can be connected to the electronic device 100 in FIG. 1 through a communication module or provided integrally with the electronic device 100 in FIG. 1. The electronic device 300 can be, for example, an X-ray imaging device.

[0057] Referring to FIG. 3, the electronic device 300 can include a main body 310, a lifting unit 320, a rotating unit 330, a C-shaped frame unit 340, an X-ray generating device 354, and an image acquisition device 352. However, the configuration of the electronic device 300 is not limited thereto. The electronic device 300 may be provided in any configuration and in any form as long as it includes the image acquisition device 352.

[0058] The main body 310 may have a built-in driving unit for lifting. According to an embodiment, the main body 310 may have a built-in control unit (e.g., a processor) for controlling the configuration of the electronic device 300. Also, when the electronic device 300 is connected to the electronic device 100 of FIG. 1 through a communication module, the main body 310 may have a built-in communication module.

[0059] The lifting unit 320 is fixed to the upper end of the driving unit for lifting built in the main body 310 and can be lifted in the first direction 392 (e.g., the vertical direction). For example, the lifting unit 320 can be adjusted according to the posture of the subject to match the height of the inspection target (or the imaging target) (e.g., the heart).

[0060] One end of the rotating unit 330 is rotatably connected to the lifting unit 320 about a first axis in a second direction perpendicular to the first direction 392, and a curved surface can be formed at the other end. When the rotating unit 330 rotates 394 about the first axis, the rotation angle (e.g., the first rotation angle) of the image acquisition device 352 can be changed. Here, the first axis can be an axis in the vertical direction (or the longitudinal direction) of the subject (e.g., the direction connecting the head and the feet) or a parallel axis. For example, the rotating unit 330 rotating 394 about the first axis indicates that the image acquisition device 352 rotates about the first axis, and the image acquisition device 352 rotating about the first axis can indicate that the image acquisition device 352 rotates in the left-right direction about the body (or the heart) of the subject. In the following description, the rotation angle information of the image acquisition device 352 formed when the rotating unit 330 rotates 394 about the first axis may be referred to as the first rotation angle information.

[0061] The C-shaped frame portion 340 is slidably connected to a curved surface formed on the rotating portion 330 and can be provided in a "C" shape (or a ring shape with a part cut off). Due to the shape of such a C-shaped frame portion 340, the electronic device 300 can be referred to as a C-arm or a C-arm imaging device. When the C-shaped frame portion 340 slides on the curved surface formed on the rotating portion 330, the rotation angle (e.g., the second rotation angle) of the image acquisition device 352 can be changed. When the C-shaped frame portion 340 slides on the curved surface formed on the rotating portion 330, the image acquisition device 352 can rotate about a second axis in a third direction perpendicular to the first direction 392 and the second direction. Here, the second axis can be an axis in the left-right direction (or width direction) of the subject (e.g., the direction connecting both shoulders or both arms on both sides) or a parallel axis. For example, the C-shaped frame portion 340 sliding on the curved surface formed on the rotating portion 330 indicates that the image acquisition device 352 rotates about the second axis, and the image acquisition device 352 rotating about the second axis can indicate that the image acquisition device 352 rotates vertically about the body (or heart) of the subject. In the following description, the rotation angle information of the image acquisition device 352 formed when the C-shaped frame portion 340 slides on the curved surface formed on the rotating portion 330 can be referred to as the second rotation angle information.

[0062] The X-ray generating device 354 is arranged at one end of the C-shaped frame portion 340, and the image acquisition device 352 can be arranged at the other end of the C-shaped frame portion 340. The X-ray generating device 354 can generate X-rays and transmit them through the inspection object (or imaging object), detect the transmitted X-ray dose with the image acquisition device 352, and process this signal to obtain an image (e.g., the image 112 in FIG. 1). At this time, the electronic device 300 can obtain the angle information (e.g., the first rotation angle information and the second rotation angle information) (e.g., the angle information 114 in FIG. 1) of the image acquisition device 352 at the time when the image is taken together with the image obtained through the image acquisition device 352.

[0063] FIG. 4 is a drawing for explaining the angle information of the imaging acquisition device 352 with respect to a subject according to an embodiment of the present disclosure. Referring to FIG. 4, an X-ray imaging device (or C-arm or C-arm imaging device) (e.g., the electronic device 300 in FIG. 3) can change (or set) the angles 422 and 424 of the imaging acquisition device 352 so as to correspond to the cardiovascular region to be imaged in order to confirm in which region an abnormal phenomenon has occurred in the cardiovascular system of the subject. As described with reference to FIG. 3, the X-ray imaging device has an X-ray generating device 354 and an imaging acquisition device 352 disposed at both ends of a C-shaped frame portion 340. The angles 422 and 424 of the imaging acquisition device 352 can be changed by the C-shaped frame portion 340 sliding (e.g., the sliding 396 in FIG. 3) on the curved surface of the rotating portion (e.g., the rotating portion 330 in FIG. 3) or the rotating portion rotating (e.g., the rotation 394 in FIG. 3).

[0064] The angles 422 and 424 of the imaging acquisition device 352 can be set with respect to the inspection object (or imaging object) as a reference. For example, when the subject lies horizontally on the examination table 410, the up-down direction (or longitudinal direction) of the subject (e.g., the direction connecting the head and the feet) can be the X-axis direction, and the left-right direction (or width direction) of the subject (e.g., the direction connecting the shoulders on both sides or the arms on both sides) can be the Y-axis direction. Here, more specifically, the direction from the head to the feet is the (+)X-axis direction, and conversely, the direction from the feet to the head is the (-)X-axis direction. The direction from the right shoulder (or right arm) to the left shoulder (or left arm) is the (+)Y-axis direction, and the direction from the left shoulder (or left arm) to the right shoulder (or right arm) can be the (-)Y-axis direction. At this time, the first rotation angle information of the imaging acquisition device 352 formed when the rotating portion rotates and the imaging acquisition device 352 rotates about the X-axis is set by the first rotation angle (α) 422, and the second rotation angle information of the imaging acquisition device 352 formed when the C-shaped frame portion 340 slides on the curved surface of the rotating portion and the imaging acquisition device 352 rotates about the Y-axis can be set by the second rotation angle (β) 424.

[0065] The first rotation angle 422 may be referred to as the primary angle. When the first rotation angle 422 has a rotation angle in the (-)Y-axis direction, the image may be referred to as having a RAO view, and the first rotation angle 422 may be expressed as a RAO angle. Also, when the first rotation angle 422 has a rotation angle in the (+)Y-axis direction, the image may be referred to as having a LAO view, and the first rotation angle 422 may be expressed as a LAO angle. Further, when the first rotation angle 422 has a rotation angle centered on the Y-axis (i.e., 0 degrees), the image may be referred to as having an AP view.

[0066] The second rotation angle 424 may be referred to as the secondary angle. When the second rotation angle 424 has a rotation angle in the (-)X-axis direction, the image may be referred to as having a CRA (or CRANIAL) view, and the second rotation angle 424 may be expressed as a CRA angle. Also, when the second rotation angle 424 has a rotation angle in the (+)X-axis direction, the image may be referred to as having a CAU (or CAUDAL) view, and the second rotation angle 424 may be expressed as a CAU angle.

[0067] According to one embodiment, through the combination of the first rotation angle 422 and the second rotation angle 424, the type of cardiovascular system to be confirmed in the image or included in the image may be set. The types of cardiovascular systems that can be set through the combination of the first rotation angle 422 and the second rotation angle 424 will be described in detail with reference to FIGS. 6 and 7.

[0068] FIG. 5 is a drawing for explaining a method of classifying blood vessels based on video and angle information according to an embodiment of the present disclosure. An X-ray imaging device (or C-arm or C-arm imaging device) (e.g., the electronic device 300 in FIG. 3) changes (or sets) the angle (e.g., the angles 422, 424 in FIG. 4) of an image acquisition device (e.g., the image acquisition device 352 in FIGS. 3 and 4) so as to correspond to the cardiovascular region to be imaged in order to confirm in which region an abnormal phenomenon has occurred in the cardiovascular system of a subject. Further, when the image acquisition device images the cardiovascular system of the subject, the X-ray imaging device can transmit the captured video (e.g., CAG video) and the angle information of the image acquisition device at the time of imaging to an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2). Here, since the X-ray imaging device (e.g., the electronic device 300 in FIG. 3) and the electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) that provides blood vessel information in the video are provided integrally or operable in association with each other, in the following description, for convenience of explanation, they will be described integratedly as an electronic device.

[0069] Referring to FIG. 5, based on the acquired images 512 and 532 and the angle information 514 and 534 of the image acquisition device with respect to the subject at the time of shooting the images 512 and 532, the electronic device can identify at least one type of cardiovascular in the images 512 and 532 and provide vascular information 520 and 540 for the identified at least one cardiovascular. For example, based on the first image 512 and the first angle information 514 of the image acquisition device with respect to the subject at the time of shooting the first image 512, the electronic device can identify at least one type of cardiovascular in the first image 512 and provide the first vascular information 520 for the identified at least one cardiovascular. Further, based on the second image 532 and the second angle information 534 of the image acquisition device with respect to the subject at the time of shooting the second image 532, the electronic device can identify at least one type of cardiovascular in the second image 532 and provide the second vascular information 540 for the identified at least one cardiovascular. However, the number of images that can be used for vascular classification and the angle information of the image acquisition device with respect to the subject at the time of shooting the corresponding images are not limited to this. For example, although not shown in the figure, based on at least one image different from the first image 512 and the second image 532 and the angle information of the image acquisition device with respect to the subject at the time of shooting the at least one image, the electronic device can identify at least one type of cardiovascular in the at least one image and provide vascular information for the identified at least one cardiovascular.

[0070] According to one embodiment, after identifying at least one type of cardiovascular in the images 512 and 532, the electronic device can correct the identified at least one type of cardiovascular based on the angle information 514 and 534. Thereafter, the electronic device can provide the vascular information 520 and 540 for the at least one cardiovascular. For example, after classifying the blood vessels in the images 512 and 532, the electronic device can verify the error with respect to the vascular classification based on the angle information 514 and 534, and if there is an error in the vascular classification, the error can be corrected.

[0071] According to one embodiment, after the electronic device restricts (or sets) the types of cardiovascular vessels that can be identified in the videos 512 and 532 based on the angle information 514 and 534, at least one type of cardiovascular vessel can be identified in the videos 512 and 532 based on the restricted types of cardiovascular vessels. Then, the electronic device can provide the vessel information 520 and 540 for the identified at least one cardiovascular vessel. For example, before classifying the blood vessels in the videos 512 and 532, the electronic device restricts (or sets) the types of cardiovascular vessels that can be identified in the videos 512 and 532 based on the angle information 514 and 534, and can identify at least one type of cardiovascular vessel included in the videos 512 and 532 so as not to deviate from the restricted (or set) types of cardiovascular vessels.

[0072] FIG. 6 is a drawing showing information regarding the types of left coronary arteries matched with the angle information according to an embodiment of the present disclosure. An X-ray imaging device (or C-arm or C-arm imaging device) (e.g., the electronic device 300 in FIG. 3) can differently set the types of cardiovascular vessels included in a video (e.g., a CAG video) according to the angle (e.g., the angles 422 and 424 in FIG. 4) of a video acquisition device (e.g., the video acquisition device 352 in FIGS. 3 and 4). In FIG. 6, the types of left coronary arteries that can be set through the combination of the first rotation angle (α) and the second rotation angle (β) of the video acquisition device will be described. In FIG. 6, the angle information of the video acquisition device and the information regarding the types of left coronary arteries matched with the angle information are illustrated as having a table data structure, but the data structure is not limited thereto.

[0073] Referring to FIG. 6, when the first rotation angle (α) has the RAO angle and the second rotation angle (β) has the CRA angle, that is, when the first rotation angle of the imaging acquisition device has a rotation angle in the (-) Y-axis direction and the second rotation angle of the imaging acquisition device has a rotation angle in the (-) X-axis direction, the image can have a RAO CRANIAL view. When the image has a RAO CRANIAL view, the left anterior descending coronary artery (LAD) can be identified in the image. The "+" sign indicated in the table of FIG. 6 for the degree of identification indicates that it can be identified, the "++" sign indicates that the identification is well done, and the "-" sign can indicate that the identification is difficult. For example, when the degrees of identification indicated by the "+", "++", and "-" signs are set as the first degree of identification, the second degree of identification, and the third degree of identification respectively, the second degree of identification has the largest value, the third degree of identification can have the smallest value, and the first degree of identification can have a value between the second degree of identification and the third degree of identification. Also, in the table of FIG. 6, "LAD-p" indicates the proximal portion of the left anterior descending coronary artery, "LAD-m" indicates the middle portion of the left anterior descending coronary artery, and "LAD-d" can indicate the distal portion of the left anterior descending coronary artery. Also, in the table of FIG. 6, "LCX-p" indicates the proximal portion of the left circumflex coronary artery, and "LCX-d" can indicate the distal portion of the left circumflex coronary artery. For example, when the image has a RAO CRANIAL view, the middle and distal portions of the left anterior descending coronary artery are most clearly identified in the image, the proximal portion of the left anterior descending coronary artery is identifiable, and the proximal and distal portions of the left circumflex coronary artery may be difficult to identify.

[0074] When the first rotation angle (α) has the AP angle and the second rotation angle (β) has the CRA angle, that is, when the first rotation angle of the imaging acquisition device is 0 degrees and the second rotation angle of the imaging acquisition device has a rotation angle in the (-) X-axis direction, the image can have an AP CRANIAL view. When the image has an AP CRANIAL view, the proximal, middle, and distal portions of the left anterior descending coronary artery are identifiable in the image, and the proximal and distal portions of the left circumflex coronary artery may be difficult to identify.

[0075] When the first rotation angle (α) has the LAO angle and the second rotation angle (β) has the CRA angle, that is, when the first rotation angle of the imaging acquisition device has a rotation angle in the (+)Y-axis direction and the second rotation angle of the imaging acquisition device has a rotation angle in the (-)X-axis direction, the image can have a LAO CRANIAL view. When the image has a LAO CRANIAL view, the left main coronary artery (LM), the proximal, middle, and distal portions of the left anterior descending coronary artery can be identified in the image, and the proximal and distal portions of the left circumflex coronary artery may be difficult to identify.

[0076] When the first rotation angle (α) has the AP angle and the second rotation angle (β) is 0 degrees, that is, when the first rotation angle of the imaging acquisition device is 0 degrees and the second rotation angle of the imaging acquisition device is also 0 degrees, the image can have an AP view. When the image has an AP view, the left anterior descending coronary artery may be identifiable in the image.

[0077] When the first rotation angle (α) has the RAO angle and the second rotation angle (β) has the CAU angle, that is, when the first rotation angle of the imaging acquisition device has a rotation angle in the (-)Y-axis direction and the second rotation angle of the imaging acquisition device has a rotation angle in the (+)X-axis direction, the image can have a RAO CAUDAL view. When the image has a RAO CAUDAL view, the left main coronary artery, the proximal portion of the left anterior descending coronary artery, the proximal and distal portions of the left circumflex coronary artery can be identified in the image, and the middle and distal portions of the left anterior descending coronary artery may be difficult to identify.

[0078] When the first rotation angle (α) has the AP angle and the second rotation angle (β) has the CAU angle, that is, when the first rotation angle of the imaging acquisition device is 0 degrees and the second rotation angle of the imaging acquisition device has a rotation angle in the (+)X-axis direction, the image can have an AP CAUDAL view. When the image has an AP CAUDAL view, the left main coronary artery is most clearly identifiable in the image, the proximal portion of the left anterior descending coronary artery, the proximal and distal portions of the left circumflex coronary artery can be identified, and the middle and distal portions of the left anterior descending coronary artery may be difficult to identify.

[0079] When the first rotation angle (α) has the LAO angle and the second rotation angle (β) has the CAU angle, that is, when the first rotation angle of the imaging acquisition device has a rotation angle in the (+)Y-axis direction and the second rotation angle of the imaging acquisition device has a rotation angle in the (+)X-axis direction, the image can have a LAO CAUDAL view. The LAO CAUDAL view can be referred to as the SPIDER view. When the image has a LAO CAUDAL view, the left main coronary artery is most clearly identified in the image, the proximal portions of the left anterior descending coronary artery and the left circumflex coronary artery are identifiable, and the middle and distal portions of the left anterior descending coronary artery and the distal portion of the left circumflex coronary artery may be difficult to identify.

[0080] According to one embodiment, in the process of identifying the types of cardiovascular systems in an image, the electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can be processed so that the types of cardiovascular systems corresponding to the degree of identification set in the above-described table, where the identification is difficult (e.g., indicated by a "-" symbol), are not identified. For example, the electronic device can process (or limit) the image having a RAO CRANIAL view so that the left circumflex coronary artery is not identified.

[0081] FIG. 7 is a drawing showing information regarding the types of right coronary arteries matched with angle information according to an embodiment of the present disclosure. Referring to FIG. 7, an X-ray imaging device (or a C-arm or a C-arm imaging device) (e.g., the electronic device 300 in FIG. 3) can set different types of cardiovascular systems included in an image (e.g., a CAG image) according to the angles (e.g., the angles 422 and 424 in FIG. 4) of an imaging acquisition device (e.g., the imaging acquisition device 352 in FIGS. 3 and 4). In FIG. 7, the combination of the first rotation angle (α) and the second rotation angle (β) of the imaging acquisition device will be used to explain the types of right coronary arteries that can be set. In FIG. 7, the angle information of the imaging acquisition device and the information regarding the types of right coronary arteries matched with the angle information are illustrated as having a table data structure, but the data structure is not limited thereto.

[0082] Referring to FIG. 7, when the first rotation angle (α) has an RAO angle and the second rotation angle (β) has a CRA angle, that is, when the first rotation angle of the imaging acquisition device has a rotation angle in the (-) Y-axis direction and the second rotation angle of the imaging acquisition device has a rotation angle in the (-) X-axis direction, the image can have an RAO CRANIAL view. The "+" sign indicated in the table of FIG. 7 to some extent of identification indicates that it is distinguishable, the "++" sign indicates that the identification is well done, and the "-" sign can indicate that the identification is difficult. Also, in the table of FIG. 7, "prox." can indicate the proximal part, "mid." can indicate the middle part, and "dis." can indicate the distal part. For example, when the image has an RAO CRANIAL view, the proximal part of the right coronary artery is most clearly distinguishable in the image, and the middle part of the right coronary artery may be distinguishable.

[0083] When the first rotation angle (α) has an AP angle and the second rotation angle (β) has a CRA angle, that is, when the first rotation angle of the imaging acquisition device is 0 degrees and the second rotation angle of the imaging acquisition device has a rotation angle in the (-) X-axis direction, the image can have an AP CRANIAL view. When the image has an AP CRANIAL view, the distal part of the right coronary artery is most clearly distinguishable in the image, and the middle part of the right coronary artery may be distinguishable.

[0084] When the first rotation angle (α) has an LAO angle and the second rotation angle (β) has a CRA angle, that is, when the first rotation angle of the imaging acquisition device has a rotation angle in the (+) Y-axis direction and the second rotation angle of the imaging acquisition device has a rotation angle in the (-) X-axis direction, the image can have an LAO CRANIAL view. When the image has an LAO CRANIAL view, the proximal part of the right coronary artery is most clearly distinguishable in the image, and the middle part and the distal part of the right coronary artery may be distinguishable.

[0085] When the first rotation angle (α) has an RAO angle and the second rotation angle (β) is 0 degrees, that is, when the first rotation angle of the imaging acquisition device has a rotation angle in the (-) Y-axis direction and the second rotation angle of the imaging acquisition device is 0 degrees, the image can have an RAO view. When the image has an RAO view, the middle part of the right coronary artery is most clearly distinguishable in the image, and the proximal and distal parts of the right coronary artery may be difficult to distinguish.

[0086] When the first rotation angle (α) has an LAO angle and the second rotation angle (β) is 0 degrees, that is, when the first rotation angle of the imaging acquisition device has a rotation angle in the (+) Y-axis direction and the second rotation angle of the imaging acquisition device is 0 degrees, the image can have an LAO view. When the image has an LAO view, the proximal, middle, and distal parts of the right coronary artery may be distinguishable in the image.

[0087] When the first rotation angle (α) has an LAO angle and the second rotation angle (β) has a CAU angle, that is, when the first rotation angle of the imaging acquisition device has a rotation angle in the (+) Y-axis direction and the second rotation angle of the imaging acquisition device has a rotation angle in the (+) X-axis direction, the image can have an LAO CAUDAL view. When the image has an LAO CAUDAL view, the proximal and middle parts of the right coronary artery may be distinguishable in the image.

[0088] According to an embodiment, in the process of identifying the type of cardiovascular in the image, the electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can be processed so that the type of cardiovascular corresponding to the degree of identification set in the above-described table, which is difficult to identify (e.g., indicated by a - symbol), is not identified. For example, the electronic device can process (or limit) so that the proximal and distal parts of the right coronary artery are not identified in an image having an RAO view.

[0089] FIG. 8 is a drawing for explaining a method of classifying blood vessels according to an embodiment of the present disclosure. Referring to FIG. 8, a processor (e.g., the processor 220 in FIG. 2) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) for classifying blood vessels can acquire, at step S810, an image (e.g., the image 112 in FIG. 1) of the cardiovascular system of a subject that has been photographed and angle information (e.g., the angle information 114 in FIG. 1 or the angle information 422, 424 in FIG. 4) of an image acquisition device (e.g., the image acquisition device 352 in FIGS. 3 and 4) with respect to the subject. Here, the angle information of the image acquisition device with respect to the subject can include first rotation angle information of the image acquisition device centered on a first axis (e.g., the X axis in FIG. 4) in the vertical direction (or longitudinal direction) (e.g., the direction connecting the head and the feet) of the subject and second rotation angle information of the image acquisition device centered on a second axis (e.g., the Y axis in FIG. 4) in the left-right direction (or width direction) (e.g., the direction connecting the shoulders on both sides or the arms on both sides) of the subject. According to an embodiment, the processor can acquire the image and the angle information simultaneously or at regular time intervals.

[0090] At step S820, the processor can identify at least one type of blood vessel included in the image based on the angle information. According to an embodiment, the processor can identify at least one type of blood vessel included in the image based on the angle information and information regarding the type of blood vessel matched with the angle information. Here, the information regarding the type of blood vessel matched with the angle information can be information that defines (or sets) the type of blood vessel that can be identified in the photographed image according to the shooting angle of the image acquisition device. According to an embodiment, the angle information and the information regarding the type of blood vessel matched with the angle information can be in the form of a table data structure and can be pre-stored in the memory (e.g., the memory 210 in FIG. 2) of the electronic device.

[0091] According to one embodiment, after the processor identifies at least one type of cardiovascular in the video, it can correct the identified at least one type of cardiovascular based on the angle information. For example, after the processor classifies blood vessels in the video, it can verify errors in the blood vessel classification based on the angle information, and if there are errors in the blood vessel classification, it can correct the incorrect classification.

[0092] According to one embodiment, the processor can limit (or set) the types of cardiovascular that can be identified in the video based on the angle information, and identify at least one type of cardiovascular in the video based on the limited types of cardiovascular. For example, before classifying blood vessels in the video, the processor can limit (or set) the types of cardiovascular that can be identified in the video based on the angle information, and identify at least one type of cardiovascular included in the video so as not to deviate from the limited (or set) types of cardiovascular.

[0093] FIG. 9 is a diagram for explaining a method of limiting the types of cardiovascular that can be identified in the video based on the angle information according to an embodiment of the present disclosure. A processor (e.g., the processor 220 in FIG. 2) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) for classifying blood vessels can identify at least one type of cardiovascular included in the video based on the video (e.g., the video 112 in FIG. 1) of the cardiovascular of the subject and the angle information (e.g., the angle information 114 in FIG. 1 or the angle information 422, 424 in FIG. 4) of the video acquisition device (e.g., the video acquisition device 352 in FIGS. 3 and 4) for the subject. In this process, the processor can identify at least one type of cardiovascular included in the video through a machine learning model (e.g., a blood vessel classification model) that takes the video as input.

[0094] Referring to FIG. 9, in step S910, the processor can input the angle information into the machine learning model to limit the types of cardiovascular that can be identified in the video. For example, when additional angle information is input into the video in the machine learning model, the machine learning model can be trained to limit the types of cardiovascular that can be identified in the video based on the angle information.

[0095] At stage 920 (S920), the processor can identify at least one cardiovascular type included in the video through a machine learning model. For example, the machine learning model can identify at least one cardiovascular type in the video based on a limited set of cardiovascular types. That is, the machine learning model can identify at least one cardiovascular type included in the video so as not to deviate from the restricted (or set) cardiovascular types.

[0096] According to one embodiment, the machine learning models used at stages 910 and 920 can be the same machine learning model. For example, the machine learning model can include a machine learning model that simultaneously receives inputs of the video and the angle information, restricts the types of blood vessels, and can classify the blood vessels in the video.

[0097] According to one embodiment, the machine learning models used at stages 910 and 920 can be different machine learning models. For example, the machine learning model used at stage 910 can include a machine learning model that receives an input of the angle information and outputs information regarding the types of blood vessels whose identification in the video is restricted, and the machine learning model used at stage 920 can include a machine learning model that receives inputs of the video and the information regarding the types of blood vessels whose identification in the video is restricted and can classify the blood vessels in the video.

[0098] FIG. 10 is a diagram for explaining a method of correcting the cardiovascular type identified based on the angle information according to an embodiment of the present disclosure. A processor (e.g., processor 220 in FIG. 2) of an electronic device (e.g., electronic device 100 in FIGS. 1 and 2) for classifying blood vessels can identify at least one cardiovascular type included in a video (e.g., video 112 in FIG. 1) of a subject's cardiovascular system and angle information (e.g., angle information 114 in FIG. 1 or angle 422, 424 information in FIG. 4) of a video acquisition device (e.g., video acquisition device 352 in FIGS. 3 and 4) with respect to the subject. In this process, the processor can identify at least one cardiovascular type included in the video through a machine learning model (e.g., a blood vessel classification model) that takes the video as an input.

[0099] Referring to FIG. 10, at step 1010 (S1010), the processor can identify at least one cardiovascular type included in the video through a machine learning model. For example, the machine learning model can identify at least one cardiovascular type in the input video.

[0100] At step 1020 (S1020), the processor can correct the identified at least one cardiovascular type based on the angle information. For example, the processor can correct the identified at least one cardiovascular type based on the angle information. According to one embodiment, the processor can correct the identified cardiovascular type through a machine learning model based on the angle information. In this case, the machine learning model that can be used at step 1020 can be the same machine learning model as the one used at step 1010. For example, the machine learning model can receive the input of the video and the angle information simultaneously, classify the blood vessels in the video, verify the error for the blood vessel classification, and include a machine learning model that can correct the error if there is an error in the blood vessel classification. Or the machine learning model that can be used at step 1020 can be a different machine learning model from the one used at step 1010. For example, the machine learning model used at step 1010 includes a machine learning model that receives the input of the video and classifies the blood vessels in the video, and the machine learning model that can be used at step 1020 can receive the input of the blood vessel classification information (e.g., the video in which the blood vessels are classified) and the angle information, verify the error for the blood vessel classification, and include a machine learning model that can correct the error if there is an error in the blood vessel classification.

[0101] According to one embodiment, the processor can classify the views that the video can have based on the angle information. Here, the angle information can include the first rotation angle and the second rotation angle of the video acquisition device. The first rotation angle indicates the rotation angle in the left - right direction (or width direction) of the subject (e.g., the direction connecting the shoulders or arms on both sides) (hereinafter referred to as the Y - axis direction), and the second rotation angle can indicate the rotation angle in the up - down direction (or longitudinal direction) of the subject (e.g., the direction connecting the head and feet) (hereinafter referred to as the X - axis direction). For example, in the case of the right coronary artery, when the first rotation angle included in the angle information is 0 degrees and the second rotation angle is the rotation angle in the (-) X - axis direction, the processor can classify it as the AP CRANIAL view. Also, in the case of the right coronary artery, when the first rotation angle included in the angle information is the rotation angle in the (+) Y - axis direction and the second rotation angle is the rotation angle in the (-X) axis direction, the processor can classify it as the LAO CRANIAL view. Also, in the case of the right coronary artery, when the first rotation angle included in the angle information is the rotation angle in the (+) Y - axis direction and the second rotation angle is 0 degrees, the processor can classify it as the LAO view. Also, in the case of the right coronary artery, when the first rotation angle included in the angle information is the rotation angle in the (-) Y - axis direction and the second rotation angle is 0 degrees, the processor can classify it as the RAO view. Also, in the case of the left anterior descending coronary artery, when the first rotation angle included in the angle information is 0 degrees and the second rotation angle is also 0 degrees, the processor can classify it as the AP view. Also, in the case of the left anterior descending coronary artery, when the first rotation angle included in the angle information is 0 degrees and the second rotation angle is the rotation angle in the (-) X - axis direction, the processor can classify it as the AP CRANIAL view. Also, in the case of the left anterior descending coronary artery, when the first rotation angle included in the angle information is the rotation angle in the (+) Y - axis direction and the second rotation angle is the rotation angle in the (-) X - axis direction, the processor can classify it as the LAO CRANIAL view. Also, in the case of the left anterior descending coronary artery, when the first rotation angle included in the angle information is the rotation angle in the (-) Y - axis direction and the second rotation angle is the rotation angle in the (-) X - axis direction, the processor can classify it as the RAO CRANIAL view.Also, when the processor is dealing with the left circumflex artery, if the first rotation angle included in the angle information is 0 degrees and the second rotation angle is also 0 degrees, it can be classified as the AP view. Also, when the processor is dealing with the left circumflex artery, if the first rotation angle included in the angle information is 0 degrees and the second rotation angle is the rotation angle in the (+)X-axis direction, it can be classified as the AP CAUDAL view. Also, when the processor is dealing with the left circumflex artery, if the first rotation angle included in the angle information is the rotation angle in the (-)Y-axis direction and the second rotation angle is the rotation angle in the (+)X-axis direction, it can be classified as the RAO CAUDAL view. Also, when the processor is dealing with the left main coronary artery, if the first rotation angle included in the angle information is the rotation angle in the (+)Y-axis direction and the second rotation angle is the rotation angle in the (+)X-axis direction, it can be classified as the LAO CAUDAL view.

[0102] After that, as shown in Table 1, the processor can specify (or assign) the classified view information to a class together with the vessel type. At this time, the processor can add to the class list a class (e.g., the ("Non-CAG", "") class in Table 1) that enables vessel classification for other images in the cardiovascular images that are not CAG images. Also, the processor can add to the class list a dummy class (e.g., the ("RCA", ""), ("LAD", ""), ("LCX", ""), and ("LM", "") classes in Table 1) that contains only the vessel type without view information so that it can also handle cases where the shooting angle is located among a large number of views and it is difficult to classify it into any one view.

[0103]

Table 1

[0104] Subsequently, the processor can train a machine learning model to classify views with the video as input based on class information (e.g., a class list). At this time, the processor can limit the types of major blood vessels that can be identified for each view and train the machine learning model so that the major blood vessels in the video can also be classified together. According to one embodiment, the processor can process the identification numbers of classes related to the AP view (e.g., the ("LAD", "AP") class and the ("LCX", "AP") class in Table 1) in the class information of Table 1 as the same. In this case, the processor can train the machine learning model so that the type of blood vessel that can be identified in the AP view can be at least one of the left anterior descending coronary artery or the left circumflex coronary artery. In an embodiment, the processor can set the identification numbers of classes related to the AP view (e.g., the ("LAD", "AP") class and the ("LCX", "AP") class in Table 1) to be different from each other. In this case, the processor can train the machine learning model so that the type of blood vessel that can be identified in the AP view can be the left anterior descending coronary artery or the left circumflex coronary artery.

[0105] Subsequently, the processor can input the video into the machine learning model in relation to the inference process through the learned machine learning model. According to one embodiment, the processor can generate a weighted value (e.g., Gaussian weight) based on a predetermined number of points in the video based on the intensity of the contrast agent, and generate (or extract) at least one representative frame based on the generated weighted value. Or the processor can generate a weighted value based on a predetermined number of points at a constant rate, and generate (or extract) at least one representative frame based on the generated weighted value. Subsequently, the processor can input at least one representative frame into the machine learning model.

[0106] Subsequently, the processor can classify the view based on the inference result for at least one representative frame through the machine learning model. At this time, the processor can classify the view based on the class information. Also, the processor can limit the types of blood vessels that can be identified in the video based on the classified view. Subsequently, the processor can classify the blood vessels included in the video.

[0107] According to an embodiment, when the processor classifies a view based on the inference results for a plurality of representative frames through a machine learning model, it can determine the final result based on the class information. For example, the processor can determine the final result for the inference results for a plurality of representative frames through a voting method. To explain this in more detail, when the processor votes on the inference results for a plurality of representative frames based on the class information and a valid view is selected as a result, the processor can determine the combination of the type of blood vessel corresponding to the selected valid view and the view information as the final result. Or when the processor votes on the inference results for a plurality of representative frames based on the class information and an invalid view is selected as a result, the processor can vote again on the remaining results excluding the invalid view from the inference results for the plurality of representative frames. At this time, when a valid view is selected as a result of the re-voting, the processor can determine the combination of the type of blood vessel corresponding to the selected valid view and the view information as the final result. Or when all are invalid views as a result of the re-voting, the processor can vote again with the 2nd confidence. Then, when a valid view is selected as a result of the re-voting, the processor can determine the combination of the type of blood vessel corresponding to the selected valid view and the view information as the final result. Or when the result of the re-voting is an invalid view or a video that is not a CAG video (e.g., Non-CAG), the processor can vote again only on the view information of the class including the type of blood vessel in the first inference result with the 1st confidence and determine the final result.

[0108] FIG. 11 is a drawing showing an artificial neural network model 1100 according to an embodiment of the present disclosure. Referring to FIG. 11, the artificial neural network model 1100 is an example of a machine learning model, and shows a statistical learning algorithm embodied based on the structure of a biological neural network in machine learning technology and cognitive science, or a structure for executing the algorithm.

[0109] According to one embodiment, an artificial neural network model 1100 can be a machine learning model having problem-solving ability by nodes, which are artificial neurons forming a network with synaptic connections like a biological neural network, repeatedly adjusting synaptic weights so that the error between a correct output corresponding to a specific input and an inferred output decreases by learning. For example, the artificial neural network model 1100 can include any probabilistic model, neural network model, etc. used in artificial intelligence learning methods such as machine learning and deep learning.

[0110] According to one embodiment, the above-described blood vessel classification model can be generated in the form of the artificial neural network model 1100. For example, the artificial neural network model 1100 can receive an image of a subject's cardiovascular system and angle information of an image acquisition device for the subject, and based on this, estimate at least one type of cardiovascular system included in the image.

[0111] The artificial neural network model 1100 can be implemented as a multi-layer perceptron (MLP) composed of multiple layers of nodes and connections between them. The artificial neural network model 1100 according to this embodiment can be implemented using one of the artificial neural network model structures including a multi-layer perceptron. The artificial neural network model 1100 can include an input layer 1120 that receives input data 1110 (or an input signal) from the outside, an output layer 1140 that outputs output data 1150 (or an output signal) corresponding to the input data 1110, and n (where n is a positive integer) hidden layers 1130_1 to 1130_n located between the input layer 1120 and the output layer 1140, which receive signals from the input layer 1120, extract features, and transmit them to the output layer 1140. Here, the output layer 1140 can receive signals from the hidden layers 1130_1 to 1130_n and output them to the outside.

[0112] The learning method of the artificial neural network model 1100 may include a supervised learning method that learns to be optimized for problem solving by inputting a correct teacher signal (or label), and an unsupervised learning method that does not require a teacher signal. According to an embodiment, an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) according to an embodiment of the present disclosure can learn the artificial neural network model 1100 by using an image of the cardiovascular system of a subject that has been captured and the angle information of the image acquisition device with respect to the subject.

[0113] According to an embodiment, the electronic device can generate learning data for learning the artificial neural network model 1100. For example, the electronic device can generate a learning data set including an image of the cardiovascular system of a subject that has been captured and the angle information of the image acquisition device with respect to the subject. Then, the electronic device can learn the artificial neural network model 1100 for identifying at least one type of cardiovascular system included in the image (or classifying blood vessels in the image) based on the generated learning data set.

[0114] According to an embodiment, the input variables of the artificial neural network model 1100 can include an image of the cardiovascular system of a subject that has been captured and the angle information of the image acquisition device with respect to the subject. When the input variables described above are input through the input layer 1120 in this way, the output variables output by the output layer 1140 of the artificial neural network model 1100 can be information identifying at least one type of cardiovascular system included in the image (or blood vessel classification information).

[0115] In this way, a plurality of input variables and a plurality of output variables corresponding thereto are respectively matched to the input layer 1120 and the output layer 1140 of the artificial neural network model 1100, and by adjusting the synaptic values between the nodes included in the input layer 1120, the hidden layers 1130_1 to 1130_n, and the output layer 1140, learning can be performed so that the correct output corresponding to a specific input can be extracted. Through such a learning process, the characteristics hidden in the input variables of the artificial neural network model 1100 can be grasped, and the synaptic values (or weighted values) between the nodes of the artificial neural network model 1100 can be adjusted so that the error between the output variable calculated based on the input variable and the target output is reduced. Further, the electronic device learns an algorithm that receives, as inputs, the video of the cardiovascular system of the subject and the angle information of the video acquisition device with respect to the subject, and learns in a manner that minimizes the loss with the information (or blood vessel classification information) that identifies at least one type of cardiovascular system included in the video (i.e., annotation information). Using the artificial neural network model 1100 learned in this way, the information that identifies at least one type of cardiovascular system included in the video can be estimated.

[0116] The above-described flowchart and the above-described description are merely examples, and in some embodiments, they may be implemented differently. For example, in some embodiments, the order of each step may be changed, some steps may be repeatedly performed, some steps may be omitted, or some steps may be added.

[0117] The above-described method can be provided by a computer program stored in a computer-readable recording medium for execution by a computer. The medium can be one that continuously stores a computer-executable program, or temporarily stores it for execution or download. Further, the medium can be various recording or storage means in a form in which one or several pieces of hardware are combined, but is not limited to a medium directly connected to a certain computer system, and may be distributed and present on a network. Examples of the medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto optical media such as floptical disks, and those configured to store program instruction words including ROM, RAM, flash memory, and the like. Also, as examples of other media, there can be mentioned recording media or storage media managed by app stores through which applications are distributed, and sites, servers, etc. that supply or distribute various other software.

[0118] The method, operation, or technique of the present disclosure may be implemented by various means. For example, such a technique may be implemented in hardware, firmware, software, or a combination thereof. Those of ordinary skill in the art will understand that the various exemplary logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure of the present application may be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate such an interchange between hardware and software, the various exemplary components, blocks, modules, circuits, and steps have been generally described above in terms of their functionality. Whether such a function is implemented as hardware or as software will vary depending on the design requirements imposed on the particular application and the overall system. Those of ordinary skill in the art may implement the functions described in various ways for each particular application, but such implementations should not be construed as departing from the scope of the present disclosure.

[0119] In a hardware implementation, the processing unit utilized to implement the techniques may be embodied in one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, other electronic units designed to perform the functions described in this disclosure, computers, or combinations thereof.

[0120] Accordingly, the various exemplary logical blocks, modules, and circuits described in connection with this disclosure may be implemented or performed in any combination by, for example, a general purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or devices designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in association with a DSP core, or any other configuration.

[0121] In an embodiment of firmware and / or software, the techniques may be implemented by instructions stored on a computer-readable medium such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), PROM (programmable read-only memory), EPROM (erasable programmable read-only memory), EEPROM (electrically erasable PROM), flash memory, compact disc (CD), magnetic or marked data storage devices, etc. The instructions may be executable by one or more processors and may cause the processor(s) to perform particular aspects of the functions described in this disclosure.

[0122] When implemented in software, the techniques described above may be stored on or transmitted across a computer-readable medium by one or more instructions or codes. A computer-readable medium includes both a computer storage medium and a communication medium 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. By way of example, and not limitation, such computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium.

[0123] For example, when software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, wireless, and microwave, the coaxial cable, fiber optic cable, twisted pair, digital subscriber line, or wireless technologies such as infrared, wireless, and microwave are included within the definition of the medium. As used herein, disk and disc include CD, laser disk, optical disk, DVD (digital versatile disc), floppy disk, and Blu-ray disk, where disks typically reproduce data magnetically, while discs reproduce data optically using a laser. The foregoing combinations must also be included within the scope of computer-readable media.

[0124] A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other known form of storage medium. An exemplary storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium. Alternatively, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Alternatively, the processor and the storage medium may reside as discrete components in a user terminal.

[0125] Although the embodiments described above have been described as utilizing aspects of the presently disclosed subject matter in one or more stand-alone computer systems, the present disclosure is not so limited and may be implemented in conjunction with any computing environment such as a network or a distributed computing environment. Consequently, aspects of the subject matter of the present disclosure may be implemented on multiple processing chips or devices, and storage may be affected similarly across multiple devices. Such devices may include a PC, a network server, and a portable device.

[0126] Although the present disclosure has been described in connection with some embodiments, various modifications and changes can be made without departing from the scope of the present disclosure that can be understood by those of ordinary skill in the art to which the invention of the present disclosure belongs. Also, such modifications and changes should be understood to fall within the scope of the claims appended hereto.

Description of Reference Numerals

[0127] 100: Electronic device 210: Memory 220: Processor 230: Communication module 240: Input / output interface

Claims

1. 1. A method for vessel classification performed by at least one processor, comprising: acquiring an image including the cardiovascular system of a subject and angle information of an image acquisition device relative to the subject; and The method includes identifying a type of at least one cardiac vessel included in the image based on the angle information.

2. The angle information is First rotation angle information of the image acquisition device about a first axis in the vertical direction of the subject; and The method of claim 1 , further comprising: second rotation angle information of the image acquisition device about a second axis in a left-right direction of the subject.

3. The step of identifying the at least one cardiovascular type comprises: The method of claim 1 , further comprising identifying a type of the at least one cardiac vessel included in the image based on the angle information and information on a type of the cardiac vessel matched with the angle information.

4. 1. A method for vessel classification performed by at least one processor, comprising: acquiring an image including the cardiovascular system of the subject; and A method for vessel classification comprising: identifying a type of at least one cardiovascular vessel contained in the image through a machine learning model that uses the image as an input.

5. The machine learning model is The method of claim 4 , further comprising: learning to limit the types of cardiac blood vessels that can be identified in the image based on angle information of an image acquisition device relative to the subject.

6. The step of identifying the at least one cardiovascular type comprises: The method of claim 4 , further comprising: correcting the identified type of at least one cardiac vessel based on angle information of an image acquisition device relative to the subject.

7. The method further includes a step of training a machine learning model to identify views corresponding to each of a plurality of images of cardiac blood vessels by inputting the plurality of images based on view information classified according to angle information of the image acquisition device and class information in which a type of blood vessel matched to the view information is designated as one class, The step of identifying the at least one cardiovascular type comprises: identifying a view corresponding to the video based on the machine learning model; and The method of claim 4 , further comprising identifying a type of at least one cardiac vessel included in the image based on the identified views.

8. The class information is 8. The method of claim 7, further comprising at least one of a class that enables blood vessel classification for images other than a coronary angiography (CAG) image among the plurality of images, or a dummy class that includes only the type of blood vessel without the view information.

9. The step of identifying the at least one cardiovascular type comprises: The method of claim 7 , further comprising limiting the types of cardiac vessels that may be identified in the video based on the identified views.

10. The step of identifying a view corresponding to the image includes: generating weights based on a predetermined number of points in the image; extracting at least one representative frame from the image based on the generated weighted value; inputting the at least one representative frame into the machine learning model; and The method of claim 7 , further comprising identifying a view corresponding to the image based on an inference result for the at least one representative frame through the machine learning model.

11. The step of identifying a view corresponding to the image based on an inference result for the at least one representative frame includes: When the at least one representative frame includes a plurality of representative frames, determining a final result through a voting method for inference results for the plurality of representative frames through the machine learning model; The step of determining the final result comprises: determining, as a final result, a class including a type of blood vessel and view information corresponding to the selected valid view when a valid view is selected as a result of voting on the inference results for the plurality of representative frames; if an invalid view is selected as a result of the voting, voting again for the remaining views excluding the invalid view in the inference result for the plurality of representative frames, and if a valid view is selected as a result of the re-voting, determining a class including a type of blood vessel and view information corresponding to the selected valid view as a final result; When an invalid view is selected as a result of the voting, a second vote is performed on the remaining views excluding the invalid view in the inference results for the representative frames, and when all the views are invalid as a result of the second vote, a second vote is performed on the remaining views with a second degree of confidence. When a valid view is selected as a result of the second vote, a class including a type of blood vessel and view information corresponding to the selected valid view is determined as a final result; and 11. The method of claim 10, further comprising the steps of: when an invalid view is selected as a result of the voting, voting again on the remaining inference results for the representative frames excluding the invalid view; if the result of the re-voting is that all views are invalid, voting again with a second degree of confidence; if the result of the re-voting is that the view is invalid or is not a CAG image, voting again with a first degree of confidence only for view information of a class including a type of blood vessel in the initial inference result, thereby determining a final result.

12. In an electronic device, memory; and at least one processor coupled to the memory and configured to execute at least one computer readable program contained in the memory; The at least one program comprises: Acquiring an image including a cardiovascular system of a subject and angle information of an image acquisition device relative to the subject; An electronic device comprising instructions for identifying at least one type of cardiovascular vessel included in the image based on the angle information.

13. A main body with a built-in lift drive unit; an elevation unit fixed to an upper end of the elevation drive unit and raised and lowered in a first direction; a rotating part, one end of which is connected to the lifting part so as to be rotatable about a first axis in a second direction perpendicular to the first direction, and the other end of which is formed with a curved surface; a C-shaped frame portion slidably connected to the bending surface and configured in a "C" shape; an x-ray generating device disposed at one end of the C-shaped frame portion; and The electronic device of claim 12 further comprising an image capture device disposed at the other end of the C-shaped frame portion.

14. The angle information is first rotation angle information of the image acquisition device formed when the rotation unit rotates around the first axis; and 14. The electronic device of claim 13, further comprising: second rotation angle information of the image capturing device about a second axis in a third direction perpendicular to the first direction and the second direction, the second axis being formed when the C-shaped frame portion slides.

15. A computer readable computer program for carrying out the method according to any one of claims 1 to 11 on a computer.

Images