Method and electronic device for generating three-dimensional blood vessel profile data

Abstract

To provide a method for generating 3-dimensional blood vessel profile data by using a plurality of 2-dimensional images.SOLUTION: The method includes the steps of: acquiring a plurality of images including blood vessels; generating three-dimensional first blood vessel profile data by using a first set of images including a first image and a second image of the plurality of images; generating three-dimensional second blood vessel profile data by using a second set of images including a third image and a fourth image; identifying a first coordinate value indicating a common point based on the first set of images and the second set of images; identifying a second coordinate value in the first blood vessel profile data corresponding to the common point based on the first coordinate value; identifying a third coordinate value in the second blood vessel profile data corresponding to the common point based on the first coordinate value; and acquiring a third blood vessel profile data by merging the first blood vessel profile data and the second blood vessel profile data based on the second coordinate value and the third coordinate value.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a method for generating three-dimensional vascular profile data and an electronic device.

Background Art

[0002] In the medical field, by analyzing medical images obtained using X-ray, CT (Computed Tomography) imaging, angiography, etc., lesions of a subject to be imaged (e.g., a patient) can be diagnosed. For example, vascular lesions can be diagnosed by analyzing angiography images. However, it is difficult to accurately diagnose lesions such as myocardial ischemia caused by coronary artery stenosis only by analyzing two-dimensional angiography images. For example, even if the stenosis degree of the coronary artery is judged to be strong in imaging, it may not significantly affect the actual blood flow and may not induce myocardial ischemia. Therefore, it is difficult to judge the ischemia that has occurred in the myocardium only based on the stenosis degree of the coronary artery analyzed from two-dimensional angiography images.

[0003] On the other hand, in order to quickly and accurately diagnose vascular lesions such as coronary artery stenosis, blood flow characteristic values such as FFR (Fractional Flow Reserve) can be used. Also, three-dimensional vascular profile data can be used to predict blood flow characteristic values. Therefore, in order to quickly and accurately analyze and diagnose vascular lesions, the development of a technique for generating three-dimensional vascular profile data using a plurality of two-dimensional images is required.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The present disclosure provides a method and an electronic device for generating three-dimensional vascular profile data for solving the above problems.

Means for Solving the Problems

[0006] The present disclosure can be implemented in various ways including a method, an apparatus (system), and / or a computer program.

[0007] According to an embodiment of the present disclosure, a method for generating three-dimensional vascular profile data performed by at least one processor includes: acquiring a plurality of images including blood vessels; generating three-dimensional first vascular profile data using a first set of images including a first image and a second image among the plurality of images; generating three-dimensional second vascular profile data using a second set of images including a third image and a fourth image among the plurality of images; identifying a first coordinate value indicating a common point based on at least one of the first set of images and at least one of the second set of images; identifying a second coordinate value in the first vascular profile data corresponding to the common point based on the identified first coordinate value; identifying a third coordinate value in the second vascular profile data corresponding to the common point based on the identified first coordinate value; and acquiring three-dimensional third vascular profile data by merging at least the first vascular profile data and the second vascular profile data based on at least the second coordinate value and the third coordinate value.

[0008] According to an embodiment of the present disclosure, a method for generating three-dimensional vascular profile data performed by at least one processor includes: obtaining a plurality of images including blood vessels; using a first image and a second image among the plurality of images to generate three-dimensional first vascular profile data; using a second image and a third image among the plurality of images to generate three-dimensional second vascular profile data; identifying a first coordinate value corresponding to a first point of a blood vessel from the second vascular profile data; identifying a second coordinate value from the second image based on the first coordinate value; identifying a third coordinate value corresponding to the first point of the blood vessel from the first vascular profile data based on the second coordinate value; and obtaining three-dimensional third vascular profile data by merging at least the first vascular profile data and the second vascular profile data based on at least the third coordinate value.

[0009] According to an embodiment of the present disclosure, a computer program for executing, by a computer, the method for generating the three-dimensional vascular profile data described above can be provided.

[0010] 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 is configured to: obtain a plurality of images including blood vessels; generate three-dimensional first blood vessel profile data using a first set of images including a first image and a second image among the plurality of images; generate three-dimensional second blood vessel profile data using a second set of images including a third image and a fourth image among the plurality of images; identify a first coordinate value indicating a common point based on at least one of the first set of images and at least one of the second set of images; identify a second coordinate value in the first blood vessel profile data corresponding to the common point based on the identified first coordinate value; identify a third coordinate value in the second blood vessel profile data corresponding to the common point based on the identified first coordinate value; and include instructions for obtaining three-dimensional third blood vessel profile data by merging at least the first blood vessel profile data and the second blood vessel profile data based on at least the second coordinate value and the third coordinate value.

[0011] 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 is configured to obtain a plurality of images including blood vessels, generate three-dimensional first blood vessel profile data using a first image and a second image among the plurality of images, generate three-dimensional second blood vessel profile data using the second image and a third image among the plurality of images, identify a first coordinate value corresponding to a first point of the blood vessel from the second blood vessel profile data, identify a second coordinate value from the second image based on the first coordinate value, identify a third coordinate value corresponding to the first point of the blood vessel from the first blood vessel profile data based on the second coordinate value, and include instructions for obtaining three-dimensional third blood vessel profile data by merging at least the first blood vessel profile data and the second blood vessel profile data based on at least the third coordinate value.

Advantages of the Invention

[0012] According to some embodiments of the present disclosure, by generating three-dimensional blood vessel profile data using a plurality of two-dimensional images, blood flow characteristic values can be easily predicted, and the predicted blood flow characteristic values can be used to support rapid and accurate analysis and diagnosis of blood vessel lesions.

[0013] The effects of the present disclosure are not limited thereto, and other effects not mentioned should be clearly understood by those of ordinary skill in the technical field to which the present disclosure pertains (hereinafter referred to as "those skilled in the art") from the description of the claims.

Brief Description of the Drawings

[0014] Embodiments of the present disclosure will be described based on the following attached drawings. Here, similar reference numerals indicate similar 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

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

DETAILED DESCRIPTION OF THE INVENTION

[0015] <SUMMARY OF THE INVENTION> According to one embodiment, the plurality of images can include a plurality of angiographic images taken from different viewing angles.

[0016] According to one embodiment, the step of identifying a first coordinate value indicating a common point can include outputting at least one of a first set of images and at least one of a second set of images, receiving user input for the common point in at least one of the output first set of images and at least one of the second set of images, and identifying the first coordinate value based on the received user input.

[0017] According to one embodiment, the step of identifying a first coordinate value indicating a common point can include inputting at least one of a first set of images and at least one of a second set of images into a CIP (Common Image Point) extraction model to automatically detect the common point, and identifying the first coordinate value based on the detected common point.

[0018] According to one embodiment, a method for generating three-dimensional vascular profile data can further include: generating three-dimensional fourth vascular profile data using a third set of images including a fifth image and a sixth image among a plurality of images; identifying fourth coordinate values indicating a common point based on at least one of the third set of images; identifying fifth coordinate values in the fourth vascular profile data corresponding to the common point based on the identified fourth coordinate values; and obtaining three-dimensional fifth vascular profile data by merging at least the third vascular profile data and the fourth vascular profile data based on at least the fifth coordinate values.

[0019] According to one embodiment, a first point of a blood vessel can include a boundary point where a value indicating the degree to which a specific region of the blood vessel is identified from a third image is less than a predetermined value between the proximal portion and the distal portion of the blood vessel.

[0020] According to one embodiment, a method for generating three-dimensional vascular profile data further includes predicting a blood flow characteristic value of a blood vessel using the third vascular profile data, where the blood flow characteristic value is associated with a first blood flow characteristic value predicted using the second vascular profile data from the proximal portion of the blood vessel to the first point of the blood vessel, and from the first point of the blood vessel to the distal portion of the blood vessel, is associated with a second blood flow characteristic value predicted using the first vascular profile data with the first blood flow characteristic value corresponding to the first point of the blood vessel as an initial value.

[0021] According to one embodiment, a method for generating three-dimensional vascular profile data may further include: generating three-dimensional fourth vascular profile data using a first image and a fourth image among a plurality of images; identifying three-dimensional fourth coordinate values corresponding to a second point of a blood vessel from third vascular profile data; identifying two-dimensional fifth coordinate values from the first image based on the fourth coordinate values; identifying three-dimensional sixth coordinate values corresponding to the second point of the blood vessel from the fourth vascular profile data based on the fifth coordinate values; and obtaining three-dimensional fifth vascular profile data by merging at least the third vascular profile data and the fourth vascular profile data based on at least the sixth coordinate values.

[0022] According to one embodiment, a method for generating three-dimensional vascular profile data may further include: generating three-dimensional sixth vascular profile data using a first image and a fifth image among a plurality of images; identifying three-dimensional seventh coordinate values corresponding to a third point of a blood vessel from the sixth vascular profile data; identifying two-dimensional eighth coordinate values from the first image based on the seventh coordinate values; identifying three-dimensional ninth coordinate values corresponding to the third point of the blood vessel from the fourth vascular profile data based on the eighth coordinate values; and the step of obtaining fifth vascular profile data may include obtaining fifth vascular profile data by merging at least the third vascular profile data, the fourth vascular profile data, and the sixth vascular profile data based on at least the sixth coordinate values and the ninth coordinate values.

[0023] According to one embodiment, a method for generating three-dimensional vascular profile data further includes generating three-dimensional fourth vascular profile data using a second image and a fourth image among a plurality of images; identifying three-dimensional fourth coordinate values corresponding to a second point of a blood vessel from the fourth vascular profile data; identifying two-dimensional fifth coordinate values from the first image based on the fourth coordinate values; and identifying three-dimensional sixth coordinate values corresponding to the second point of the blood vessel from the first vascular profile data based on the fifth coordinate values. The step of obtaining third vascular profile data can include obtaining the third vascular profile data by merging at least the first vascular profile data, the second vascular profile data, and the fourth vascular profile data based on at least the third coordinate values and the sixth coordinate values.

[0024] According to one embodiment, a method for generating three-dimensional vascular profile data further includes generating three-dimensional fourth vascular profile data using a first image and a fourth image among a plurality of images; identifying three-dimensional fourth coordinate values corresponding to a second point of a blood vessel from the fourth vascular profile data; identifying two-dimensional fifth coordinate values from the first image based on the fourth coordinate values; and identifying three-dimensional sixth coordinate values corresponding to the second point of the blood vessel from the first vascular profile data based on the fifth coordinate values. The step of obtaining third vascular profile data can include obtaining the third vascular profile data by merging at least the first vascular profile data, the second vascular profile data, and the fourth vascular profile data based on at least the third coordinate values and the sixth coordinate values.

[0025] <Detailed Description of the Invention> Hereinafter, specific contents for implementing the present disclosure will be described in detail based on the accompanying drawings. However, in the following description, specific descriptions of known functions and configurations will be omitted if they may unnecessarily obscure the gist of the present disclosure.

[0026] In the accompanying drawings, the same or corresponding components are given the same reference numerals. Also, in the description of the following embodiments, redundant descriptions of the same or corresponding components may be omitted. However, even if the description of a component is omitted, such a component should not be construed as not being included in a certain embodiment.

[0027] The advantages and features of the disclosed embodiments, and the methods for achieving them, will become clear by referring to the embodiments described below with reference to 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 so that the present disclosure is complete and so that the present disclosure enables those skilled in the art to accurately recognize the category of the invention.

[0028] The terms used in the present disclosure will be briefly explained, and the embodiments of the disclosure will be specifically described. The terms used in the present disclosure are selected as general terms that are currently widely used as much as possible while considering their functions in the present disclosure. However, this may change depending on the intentions or precedents of those skilled in the relevant art, the emergence of new technologies, etc. Also, in certain cases, there may be terms arbitrarily selected by the applicant, and the meanings of these will be described in detail in the description part of the invention. Therefore, the terms used in the present disclosure should be defined based on the meaning that the term has and the overall content of the present disclosure, rather than simply as the name of a term.

[0029] In the present disclosure, unless specifically specified in the context, singular expressions include plural expressions, and plural expressions can include singular expressions. Throughout the specification, if a certain part includes a certain component, this means that, unless otherwise stated to the contrary, it does not exclude other components and can further include other components.

[0030] Also, the terms "module" or "section" used in the specification mean software or hardware components, and the "module" or "section" performs a certain 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 on an addressable storage medium or to cause one or more processors to execute. Thus, by way of example, the "module" or "section" can include at least one of software components, object-oriented software components, class components, components such as task components, and processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. Components and "modules" or "sections" can be combined with a smaller number of other components and "modules" or "sections" that provide further internal functionality, or can be further separated into additional components and "modules" or "sections".

[0031] According to an embodiment of the present disclosure, a "module" or a "unit" may be implemented by a processor and a memory. The "processor" should be broadly interpreted 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 also refer to an application-specific integrated circuit (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 any other such configuration combination. Also, the "memory" should be broadly interpreted 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 programmable read-only memory (EEPROM), flash memory, magnetic or optical data storage devices, registers, etc. When a processor can read information from / to the memory, the memory is said to be in electronic communication with the processor. The memory integrated with the processor is in electronic communication with the processor.

[0032] Also, terms such as first, second, A, B, (a), (b), etc. used in the following embodiments, etc. are only used to distinguish one component from another component, and the essence, order, procedure, etc. of the component are not limited by the terms.

[0033] Also, in the following examples and the like, if a certain component is "connected", "coupled", or "joined" to another component, it can be directly connected or joined to each other, but it should be understood that other components can also be "connected", "coupled", or "joined" between the components.

[0034] Also, "comprise (comprise, comprising)" used in the following examples and the like does not exclude the presence or addition of one or more other components, steps, operations, and / or elements.

[0035] Hereinafter, various embodiments of the present disclosure will be described in detail based on the accompanying drawings.

[0036] FIG. 1 is a diagram showing an example of an electronic device for generating three-dimensional vascular profile data according to an embodiment of the present disclosure. Referring to FIG. 1, the electronic device 100 can generate three-dimensional vascular profile data 120 based on a plurality of images 110 including blood vessels. Here, the plurality of images 110 including blood vessels can include all types of images, such as X-ray images, ultrasonic images, chest radiographs, CT (Computed Tomography) images, PET (Positron Emission Tomography) images, MRI (Magnetic Resonance Imaging) images, Sonography (Ultrasound, US) images, fMRI (functional Magnetic Resonance Imaging) images, pathological tissue images (digital pathology Whole Slide Image, WSI), DBT (Digital Breast Tomosynthesis) images, etc., as medical images. As an example, each of the plurality of images 110 including blood vessels can include a medical image in which the blood vessels of the target patient are photographed with a contrast agent administered to the target patient. Further, the vascular profile data 120 can include not only data representing the shape of the blood vessels, but also the data itself of the shape of the blood vessels (for example, a three-dimensionally reconstructed blood vessel model), or data corresponding to the shape of the blood vessels (for example, FFR data corresponding to the three-dimensional blood vessel model).

[0037] In FIG. 1, although a storage system communicable with the electronic device 100 is not shown, the electronic device 100 can be connected to or configured to communicate with one or more storage systems. A storage system connected to or configured to communicate with the electronic device 100 can include a device or a cloud system that stores and manages various data related to the operation of generating three-dimensional vascular profile data 120 based on a plurality of images 110. In order to efficiently manage the data, the storage system can use a database to store and manage various data. Here, the various data can include any data related to the generation of the vascular profile data 120. For example, the various data can include, but are not limited to, a machine learning model, learning data, a plurality of images 110, etc. related to the generation of the vascular profile data 120.

[0038] The electronic device 100 can acquire a plurality of images 110 including blood vessels. Then, the electronic device 100 can generate a plurality of three-dimensional vascular profile data using at least two of the plurality of images 110. For example, the electronic device 100 can generate first three-dimensional vascular profile data using a first image and a second image among the plurality of images 110, and can generate second three-dimensional vascular profile data using a second image and a third image among the plurality of images 110. At this time, among the plurality of images 110, there may be an image that is commonly used when generating a plurality of vascular profile data, which can be referred to as a bridge image in the following description. For example, when generating the first vascular profile data, the first image and the second image are used, and when generating the second vascular profile data, the second image and the third image are used, the second image can be a bridge image. Here, one or two or more bridge images can be used according to the method of generating the three-dimensional vascular profile data.

[0039] As described above, when a plurality of vascular profile data (e.g., first vascular profile data and second vascular profile data) are generated using at least one bridge image, the electronic device 100 can merge the plurality of vascular profile data to obtain three-dimensional vascular profile data. For example, the electronic device 100 can merge the first vascular profile data and the second vascular profile data to obtain third vascular profile data. At this time, the electronic device 100 can merge the plurality of vascular profile data using the bridge image. For example, the electronic device 100 can identify a first coordinate value corresponding to a specific point of a blood vessel from any one of the plurality of vascular profile data. Here, the specific point of the blood vessel can include a boundary point at which it is determined whether the blood vessel can be identified. For example, the specific point of the blood vessel can include a boundary point at which a value indicating the degree to which a specific region of the blood vessel is identified from the image is less than a predetermined value between the proximal part and the distal part of the blood vessel. Thereafter, the electronic device 100 can identify a second coordinate value from the bridge image based on the identified first coordinate value. For example, the electronic device 100 can identify a two-dimensional second coordinate value corresponding to the three-dimensional first coordinate value. Next, the electronic device 100 can identify a third coordinate value corresponding to the specific point of the blood vessel from another one of the plurality of vascular profile data based on the identified second coordinate value. For example, the electronic device 100 can identify a third coordinate value in another one of the vascular profile data corresponding to the first coordinate value in any one of the vascular profile data using the second coordinate value in the commonly used bridge image. Thereafter, the electronic device 100 can merge the plurality of vascular profile data based on the identified third coordinate value. For example, the electronic device 100 can merge the first vascular profile data and the second vascular profile data generated using the bridge image in common to obtain three-dimensional third vascular profile data.

[0040] FIG. 2 is a diagram for explaining the configuration of an electronic device 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 the like, and may further include at least one other component. As an example, the electronic device 100 may further include a display. At this time, the electronic device 100 may display at least one of a medical image obtained by photographing a blood vessel (for example, a plurality of images 110 in FIG. 1) or blood vessel profile data 120 on the display.

[0041] The memory 210 may store various data used by at least one other component of the electronic device 100 (for example, the processor 220). The data may include, for example, input data or output data for software (or a program) and related instructions.

[0042] The memory 210 may include any non-transitory computer-readable recording medium. According to one embodiment, the memory 210 may include a permanent mass storage device such as a ROM (read only memory), a disk drive, an SSD (solid state drive), and a flash memory. As another example, a permanent mass storage device such as a ROM, an SSD, a flash memory, and a disk drive may be included in the electronic device 100 as a separate permanent storage device distinct from the memory 210. Also, an operating system and at least one program code (for example, an instruction word such as generation of blood vessel profile data installed and driven in the electronic device 100) may be stored in the memory 210. In FIG. 2, the memory 210 shows a single memory, but this is for convenience of explanation, and the memory 210 may include a plurality of memories and / or buffer memories.

[0043] Software components and the like can be loaded from a computer-readable recording medium separate from the memory 210. Such a separate computer-readable recording medium can include a recording medium directly connectable to the electronic device 100, and can include, for example, computer-readable recording media such as a floppy (registered trademark) drive, a disk, a tape, a DVD / CD-ROM drive, and a memory card. As another example, software components and the like can be loaded into the memory 210 via the communication module 230 rather than a computer-readable recording medium. For example, at least one program is a computer program (for example, a program for data transfer such as a medical image in which blood vessels are photographed) installed by a file provided by a file distribution system that distributes developer or application installation files via the communication module 230, and can be loaded into the memory 210.

[0044] The processor 220 can execute software (or a program) to control at least one other component (for example, 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 a part of the data processing or operation, the processor 220 can load instructions or data received from another component (for example, the communication module 230) into the volatile memory, process the instructions or data stored in the volatile memory, and store the result data in the non-volatile memory.

[0045] Processor 220 can be configured to process 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, processor 220 can generate three-dimensional vascular profile data. Thereafter, processor 220 can store the generated three-dimensional vascular profile data in memory 210, display it on the display of electronic device 100, or transfer it to an external electronic device via communication module 230. Alternatively, processor 220 can perform additional analysis operations such as predicting blood flow characteristic values using the three-dimensional vascular profile data. In FIG. 2, processor 220 is shown as a single processor, which is for convenience of explanation, and processor 220 can include multiple processors.

[0046] Communication module 230 can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device 100 and an external electronic device, and the performance of communication via the established communication channel. For example, communication module 230 can provide the configuration and functions for the electronic device 100 and an external electronic device (e.g., a user terminal or a cloud server) to communicate with each other via 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 transferred to the external electronic device via the communication module 230 and the network and via the communication module of the external electronic device. For example, the electronic device 100 can receive a medical image of the blood vessels of a subject taken by an external electronic device via the communication module 230.

[0047] The input / output interface 240 can be a means for interfacing with the electronic device 100 or with a device (not shown) for input or output that the electronic device 100 can include. For example, the input / output interface 240 can include at least one of a PCI express interface and an Ethernet (registered trademark) interface. In FIG. 2, the input / output interface 240 is shown as an element configured separately from the processor 220, but is not limited thereto, and can be configured to be included in the processor 220.

[0048] According to one embodiment, the processor 220 can perform functions related to the generation of three-dimensional vascular profile data. The processor 220 can execute at least one computer-readable program included in the memory 210 to perform functions related to the generation of three-dimensional vascular profile data. Here, the at least one program acquires a plurality of images including blood vessels, generates three-dimensional first vascular profile data using a first image and a second image among the plurality of images, generates three-dimensional second vascular profile data using the second image and a third image among the plurality of images, identifies a first coordinate value corresponding to a first point of the blood vessel from the second vascular profile data, identifies a second coordinate value from the second image based on the first coordinate value, identifies a third coordinate value corresponding to the first point of the blood vessel from the first vascular profile data based on the second coordinate value, and can include instructions for merging at least the first vascular profile data and the second vascular profile data based on at least the third coordinate value to obtain three-dimensional third vascular profile data. In the following description, for convenience of explanation, the fact that the processor 220 executes at least one program to perform functions related to the generation of three-dimensional vascular profile data can be described in association with the processor 220 performing functions related to the generation of three-dimensional vascular profile data. For example, the fact that the at least one program includes instructions related to the generation of three-dimensional vascular profile data can be described in association with the processor 220 performing functions related to the generation of three-dimensional vascular profile data.

[0049] FIG. 3 is a diagram for explaining the configuration of a processor of an electronic device according to an embodiment of the present disclosure. Referring to FIG. 3, the processor 220 can generate three-dimensional vascular profile data (e.g., the vascular profile data 120 in FIG. 1) based on a plurality of images including blood vessels (e.g., the plurality of images 110 in FIG. 1). For this purpose, the processor 220 can include an image acquisition unit 310, a vascular profile data generation unit 320, a specific point identification unit 330, and a vascular profile data merging unit 340. However, the types of components included in the processor 220 are classified according to functions related to the generation of three-dimensional vascular profile data, and the types and numbers thereof are not limited thereto. Also, at least one of the components included in the processor 200 can be embodied in the form of instruction words stored in a memory (e.g., the memory 210 in FIG. 2).

[0050] The image acquisition unit 310 can acquire a plurality of images including blood vessels (e.g., the plurality of images 110 in FIG. 1). According to an embodiment, the processor 220 can acquire a medical image of a blood vessel of a target patient while administering a contrast agent to the target patient. For example, the plurality of images can include a plurality of angiographic images taken from different viewing angles. Such medical images can be received from a storage system (e.g., a hospital system, an electronic medical record, a prescription transmission system, a medical image system, a test information system, a local / cloud storage system, etc.) connected to or communicably configured with the electronic device, an internal memory, and / or a user terminal. The image acquisition unit 310 can provide at least one of the acquired plurality of images to the vascular profile data generation unit 320, the specific point identification unit 330, and / or the vascular profile data merging unit 340.

[0051] The blood vessel profile data generation unit 320 can generate a plurality of three-dimensional blood vessel profile data using at least two of the plurality of images acquired by the image acquisition unit 310. For example, the blood vessel profile data generation unit 320 can generate the first three-dimensional blood vessel profile data using the first image and the second image among the plurality of images. Additionally or alternatively, the blood vessel profile data generation unit 320 can generate the second three-dimensional blood vessel profile data using the second image and the third image among the plurality of images.

[0052] The specific point identification unit 330 can identify specific points of blood vessels included in the image. According to one embodiment, the specific points of the blood vessels can include boundary points where the determination of the identifiability of the blood vessels is made. For example, the specific points of the blood vessels can include boundary points where a value indicating the degree to which a specific region of the blood vessel is identified from the image is less than a predetermined value between the proximal part and the distal part of the blood vessel. According to other embodiments, the specific points of the blood vessels can refer to common points in at least two images, and for example, can refer to branch points, but are not limited thereto.

[0053] The blood vessel profile data merging unit 340 can merge a plurality of blood vessel profile data to obtain three-dimensional blood vessel profile data. For example, the blood vessel profile data merging unit 340 can merge the first blood vessel profile data and the second blood vessel profile data to obtain the third blood vessel profile data. According to one embodiment, the blood vessel profile data merging unit 340 can merge a plurality of blood vessel profile data using a bridge image. Here, the bridge image can refer to an image that is commonly used when generating a plurality of blood vessel profile data used for merging. For example, when the first image and the second image are used when generating the first blood vessel profile data, and the second image and the third image are used when generating the second blood vessel profile data, the second image can be the bridge image. Here, one or more bridge images can be used depending on the method of generating the three-dimensional blood vessel profile data.

[0054] According to another embodiment, the blood vessel profile data merging unit 340 can generate three-dimensional blood vessel profile data by merging the first blood vessel profile data and the second blood vessel profile data using at least one image used in the generation of the first blood vessel profile data and at least one image used in the generation of the second blood vessel profile data at common points. A method of merging a plurality of three-dimensional blood vessel profile data using such common points to generate new three-dimensional blood vessel profile data will be described later with reference to FIGS. 15 to 17.

[0055] Examining the process of merging the blood vessel profile data, the blood vessel profile data merging unit 340 can identify a first coordinate value corresponding to a specific point of the blood vessel from any one of the plurality of blood vessel profile data. Here, the specific point of the blood vessel can be identified by the specific point identification unit 330. Next, the blood vessel profile data merging unit 340 can identify a second coordinate value from the bridge image based on the identified first coordinate value. For example, the blood vessel profile data merging unit 340 can identify a two-dimensional second coordinate value corresponding to the three-dimensional first coordinate value. Thereafter, the blood vessel profile data merging unit 340 can identify a third coordinate value corresponding to the specific point of the blood vessel from another one of the plurality of blood vessel profile data based on the identified second coordinate value. For example, the blood vessel profile data merging unit 340 can identify a third coordinate value in another one of the blood vessel profile data corresponding to the first coordinate value in any one of the blood vessel profile data using the second coordinate value in the commonly used bridge image. Thereafter, the blood vessel profile data merging unit 340 can merge the plurality of blood vessel profile data based on the identified third coordinate value.

[0056] According to one embodiment, the processor 220 can predict the blood flow characteristic value of a blood vessel using the merged blood vessel profile data (e.g., the third blood vessel profile data). The blood flow characteristic value can include, for example, FFR (Fractional Flow Reserve). FFR can refer to a value obtained by evaluating the pressure difference between the distal part and the proximal part of a lesion site due to the decrease in coronary perfusion pressure when there is a lesion in a blood vessel. According to one embodiment, the processor 220 can predict the blood flow characteristic value of a blood vessel through a machine learning model that takes the blood vessel profile data as input. The machine learning model can include any model used to infer the ground truth for a given input. According to one 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 the plurality of nodes included in the machine learning model. Here, the weight values can include any parameter associated with the machine learning model. The machine learning model of the present disclosure can be a model learned by various learning methods. For example, various learning methods such as supervised learning, semi-supervised learning, unsupervised learning (or self-learning), and reinforcement learning are 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.

[0057] According to one embodiment, the blood flow characteristic value of the blood vessel predicted using the blood vessel profile data is associated with the first blood flow characteristic value predicted using the second blood vessel profile data from the proximal part of the blood vessel to a specific point of the blood vessel. Also, the blood flow characteristic value of the blood vessel is associated with the second blood flow characteristic value predicted using the first blood vessel profile data with the first blood flow characteristic value corresponding to the specific point of the blood vessel as the initial value from the specific point of the blood vessel to the distal part of the blood vessel.

[0058] For a method of obtaining vascular profile data using more than three images, various methods are used depending on the image used as the bridge image among the plurality of images. Such methods can include, for example, a chain coupling method, a one bridge coupling method, a side coupling method, or a method combining these. The method of obtaining vascular profile data using more than three images will be described in detail based on FIGS. 7 to 13.

[0059] FIG. 4 is a diagram for explaining a first method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure, FIG. 5 is a diagram schematizing image information included in the vascular profile data in the first method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure, and FIG. 6 is a diagram for explaining a method of predicting a blood flow characteristic value in the first method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure. Referring to FIGS. 4 to 6, a processor (e.g., the processor 220 in FIGS. 2 and 3) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can generate three-dimensional vascular profile data 432, 434, 422 based on a plurality of images 412, 414, 416 including blood vessels. In FIGS. 4 and 5, a method of obtaining vascular profile data using three images will be described. In FIG. 5, a plurality of image data 512, 514, 516 used at the time of generating the vascular profile data 432, 434, 422 are associated with the plurality of images 412, 414, 416 and are schematized in a linear form for convenience of explanation. For example, the first image data 512 is associated with the first image 412, the second image data 514 is associated with the second image 414, and the third image data 516 is associated with the third image 416.

[0060] To describe a method of obtaining vascular profile data, the processor can generate three-dimensional first vascular profile data 432 using a first image 412 and a second image 414. For example, the processor can generate first vascular profile data 432 using first image data 512 and second image data 514. Also, the processor can generate three-dimensional second vascular profile data 434 using the second image 414 and a third image 416. For example, the processor can generate second vascular profile data 434 using second image data 514 and third image data 516. At this time, the second image 414 can be a bridge image commonly used when generating the first vascular profile data 432 and the second vascular profile data 434.

[0061] When the first vascular profile data 432 and the second vascular profile data 434 are generated using the bridge image, the processor can merge the first vascular profile data 432 and the second vascular profile data 434 to obtain three-dimensional third vascular profile data 422. More specifically, the processor can identify a first coordinate value 434a corresponding to a first point of the blood vessel from the second vascular profile data 434. For example, the processor can identify a first coordinate value 434a corresponding to a first point of the blood vessel by assuming that the proximal part of the blood vessel is the origin of the three-dimensional coordinate system from the second vascular profile data 434. Also, the processor can obtain a predicted blood flow characteristic value (f3) at the first coordinate value 434a corresponding to the first point of the blood vessel. Here, the first point of the blood vessel can include a boundary point at which the identifiability of the blood vessel is determined. For example, the first point of the blood vessel can include a boundary point at which a value indicating the degree to which a specific region of the blood vessel is identified from the second vascular profile data 434 or the image used when generating the second vascular profile data 434 (e.g., the second image 414 or the third image 416) is less than a predetermined value between the proximal part and the distal part of the blood vessel.

[0062] Thereafter, based on the first coordinate value 434a, the processor can identify the second coordinate value 514a from the second image 414 which is a bridge image. For example, the processor can identify the two-dimensional second coordinate value 514a corresponding to the three-dimensional first coordinate value 434a. According to one embodiment, the processor can use a method such as back projection to identify the two-dimensional second coordinate value 514a in the second image 414 from the three-dimensional first coordinate value 434a.

[0063] Next, based on the second coordinate value 514a, the processor can identify the third coordinate value 432a corresponding to the first point of the blood vessel from the first blood vessel profile data 432. For example, the processor can use the second coordinate value 514a in a commonly used bridge image (e.g., the second image 414) to identify the third coordinate value 432a in the first blood vessel profile data 432 corresponding to the first coordinate value 434a in the second blood vessel profile data 434. Also, the processor can inject (or substitute) the predicted blood flow characteristic value (f3) at the first coordinate value 434a corresponding to the first point of the blood vessel into the third coordinate value 432a in the first blood vessel profile data 432.

[0064] Thereafter, the processor can obtain three-dimensional third blood vessel profile data 422 by merging at least first blood vessel profile data 432 and second blood vessel profile data 434 based on at least a third coordinate value 432a. In this way, by merging the first blood vessel profile data 432 and the second blood vessel profile data 434 generated based on the second image 414 which is a bridge image, three-dimensional third blood vessel profile data 422 can be obtained. At this time, for the third blood vessel profile data 422, from the proximal part of the blood vessel to the first point of the blood vessel, it can be obtained using the second blood vessel profile data 434, and from the first point of the blood vessel to the distal part of the blood vessel, it can be obtained using the first blood vessel profile data 432. In such a process, the processor can recalculate the blood flow characteristic value of the blood vessel in the third blood vessel profile data 422. For example, since the predicted blood flow characteristic value (f3) at the first coordinate value 434a corresponding to the first point of the blood vessel is injected (or substituted) into the third coordinate value 432a in the first blood vessel profile data 432, the processor can recalculate the blood flow characteristic value with the injected (or substituted) value (f3) as the initial value. Thereby, as shown in FIG. 6, the blood flow characteristic value of the blood vessel is associated with the first group of blood flow characteristic values (f1→f2→f3) predicted using the second blood vessel profile data from the proximal part of the blood vessel to the first point of the blood vessel, and from the first point of the blood vessel to the distal part of the blood vessel, it is associated with the second group of blood flow characteristic values (f3→f11→f12) predicted using the first blood vessel profile data with the first blood flow characteristic value (f3) corresponding to the first point of the blood vessel as the initial value.

[0065] FIG. 7 is a diagram for explaining a second method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure, and FIG. 8 is a diagram schematically showing image information included in the vascular profile data in the second method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure. Referring to FIGS. 7 and 8, a processor (e.g., the processor 220 in FIGS. 2 and 3) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can generate three-dimensional vascular profile data 732, 734, 736, 722, 724 based on a plurality of images 712, 714, 716, 718 including blood vessels. In FIGS. 7 and 8, the chain coupling method is described among the methods of acquiring vascular profile data using four images. In FIG. 8, a plurality of image data 812, 814, 816, 818 used for generating the vascular profile data 732, 734, 736, 722, 724 are associated with the plurality of images 712, 714, 716, 718 and are schematically shown in a straight line form for convenience of explanation. For example, the first image data 812 is associated with the first image 712, the second image data 814 is associated with the second image 714, the third image data 816 is associated with the third image 716, and the fourth image data 818 is associated with the fourth image 718.

[0066] To explain the method (chain coupling method) for obtaining blood vessel profile data, the processor can generate three-dimensional first blood vessel profile data 732 using the first image 712 and the second image 714. For example, the processor can generate the first blood vessel profile data 732 using the first image data 812 and the second image data 814. Also, the processor can generate three-dimensional second blood vessel profile data 734 using the second image 714 and the third image 716. For example, the processor can generate the second blood vessel profile data 734 using the second image data 814 and the third image data 816. Also, the processor can generate three-dimensional fourth blood vessel profile data 736 using the first image 712 and the fourth image 718. For example, the processor can generate the fourth blood vessel profile data 736 using the first image data 812 and the fourth image data 818. At this time, the second image 714 is the first bridge image commonly used when generating the first blood vessel profile data 732 and the second blood vessel profile data 734, and the first image 712 can be the second bridge image commonly used when generating the first blood vessel profile data 732 and the fourth blood vessel profile data 736.

[0067] When the first blood vessel profile data 732 and the second blood vessel profile data 734 are generated using the first bridge image, the processor can merge the first blood vessel profile data 732 and the second blood vessel profile data 734 to obtain three-dimensional third blood vessel profile data 722. The process of merging the first blood vessel profile data 732 and the second blood vessel profile data 734 to obtain the three-dimensional third blood vessel profile data 722 is the same as or similar to the process of obtaining blood vessel profile data described based on FIGS. 4 to 6, so a detailed description thereof will be omitted.

[0068] Thereafter, the processor can identify the three-dimensional fourth coordinate value 722a corresponding to the second point of the blood vessel from the third blood vessel profile data 722. Further, the processor can obtain the predicted blood flow characteristic value at the fourth coordinate value 722a corresponding to the second point of the blood vessel. Here, the second point of the blood vessel is a point different from the first point of the blood vessel described based on FIGS. 4 to 6, and similar to the first point of the blood vessel, it can include a boundary point at which it is determined whether the blood vessel can be identified. For example, the second point of the blood vessel can include a boundary point at which a value indicating the degree to which a specific region of the blood vessel is identified from the third blood vessel profile data 722 or an image (e.g., the first image 712, the second image 714, or the third image 716) used when generating the third blood vessel profile data 722 is less than a predetermined value between the proximal part and the distal part of the blood vessel.

[0069] Next, the processor can identify the two-dimensional fifth coordinate value 812a from the first image 712, which is the second bridge image, based on the fourth coordinate value 722a. For example, the processor can identify the two-dimensional fifth coordinate value 812a corresponding to the three-dimensional fourth coordinate value 722a. According to one embodiment, the processor can identify the two-dimensional fifth coordinate value 812a in the first image 712 from the three-dimensional fourth coordinate value 722a using, for example, a back-projection method.

[0070] Thereafter, the processor can identify the three-dimensional sixth coordinate value 736a corresponding to the second point of the blood vessel from the fourth blood vessel profile data 736 based on the fifth coordinate value 812a. For example, the processor can identify the sixth coordinate value 736a in the fourth blood vessel profile data 736 corresponding to the fourth coordinate value 722a in the third blood vessel profile data 722 using the fifth coordinate value 812a in the commonly used second bridge image (e.g., the first image 712). Further, the processor can inject (or substitute) the predicted blood flow characteristic value at the fourth coordinate value 722a corresponding to the second point of the blood vessel into the sixth coordinate value 736a in the fourth blood vessel profile data 736.

[0071] Next, the processor can obtain three-dimensional fifth blood vessel profile data 724 by merging at least third blood vessel profile data 722 and fourth blood vessel profile data 736 based on at least a sixth coordinate value 736a. In this way, the first blood vessel profile data 732 and the second blood vessel profile data 734 generated based on the second image 714, which is the first bridge image, can be merged to obtain three-dimensional third blood vessel profile data 722, and the third blood vessel profile data 722 and the fourth blood vessel profile data 736 generated (or merged) based on the first image 712, which is the second bridge image, can be merged to obtain three-dimensional fifth blood vessel profile data 724. Since such a process is schematized to continuously connect the images, it can be called a chain connection method. Also, at this time, for the fifth blood vessel profile data 724, from the proximal part of the blood vessel to the second point of the blood vessel, it can be obtained using the third blood vessel profile data 722, and from the second point of the blood vessel to the distal part of the blood vessel, it can be obtained using the fourth blood vessel profile data 736. In such a process, the processor can recalculate the blood flow characteristic value of the blood vessel in the fifth blood vessel profile data 724. For example, since the predicted blood flow characteristic value at the fourth coordinate value 722a corresponding to the second point of the blood vessel is injected (or substituted) into the sixth coordinate value 736a in the fourth blood vessel profile data 736, the processor can recalculate the blood flow characteristic value with the injected (or substituted) value as the initial value.

[0072] FIG. 9 is a diagram for explaining a third method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure, and FIG. 10 is a diagram schematically showing image information included in the vascular profile data in the third method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure. Referring to FIGS. 9 and 10, a processor (e.g., the processor 220 in FIGS. 2 and 3) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can generate three-dimensional vascular profile data 932, 934, 936, 922 based on a plurality of images 912, 914, 916, 918 including blood vessels. FIGS. 9 and 10 illustrate the one-bridge connection method among the methods of obtaining vascular profile data using four images. In FIG. 10, a plurality of image data 1012, 1014, 1016, 1018 used in generating the vascular profile data 932, 934, 936, 922 are associated with the plurality of images 912, 914, 916, 918 and are schematically shown in the form of straight lines for convenience of explanation. For example, the first image data 1012 is associated with the first image 912, the second image data 10104 is associated with the second image 914, the third image data 1016 is associated with the third image 916, and the fourth image data 1018 is associated with the fourth image 918.

[0073] To explain the method of obtaining vascular profile data (one-bridge connection method), the processor can generate three-dimensional first vascular profile data 932 using the first image 912 and the second image 914. For example, the processor can generate the first vascular profile data 932 using the first image data 1012 and the second image data 1014. Also, the processor can generate three-dimensional second vascular profile data 934 using the second image 914 and the third image 916. For example, the processor can generate the second vascular profile data 934 using the second image data 1014 and the third image data 1016. Also, the processor can generate three-dimensional fourth vascular profile data 936 using the second image 914 and the fourth image 918. For example, the processor can generate the fourth vascular profile data 936 using the second image data 1014 and the fourth image data 1018. At this time, the second image 914 can be a bridge image commonly used when generating the first vascular profile data 932, the second vascular profile data 934, and the fourth vascular profile data 936.

[0074] When the first vascular profile data 932, the second vascular profile data 934, and the fourth vascular profile data 936 are generated using the bridge image, the processor can merge the first vascular profile data 932, the second vascular profile data 934, and the fourth vascular profile data 936 to obtain three-dimensional third vascular profile data 922. That is, the processor can merge three or more vascular profile data using one bridge image.

[0075] More specifically, the processor can identify a first coordinate value 934a corresponding to a first point of the blood vessel from the second blood vessel profile data 934. Further, the processor can obtain a predicted blood flow characteristic value at the first coordinate value 934a corresponding to the first point of the blood vessel. Similarly, the processor can identify a fourth coordinate value 936a corresponding to a second point of the blood vessel from the fourth blood vessel profile data 936. Here, the first point and the second point of the blood vessel can include boundary points at which the identifiability of the blood vessel is determined. For example, the first point of the blood vessel can include a boundary point at which a value indicating the degree to which a specific region of the blood vessel is identified from the second blood vessel profile data 934 or an image (e.g., the second image 914 or the third image 916) used when generating the second blood vessel profile data 934 is less than a predetermined value between the proximal part and the distal part of the blood vessel. Also, the second point of the blood vessel can include a boundary point at which a value indicating the degree to which a specific region of the blood vessel is identified from the fourth blood vessel profile data 936 or an image (e.g., the second image 914 or the fourth image 918) used when generating the fourth blood vessel profile data 936 is less than a predetermined value between the proximal part and the distal part of the blood vessel.

[0076] Next, the processor can identify a second coordinate value 1014a from the second image 914, which is a bridge image, based on the first coordinate value 934a. For example, the processor can identify a two-dimensional second coordinate value 1014a corresponding to the three-dimensional first coordinate value 934a. Also, the processor can identify a fifth coordinate value 1014b from the second image 914, which is a bridge image, based on the fourth coordinate value 936a. For example, the processor can identify a two-dimensional fifth coordinate value 1014b corresponding to the three-dimensional fourth coordinate value 936a. According to one embodiment, the processor can identify the two-dimensional second coordinate value 1014a in the second image 914 from the three-dimensional first coordinate value 934a and the two-dimensional fifth coordinate value 1014b in the second image 914 from the three-dimensional fourth coordinate value 936a using, for example, a back-projection method.

[0077] Thereafter, based on the second coordinate value 1014a, the processor can identify a third coordinate value 932a corresponding to the first point of the blood vessel from the first blood vessel profile data 932. For example, the processor can use the second coordinate value 1014a in a commonly used bridge image (e.g., the second image 914) to identify the third coordinate value 932a in the first blood vessel profile data 932 corresponding to the first coordinate value 934a in the second blood vessel profile data 934. Also, based on the fifth coordinate value 1014b, the processor can identify a sixth coordinate value 932b corresponding to the second point of the blood vessel from the first blood vessel profile data 932. For example, the processor can use the fifth coordinate value 1014b in a commonly used bridge image (e.g., the second image 914) to identify the sixth coordinate value 932b in the first blood vessel profile data 932 corresponding to the fourth coordinate value 936a in the fourth blood vessel profile data 936. Further, the processor can inject (or substitute) the predicted blood flow characteristic value at the first coordinate value 93a corresponding to the first point of the blood vessel into the third coordinate value 932a in the first blood vessel profile data 932, and inject (or substitute) the predicted blood flow characteristic value at the fourth coordinate value 936a corresponding to the second point of the blood vessel into the sixth coordinate value 932b in the first blood vessel profile data 932.

[0078] Next, the processor can obtain the third blood vessel profile data 922 by merging at least the first blood vessel profile data 932, the second blood vessel profile data 934, and the fourth blood vessel profile data 936 based on at least the third coordinate value 932a and the sixth coordinate value 932b. In this way, the first blood vessel profile data 932, the second blood vessel profile data 934, and the fourth blood vessel profile data 936 generated based on the second image 914, which is a single bridge image, can be merged to obtain the three-dimensional third blood vessel profile data 922. At this time, the third blood vessel profile data 922 is obtained using the fourth blood vessel profile data 936 from the proximal part of the blood vessel to the second point of the blood vessel, the second blood vessel profile data 934 from the second point of the blood vessel to the first point of the blood vessel, and the first blood vessel profile data 932 from the first point of the blood vessel to the distal part of the blood vessel. In such a process, the processor can recalculate the blood flow characteristic value of the blood vessel in the third blood vessel profile data 922. For example, since the predicted blood flow characteristic value at the first coordinate value 934a corresponding to the first point of the blood vessel is injected (or substituted) into the third coordinate value 932a in the first blood vessel profile data 932, and the predicted blood flow characteristic value at the fourth coordinate value 936a corresponding to the second point of the blood vessel is injected (or substituted) into the sixth coordinate value 932b in the first blood vessel profile data 932, the processor can recalculate the blood flow characteristic value with the value injected (or substituted) as the initial value.

[0079] FIG. 11 is a diagram for explaining a fourth method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure, and FIG. 12 is a diagram schematically showing image information included in the vascular profile data in the fourth method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure. Referring to FIGS. 11 and 12, a processor (e.g., the processor 220 in FIGS. 2 and 3) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can generate three-dimensional vascular profile data 1132, 1134, 1136, 1122 based on a plurality of images 1112, 1114, 1116, 1118 including blood vessels. FIGS. 11 and 12 illustrate a side coupling method among methods of acquiring vascular profile data using four images. In FIG. 12, a plurality of image data 1212, 1214, 1216, 1218 used for generating the vascular profile data 1132, 1134, 1136, 1122 are associated with the plurality of images 1112, 1114, 1116, 1118 and are schematically shown in a straight line form for convenience of explanation. For example, the first image data 1212 is associated with the first image 1112, the second image data 1214 is associated with the second image 1114, the third image data 1216 is associated with the third image 1116, and the fourth image data 1218 is associated with the fourth image 1118.

[0080] To explain the method of obtaining vascular profile data (side bonding method), the processor can generate three-dimensional first vascular profile data 1132 using the first image 1112 and the second image 1114. For example, the processor can generate the first vascular profile data 1132 using the first image data 1212 and the second image data 1214. Also, the processor can generate three-dimensional second vascular profile data 1134 using the second image 1114 and the third image 1116. For example, the processor can generate the second vascular profile data 1134 using the second image data 1214 and the third image data 1216. Also, the processor can generate three-dimensional fourth vascular profile data 1136 using the first image 1112 and the fourth image 1118. For example, the processor can generate the fourth vascular profile data 1136 using the first image data 1212 and the fourth image data 1218. At this time, the second image 1114 is the first bridge image commonly used when generating the first vascular profile data 1132 and the second vascular profile data 1134, and the first image 1112 can be the second bridge image commonly used when generating the first vascular profile data 1132 and the fourth vascular profile data 1136.

[0081] When the first vascular profile data 1132, the second vascular profile data 1134, and the fourth vascular profile data 1136 are generated using the bridge image, the processor can merge the first vascular profile data 1132, the second vascular profile data 1134, and the fourth vascular profile data 1136 to obtain three-dimensional third vascular profile data 1122.

[0082] More specifically, the processor can identify a first coordinate value 1134a corresponding to a first point of the blood vessel from the second blood vessel profile data 1134. Further, the processor can obtain a predicted blood flow characteristic value at the first coordinate value 1134a corresponding to the first point of the blood vessel. Similarly, the processor can identify a fourth coordinate value 1136a corresponding to a second point of the blood vessel from the fourth blood vessel profile data 1136. Here, the first and second points of the blood vessel can include boundary points at which the identifiability of the blood vessel is determined. For example, the first point of the blood vessel can include a boundary point at which a value indicating the degree to which a specific region of the blood vessel is identified from the second blood vessel profile data 1134 or an image (e.g., the second image 1114 or the third image 1116) used at the time of generating the second blood vessel profile data 1134 is less than a predetermined value between the proximal portion and the distal portion of the blood vessel. Also, the second point of the blood vessel can include a boundary point at which a value indicating the degree to which a specific region of the blood vessel is identified from the fourth blood vessel profile data 1136 or an image (e.g., the first image 1112 or the fourth image 1118) used at the time of generating the fourth blood vessel profile data 1136 is less than a predetermined value between the proximal portion and the distal portion of the blood vessel.

[0083] Next, the processor can identify a second coordinate value 1214a from the second image 1114, which is a bridge image, based on the first coordinate value 1134a. For example, the processor can identify a two-dimensional second coordinate value 1214a corresponding to the three-dimensional first coordinate value 1134a. Further, the processor can identify a fifth coordinate value 1212a from the first image 1112, which is a bridge image, based on the fourth coordinate value 1136a. For example, the processor can identify a two-dimensional fifth coordinate value 1212a corresponding to the three-dimensional fourth coordinate value 1136a. According to one embodiment, the processor can identify the two-dimensional second coordinate value 1214a in the second image 1114 from the three-dimensional first coordinate value 1134a and the two-dimensional fifth coordinate value 1212a in the first image 1112 from the three-dimensional fourth coordinate value 1136a using, for example, a backprojection method.

[0084] Thereafter, the processor can identify a third coordinate value 1132a corresponding to the first point of the blood vessel from the first blood vessel profile data 1132 based on the second coordinate value 1214a. For example, the processor can use the second coordinate value 1214a in the commonly used first bridge image (e.g., the second image 1114) to identify the third coordinate value 1132a in the first blood vessel profile data 1132 corresponding to the first coordinate value 1134a in the second blood vessel profile data 1134. Also, the processor can identify a sixth coordinate value 1132b corresponding to the second point of the blood vessel from the first blood vessel profile data 1132 based on the fifth coordinate value 1212a. For example, the processor can use the fifth coordinate value 1212a in the commonly used second bridge image (e.g., the first image 1112) to identify the sixth coordinate value 1132b in the first blood vessel profile data 1132 corresponding to the fourth coordinate value 1136a in the fourth blood vessel profile data 1136. Further, the processor can inject (or substitute) the predicted blood flow characteristic value at the first coordinate value 1134a corresponding to the first point of the blood vessel into the third coordinate value 1132a in the first blood vessel profile data 1132, and inject (or substitute) the predicted blood flow characteristic value at the fourth coordinate value 1136a corresponding to the second point of the blood vessel into the sixth coordinate value 1132b in the first blood vessel profile data 1132.

[0085] Next, the processor can obtain the third vascular profile data 1122 by merging at least the first vascular profile data 1132, the second vascular profile data 1134, and the fourth vascular profile data 1136 based on at least the third coordinate value 1132a and the sixth coordinate value 1132b. In this way, centering on the first vascular profile data 1132 generated based on the first image 1112 and the second image 1114 which are two bridge images, the first vascular profile data 1132, the second vascular profile data 1134, and the fourth vascular profile data 1136 are merged. Since such a process is schematized to combine both vascular profile data (for example, the second vascular profile data 1134 and the fourth vascular profile data 1136) with the central vascular profile data (for example, the first vascular profile data 1132), it can be called a side combination method. Also, at this time, the third vascular profile data 1122 can be obtained using the fourth vascular profile data 1136 from the proximal part of the blood vessel to the second point of the blood vessel, using the second vascular profile data 1134 from the second point of the blood vessel to the first point of the blood vessel, and using the first vascular profile data 1132 from the first point of the blood vessel to the distal part of the blood vessel. In such a process, the processor can recalculate the blood flow characteristic value of the blood vessel in the third vascular profile data 1122. For example, since the predicted blood flow characteristic value at the first coordinate value 1134a corresponding to the first point of the blood vessel is injected (or substituted) into the third coordinate value 1132a in the first vascular profile data 1132, and the predicted blood flow characteristic value at the fourth coordinate value 1136a corresponding to the second point of the blood vessel is injected (or substituted) into the sixth coordinate value 1132b in the first vascular profile data 1132, the processor can recalculate the blood flow characteristic value with the injected (or substituted) value as the initial value.

[0086] FIG. 13 is a diagram for explaining a fifth method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure. Referring to FIG. 13, a processor (e.g., the processor 220 in FIGS. 2 and 3) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can generate three-dimensional vascular profile data 1332, 1334, 1336, 1338, 1322, 1324 based on a plurality of images 1312, 1314, 1316, 1318, 1320 including blood vessels. In FIG. 13, a method of obtaining vascular profile data using five images is described, but the number of images is not limited to this. In FIG. 13, a method of obtaining vascular profile data by combining a chain connection method and a one-bridge connection method is described.

[0087] To explain the method of obtaining vascular profile data (a method combining a chain connection method and a one-bridge connection method), the processor can generate three-dimensional first vascular profile data 1332 using the first image 1312 and the second image 1314. Also, the processor can generate three-dimensional second vascular profile data 1334 using the second image 1314 and the third image 1316. Also, the processor can generate three-dimensional fourth vascular profile data 1336 using the first image 1312 and the fourth image 1318. Also, the processor can generate three-dimensional sixth vascular profile data 1338 using the first image 1312 and the fifth image 1320. At this time, the second image 1314 is a first bridge image commonly used when generating the first vascular profile data 1332 and the second vascular profile data 1334, and the first image 1312 can be a second bridge image commonly used when generating the first vascular profile data 1332, the fourth vascular profile data 1336, and the sixth vascular profile data 1338.

[0088] When the first bridge image is used to generate the first vascular profile data 1332 and the second vascular profile data 1334, the processor can merge the first vascular profile data 1332 and the second vascular profile data 1334 to obtain three-dimensional third vascular profile data 1322. The process of merging the first vascular profile data 1332 and the second vascular profile data 1334 to obtain the three-dimensional third vascular profile data 1322 may be the same as or similar to the process of obtaining vascular profile data described based on FIGS. 4 to 6.

[0089] Next, the processor can merge the third vascular profile data 1322, the fourth vascular profile data 1336, and the sixth vascular profile data 1338 generated (or merged) based on the second bridge image to obtain three-dimensional fifth vascular profile data 1324. The process of merging the third vascular profile data 1322, the fourth vascular profile data 1336, and the sixth vascular profile data 1338 to obtain the three-dimensional fifth vascular profile data 1324 may be the same as or similar to the process of obtaining vascular profile data described based on FIGS. 9 and 10.

[0090] More specifically, the processor can identify the three-dimensional fourth coordinate value corresponding to the second point of the blood vessel from the third vascular profile data 1322. Also, the processor can identify the three-dimensional seventh coordinate value corresponding to the third point of the blood vessel from the sixth vascular profile data 1338. Further, the processor can obtain the predicted blood flow characteristic value at the fourth coordinate value corresponding to the second point of the blood vessel and the predicted blood flow characteristic value at the seventh coordinate value corresponding to the third point of the blood vessel.

[0091] Next, based on the fourth coordinate value, the processor can identify the two-dimensional fifth coordinate value from the first image 1312, which is the second bridge image. For example, the processor can identify the two-dimensional fifth coordinate value corresponding to the three-dimensional fourth coordinate value. Also, based on the seventh coordinate value, the processor can identify the two-dimensional eighth coordinate value from the first image 1312, which is the second bridge image. For example, the processor can identify the two-dimensional eighth coordinate value corresponding to the three-dimensional seventh coordinate value. According to one embodiment, the processor can use a back-projection method or the like to identify the two-dimensional fifth coordinate value and the eighth coordinate value in the first image 1312 from each of the three-dimensional fourth coordinate value and the seventh coordinate value.

[0092] Thereafter, based on the fifth coordinate value, the processor can identify the three-dimensional sixth coordinate value corresponding to the second point of the blood vessel from the fourth blood vessel profile data 1336. For example, the processor can use the fifth coordinate value in the second bridge image (e.g., the first image 1312) commonly used to identify the sixth coordinate value in the fourth blood vessel profile data 1336 corresponding to the fourth coordinate value in the third blood vessel profile data 1322. Also, based on the eighth coordinate value, the processor can identify the three-dimensional ninth coordinate value corresponding to the third point of the blood vessel from the fourth blood vessel profile data 1336. For example, the processor can use the eighth coordinate value in the second bridge image (e.g., the first image 1312) commonly used to identify the ninth coordinate value in the fourth blood vessel profile data 1336 corresponding to the seventh coordinate value in the sixth blood vessel profile data 1338. Also, the processor can inject (or substitute) the predicted blood flow characteristic value at the fourth coordinate value corresponding to the second point of the blood vessel into the sixth coordinate value in the fourth blood vessel profile data 1336, and inject (or substitute) the predicted blood flow characteristic value at the seventh coordinate value corresponding to the third point of the blood vessel into the ninth coordinate value in the fourth blood vessel profile data 1336.

[0093] Next, the processor can obtain fifth vascular profile data 1324 by merging at least third vascular profile data 1322, fourth vascular profile data 1336, and sixth vascular profile data 1338 based on at least a sixth coordinate value and a ninth coordinate value. Further, the processor can recalculate the blood flow characteristic value of the blood vessel in the fifth vascular profile data 1324. For example, the predicted blood flow characteristic value at the fourth coordinate value corresponding to the second point of the blood vessel is injected (or substituted) into the sixth coordinate value in the fourth vascular profile data 1336, and the predicted blood flow characteristic value at the seventh coordinate value corresponding to the third point of the blood vessel is injected (or substituted) into the ninth coordinate value in the fourth vascular profile data 1336. Therefore, the processor can recalculate the blood flow characteristic value with the initial value being the injected (or substituted) value.

[0094] FIG. 14 is a diagram for explaining a method of generating three-dimensional vascular profile data according to an embodiment of the present disclosure. Referring to FIG. 14, a processor (e.g., the processor 220 in FIGS. 2 and 3) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can obtain a plurality of images in step S1410. For example, the processor can obtain a plurality of images (e.g., the plurality of images 110 in FIG. 1) including blood vessels. According to an embodiment, the plurality of images can include a plurality of angiographic images taken from different viewing angles.

[0095] In step S1420, the processor can generate three-dimensional first vascular profile data using the first image and the second image. For example, the processor can generate three-dimensional first vascular profile data using the first image and the second image among the plurality of images.

[0096] In step S1430, the processor can generate three-dimensional second blood vessel profile data using the second image and the third image. For example, the processor can generate three-dimensional second blood vessel profile data using the second image and the third image among a plurality of images. At this time, the second image can be a bridge image commonly used when generating the first blood vessel profile data and the second blood vessel profile data.

[0097] In step S1440, the processor can identify a first coordinate value corresponding to a first point of the blood vessel from the second blood vessel profile data. For example, the processor can identify a first coordinate value corresponding to a first point of the blood vessel by assuming that the proximal part of the blood vessel is the origin of the three-dimensional coordinate system from the second blood vessel profile data. In addition, the processor can obtain a predicted blood flow characteristic value at the first coordinate value corresponding to the first point of the blood vessel. Here, the first point of the blood vessel can include a boundary point at which the identifiability of the blood vessel is determined. For example, the first point of the blood vessel can include a boundary point at which a value indicating the degree to which a specific region of the blood vessel is identified from the second blood vessel profile data or an image used when generating the second blood vessel profile data (for example, the second image or the third image) is less than a predetermined value between the proximal part and the distal part of the blood vessel.

[0098] In step S1450, the processor can identify a second coordinate value from the second image based on the first coordinate value. That is, the processor can identify a second coordinate value corresponding to the first coordinate value from the second image which is a bridge image. For example, the processor can identify a two-dimensional second coordinate value corresponding to the three-dimensional first coordinate value. According to one embodiment, the processor can identify a two-dimensional second coordinate value in the second image from the three-dimensional first coordinate value using a back-projection method or the like.

[0099] In step S1460, the processor can identify a third coordinate value corresponding to a first point of the blood vessel from the first blood vessel profile data based on the second coordinate value. For example, the processor can identify a third coordinate value in the first blood vessel profile data corresponding to the first coordinate value in the second blood vessel profile data by using the second coordinate value in the second image which is the bridge image. Also, the processor can inject (or substitute) the predicted blood flow characteristic value at the first coordinate value corresponding to the first point of the blood vessel into the third coordinate value in the first blood vessel profile data.

[0100] In step S1470, the processor can obtain three-dimensional third blood vessel profile data by merging at least the first blood vessel profile data and the second blood vessel profile data based on at least the third coordinate value. For example, the processor can obtain three-dimensional third blood vessel profile data by merging the first blood vessel profile data and the second blood vessel profile data generated based on the second image which is the bridge image. At this time, for the third blood vessel profile data, from the proximal part of the blood vessel to the first point of the blood vessel, it can be obtained using the second blood vessel profile data, and from the first point of the blood vessel to the distal part of the blood vessel, it can be obtained using the first blood vessel profile data. In such a process, the processor can recalculate the blood flow characteristic value of the blood vessel in the third blood vessel profile data. For example, since the predicted blood flow characteristic value at the first coordinate value corresponding to the first point of the blood vessel is injected (or substituted) into the third coordinate value in the first blood vessel profile data, the processor can recalculate the blood flow characteristic value with the injected (or substituted) value as the initial value. Thereby, the blood flow characteristic value of the blood vessel is associated with the first blood flow characteristic value predicted using the second blood vessel profile data from the proximal part of the blood vessel to the first point of the blood vessel, and from the first point of the blood vessel to the distal part of the blood vessel, it is associated with the second blood flow characteristic value predicted using the first blood vessel profile data with the first blood flow characteristic value corresponding to the first point of the blood vessel as the initial value.

[0101] The above-described flowchart and the above description are merely examples and can be implemented differently in some embodiments. For example, in some embodiments, the order of each step can be changed, some steps can be repeatedly performed, some steps can be omitted, and some steps can be added.

[0102] FIG. 15 is a diagram for explaining a first method of generating three-dimensional vascular profile data according to another embodiment of the present disclosure. Referring to FIG. 15, a processor (e.g., the processor 220 in FIGS. 2 and 3) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can generate three-dimensional vascular profile data 1520, 1522, 1524 based on a plurality of images 1512, 1514, 1516, 1518 including blood vessels. In FIG. 15, it shows that three-dimensional vascular profile data is generated using the first image 1512 and the second image 1514 included in the first set of images and the third image 1516 and the fourth image 1518 included in the second set of images, but it is not limited thereto. For example, the first set of images can include one or three or more images, and the second set of images can include one or three or more images.

[0103] The electronic device can generate three-dimensional first vascular profile data 1520 using a first set of images including a first image 1512 and a second image 1514. Also, the electronic device can generate three-dimensional second vascular profile data 1522 using a second set of images including a third image 1516 and a fourth image 1518. At this time, the first image 1512 and the second image 1514 included in the first set of images can refer to angiographic images taken from different viewing angles. Also, the third image 1516 and the fourth image 1518 included in the second set of images can refer to angiographic images taken from different viewing angles. Additionally or alternatively, the first image 1512 and the second image 1514 included in the first set of images and the third image 1516 and the fourth image 1518 included in the second set of images can each refer to angiographic images taken from different viewing angles.

[0104] The electronic device can merge at least the three-dimensional first vascular profile data 1520 and the three-dimensional second vascular profile data 1522 to generate three-dimensional third vascular profile data 1524. For this purpose, the electronic device can identify a first coordinate value indicating a common location based on at least one of the first set of images and at least one of the second set of images. Based on the first coordinate value thus identified, a second coordinate value in the first vascular profile data 1520 corresponding to the common location can be identified. Also, based on the identified first coordinate value, a third coordinate value in the second vascular profile data 1522 corresponding to the common location can be identified. Here, the common location can refer to any location within a blood vessel indicating the same region or point in at least two images, and for example, can refer to a branch portion, but is not limited thereto.

[0105] According to one embodiment, in order to identify a first coordinate value indicating a common point, the electronic device can output at least one of a first set of images and at least one of a second set of images. For example, the second image 1514 among the first set of images and the third image 1516 among the second set of images can be output or displayed by an output device (e.g., a display, etc.) of the electronic device. Then, the electronic device can receive a user input for the common point from the second image 1514 and the third image 1516 through an input device (e.g., a touch screen, a mouse, a keyboard, etc.) of the electronic device. Based on such a user input, the first coordinate value can be identified.

[0106] Additionally or alternatively, the electronic device can input at least one of the first set of images and at least one of the second set of images into a CIP (Common Image Point) extraction model to automatically detect a common point. Here, the CIP extraction model can refer to any known algorithm and / or artificial neural network model for receiving at least two images and extracting common points within the two images. For example, the CIP extraction model can be an artificial neural network model trained to extract at least one branching portion within a blood vessel as a common point in at least two images including the received blood vessels, but is not limited thereto.

[0107] The blood flow characteristic value in the thus generated third blood vessel profile data 1524 can be predicted and provided to the user. According to one embodiment, the common point can include a boundary point where a value indicating the degree to which a specific region of the blood vessel is identified from an image including the common point is less than a predetermined value between the proximal portion and the distal portion of the blood vessel. At this time, the blood flow characteristic value from the proximal portion of the blood vessel to the common point of the blood vessel is associated with a first blood flow characteristic value predicted using the first blood vessel profile data 1520 or the second blood vessel profile data 1522. Also, the blood flow characteristic value from the common point of the blood vessel to the distal portion of the blood vessel is associated with a second blood flow prediction value predicted using blood vessel profile data not used for the first blood flow characteristic value, with the first blood flow characteristic value corresponding to the common point of the blood vessel as an initial value.

[0108] FIG. 16 is a diagram for explaining a second method of generating three-dimensional vascular profile data according to another embodiment of the present disclosure. Referring to FIG. 16, a processor (e.g., the processor 220 in FIGS. 2 and 3) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can generate three-dimensional vascular profile data 1622, 1624, 1626, 1636, 1638 based on a plurality of images 1612, 1614, 1616, 1618, 1632, 1634 including blood vessels. Here, each of the first to fourth images 1612, 1614, 1616, 1618 in FIG. 16 is associated with the first to fourth images 1512, 1514, 1516, 1518 in FIG. 15. Similarly, each of the first to third vascular profile data 1622, 1624, 1626 in FIG. 16 is associated with the first to third vascular profile data 1520, 1522, 1524 in FIG. 15. In FIG. 16, in order to explain the chain connection method based on common points among the methods of generating vascular profile data using six images, the configurations overlapping with FIG. 15 are omitted, and the configurations different from FIG. 15 are described below.

[0109] The electronic device can generate three-dimensional fourth vascular profile data 1636 using a third set of images including a fifth image 1632 and a sixth image 1634. In FIG. 16, although it shows generating three-dimensional vascular profile data using the fifth image 1632 and the sixth image 1634 included in the third set of images, it is not limited thereto. For example, the third set of images can include one or three or more images. Also, the fifth image 1632 and the sixth image 1634 included in the third set of images can refer to angiography images taken from different viewing angles.

[0110] Thereafter, the electronic device can identify a fourth coordinate value indicating the same location as the common location used to generate the third vascular profile data 1626 based on at least one of the third set of images. For example, user input for the coordinate value corresponding to the common location can be received from the sixth image 1634. Additionally or alternatively, the electronic device can input at least one of the third set of images, along with at least one of the first set of images and at least one of the second set of images, into the CIP extraction model described in FIG. 15 to identify the common location.

[0111] Based on the fourth coordinate value thus identified, a fifth coordinate value in the fourth vascular profile data 1636 corresponding to the common location can be identified. The electronic device can merge the three-dimensional third vascular profile data 1626 and the three-dimensional fourth vascular profile data 1636 based on at least the fifth coordinate value to obtain three-dimensional fifth vascular profile data.

[0112] FIG. 17 is a diagram for explaining a method of generating three-dimensional vascular profile data according to another embodiment of the present disclosure. Referring to FIG. 17, a processor (e.g., the processor 220 in FIGS. 2 and 3) of an electronic device (e.g., the electronic device 100 in FIGS. 1 and 2) can obtain a plurality of images in step S1710. For example, the processor can obtain a plurality of images (e.g., the plurality of images 110 in FIG. 1) including blood vessels. According to one embodiment, the plurality of images can include a plurality of angiographic images taken from different viewing angles.

[0113] In step S1720, the processor can generate three-dimensional first vascular profile data using a first set of images including a first image and a second image among the plurality of images. Also, in step S1730, the processor can generate three-dimensional second vascular profile data using a second set of images including a third image and a fourth image among the plurality of images.

[0114] In step S1740, the processor can identify a first coordinate value indicating a common point based on at least one image of the first set and at least one image of the second set. For this purpose, the processor can output at least one image of the first set and at least one image of the second set. Then, the processor can receive user input for the common point in at least one image of the output first set and at least one image of the second set, and can identify the first coordinate value based on the received user input. Additionally or alternatively, the processor can input at least one image of the first set and at least one image of the second set into a CIP extraction model to automatically detect the common point, and can identify the first coordinate value based on the detected common point.

[0115] In step S1750, the processor can identify a second coordinate value in the first vascular profile data corresponding to the common point based on the identified first coordinate value. Also, in step S1760, the processor can identify a third coordinate value in the second vascular profile data corresponding to the common point based on the identified first coordinate value. Then, in step S1770, the processor can merge at least the first vascular profile data and the second vascular profile data based on at least the second coordinate value and the third coordinate value to obtain three-dimensional third vascular profile data.

[0116] Additionally, the processor can generate three-dimensional fourth vascular profile data using a third set of images including a fifth image and a sixth image among the plurality of images. At this time, a fourth coordinate value indicating a common point can be identified based on at least one image of the third set. Then, the processor can identify a fifth coordinate value in the fourth vascular profile data corresponding to the common point based on the identified fourth coordinate value. The processor can merge at least the third vascular profile data and the fourth vascular profile data based on at least the fifth coordinate value to obtain three-dimensional fifth vascular profile data.

[0117] The above-mentioned flowchart and the above description are merely examples and can be implemented differently in some embodiments. For example, in some embodiments, the order of each step can be changed, some steps can be repeatedly performed, some steps can be omitted, or some steps can be added.

[0118] The above-mentioned method can be provided as a computer program stored in a computer-readable recording medium for execution by a computer. The medium can continuously store a computer-executable program, or temporarily store it for execution or download. Also, the medium can be various recording or storage means in a form where a single or multiple hardware components are combined, and is not limited to a medium directly connected to a certain computer system, and can exist distributed 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, etc. Also, examples of other media include application stores that distribute applications and recording media or storage media managed by sites, servers, etc. that supply or distribute other various software.

[0119] The methods, operations, or techniques of the present disclosure can be implemented by various means. For example, such techniques can be implemented in hardware, firmware, software, or combinations thereof. Those skilled in the art should understand that the various exemplary logical blocks, modules, circuits, and algorithm steps described by the disclosure of this application can be implemented in electronic hardware, computer software, or combinations of both. To clearly illustrate such mutual substitutions between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been generally described from their functional perspectives. Whether such functions are implemented as hardware or as software varies depending on the design requirements imposed on the specific application and the overall system. Those skilled in the art can also implement the functions described in various ways for each specific application, but such implementations should not be construed as departing from the scope of the present disclosure.

[0120] In a hardware implementation, the processing unit utilized for the execution of the technique can also be implemented 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 the present disclosure, computers, or combinations thereof.

[0121] Accordingly, the various illustrative logical blocks, modules, and circuits described by the present disclosure can be embodied or performed in any combination of a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gates or transistor logic, discrete hardware components, or the like designed to perform the functions described herein. The general-purpose processor can be a microprocessor, but alternatively, the processor can be any conventional processor, controller, microcontroller, or state machine. The processor can also be embodied as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors associated with a DSP core, or any other configuration.

[0122] In a firmware and / or software embodiment, the techniques can be embodied as instructions stored on a computer-readable medium such as RAM (random access memory), ROM (read-only memory), NVRAM (non-volatile random access memory), PROM (programmable read-only memory), EPROM (erasable programmable read-only memory), EEPROM (electrically erasable programmable read-only memory), flash memory, CD (compact disc), magnetic or optical data storage device, and the like. The instructions are executable by one or more processors such that the processors, among other things, can perform particular aspects of the functions described by the present disclosure.

[0123] When embodied as software, the techniques can be stored on a computer-readable medium as one or more instructions or code, or transferred via a computer-readable medium. A computer-readable medium includes any medium that facilitates transfer of a computer program from one location to another and includes both computer storage media and communication media. A storage media can be any available media accessible by a computer. By way of non-limiting example, 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 media that can be used to transfer or store the desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection can properly be termed a computer-readable medium.

[0124] For example, when software is transferred 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, radio and microwave, the coaxial cable, fiber optic cable, twisted pair, digital subscriber line, or wireless technologies such as infrared, radio and microwave are included in the definition of a medium. As used herein, disk and disc include CD, laser disk, optical disk, DVD (digital versatile disc), floppy disk and Blu-ray disk, where disk typically magnetically reproduces data, while disc optically reproduces data using a laser. Combinations thereof etc. must also be included within the scope of computer-readable media etc.

[0125] The software module can also reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other known form of storage medium. An exemplary storage medium can be connected to the processor such that the processor can read information from, or write information to, the storage medium. Alternatively, the storage medium can be integrated with the processor. The processor and the storage medium can also be present in an ASIC. The ASIC can be present in a user terminal. Alternatively, the processor and the storage medium can be present as individual components in the user terminal.

[0126] The foregoing embodiments have been described as utilizing aspects of the presently disclosed subject matter in one or more stand-alone computer systems, but the present disclosure is not so limited and can be embodied in any computing environment such as a network or a distributed computing environment. Further, aspects of the subject matter of the present disclosure can be embodied in multiple processing chips or devices, and storage can be similarly affected across multiple devices. Such devices can also include a PC, a network server, and a portable device.

[0127] Although the present disclosure has been described by way of some embodiments herein, various modifications and changes can be made within the scope that can be understood by those of ordinary skill in the art to which the invention of the present disclosure pertains without departing from the present disclosure. Also, such modifications and changes should be understood to fall within the scope of the claims appended hereto.

Description of Reference Numerals

[0128] 100 Electronic device 210 Memory 220 Processor 230 Communication module 240 Input / output interface

Claims

1. 1. A method for generating three-dimensional vascular profile data performed by at least one processor, comprising: acquiring a plurality of images including a blood vessel; generating three-dimensional first vascular profile data using a first set of images of the plurality of images, the first set including a first image and a second image; generating three-dimensional second vascular profile data using a second set of images of the plurality of images, the second set including a third image and a fourth image; identifying a first coordinate value indicative of a common point based on at least one of the first set of images and at least one of the second set of images; identifying a second coordinate value in the first vascular profile data that corresponds to the common point based on the identified first coordinate value; identifying a third coordinate value in the second vascular profile data that corresponds to the common point based on the identified first coordinate value; and a step of combining at least the first vascular profile data and the second vascular profile data based on at least the second coordinate values ​​and the third coordinate values ​​to obtain three-dimensional third vascular profile data.

2. The method of claim 1 , wherein the plurality of images comprises a plurality of angiographic images taken from different viewing angles.

3. The step of identifying a first coordinate value indicative of the common point comprises: outputting at least one of the first set of images and at least one of the second set of images; receiving user input for the common point on at least one of the output first set of images and at least one of the output second set of images; and identifying the first coordinate value based on the received user input.

4. The step of identifying a first coordinate value indicative of the common point comprises: inputting at least one of the first set of images and at least one of the second set of images into a CIP extraction model to automatically detect the common points; and identifying the first coordinate value based on the detected common point.

5. generating three-dimensional fourth vascular profile data using a third set of images of the plurality of images, the third set including a fifth image and a sixth image; identifying a fourth coordinate value indicative of the common point based on at least one of the images of the third set; identifying a fifth coordinate value in the fourth vascular profile data that corresponds to the common point based on the identified fourth coordinate value; The method for generating three-dimensional vascular profile data of claim 1 , further comprising: merging at least the third vascular profile data and the fourth vascular profile data based on at least the fifth coordinate value to obtain three-dimensional fifth vascular profile data.

6. 1. A method for generating three-dimensional vascular profile data performed by at least one processor, comprising: acquiring a plurality of images including a blood vessel; generating three-dimensional first vascular profile data using a first image and a second image of the plurality of images; generating three-dimensional second vascular profile data using the second and third images of the plurality of images; identifying a first coordinate value from the second vascular profile data corresponding to a first point of the blood vessel; identifying a second coordinate value from the second image based on the first coordinate value; identifying a third coordinate value from the first vascular profile data corresponding to a first point of the blood vessel based on the second coordinate value; and a step of merging at least the first vascular profile data and the second vascular profile data based on at least the third coordinate values ​​to obtain three-dimensional third vascular profile data.

7. The method of claim 6 , wherein the plurality of images comprises a plurality of angiographic images taken from different viewing angles.

8. The method for generating three-dimensional vascular profile data of claim 6, wherein the first point of the blood vessel includes a boundary point where a value indicating the degree to which a particular region of the blood vessel is identified from the third image is less than a predetermined value between the proximal and distal portions of the blood vessel.

9. using the third vascular profile data to predict a blood flow characteristic value of the blood vessel; The blood flow characteristic value is a first blood flow feature value predicted using the second vascular profile data from a proximal portion of the blood vessel to a first point of the blood vessel; The method for generating three-dimensional vascular profile data as described in claim 6, wherein a portion of the blood vessel from a first point to a distal portion of the blood vessel is associated with a second blood flow feature value predicted using the first vascular profile data, with the first blood flow feature value corresponding to the first point of the blood vessel being used as an initial value.

10. generating three-dimensional fourth vascular profile data using the first image and a fourth image of the plurality of images; identifying a third three-dimensional fourth coordinate value from the third vessel profile data corresponding to a second point of the vessel; identifying a two-dimensional fifth coordinate value from the first image based on the fourth coordinate value; identifying a three-dimensional sixth coordinate value from the fourth vascular profile data corresponding to a second point of the blood vessel based on the fifth coordinate value; The method for generating three-dimensional vascular profile data of claim 6, further comprising: merging at least the third vascular profile data and the fourth vascular profile data based on at least the sixth coordinate value to obtain three-dimensional fifth vascular profile data.

11. generating three-dimensional sixth vascular profile data using the first image and a fifth image of the plurality of images; identifying a three-dimensional seventh coordinate value from the sixth vessel profile data corresponding to a third point of the vessel; identifying a two-dimensional eighth coordinate value from the first image based on the seventh coordinate value; and identifying a ninth three-dimensional coordinate value from the fourth vascular profile data corresponding to a third point of the blood vessel based on the eighth coordinate value; The method for generating three-dimensional vascular profile data of claim 10, wherein the step of acquiring the fifth vascular profile data includes a step of acquiring the fifth vascular profile data by merging at least the third vascular profile data, the fourth vascular profile data, and the sixth vascular profile data based on at least the sixth coordinate value and the ninth coordinate value.

12. generating three-dimensional fourth vascular profile data using the second image and a fourth image of the plurality of images; identifying a fourth three-dimensional coordinate value from the fourth vessel profile data corresponding to a second point of the vessel; identifying a two-dimensional fifth coordinate value from the second image based on the fourth coordinate value; and identifying a third coordinate value from the first vascular profile data corresponding to a second point of the blood vessel based on the fifth coordinate value; 7. The method of generating three-dimensional vascular profile data of claim 6, wherein the step of acquiring third vascular profile data includes a step of acquiring the third vascular profile data by merging at least the first vascular profile data, the second vascular profile data, and the fourth vascular profile data based on at least the third coordinate value and the sixth coordinate value.

13. generating three-dimensional fourth vascular profile data using the first image and a fourth image of the plurality of images; identifying a fourth three-dimensional coordinate value from the fourth vessel profile data corresponding to a second point of the vessel; identifying a two-dimensional fifth coordinate value from the first image based on the fourth coordinate value; and identifying a third coordinate value from the first vascular profile data corresponding to a second point of the blood vessel based on the fifth coordinate value; 7. The method of generating three-dimensional vascular profile data of claim 6, wherein the step of acquiring third vascular profile data includes a step of acquiring the third vascular profile data by merging at least the first vascular profile data, the second vascular profile data, and the fourth vascular profile data based on at least the third coordinate value and the sixth coordinate value.

14. A computer readable computer program for carrying out the method according to any one of claims 1 to 13 on a computer.

15. In an electronic device, Memory, 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: Acquire multiple images including blood vessels, generating three-dimensional first vascular profile data using a first set of images of the plurality of images, the first set including a first image and a second image; generating three-dimensional second vascular profile data using a second set of images of the plurality of images, the second set including a third image and a fourth image; identifying a first coordinate value indicative of a common point based on at least one of the first set of images and at least one of the second set of images; identifying a second coordinate value in the first vascular profile data that corresponds to the common point based on the identified first coordinate value; identifying a third coordinate value in the second vascular profile data that corresponds to the common point based on the identified first coordinate value; An electronic device comprising instructions for merging at least the first vascular profile data and the second vascular profile data based on at least the second coordinate values ​​and the third coordinate values ​​to obtain three-dimensional third vascular profile data.

16. In an electronic device, Memory, 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: Acquire multiple images including blood vessels, generating three-dimensional first vascular profile data using a first image and a second image of the plurality of images; generating three-dimensional second vascular profile data using the second image and a third image of the plurality of images; identifying a first coordinate value from the second vessel profile data corresponding to a first point of the vessel; identifying a second coordinate value from the second image based on the first coordinate value; identifying a third coordinate value from the first vessel profile data corresponding to a first point of the vessel based on the second coordinate value; and instructions for merging at least the first vascular profile data and the second vascular profile data based on at least the third coordinate values ​​to obtain three-dimensional third vascular profile data.

Images