Method for calculating the ratio of blood flow to different blood vessels using vascular images and electronic device

Abstract

This disclosure relates to a method and electronic apparatus for calculating the ratio of blood flow rates by blood vessel using vascular images, which is performed by at least one processor. [Solution] A method for calculating the ratio of blood flow by blood vessel using vascular images includes the steps of: acquiring at least one vascular image; classifying multiple blood vessels from at least one vascular image; extracting geometric information for each of the multiple blood vessels from at least one vascular image; and calculating the ratio of blood flow by blood vessel based on the extracted values ​​as geometric information for each of the multiple blood vessels and a reference value for the geometric information for each of the multiple blood vessels, wherein the reference value may be set based on values ​​calculated from multiple subjects.

Description

Technical Field

[0001] The present disclosure relates to a method for calculating the ratio of blood flow rates for each blood vessel using vascular images and an electronic device.

Background Art

[0002] The coronary artery is an artery that surrounds the heart and can supply blood to the myocardium, which is the muscle of the heart. The amount of myocardium connected to the coronary artery can correspond to the amount of blood flowing through the artery, that is, the blood flow rate. Therefore, the situation where a disease occurring in the coronary artery substantially becomes a problem for a patient can ultimately occur when the blood flow rate supplied to the amount of myocardium is insufficient.

[0003] Conventional methods for measuring the amount of myocardium include a method of directly imaging a cross-section of the entire heart and tracing and summing up the regions corresponding to the myocardium in the whole image. However, this method requires CT imaging that is not essential for the procedure, and additional processes such as blood vessel segmentation are required to trace the myocardial region (or the amount of myocardium) responsible for each blood vessel.

[0004] Also, although blood flow rate is used when calculating the fractional flow reserve (FFR), the ratio of the region responsible for the corresponding blood vessel in the whole myocardium is not reflected in the calculation of this blood flow rate. For example, the blood flow rate can be calculated by estimating the reference diameter of the blood vessel, calculating the reference area based on the estimated diameter, and then multiplying the calculated area by an assumed blood velocity. However, this blood flow rate calculation method has limitations in that it cannot reflect the type of blood vessel, the ratio of the myocardial mass allocated to other blood vessels, the total volume of the blood vessels, the size of the patient's heart, etc. Therefore, there is a need to develop a technique for calculating the ratio of blood flow rates for each blood vessel using vascular images used in actual procedures such as coronary angiography (CAG) without CT imaging.

Prior Art Documents

Patent Documents

[0005] [Patent Document 1] Korean Registered Patent Publication No. 10-1939778 [Overview of the project] [Problems that the invention aims to solve]

[0006] This disclosure aims to provide a method for calculating the ratio of blood flow rates for different blood vessels using vascular images, and an electronic device, to solve the aforementioned problems. [Means for solving the problem]

[0007] This disclosure can be implemented in a variety of forms, including methods, apparatus (systems), and / or computer-readable recording media for storing computer-readable instructions.

[0008] According to one embodiment of the present disclosure, a method for calculating the ratio of blood flow by blood vessel using vascular images, performed by at least one processor, includes the steps of: acquiring at least one vascular image; classifying a plurality of blood vessels from the at least one vascular image; extracting geometric information for each of the plurality of blood vessels from the at least one vascular image; and calculating the ratio of blood flow by blood vessel based on the values ​​extracted as geometric information for each of the plurality of blood vessels and a reference value for the geometric information for each of the plurality of blood vessels, wherein the reference value may be set based on values ​​calculated from a plurality of subjects.

[0009] According to one embodiment of the present disclosure, the electronic device includes a memory and at least one processor connected to the memory and configured to execute computer-readable instructions stored in the memory, wherein the at least one processor is configured to acquire at least one vascular image, classify a plurality of blood vessels from the at least one vascular image, extract geometric information for each of the plurality of blood vessels from the at least one vascular image, and calculate the ratio of blood flow for each blood vessel based on the values ​​extracted as geometric information for each of the plurality of blood vessels and a reference value for the geometric information for each of the plurality of blood vessels, wherein the reference value may be set based on values ​​calculated from a plurality of subjects.

[0010] According to one embodiment of the present disclosure, a non-temporary computer-readable recording medium storing a computer-readable instruction is configured such that, when the instruction is executed by at least one processor, the at least one processor acquires at least one vascular image, classifies a plurality of blood vessels from the at least one vascular image, extracts geometric information for each of the plurality of blood vessels from the at least one vascular image, and calculates the ratio of blood flow by blood vessel based on the extracted values ​​as geometric information for each of the plurality of blood vessels and a reference value for the geometric information for each of the plurality of blood vessels, the reference value may be set based on values ​​calculated from a plurality of subjects.

[0011] According to some embodiments of this disclosure, by using vascular images used in the actual procedure without performing CT scans, not only are costs reduced, but it is also possible to support the calculation of the ratio of blood flow to each vessel more simply without unnecessary steps.

[0012] Furthermore, according to some embodiments of this disclosure, by using reference values ​​set based on values ​​calculated from multiple subjects for the geometric information of each of the multiple blood vessels, it may be possible to help calculate the ratio of blood flow to each blood vessel without the step of calculating myocardial mass.

[0013] Furthermore, according to certain embodiments of this disclosure, by using blood flow rates for each blood vessel, a more accurate fractional blood flow reserve can be calculated, thereby supporting more accurate lesion diagnosis.

[0014] The effects of this disclosure are not limited to those described above, and other effects not mentioned can be clearly understood by a person with ordinary skill in the art to which this disclosure pertains ("ordinary engineer") from the description of the claims.

[0015] According to one embodiment, geometric information may include at least one of diameter, length, volume, placement position, or placement direction.

[0016] According to one embodiment, the step of classifying multiple blood vessels may include the step of classifying the right coronary artery, the left anterior descending coronary artery, and the left circumflex coronary artery from at least one vascular image, or the step of classifying the right coronary artery and the left main coronary artery from at least one vascular image.

[0017] According to one embodiment, the step of calculating the ratio of blood flow rates by blood vessel may include the step of calculating the difference between a reference value and an extracted value for the geometric information of each of the multiple blood vessels, and the step of calculating the ratio of blood flow rates by blood vessel based on the difference calculated for each of the multiple blood vessels and reference distribution information of blood flow rates by blood vessel.

[0018] According to one embodiment, the difference between the reference value and the extracted value may include the ratio of the reference value to the extracted value or the ratio of the difference between the reference value and the extracted value to the extracted value.

[0019] According to one embodiment, a method for calculating the ratio of blood flow rates by blood vessel using vascular images may further include the step of reconstructing the three-dimensional shape of multiple blood vessels based on at least one vascular image.

[0020] According to one embodiment, geometric information may include at least one of diameter, length, volume, area, placement position, or placement direction.

[0021] According to one embodiment, the method for calculating the ratio of blood flow rates in blood vessels using blood vessel images may further include the step of estimating the blood flow rate in each blood vessel based on the ratio of blood flow rates in each blood vessel.

[0022] According to one embodiment, at least one blood vessel image may include an image taken by coronary angiography.

[0023] According to one embodiment, at least one processor may be configured to calculate the difference between a reference value and an extracted value, and calculate the ratio of blood flow rates in each blood vessel based on the differences calculated for each of the plurality of blood vessels and the reference distribution information of blood flow rates in each blood vessel.

[0024] According to one embodiment, at least one processor may be configured to reconstruct the three-dimensional shapes of a plurality of blood vessels based on at least one blood vessel image.

[0025] According to one embodiment, at least one processor may be configured to estimate the blood flow rate in each blood vessel based on the ratio of blood flow rates in each blood vessel.

[0026] According to one embodiment, the instruction may enable at least one processor to calculate the difference between a reference value and an extracted value, and calculate the ratio of blood flow rates in each blood vessel based on the differences calculated for each of the plurality of blood vessels and the reference distribution information of blood flow rates in each blood vessel.

[0027] According to one embodiment, the instruction may enable at least one processor to reconstruct the 3D shapes of a plurality of blood vessels based on at least one blood vessel image.

[0028] According to one embodiment, the instruction may enable at least one processor to estimate the blood flow rate in each blood vessel based on the ratio of blood flow rates in each blood vessel.

[0029] Embodiments of the present disclosure will be described with reference to the accompanying drawings described below, where like reference numerals indicate like elements, but are not limited thereto.

Brief Description of the Drawings

[0030] [Figure 1] This figure illustrates an electronic device for calculating the ratio of blood flow to different blood vessels using vascular images according to one embodiment of the present disclosure. [Figure 2] This figure illustrates the configuration of an electronic device according to one embodiment of the present disclosure. [Figure 3] This figure illustrates the configuration of a processor in an electronic device according to one embodiment of the present disclosure. [Figure 4] This figure illustrates a method for extracting geometric information from multiple classified blood vessels from a vascular image according to one embodiment of the present disclosure. [Figure 5] This figure illustrates a method for calculating the ratio of blood flow to different blood vessels using vascular images according to one embodiment of the present disclosure. [Figure 6] This figure illustrates another method for calculating the ratio of blood flow to different vessels using vascular images according to one embodiment of the present disclosure. [Figure 7] This figure illustrates a method for calculating the ratio of blood flow to different blood vessels using the geometric information of each of several blood vessels according to one embodiment of the present disclosure. [Figure 8] This figure illustrates a method for calculating the ratio of blood flow rates in different blood vessels using the respective diameters of multiple blood vessels according to one embodiment of the present disclosure. [Figure 9] This figure shows an artificial neural network model according to one embodiment of the present disclosure. [Modes for carrying out the invention]

[0031] The specific details for implementing this disclosure will be described below with reference to the attached drawings. However, in the following description, if there is a risk of unnecessarily obscuring the essence of this disclosure, specific descriptions of widely known functions and configurations will be omitted.

[0032] In the attached drawings, identical or corresponding components are given the same reference numerals. Furthermore, in the following description of embodiments, the description of identical or corresponding components may be omitted. However, the omission of technical details regarding a component does not mean that such a component is not included in a particular embodiment.

[0033] The advantages and features of the disclosed embodiments, and how they are achieved, will become clearer with reference to the embodiments described below, along with the accompanying drawings. However, this disclosure is not limited to the embodiments disclosed below and can be embodied in a variety of other distinct forms. These embodiments are provided only to complete the disclosure and to fully inform a person of the ordinary skill of the scope of the invention.

[0034] This specification will briefly explain the terminology used and then provide a detailed description of the disclosed embodiments. The terminology used herein has been selected to the greatest extent possible to be widely used and general terms, taking into account the function of this disclosure; however, this may change depending on the intent of the articulates in the relevant field, case law, the emergence of new technologies, etc. In some cases, the applicant has arbitrarily selected terms, in which case their meaning will be described in detail in the section describing the relevant invention. Therefore, the terminology used in this disclosure should not be simply defined by its name, but rather by its meaning and the overall content of this disclosure.

[0035] In this specification, singular expressions include plural expressions unless the context clearly identifies them as singular. Similarly, plural expressions include singular expressions unless the context clearly identifies them as plural. When a part of the specification contains any component, this means that it may contain other components, not exclude them, unless otherwise stated.

[0036] Furthermore, the terms “module” or “part” as used in the specification refer to a software or hardware component, and a “module” or “part” performs some role. However, the meaning of “module” or “part” is not limited to software or hardware. A “module” or “part” may be configured to reside on an addressable storage medium, or to regenerate one or more processors. Thus, as an example, a “module” or “part” may include components such as software components, object-oriented software components, class components, and task components, and at least one of the following: processes, functions, attributes, processors, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. The components and the functions provided within a “module” or “part” may be combined with a smaller number of components and “modules” or further separated into additional components and “modules” or “parts.”

[0037] According to one embodiment of the present disclosure, “module” or “part” may be embodied in a processor and memory. “Processor” should be broadly interpreted to include general-purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, etc. In some environments, “processor” may refer to on-demand semiconductors (ASICs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), etc. “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 combination of such configurations. Also, “memory” should be broadly interpreted to include any electronic component capable of storing electronic information. "Memory" can refer to a variety of processor-readable media, such as arbitrary access memory (RAM), read-only memory (ROM), non-volatile arbitrary access memory (NVRAM), programmable read-only memory (PROM), erase-programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, magnetic or marking data storage devices, and registers. Memory is said to be in electronic communication with the processor if the processor can read / read information from or record information into it. Memory integrated into a processor is in electronic communication with the processor.

[0038] Furthermore, the terms 1st, 2nd, A, B, (a), (b), etc., used in the following examples are merely used to distinguish one component from another, and do not limit the essence, order, or sequence of the components in question.

[0039] Furthermore, in the following embodiments, when it is stated that a component is “connected,” “joined,” or “connected” to another component, it should be understood that the component may be directly connected to or linked to the other component, but that other components may be further “connected,” “joined,” or “connected” between each component.

[0040] Furthermore, the terms "comprises" and / or "comprising" used in the following embodiments do not preclude the presence or addition of one or more other components, stages, operations, and / or elements mentioned.

[0041] Various embodiments of this disclosure will be described in detail below with reference to the attached drawings.

[0042] Figure 1 is an illustrative diagram showing an electronic device for calculating the ratio of blood flow rates by blood vessel using a vascular image according to one embodiment of the present disclosure. Referring to Figure 1, the electronic device (100) can calculate the ratio of blood flow rates by blood vessel (120) using a vascular image (110). Here, the vascular image (110) is an image (e.g., a video or still image) taken for the diagnosis, treatment, or prevention of a disease, and refers to an image of the blood vessels of a subject. According to one embodiment, the vascular image (110) may include an image of the blood vessels of a subject taken while the subject has been administered a contrast agent. For example, the vascular image (110) may include an image taken through coronary angiography. Also, the blood vessels included in the vascular image (110) may include coronary arteries. Coronary arteries are located in a coronary manner surrounding the heart and can be classified into detailed types based on their arrangement. For example, the coronary arteries can be divided into the right coronary artery (RCA), which originates from the right side of the ascending aorta's ostium and runs mainly along the right side of the heart, and the left coronary artery (LCA), which originates from the left side of the ascending aorta's ostium and runs mainly along the left side of the heart. Furthermore, the left coronary artery can be further divided into the left main coronary artery (LMCA) (hereinafter referred to as LM), which originates from the upper left part of the heart, the left anterior descending coronary artery (LAD), which branches off from the left main coronary artery, and the left circumflex coronary artery (LCX). In this disclosure, support is provided for calculating the ratio of blood flow by vessel without using myocardial information, so the vascular image (110) does not have to be a three-dimensional image. For example, the vascular image (110) may include not only three-dimensional images but also two-dimensional images, projection images, contrast-enhanced images, etc.

[0043] Although Figure 1 does not show a storage system that can communicate with the electronic device (100), the electronic device (100) may be configured to connect to or communicate with one or more storage systems. A storage system configured to connect to or communicate with the electronic device (100) may include a device or cloud system that stores and manages various data related to the work of calculating the ratio of blood flow rates (120) for each blood vessel using vascular images (110). For efficient data management, the storage system may use a database to store and manage various data. Here, various data may include any data related to the work of calculating the ratio of blood flow rates (120) for each blood vessel using vascular images (110). For example, various data may include, but are not limited to, machine learning models, training data, vascular images (110), etc., related to the work.

[0044] To explain the process of calculating the ratio of blood flow to different vessels (120) using a vascular image (110), the electronic device (100) can first acquire at least one vascular image (110). This vascular image (110) can be received via a communicable storage medium (e.g., a hospital system, a local / cloud storage system, etc.).

[0045] Next, the electronic device (100) can classify multiple blood vessels from at least one vascular image (110). For example, the electronic device (100) can classify multiple blood vessels from at least one vascular image (110) using a machine learning model (e.g., a vascular classification model). As an example, the electronic device (100) can classify the right coronary artery, the left anterior descending coronary artery, and the left circumflex artery from at least one vascular image (110). As another example, the electronic device (100) can classify the right coronary artery and the left main coronary artery from at least one vascular image (110).

[0046] Subsequently, the electronic device (100) can extract geometric information for each of multiple blood vessels from at least one blood vessel image (110). The geometric information may include, for example, at least one of diameter, length, volume, position, or orientation.

[0047] Subsequently, the electronic device (100) can calculate the ratio of blood flow rates for each blood vessel (120) based on the values ​​extracted as geometric information for each of the multiple blood vessels. For example, the electronic device (100) can calculate the difference between a reference value for the geometric information of each of the multiple blood vessels and a value extracted from at least one blood vessel image (110). Here, the reference value for the geometric information of each of the multiple blood vessels can be set as the average value of values ​​calculated from multiple subjects. According to one embodiment, the electronic device (100) can calculate the difference as the ratio of the reference value for the geometric information of each of the multiple blood vessels to the value extracted from at least one blood vessel image (110). According to another embodiment, the electronic device (100) can calculate the difference as the ratio of the difference between the reference value for the geometric information of each of the multiple blood vessels to the value extracted from at least one blood vessel image (110) and the value extracted from at least one blood vessel image (110). Subsequently, the electronic device (100) can calculate the ratio of blood flow to each blood vessel (120) based on the difference calculated for each of the multiple blood vessels and the reference distribution information of blood flow to each blood vessel. Here, the reference distribution information of blood flow to each blood vessel can be set as the average value of values ​​calculated from multiple subjects.

[0048] According to one embodiment, an electronic device (100) can reconstruct the three-dimensional shapes of multiple blood vessels based on at least one blood vessel image (110). Subsequently, the electronic device (100) can extract geometric information from each of the three-dimensional shapes of the multiple blood vessels. In this case, the geometric information may further include area. For example, the geometric information may include at least one of diameter, length, volume, area, position, or orientation.

[0049] After calculating the ratio of blood flow rates by vessel (120), the electronic device (100) can estimate the blood flow rates by vessel based on the ratio of blood flow rates by vessel (120). For example, the electronic device (100) can set weights according to the ratio of blood flow rates by vessel (120) and apply the set weights to the blood flow rates by vessel.

[0050] According to one embodiment, the electronic device (100) can provide a visual object corresponding to the ratio of blood flow rates (120) for each blood vessel. Here, the visual object may include, for example, at least one of text, symbols, images, or animations that indicate the ratio of blood flow rates (120) for each blood vessel. For example, the electronic device (100) can display the visual object corresponding to the ratio of blood flow rates (120) for each blood vessel by superimposing it on a vascular image (110). In this case, the visual object corresponding to the ratio of blood flow rates (120) for each blood vessel can be displayed superimposed on the region of the vascular image (110) where the blood vessel in question is located or an adjacent region. For example, if the ratio of blood flow by vessel (120) represents the ratio of the right coronary artery, the left anterior descending coronary artery, and the left circumflex coronary artery, and corresponds to the first visual object, second visual object, and third visual object, respectively, the electronic device (100) can superimpose the first visual object onto the region where the right coronary artery is located or an adjacent region in the vascular image (110), superimpose the second visual object onto the region where the left anterior descending coronary artery is located or an adjacent region, and superimpose the third visual object onto the region where the left circumflex coronary artery is located or an adjacent region. Also, if the ratio of blood flow by vessel (120) represents the ratio of the right coronary artery and the left main coronary artery, and corresponds to the first visual object and second visual object, respectively, the electronic device (100) can superimpose the first visual object onto the region where the right coronary artery is located or an adjacent region in the vascular image (110), and superimpose the second visual object onto the region where the left main coronary artery is located or an adjacent region. In one embodiment, if the vascular image (110) does not include the blood vessels involved in calculating the ratio of blood flow rates by blood vessel (120), the electronic device (100) can display visual objects corresponding to the ratio of blood flow rates by blood vessel (120) not only for the blood vessels included in the vascular image (110) but also for the blood vessels not included.

[0051] Figure 2 is a diagram illustrating the configuration of an electronic device according to one embodiment of the present disclosure. Referring to Figure 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 components described above and may further include at least one other component. As an example, the electronic device (100) may further include a display. In this case, the electronic device (100) may display a vascular image (such as the vascular image (110) in Figure 1) on the display.

[0052] The memory (210) can store various types of 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 or output data for software (or programs) and related instructions.

[0053] The memory (210) may include any non-temporary computer-readable recording medium. According to one embodiment, the memory (210) may include a non-volatile mass storage device such as a disk drive, SSD (solid-state drive), or flash memory. As another example, a non-volatile mass storage device such as a ROM, SSD, flash memory, or disk drive may be included in the electronic device (100) as a separate permanent storage device distinct from the memory (210). The memory (210) may also store an operating system and at least one program code (such as instructions for calculating the ratio of blood flow rates per vessel, which are installed and driven in the electronic device (100)). In Figure 2, the memory (210) is shown as a single memory, but this is for illustrative purposes only, and the memory (210) may include multiple memories and / or buffer memories.

[0054] Software components can be loaded from a computer-readable storage medium other than memory (210). Such a separate computer-readable storage medium may include a storage medium that can be directly connected to the electronic device (100), and may include, for example, computer-readable storage media such as floppy drives, disks, tapes, DVD / CD-ROM drives, and memory cards. In another example, software components may also be loaded into memory (210) via a communication module (230) rather than a computer-readable storage medium. For example, at least one program may be loaded into memory (210) based on a computer program (such as a program for transferring vascular image data) that is installed by a file provided via the communication module (230) by a developer or a file distribution system that distributes installation files for applications.

[0055] The processor (220) can execute software (or programs), control at least one other component (such as a hardware or software component) of an electronic device (100) connected to the processor (220), and perform various data processing or calculations. According to one embodiment, as at least part of the data processing or calculation, the processor (220) can load instructions or data received from other components (such as a communication module (230)) into volatile memory, process the instructions or data stored in volatile memory, and store the resulting data in non-volatile memory.

[0056] The processor (220) may be configured to process instructions for a computer program by performing basic arithmetic, logical, and input / output operations. Instructions can be provided to the electronic device (100) or other external systems via memory (210) or a communication module (230). For example, the processor (220) can use vascular images to calculate the ratio of blood flow to different vessels. The processor (220) can then store the calculated ratio of blood flow to different vessels in memory (210), display it on the display of the electronic device (100), or transmit it to an external electronic device via the communication module (230). The processor (220) can also perform additional analyses, such as estimating blood flow to different vessels using the ratio of blood flow to different vessels. In Figure 2, the processor (220) is shown as a single processor, but this is for illustrative purposes only, and the processor (220) may contain multiple processors.

[0057] The communication module (230) can support the establishment of a direct (wired) communication channel or a wireless communication channel between the electronic device (100) and an external electronic device, and communication over the established communication channel. For example, the communication module (230) can provide a configuration or function for the electronic device (100) and an external electronic device (such as a user terminal or cloud server) to communicate with each other over a network. As an example, control signals, commands, data, etc., generated by the control of the processor (220) of the electronic device (100) can be transmitted to the external electronic device via the communication module (230) and the network through the communication module of the external electronic device. For example, the electronic device (100) can receive vascular images of the blood vessels of a subject from an external electronic device via the communication module (230).

[0058] The input / output interface (240) may be connected to an electronic device (100) or serve as a means for interface with input or output devices (not shown) included in the electronic device (100). For example, the input / output interface (240) may include at least one of a PCI Express interface and an Ethernet interface. In Figure 2, the input / output interface (240) is shown as a separate element from the processor (220), but is not limited thereto, and the input / output interface (240) may be configured to be integrated into the processor (220).

[0059] According to one embodiment, the processor (220) can perform a function related to calculating the ratio of blood flow rates for different vessels using vascular images. The processor (220) can execute at least one computer-readable program stored in memory (210) to perform a function related to calculating the ratio of blood flow rates for different vessels. Here, the at least one program may include instructions to acquire at least one vascular image, classify multiple vessels from at least one vascular image, extract geometric information for each of the multiple vessels from at least one vascular image, and calculate the ratio of blood flow rates for different vessels based on the values ​​extracted as geometric information for each of the multiple vessels. For convenience of explanation, in the following description, the execution of at least one program to perform a function related to calculating the ratio of blood flow rates for different vessels using vascular images may be described as the processor (220) performing a function related to calculating the ratio of blood flow rates for different vessels using vascular images. For example, the inclusion of instructions related to calculating the ratio of blood flow rates for different vessels using vascular images may correspond to the processor (220) performing the said function.

[0060] According to one embodiment, a processor (220) can obtain the ratio of blood flow rates for different vessels via a machine learning model that takes vascular images as input. Here, the machine learning model may include any model used to infer a solution for a given input. According to one embodiment, the machine learning model may include an artificial neural network model that includes an input layer, a plurality of hidden layers, and an output layer. Here, each layer may include one or more nodes. The machine learning model may also include weights associated with the plurality of nodes included in the machine learning model. Here, the weights may include any parameters associated with the machine learning model. The machine learning model in this disclosure may be a model that has been trained using various learning methods. For example, various learning methods such as supervised learning, semi-supervised learning, unsupervised learning (autonomous learning), and reinforcement learning may be used in this disclosure. In this disclosure, the machine learning model may refer to an artificial neural network model, and the artificial neural network model may refer to a machine learning model. The artificial neural network model will be described in detail with reference to Figure 9.

[0061] Figure 3 is a diagram illustrating the configuration of a processor in an electronic device according to one embodiment of the present disclosure. Referring to Figure 3, the processor (220) can calculate the ratio of blood flow rates by blood vessel (e.g., the ratio of blood flow rates by blood vessel (120) in Figure 1) using a vascular image (e.g., the vascular image (110) in Figure 1). To achieve this, the processor (220) may include an image acquisition module (310), a vascular classification module (320), a geometric information extraction module (330), and a blood flow rate ratio calculation module (340). However, the types and number of components included in the processor (220) are classified according to the functions related to calculating the ratio of blood flow rates by blood vessel using a vascular image, and are not limited thereto. Furthermore, at least one of the components included in the processor (220) may be implemented in the form of instructions stored in memory (e.g., the memory (210) in Figure 2).

[0062] The image acquisition module (310) can acquire at least one vascular image of a blood vessel. According to one embodiment, the image acquisition module (310) can acquire at least one vascular image of a patient's blood vessels while the patient has been administered a contrast agent. For example, the vascular image may include an image taken through coronary angiography (CAG). Such vascular images can be received from a storage system (such as a hospital system, electronic medical record, prescription delivery system, medical image system, laboratory information system, local / cloud storage system, etc.), internal memory, and / or a user terminal that is connected to or communicates with the electronic device (100).

[0063] The vascular classification module (320) can classify multiple vessels from at least one vascular image acquired by the image acquisition module (310). For example, the vascular classification module (320) can classify multiple vessels from at least one vascular image using a machine learning model (such as a vascular classification model). As an example, the vascular classification module (320) can classify the three major coronary arteries—the right coronary artery, the left anterior descending coronary artery, and the left circumflex coronary artery—from at least one vascular image. As another example, the vascular classification module (320) can broadly classify the coronary arteries from at least one vascular image into the right coronary artery and the left main coronary artery.

[0064] The geometric information extraction module (330) can extract geometric information for each of multiple blood vessels from at least one blood vessel image. The geometric information may include, for example, at least one of diameter, length, volume, position, or orientation. According to one embodiment, the geometric information extraction module (330) can measure the diameter of the proximal part of each of multiple blood vessels from at least one blood vessel image.

[0065] The blood flow ratio calculation module (340) can calculate the ratio of blood flow to individual vessels based on values ​​extracted as geometric information for each of multiple vessels. For example, the blood flow ratio calculation module (340) can calculate the difference between a reference value for the geometric information of each of multiple vessels and a value extracted from at least one vessel image. Here, the reference value for the geometric information of each of multiple vessels can be set as the average value calculated from multiple subjects. Furthermore, the blood flow ratio calculation module (340) can calculate the ratio of blood flow to individual vessels based on the difference calculated for each of multiple vessels and reference distribution information for blood flow to individual vessels. Here, the reference distribution information for blood flow to individual vessels can be set as the average value calculated from multiple subjects.

[0066] According to one embodiment, the blood flow ratio calculation module (340) can calculate the difference between a reference value and an extracted value as the ratio of a reference value to the geometric information of each of multiple blood vessels to a value extracted from at least one blood vessel image, as shown in the following formula (Equation 1).

number

[0067] Here, D represents the difference between the reference value and the extracted value for the geometric information of the blood vessels, x represents the reference value for the geometric information of the blood vessels, and x' represents the value extracted as the geometric information of the blood vessels.

[0068] According to another embodiment, the blood flow ratio calculation module (340) can calculate the difference between the reference value and the extracted value as the ratio of the difference between the reference value for the geometric information of each of the multiple blood vessels with respect to the value extracted from at least one blood vessel image, as shown in the following formula (Equation 2).

number

[0069] Similarly, Dx can represent the difference between the reference value and the extracted value for the geometric information of blood vessel x, x can represent the reference value for the geometric information of the blood vessel, and x' can represent the value extracted as the geometric information of the blood vessel.

[0070] However, the method for calculating the difference between the reference value and the extracted value for the geometric information of blood vessels is not limited to equations 1 and 2 above; the difference can be calculated using various mathematical formulas.

[0071] The blood flow ratio calculation module (340) can calculate the total required blood flow for a target patient based on the difference between a reference value and an extracted value for the geometric information of the blood vessels, using the following formula (Equation 3).

number

[0072] Here, Mmyo represents the total required blood flow, DA represents the difference between the reference value and the extracted value for the geometric information of blood vessel A, DB represents the difference between the reference value and the extracted value for the geometric information of blood vessel B, DC represents the difference between the reference value and the extracted value for the geometric information of blood vessel C, and the F function can be shown as a function that converts the difference between the reference value and the extracted value for the geometric information of a blood vessel into the specific gravity of the blood flow transported by that blood vessel.

[0073] In equation 3, it is shown that there are three types of blood vessels, A, B, and C, that are added when calculating the total required blood flow, but this is not the only way. For example, A, B, and C could represent the right coronary artery, the left anterior descending coronary artery, and the left circumflex coronary artery, respectively. Also, if the blood vessels used to calculate the total required blood flow are the right coronary artery and the left main coronary artery, then A and B would correspond to the right coronary artery and the left main coronary artery, respectively, and blood vessel C could be excluded from equation 3.

[0074] The blood flow ratio calculation module (340) can calculate the blood flow ratio of blood vessels through the following formula (Equation 4).

number

[0075] Here, Rv represents the blood flow ratio of blood vessel v, Dv represents the difference between the reference value and the extracted value for the geometric information of blood vessel v, the F function represents a function that converts the difference between the reference value and the extracted value for the geometric information of the blood vessel into the blood flow specific gravity of that blood vessel, and Mmyo can represent the total required blood flow.

[0076] According to one embodiment, the processor (220) can reconstruct the three-dimensional shapes of multiple blood vessels based on at least one blood vessel image. The processor (220) can then extract geometric information from each of the three-dimensional shapes of the multiple blood vessels. In this case, the geometric information may further include area. For example, the geometric information may include at least one of diameter, length, volume, area, position, or orientation.

[0077] According to one embodiment, the processor (220) can calculate the ratio of blood flow rates in each coronary artery using the diameter of the proximal portion of each coronary artery. The processor (220) can also calculate the ratio of blood flow rates in each coronary artery using the length of a portion of each coronary artery. Furthermore, the processor (220) can calculate the volume using the length and diameter of a portion of each coronary artery, and use the calculated volume to calculate the ratio of blood flow rates in each coronary artery. In addition, the processor (220) can calculate the ratio of blood flow rates in each coronary artery using the area of ​​a portion of each coronary artery. Furthermore, the processor (220) can calculate the ratio of blood flow rates in each coronary artery by summing the total lengths of each coronary artery and using the summed value. Furthermore, the processor (220) can calculate the ratio of blood flow rates in each coronary artery by summing the total volumes of each coronary artery and using the summed value. In addition, the processor (220) can calculate the ratio of blood flow rates in each coronary artery by summing the total areas of each coronary artery and using the summed value.

[0078] According to one embodiment, the processor (220) can estimate the blood flow rate for each blood vessel based on the ratio of blood flow rates for each vessel. For example, the processor (220) can set weights according to the ratio of blood flow rates for each vessel and apply the set weights to the blood flow rates for each vessel. The method of applying the weights set according to the ratio of blood flow rates for each vessel to the blood flow rates for each vessel can be carried out by the formula (Equation 5) described later.

number

[0079] Here, Q' is the blood flow rate with weights applied, Q is the blood flow rate before weighting, and w The function sets weights according to the ratio of blood flow to different vessels, and Rv can represent the ratio of blood flow to different vessels in vessel v.

[0080] According to one embodiment, the processor (220) can provide a visual object corresponding to the ratio of blood flow rates for different vessels. For example, the electronic device (100) may further include a display for displaying the visual object, and the processor (220) can provide the user with the visual object corresponding to the ratio of blood flow rates for different vessels via the display. In this case, the visual object may include, for example, at least one of text, symbols, images, or animations indicating the ratio of blood flow rates for different vessels. For example, the processor (220) can display the visual object corresponding to the ratio of blood flow rates for different vessels superimposed on a vascular image. In this case, the visual object may be displayed superimposed on the region of the vascular image where the vessel is located or an adjacent region. In one embodiment, if the vascular image does not include the vessels involved in calculating the ratio of blood flow rates for different vessels, the processor (220) can also display the visual object corresponding to the ratio of blood flow rates for vessels that are not included in the vascular image, as well as for the vessels included in the vascular image.

[0081] Figure 4 illustrates a method for extracting geometric information for each of several classified blood vessels from a vascular image according to one embodiment of the present disclosure. Referring to Figure 4, a processor (220) (see Figures 2 and 3) of an electronic device (100) (see Figures 1 and 2) can extract geometric information for each of several blood vessels from at least one vascular image (410, 420, 430) (see vascular image (110) in Figure 1). The geometric information may include, for example, at least one of diameter, length, volume, position, or orientation.

[0082] Before extracting geometric information, the processor can classify multiple vessels (412, 422, 432) from at least one vessel image (410, 420, 430). For example, the processor can classify multiple vessels (412, 422, 432) from at least one vessel image (410, 420, 430) using a vessel classification model. As an example, as shown in Figure 4, the processor can classify the three major coronary arteries—the right coronary artery (432), the left anterior descending coronary artery (412), and the left circumflex coronary artery (422)—from at least one vessel image (410, 420, 430). As another example, the processor can broadly classify the coronary arteries from at least one vessel image (410, 420, 430) into the right coronary artery and the left main coronary artery.

[0083] Subsequently, the processor can extract geometric information for each of the multiple blood vessels (412, 422, 432) from at least one blood vessel image (410, 420, 430). For example, as shown in Figure 4, the processor can obtain the diameter of the proximal portion (412a, 422a, 432a) of each of the multiple blood vessels (412, 422, 432) from at least one blood vessel image (410, 420, 430).

[0084] Figure 5 illustrates a method for calculating the ratio of blood flow to different vessels using vascular images according to one embodiment of the present disclosure. Referring to Figure 5, in order to calculate the ratio of blood flow to different vessels (the ratio of blood flow to different vessels (120) in Figure 1) using vascular images (vascular images (110) in Figure 1), the processor (220) (see Figures 2 and 3) of the electronic device (100) (see Figures 1 and 2) can acquire at least one vascular image in step 510 (S510). According to one embodiment, the processor can acquire at least one vascular image of the blood vessels of the patient taken while the patient has been administered a contrast agent. For example, the vascular image may include an image taken through coronary angiography.

[0085] In step 520 (S520), the processor can classify multiple blood vessels. For example, the processor can classify multiple blood vessels from at least one blood vessel image using a machine learning model (such as a blood vessel classification model). As an example, the processor can classify the right coronary artery, the left anterior descending coronary artery, and the left circumflex coronary artery from at least one blood vessel image. As another example, the processor can classify the right coronary artery and the left major coronary artery from at least one blood vessel image.

[0086] In step 530 (S530), the processor can extract geometric information for each of the multiple blood vessels. For example, the processor can extract geometric information for each of the multiple blood vessels from at least one blood vessel image. The geometric information may include, for example, at least one of the following: diameter, length, volume, position, or orientation.

[0087] In step 540 (S540), the processor can calculate the ratio of blood flow to each blood vessel. For example, the processor can calculate the ratio of blood flow to each blood vessel based on values ​​extracted as geometric information for each of the multiple blood vessels. According to one embodiment, the processor can calculate the difference between a reference value for the geometric information of each of the multiple blood vessels and a value extracted from at least one blood vessel image. Here, the reference value for the geometric information of each of the multiple blood vessels can be set as the average value calculated from multiple subjects. Subsequently, the processor can calculate the ratio of blood flow to each blood vessel based on the difference between the reference value for the geometric information and the extracted value for each of the multiple blood vessels, and the reference distribution information for blood flow to each blood vessel. Here, the reference distribution information for blood flow to each blood vessel can be set as the average value calculated from multiple subjects.

[0088] According to one embodiment, the processor (220) can estimate the blood flow rate for each blood vessel based on the ratio of blood flow rates for each vessel. For example, the processor can set weights according to the ratio of blood flow rates for each vessel and apply the set weights to the blood flow rates for each vessel.

[0089] According to one embodiment, the processor (220) can provide a visual object corresponding to the ratio of blood flow rates for each vessel. For example, the processor can provide the user with a visual object corresponding to the ratio of blood flow rates for each vessel via a display. In this case, the visual object may include, for example, at least one of text, symbols, images, or animations that indicate the ratio of blood flow rates for each vessel. For example, the processor can display the visual object corresponding to the ratio of blood flow rates for each vessel superimposed on a vascular image. In this case, the visual object may be displayed superimposed on the region where the vessel in question is located or an adjacent region of the vascular image. In one embodiment, if the vascular image does not include any vessels involved in calculating the ratio of blood flow rates for each vessel, the processor can also display the visual object corresponding to the ratio of blood flow rates for vessels that are not included in the vascular image, as well as for vessels that are not included.

[0090] Figure 6 illustrates another method for calculating the ratio of blood flow to different vessels using vascular images according to one embodiment of the present disclosure. Referring to Figure 6, in order to calculate the ratio of blood flow to different vessels (e.g., the ratio of blood flow to different vessels (120) in Figure 1) using vascular images (e.g., the vascular image (110) in Figure 1), the processor (e.g., the processor (220) in Figures 2 and 3) of an electronic device (e.g., the electronic device (100) in Figures 1 and 2) can acquire at least one vascular image in step 610 (S610). According to one embodiment, the processor can acquire at least one vascular image of the blood vessels of a subject patient taken while the subject patient has been administered a contrast agent. For example, the vascular image may include an image taken through coronary angiography.

[0091] In step 620 (S620), the processor can reconstruct the three-dimensional shape of multiple blood vessels. For example, the processor can reconstruct the three-dimensional shape of multiple blood vessels based on at least one blood vessel image.

[0092] In step S630, the processor (220) can classify multiple blood vessels. For example, the processor can use a machine learning model (e.g., a blood vessel classification model) to classify multiple blood vessels based on the three-dimensional shape of each of them.

[0093] In step S640, the processor (220) can extract geometric information for each of the multiple blood vessels. For example, the processor can extract geometric information for each of the multiple blood vessels from each of the three-dimensional shapes of the multiple blood vessels. The geometric information may include, for example, at least one of the following: diameter, length, volume, area, position, or orientation.

[0094] In step S650, the processor (220) can calculate the ratio of blood flow to each blood vessel. For example, the processor can calculate the ratio of blood flow to each blood vessel based on values ​​extracted as geometric information for each of the multiple blood vessels. According to one embodiment, the processor can calculate the difference between a reference value for the geometric information of each of the multiple blood vessels and a value extracted from at least one blood vessel image. Here, the reference value for the geometric information of each of the multiple blood vessels can be set as the average value calculated from multiple subjects. Subsequently, for each of the multiple blood vessels, the processor can calculate the ratio of blood flow to each blood vessel based on the difference between the reference value for the geometric information and the extracted value, and reference distribution information for blood flow to each blood vessel. Here, the reference distribution information for blood flow to each blood vessel can be set as the average value calculated from multiple subjects.

[0095] According to one embodiment, the processor (220) can estimate the blood flow rate for each blood vessel based on the ratio of blood flow rates for each vessel. For example, the processor can set weights according to the ratio of blood flow rates for each vessel and apply the set weights to the blood flow rates for each vessel.

[0096] According to one embodiment, the processor (220) can provide a visual object corresponding to the ratio of blood flow rates for each vessel. For example, the processor can provide the user with a visual object corresponding to the ratio of blood flow rates for each vessel via a display. In this case, the visual object may include, for example, at least one of text, symbols, images, or animations representing the ratio of blood flow rates for each vessel. For example, the processor can overlay the visual object corresponding to the ratio of blood flow rates for each vessel onto a vascular image. In this case, the visual object may be overlaid on the region of the vascular image where the vessel is located or an adjacent region. In one embodiment, if the vascular image does not include the vessels involved in calculating the ratio of blood flow rates for each vessel, the processor can also display the visual object corresponding to the ratio of blood flow rates for vessels that are not included in the vascular image, as well as for vessels that are not included.

[0097] Figure 7 illustrates a method for calculating the ratio of blood flow to individual vessels using geometric information of multiple vessels according to one embodiment of the present disclosure. Referring to Figure 7, the processor (e.g., processor 220 in Figures 2 and 3) of an electronic device (e.g., electronic device 100 in Figures 1 and 2) that calculates the ratio of blood flow to individual vessels (e.g., the ratio of blood flow to individual vessels 120 in Figure 1) using a vascular image (e.g., vascular image 110 in Figure 1) can calculate the difference between a reference value and an extracted value for the geometric information of each of the multiple vessels in step S710. Here, the reference value for the geometric information of each of the multiple vessels can be set as the average value of values ​​calculated from multiple subjects.

[0098] According to one embodiment, the processor can calculate the difference between the reference value and the extracted value by the ratio of the reference value to the geometric information of each of the multiple blood vessels to the value extracted from at least one blood vessel image, as shown in Equation 1 above. According to another embodiment, the processor can calculate the difference between the reference value and the extracted value by the ratio of the difference between the reference value to the geometric information of each of the multiple blood vessels to the value extracted from at least one blood vessel image, as shown in Equation 2 above.

[0099] In step S720, the processor can calculate the ratio of blood flow to each vessel based on the calculated difference and the reference distribution information of blood flow to each vessel. For example, the processor can calculate the ratio of blood flow to each vessel based on the difference between the reference value for geometric information and the extracted value, and the reference distribution information of blood flow to each vessel. Here, the reference distribution information of blood flow to each vessel can be set as the average value of values ​​calculated from multiple subjects. For example, the processor can calculate the total blood flow of a subject patient based on the difference between the reference value for geometric information of the vessel and the extracted value using equation 3 above. The processor can also calculate the blood flow ratio of a vessel using the total blood flow of the subject patient using equation 4 above.

[0100] Figure 8 illustrates a method for calculating the ratio of blood flow rates per vessel using the diameters of each of a plurality of vessels according to one embodiment of the present disclosure. Referring to Figure 8, the processor (e.g., processor 220 in Figures 2 and 3) of an electronic device (e.g., electronic device 100 in Figures 1 and 2) that calculates the ratio of blood flow rates per vessel (e.g., the ratio of blood flow rates per vessel in Figure 120) using a vascular image (e.g., vascular image 110 in Figure 1) can acquire at least one vascular image in step S810. According to one embodiment, the processor can acquire at least one vascular image of the patient's blood vessels taken while the patient has been administered a contrast agent. For example, the vascular image may include an image taken by coronary angiography.

[0101] In step S820, the processor can classify multiple blood vessels. For example, the processor can classify multiple blood vessels from at least one blood vessel image using a machine learning model (e.g., a blood vessel classification model). As an example, the processor can classify the right coronary artery, the left anterior descending coronary artery, and the left circumflex coronary artery from at least one blood vessel image. As another example, the processor can classify the right coronary artery and the left major coronary artery from at least one blood vessel image.

[0102] In step S830, the processor can extract the diameter of each of the multiple blood vessels. For example, the processor can measure the diameter of the proximal portion of each of the multiple blood vessels from at least one blood vessel image.

[0103] In step S840, the processor can calculate the difference between the reference diameter of each of the multiple blood vessels and the extracted diameter. Here, the reference diameter of each of the multiple blood vessels can be set as the average value of the diameter values ​​of each of the multiple blood vessels calculated from multiple subjects. For example, the reference diameter of the left anterior descending coronary artery can be set to 4.0 mm, the reference diameter of the left circumflex coronary artery can be set to 3.94 mm, and the reference diameter of the right coronary artery can be set to 3.36 mm.

[0104] According to one embodiment, the processor can use equation 1 described above to calculate the difference between a reference value and an extracted value by the ratio of the reference diameter value of each of the multiple blood vessels extracted from at least one blood vessel image to the diameter value of each of the multiple blood vessels extracted from at least one blood vessel image. According to another embodiment, the processor can use equation 2 described above to calculate the difference between a reference value and an extracted value by the ratio of the difference between the reference diameter value of each of the multiple blood vessels extracted from at least one blood vessel image to the diameter value of each of the multiple blood vessels extracted from at least one blood vessel image.

[0105] In step S850, the processor can calculate the ratio of blood flow to each vessel based on the calculated difference and the reference distribution information of blood flow to each vessel. For example, the processor can calculate the ratio of blood flow to each vessel based on the difference between the reference diameter value and the extracted diameter value, and the reference distribution information of blood flow to each vessel. Here, the reference distribution information of blood flow to each vessel can be set as the average value of values ​​calculated from multiple subjects.

[0106] According to one embodiment, the processor (220) can estimate the blood flow rate for each blood vessel based on the ratio of blood flow rates for each vessel. For example, the processor can set weights according to the ratio of blood flow rates for each vessel and apply the set weights to the blood flow rates for each vessel.

[0107] According to one embodiment, the processor (220) can provide a visual object corresponding to the ratio of blood flow rates for each vessel. For example, the processor can provide the user with a visual object corresponding to the ratio of blood flow rates for each vessel via a display. In this case, the visual object may include, for example, at least one of text, symbols, images, or animations indicating the ratio of blood flow rates for each vessel. For example, the processor can superimpose the visual object corresponding to the ratio of blood flow rates for each vessel onto a vascular image. In this case, the visual object may be superimposed on the region where the vessel is located or an adjacent region among the vessels included in the vascular image. In one embodiment, if the vascular image does not include the vessels involved in calculating the ratio of blood flow rates for each vessel, the processor can also display the visual object corresponding to the ratio of blood flow rates for vessels that are not included in the vascular image, as well as for vessels that are not included.

[0108] Figure 9 shows an artificial neural network model according to one embodiment of the present disclosure. Referring to Figure 9, the artificial neural network model (900) may represent, as an example of a machine learning model, a statistical learning algorithm implemented based on the structure of a biological neural network in machine learning technology and cognitive science, or a structure that executes such an algorithm.

[0109] According to one embodiment, the artificial neural network model (900) may exhibit a machine learning model with problem-solving capabilities, in which nodes, which are artificial neurons that form a network by synaptic connections similar to biological neural networks, repeatedly adjust the weights of the synapses and learn to reduce the error between the correct output corresponding to a specific input and the inferred output. For example, the artificial neural network model (900) may include any probabilistic model, neural network model, etc., used in artificial intelligence learning methods such as machine learning and deep learning.

[0110] According to one embodiment, the above-mentioned vascular classification model and / or the model for calculating the ratio of blood flow rates by vascular type can be generated in the form of an artificial neural network model (900). For example, the artificial neural network model (900) can receive vascular images taken of blood vessels and estimate the ratio of blood flow rates by vascular type from the vascular images based on this.

[0111] The artificial neural network model (900) may be implemented as a multi-layer perceptron (MLP) composed of multiple layers of nodes and connections between them. The artificial neural network model (900) according to this embodiment may be implemented using any artificial neural network model structure including a multi-layer perceptron. The artificial neural network model (900) may consist of an input layer (920) that receives input data (910) (or input signals) from the outside, an output layer (940) that outputs output data (950) (or output signals) corresponding to the input data (910), and n hidden layers (930_1~930_n) located between the input layer (920) and the output layer (940) that receive signals from the input layer (920), extract features, and transmit them to the output layer (940). Here, the output layer (940) may receive signals from the hidden layers (930_1~930_n) and output them to the outside.

[0112] The learning methods for the artificial neural network model (900) may include supervised learning methods, in which the model learns to be optimized for problem solving by inputting correct teacher signals (or labels), and unsupervised learning methods, which do not require teacher signals. According to one embodiment, an electronic device according to one embodiment of the present disclosure (e.g., the electronic device 100 in Figures 1 and 2) can train an artificial neural network model (900) using vascular images.

[0113] According to one embodiment, the electronic device can generate training data for training an artificial neural network model (900). For example, the electronic device can generate a training dataset including vascular images. Subsequently, based on the generated training dataset, the electronic device can train an artificial neural network model (900) for calculating the ratio of blood flow rates for each blood vessel from the vascular images.

[0114] According to one embodiment, the input variables of the artificial neural network model (900) may include vascular images in which blood vessels have been captured. When the above input variables are input via the input layer (920), the output variables output from the output layer (940) of the artificial neural network model (900) may be the ratio of blood flow rates for each blood vessel.

[0115] Thus, the input layer (920) and output layer (940) of the artificial neural network model (900) are matched with multiple output variables corresponding to multiple input variables, and the synaptic values ​​between nodes in the input layer (920), hidden layers (930_1~930_n), and output layer (940) are adjusted so that the correct output corresponding to a specific input can be extracted. Through this learning process, the hidden features in the input variables of the artificial neural network model (900) are grasped, and the synaptic values ​​(or weights) between nodes of the artificial neural network model (900) can be adjusted so that the error between the output variable calculated based on the input variables and the target output is reduced. Furthermore, the electronic device can learn an algorithm that takes vascular images of blood vessels as input and learn in a way that minimizes the loss with respect to the ratio of blood flow to blood vessels (i.e., annotation information). The ratio of blood flow to blood vessels can then be estimated using the artificial neural network model (900) thus learned.

[0116] The flowchart and description above are merely illustrative examples, and different implementations are possible in some embodiments. For example, in some embodiments, the order of the steps may be changed, some steps may be repeated, some steps may be omitted, or some steps may be added.

[0117] The aforementioned methods may be provided by computer programs stored on computer-readable recording media for execution on a computer. The media may be for permanently storing computer-executable programs or for temporary storage for execution or download. Furthermore, the media may be a variety of recording or storage means, often consisting of a single or multiple hardware components, and is not limited to media directly connected to any computer system; it may also be distributed across a network. Examples of media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, and flash memory. Other examples of media include recording or storage media managed by app stores and other sites, servers, etc., that distribute applications and various other software.

[0118] The methods, operations, or techniques described herein may be embodied by a variety of means. For example, such techniques may be embodied in hardware, firmware, software, or a combination thereof. A person of ordinary skill will understand that the various exemplary logical blocks, modules, circuits, and algorithmic stages described in conjunction with the disclosure may be embodied in electronic hardware, computer software, or a combination thereof. To clearly illustrate such interchangeability of hardware and software, various exemplary components, blocks, modules, circuits, and stages have been generally described above in terms of their functional aspects. Whether such functions are embodied as hardware or software depends on the design requirements imposed on the particular application and the overall system. A person of ordinary skill may embodied the described functions in a variety of ways for their respective specific applications, but such embodiments should not be construed as deviating from the scope of this disclosure.

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

[0120] Accordingly, the various exemplary logic blocks, modules, and circuits described in conjunction with this disclosure may be embodied or performed by any combination of general-purpose processors, DSPs, ASICs, FPGAs and other programmable logic devices, discrete gates and transistor logic, discrete hardware components, or any other devices designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be embodied by a combination of computing devices, such as a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other combination of configurations.

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

[0122] When embodied in software, the techniques described above may be stored on or transmitted through a computer-readable medium in the form of one or more instructions or codes. A computer-readable medium includes both computer storage media and communication media, encompassing any medium that facilitates the transmission of computer programs from one location to another. The storage medium may be any available medium accessible by a computer. As an unrestricted example, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to transport or store desired program code in the form of instructions or data structures and is accessible by a computer. Furthermore, any connection may appropriately be referred to as a computer-readable medium.

[0123] For example, when software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, lead wire, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, these are included within the definition of a medium. The terms "disk" and "disc" as used in this application include CDs, laserdiscs, optical discs, DVDs (digital versatile discs), floppy disks, and Blu-ray discs, where "disks" typically reproduce data magnetically, and "discs" reproduce data optically using a laser. The aforementioned combinations should also be included within the scope of computer-readable media.

[0124] The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, portable disk, CD-ROM, or any other known form of storage medium. An exemplary storage medium may be linked to the processor so that the processor can read information from or record information to the storage medium. Alternatively, the storage medium may be integrated into the processor. The processor and storage medium may reside within an ASIC. The ASIC may reside within a user terminal. Alternatively, the processor and storage medium may reside as separate components in the user terminal.

[0125] Although the embodiments described above are described as utilizing the aspects of the subject matter currently disclosed in one or more standalone computer systems, the disclosure is not limited to and may be embodied in conjunction with any computing environment, such as a network or a distributed computing environment. In other words, aspects of the subject matter may be embodied in multiple processing chips or devices, and storage may be similarly affected across multiple devices. Such devices may include PCs, network servers, and portable devices.

[0126] While this disclosure has been described in relation to some embodiments, various modifications and alterations are possible without departing from the scope of this disclosure as understandable to a person of the ordinary skill in the art to which the invention of this disclosure pertains. Such modifications and alterations should be understood to fall within the scope of the claims appended to this specification. [Explanation of symbols]

[0127] 100 electronic devices, 210 memory, 220 processors, 230 communication modules, 240 input / output interfaces.

Claims

1. A method for calculating the ratio of blood flow by blood vessel using vascular images, which is performed by at least one processor, comprising the steps of: acquiring at least one vascular image without CT scanning; classifying multiple blood vessels from the at least one vascular image; extracting geometric information for each of the multiple blood vessels from the at least one vascular image; and calculating the ratio of blood flow by blood vessel based on the values ​​extracted as geometric information for each of the multiple blood vessels and reference values ​​for the geometric information for each of the multiple blood vessels, The step of calculating the ratio of blood flow rates for each blood vessel includes the step of calculating the difference between the reference value and the extracted value, and the step of calculating the ratio of blood flow rates for each blood vessel based on the difference calculated for each of the plurality of blood vessels and the reference distribution information of blood flow rates for each blood vessel. The aforementioned reference value is set based on values ​​calculated from multiple subjects. The aforementioned reference distribution information includes the average value of values ​​calculated from the multiple subjects, and is a method for calculating the ratio of blood flow by blood vessel using vascular images.

2. The method for calculating the ratio of blood flow rates by blood vessel using a vascular image according to claim 1, wherein the geometric information includes at least one of diameter, length, volume, position, or direction of arrangement.

3. The method for calculating the ratio of blood flow by blood vessel using a vascular image according to claim 1, wherein the step of classifying the plurality of blood vessels includes the step of classifying the right coronary artery, the left anterior descending coronary artery and the left circumflex coronary artery from the at least one vascular image, or the step of classifying the right coronary artery and the left main coronary artery from the at least one vascular image.

4. The method for calculating the ratio of blood flow rates by blood vessel using a vascular image according to claim 1, wherein the difference between the reference value and the extracted value includes the ratio of the reference value to the extracted value or the ratio of the difference between the reference value and the extracted value to the extracted value.

5. A method for calculating the ratio of blood flow rates by blood vessel using a blood vessel image according to claim 1, further comprising the step of reconstructing the 3D shape of the plurality of blood vessels based on the at least one blood vessel image.

6. The method for calculating the ratio of blood flow rates by blood vessel using a vascular image according to claim 5, wherein the geometric information includes at least one of diameter, length, volume, area, position, or direction of arrangement.

7. A method for calculating the ratio of blood flow rates by blood vessels using a vascular image according to claim 1, further comprising the step of estimating the blood flow rate by blood vessel based on the ratio of blood flow rates by blood vessel.

8. A method for calculating the ratio of blood flow rates by blood vessel using a vascular image according to claim 1, further comprising the step of providing a visual object corresponding to the calculated ratio of blood flow rates by blood vessel.

9. The method for calculating the ratio of blood flow by blood vessel using a vascular image according to claim 1, wherein the at least one vascular image includes an image taken by coronary angiography.

10. An electronic device comprising: a memory; and at least one processor connected to the memory and configured to execute computer-readable instructions stored in the memory; The at least one processor is configured to acquire at least one vascular image without CT scanning, classify multiple blood vessels from the at least one vascular image, extract geometric information for each of the multiple blood vessels from the at least one vascular image, and calculate the ratio of blood flow for each blood vessel based on the extracted values ​​as geometric information for each of the multiple blood vessels and reference values ​​for the geometric information for each of the multiple blood vessels. The at least one processor is configured to calculate the difference between the reference value and the extracted value, and to calculate the ratio of the blood flow rates for each of the multiple blood vessels based on the difference calculated for each of the multiple blood vessels and the reference distribution information of blood flow rates for each blood vessel. The aforementioned reference value is set based on values ​​calculated from multiple subjects. The aforementioned reference distribution information includes the average value of the values ​​calculated from the multiple subjects, in an electronic device.

11. The electronic device according to claim 10, wherein the difference between the reference value and the extracted value includes the ratio of the reference value to the extracted value or the ratio of the difference between the reference value and the extracted value to the extracted value.

12. The electronic device according to claim 10, wherein the at least one processor is configured to reconstruct the three-dimensional shape of the plurality of blood vessels based on the at least one blood vessel image.

13. The electronic device according to claim 10, wherein the at least one processor is configured to estimate the blood flow rate per vessel based on the ratio of blood flow rates per vessel.

14. A non-temporary computer-readable recording medium for storing computer-readable instructions, When the aforementioned instruction is executed by at least one processor, the at least one processor is caused to acquire at least one vascular image without CT scanning, to classify multiple blood vessels from the at least one vascular image, to extract geometric information for each of the multiple blood vessels from the at least one vascular image, and to calculate the ratio of blood flow by blood vessel based on the values ​​extracted as geometric information for each of the multiple blood vessels and reference values ​​for the geometric information of each of the multiple blood vessels. The instruction causes at least one processor to calculate the difference between the reference value and the extracted value, and to calculate the ratio of the blood flow rates for each of the multiple blood vessels based on the difference calculated for each of the multiple blood vessels and the reference distribution information of blood flow rates for each blood vessel. The aforementioned reference value is set based on values ​​calculated from multiple subjects. The aforementioned reference distribution information is a non-temporary computer-readable recording medium that includes the average value calculated from the multiple subjects.

15. The non-temporary computer-readable recording medium according to claim 14, wherein the difference between the reference value and the extracted value includes the ratio of the reference value to the extracted value or the ratio of the difference between the reference value and the extracted value to the extracted value.

16. The non-temporary computer-readable recording medium according to claim 14, wherein the instruction causes the at least one processor to reconstruct the three-dimensional shape of the plurality of blood vessels based on the at least one blood vessel image.

17. The non-temporary computer-readable recording medium according to claim 14, wherein the instruction causes at least one processor to estimate the blood flow rate per vessel based on the ratio of the blood flow rates per vessel.

Images