Method and device for guiding echocardiography

The guide system uses an artificial neural network to enhance cardiac ultrasound imaging by dividing images into regions, calculating matching rates, and providing guidance for accurate measurements, addressing the variability in conventional systems and improving diagnostic reliability.

KR103044845B1Active Publication Date: 2026-11-06ONTACT HEALTH CO LTD
View PDF 12 Cites 0 Cited by

Patent Information

Application Number
KR1020230051036
Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2023-04-18
Publication Date
2026-11-06
Estimated Expiration
2043-04-18

AI Technical Summary

Technical Problem

Conventional cardiac ultrasound imaging systems face challenges in obtaining accurate measurements due to the variability in image acquisition based on the proficiency of medical staff, leading to difficulties in diagnosing heart diseases and requiring extensive training for proper image analysis.

Method used

A guide system using an artificial neural network to divide cardiac ultrasound images into multiple regions, calculate a matching rate with standard cross-sectional views, and provide guidance for obtaining accurate measurements by adjusting the probe position and orientation.

Benefits of technology

The system enhances the reliability of cardiac ultrasound measurements by ensuring that acquired images correspond to standard cross-sectional views, improving diagnostic accuracy and reducing the need for extensive training.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112023043815178-PAT00003_ABST
    Figure 112023043815178-PAT00003_ABST
Patent Text Reader

Abstract

The present invention provides a guide method for cardiac ultrasound implemented by a processor, comprising the steps of: receiving a cardiac ultrasound image of an object; dividing a plurality of cardiac cross-sectional regions in a cross-sectional view of the cardiac ultrasound image; calculating a matching rate for a cross-sectional view in which the plurality of cardiac cross-sectional regions are divided based on a previously received standard cross-sectional view; determining whether to provide a guide based on the matching rate for the cross-sectional view; and, in response to the determination of whether to provide a guide, providing a guide for obtaining a cross-sectional view having a pre-set matching rate or higher. The invention also provides a device using the same.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] This invention relates to a method for providing guidance for cardiac ultrasound measurement and a device for providing guidance for cardiac ultrasound using the same. Background Technology

[0002] Cardiac ultrasound examination is performed by projecting ultrasound waves onto the three-dimensional structure of the heart in multiple planes to acquire images of the heart and measure hemodynamic variables.

[0003] At this time, the medical team positions the ultrasound probe in a location where it is easy to obtain ultrasound images so as to acquire multi-dimensional images through anatomical structures around the heart, such as between the ribs, and records images by finding appropriate cross-sections through rotation and tilting.

[0004] Meanwhile, due to recent technological advancements, technology is also being presented that integrates multiple ultrasonic elements to simultaneously acquire a large amount of information and allows users to select and view the desired information from among them.

[0005] Nevertheless, as the image acquisition process is carried out by medical personnel, a long period of training may be required to perform appropriate examinations.

[0006] Meanwhile, the cardiac ultrasound examination process is divided into examination preparation, image acquisition, image analysis, and report writing, and the image acquisition and analysis processes, in particular, can take a significant amount of time.

[0007] At this time, if an image corresponding to a standard measurement cross-section (View) is not acquired during the image analysis process, it may be difficult to diagnose heart disease because measurements such as the area of ​​heart structures corresponding to the left ventricle, left atrium, right ventricle, right atrium, etc., are not properly measured.

[0008] In other words, since the variation in acquired ultrasound images can be significant depending on the proficiency of the medical staff, there is a continuous demand for the development of ultrasound guidance systems.

[0009] In addition, during the image acquisition process, a visualization function may be required for the navigation of 2D images of the process in which medical personnel move a probe based on a virtual 3D structure of the entire heart.

[0010] The background description of the invention is provided to facilitate a better understanding of the present invention. The matters described in the background description should not be construed as an acknowledgment that they exist as prior art. The problem to be solved

[0011] The inventors of the present invention recognized that it is difficult to obtain an image corresponding to a standard measurement cross-section (View) during the image analysis process.

[0012] In particular, the inventors of the present invention have conceived of the fact that by providing a matching rate to determine whether the cross-sectional view of the ultrasound image currently acquired corresponds to a standard measurement cross-sectional view through this recognition, the image can get closer to the standard measurement cross-sectional view as the matching rate increases.

[0013] As a result, the inventors of the present invention were able to develop a guide system for obtaining a standard measurement cross-section (View) based on the following: dividing a cardiac ultrasound image into multiple regions to obtain measurements, comparing the measurements with a standard measurement cross-section to calculate a matching rate.

[0014] The inventors of the present invention could expect that by providing a new guide system, it would be possible to overcome the limitation of difficulty in obtaining accurate measurements of conventional heart structures by facilitating the acquisition of images corresponding to standard measurement cross-sections (Views).

[0015] In particular, the inventors of the present invention anticipated that they could overcome the limitations of conventional cardiac ultrasound imaging guide systems, which provide uniform guidance regarding the direction, rotation, angle, etc., of the transducer, resulting in low reliability and thus being provided for novice medical staff or educational purposes.

[0016] In addition, during the image acquisition process, visualization functions such as 2D image navigation of the process of medical staff moving the probe based on a virtual 3D structure of the entire heart were provided, allowing for the expectation of providing an intuitive cardiac ultrasound image guide.

[0017] Accordingly, the problem that the present invention aims to solve is to provide a guiding method for cardiac ultrasound and a guiding device using an artificial neural network-based guiding system configured to divide a cardiac ultrasound image into multiple regions to obtain measurements, compare the measurements with a standard measurement cross-section (View) to calculate a matching rate, and provide a guideline for obtaining a standard measurement cross-section (View) based on this.

[0018] The problems of the present invention are not limited to those mentioned above, and other unmentioned problems will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0019] To solve the problem described above, a guide method for cardiac ultrasound according to one embodiment of the present invention is provided.

[0020] The above-described guide method comprises the steps of receiving a cardiac ultrasound image of an object, dividing a plurality of cardiac cross-sectional regions in a cross-sectional view of the cardiac ultrasound image, calculating a matching rate for a cross-sectional view in which the plurality of cardiac cross-sectional regions are divided based on a previously received standard cross-sectional view, determining whether to provide a guide based on the matching rate for the cross-sectional view, and, in response to the determination of whether to provide a guide, providing a guide for obtaining a cross-sectional view having a pre-set matching rate or higher.

[0021] The step of dividing the cross-sectional area in the cross-sectional view according to an embodiment of the present invention may further include the step of dividing the plurality of heart cross-sectional areas using a first prediction model that is trained to divide each of the plurality of heart cross-sectional areas in the cross-sectional view.

[0022] According to another embodiment of the present invention, the step of calculating a matching rate for a cross-sectional view based on a previously received standard cross-sectional view may further include the step of calculating a matching rate using a matching rate calculation model configured to output a measurement in the divided heart structure region and calculate a matching rate by comparing the measurement with a measurement determined in the cross-sectional view based on the previously received standard cross-sectional view.

[0023] According to a feature of the present invention, the plurality of cardiac cross-sectional regions may be one or more selected from structures observable in a specific cross-section of the heart, such as the right ventricle (RV), left ventricle (LV), aorta, left atrium (LA), left ventricle posterior wall (LVPW), and ventricular septum (IVS).

[0024] According to another embodiment of the present invention, the first prediction model is trained to divide a plurality of cardiac cross-sectional regions in the cross-sectional view, and may include a first feature extraction unit configured to divide a plurality of regions based on the anatomical structure within the cardiac ultrasound image using a received cardiac ultrasound image as input, and a second feature extraction unit configured to predict the location of a plurality of points within the cardiac ultrasound image using the received cardiac ultrasound image as input.

[0025] According to another embodiment of the present invention, the first prediction model may be further configured to be trained to divide a plurality of heart cross-sectional regions in the cross-sectional view, and to evaluate the region division results by inputting mask information including entropy for the divided regions, an inferenced chamber mask anatomy for each region, and an inferenced chamber mask ratio for each region.

[0026] According to another embodiment of the present invention, the matching rate calculation model is configured to calculate measurements corresponding to the area and size of each divided cardiac cross-sectional region by inputting a plurality of points within a cardiac ultrasound image determined by the first prediction model, and may be further configured to calculate the matching rate by comparing measurements determined in the cross-sectional view based on a previously received standard cross-sectional view.

[0027] According to another embodiment of the present invention, the matching rate calculation model may be further configured to evaluate measurements taken in a divided heart cross-section region using data from an entropy meter, a capacity meter, and a connectivity meter as input, and to calculate a matching rate by comparing measurements determined in a cross-section based on a previously received standard cross-section.

[0028] The guide according to an embodiment of the present invention may include movement information of a probe for obtaining a matching rate calculated by comparing a measurement value determined in a cross-section based on a previously received standard cross-section and a standard measurement cross-section (View).

[0029] The movement of the probe can include a visualization function for navigation, etc., in 2D images according to the position, direction, etc. of the movement of the probe on a virtual 3D structure of the entire heart.

[0030] To solve the problem described above, a guide device for cardiac ultrasound according to another embodiment of the present invention is provided. The guide device includes a communication unit configured to receive a cardiac ultrasound image of an object, and a processor functionally connected to the communication unit.

[0031] The processor divides a plurality of cardiac cross-sectional regions in a cross-sectional view of the cardiac ultrasound image, and

[0032] Based on the previously received standard cross-sectional view, the matching rate for the cross-sectional view in which the plurality of heart cross-sectional regions are divided is calculated, and

[0033] Determining whether to provide a guide based on the matching rate for the above cross-sectional view,

[0034] In response to whether the above guide is provided, it is configured to provide a guide for obtaining a cross-sectional view having a pre-set matching rate or higher.

[0035] According to a feature of the present invention, the processor is,

[0036] In the cross-sectional view above, it may be further configured to divide a plurality of heart cross-sectional regions using a first prediction model that is trained to divide a plurality of heart cross-sectional regions.

[0037] According to another feature of the present invention, the processor,

[0038] It may be further configured to calculate the matching rate using a matching rate calculation model configured to output measurements in the divided heart structure region and calculate the matching rate by comparing the measurements with the measurements determined in the cross-section based on the previously received standard cross-section.

[0039] According to a feature of the present invention, the plurality of cardiac cross-sectional regions may be one or more selected from structures observable in a specific cross-section of the heart, such as the right ventricle (RV), left ventricle (LV), aorta, left atrium (LA), left ventricle posterior wall (LVPW), and ventricular septum (IVS).

[0040] According to another feature of the present invention, the first prediction model is trained to divide a plurality of cardiac cross-sectional regions in the cross-sectional view, and may include a first feature extraction unit configured to divide a plurality of regions based on the anatomical structure within the cardiac ultrasound image using a received cardiac ultrasound image as input, and a second feature extraction unit configured to predict the location of a plurality of points within the cardiac ultrasound image using the received cardiac ultrasound image as input.

[0041] According to another feature of the present invention, the first prediction model may be further configured to be trained to divide a plurality of cardiac cross-sectional regions in the cross-sectional view, and to evaluate the region division results by inputting mask information including entropy for the divided regions, an inferenced chamber mask anatomy for each region, and an inferenced chamber mask ratio for each region.

[0042] According to another feature of the present invention, the matching rate calculation model is configured to calculate a measurement corresponding to the area and size of each divided cardiac cross-sectional region by taking a plurality of points within the cardiac ultrasound image determined by the first prediction model as input, and may be further configured to calculate a matching rate by comparing the measurement determined in the cross-sectional view based on a previously received standard cross-sectional view.

[0043] According to another feature of the present invention, the matching rate calculation model may be further configured to evaluate measurements taken in a divided heart cross-section region using data from an entropy meter, a capacity meter, and a connectivity meter as input, and to calculate a matching rate by comparing measurements determined in a cross-section based on a previously received standard cross-section.

[0044] The guide according to an embodiment of the present invention may include movement information of a probe for obtaining a matching rate calculated by comparing a measurement value determined in a cross-section based on a previously received standard cross-section and a standard measurement cross-section (View).

[0045] Specific details of other embodiments are included in the detailed description and drawings. Effects of the invention

[0046] The present invention provides a guide system for cardiac ultrasound cross-sections based on an artificial neural network, configured to divide a plurality of cardiac cross-sectional regions in a cross-sectional view of a cardiac ultrasound image, calculate a matching rate for the cross-sectional view in which the plurality of cardiac cross-sectional regions are divided based on a previously received standard cross-sectional view, determine whether to provide a guide based on the matching rate for the cross-sectional view, and, in response to the determination of whether to provide a guide, provide a guide for obtaining a cross-sectional view having a matching rate greater than or equal to a preset matching rate, thereby providing a guide for highly reliable cardiac ultrasound measurement.

[0047] The present invention can overcome the limitation that it is difficult to obtain accurate measurements of the conventional heart structure by providing a new guide system.

[0048] In particular, the present invention can overcome the limitations of conventional cardiac ultrasound imaging guide systems, which provide uniform guidance regarding the direction, rotation, angle, etc., of the transducer, resulting in low reliability and thus being provided for novice medical staff or educational purposes.

[0049] The effects according to the present invention are not limited to those exemplified above, and various other effects are included in this specification. Brief explanation of the drawing

[0050] FIG. 1 is a guide system for a cardiac ultrasound cross-sectional view using a guide device for cardiac ultrasound according to an embodiment of the present invention. It is a city. FIG. 2a is a block diagram showing the configuration of a medical device according to one embodiment of the present invention. FIG. 2b is a block diagram showing the configuration of a guide server according to one embodiment of the present invention. FIG. 3 illustrates the procedure of a guide method for cardiac ultrasound according to one embodiment of the present invention. FIG. 4a is a figure showing an example of a Chamber anatomy meter for the cardiac cross-sectional region segmentation result based on a previously received standard cross-sectional view according to one embodiment of the present invention. FIG. 4b is a figure showing an example of a ratio meter for the result of segmenting a heart cross-section region based on a previously received standard cross-sectional view according to one embodiment of the present invention. FIGS. 5A and 5B are figures showing an example in which the results of cardiac cross-sectional region segmentation according to one embodiment of the present invention are evaluated using an entropy meter. FIGS. 6a to 6c are figures showing examples of evaluating the results of cardiac cross-sectional region segmentation according to one embodiment of the present invention using a capacity meter. FIG. 7 is a figure showing an example in which the results of cardiac cross-sectional region segmentation according to one embodiment of the present invention are evaluated using a connectivity meter. FIGS. 8 to 10 are figures showing examples of guidelines presented using a guide method for cardiac ultrasound according to one embodiment of the present invention. Specific details for implementing the invention

[0051] The advantages of the invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims.

[0052] The shapes, sizes, ratios, angles, numbers, etc. disclosed in the drawings for explaining embodiments of the present invention are exemplary, and therefore the present invention is not limited to the depicted details. Furthermore, in describing the present invention, if it is determined that a detailed description of related known technology may unnecessarily obscure the essence of the present invention, such detailed description is omitted. Where terms such as "comprising," "having," or "consisting of" are used in this specification, other parts may be added unless "only" is used. Where a component is expressed in the singular, it includes cases where it includes the plural unless specifically stated otherwise.

[0053] In interpreting the components, they are interpreted to include a margin of error even in the absence of a separate explicit description.

[0054] The features of each of the various embodiments of the present invention may be combined or combined with one another, either partially or wholly, and as will be fully understood by those skilled in the art, various technical interlocking and operation are possible, and each embodiment may be implemented independently of one another or together in an interlocking relationship.

[0055] In this specification, 'standard image' may mean an image corresponding to a standard measurement cross-sectional view (View).

[0057] Hereinafter, various embodiments of the present invention will be described in detail with reference to the attached drawings.

[0059] Hereinafter, with reference to FIGS. 1, 2a, and 2b, a guide system for a cardiac ultrasound cross-sectional view using a guide device for cardiac ultrasound according to an embodiment of the present invention and a guide device for cardiac ultrasound will be described.

[0060] FIG. 1 illustrates a guide system for a cardiac ultrasound cross-sectional view using a guide device for cardiac ultrasound according to one embodiment of the present invention.

[0061] FIG. 2a is a block diagram showing the configuration of a medical device according to one embodiment of the present invention.

[0062] FIG. 2b is a block diagram showing the configuration of a guide server according to one embodiment of the present invention.

[0063] First, referring to FIG. 1, the guide system (1000) may be a system configured to provide a guide for cardiac ultrasound measurement based on a cardiac ultrasound image of an object. In this case, the guide system (1000) may be composed of a medical device (100) that receives a guide for cardiac ultrasound measurement, a cardiac ultrasound image diagnostic device (200) that provides a cardiac ultrasound image, and a guide server (300) that generates a guide for cardiac ultrasound measurement based on the received cardiac ultrasound image.

[0064] First, next, the medical device (100) is an electronic device that provides a user interface for displaying a guide for cardiac ultrasound measurement, and may include at least one of a smartphone, a tablet PC (Personal Computer), a laptop and / or a PC.

[0065] The medical device (100) receives a prediction result associated with the matching rate between the cardiac ultrasound cross-section and the standard cross-section for the object from the guide server (300), and can display the received result through the display unit described later.

[0066] The guide server (300) may include a general-purpose computer, laptop, and / or data server, etc., that performs various calculations to determine a guide for cardiac ultrasound measurement based on a cardiac ultrasound image provided from a cardiac ultrasound imaging diagnostic device (200), such as an ultrasound diagnostic device. In this case, the guide server (300) may be a device for accessing a web server that provides web pages or a mobile web server that provides mobile websites, but is not limited thereto.

[0067] More specifically, the guide server (300) receives a cardiac ultrasound image of an object from a cardiac ultrasound imaging diagnostic device (200), divides a plurality of cardiac cross-sectional regions in a cross-sectional view of the cardiac ultrasound image, calculates a matching rate for a cross-sectional view in which the plurality of cardiac cross-sectional regions are divided based on a previously received standard cross-sectional view, determines whether to provide a guide based on the matching rate for the cross-sectional view, and in response to the decision to provide a guide, can provide a guide to obtain a cross-sectional view having a pre-set matching rate or higher.

[0068] The guide server (300) can provide the prediction results to the medical device (100).

[0069] In this way, information provided from the guide server (300) may be provided as a web page through a web browser installed on the medical device (100), or provided in the form of an application or program. In various embodiments, such data may be provided in a form included in a platform in a client-server environment.

[0070] Next, with reference to FIGS. 2a and 2b, the components of the guide server (300) of the present invention will be described in detail.

[0071] First, referring to FIG. 2a, the medical device (100) may include a memory interface (110), one or more processors (120) and a peripheral interface (130). Various components within the medical device (100) may be connected by one or more communication buses or signal lines.

[0072] The memory interface (110) is connected to the memory (150) and can transmit various data to the processor (120). Here, the memory (150) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage, cloud, and blockchain data.

[0073] In various embodiments, memory (150) may store at least one of an operating system (151), a communication module (152), a graphical user interface module (GUI) (153), a sensor processing module (154), a telephone module (155), and an application module (156). Specifically, the operating system (151) may include instructions for processing basic system services and instructions for performing hardware operations. The communication module (152) may communicate with at least one of one or more other devices, computers, and servers. The graphical user interface module (GUI) (153) may process a graphical user interface. The sensor processing module (154) may process sensor-related functions (e.g., processing voice input received using one or more microphones (192)). The telephone module (155) may process telephone-related functions. The application module (156) may perform various functions of a user application, such as electronic messaging, web browsing, media processing, exploration, imaging, and other processing functions. In addition, the medical device (100) can store one or more software applications (156-1, 156-2) (e.g., guide applications) associated with any one type of service in memory (150).

[0074] In various embodiments, the memory (150) can store a digital assistant client module (157) (hereinafter, DA client module), and accordingly, can store commands and various user data (158) for performing client-side functions of the digital assistant.

[0075] Meanwhile, the DA client module (157) can obtain voice input, text input, touch input and / or gesture input from a user through various user interfaces (e.g., I / O subsystem (140)) provided in the medical device (100).

[0076] Additionally, the DA client module (157) can output data in the form of audiovisual and tactile signals. For example, the DA client module (157) can output data consisting of a combination of at least two of voice, sound, notifications, text messages, menus, graphics, videos, animations, and vibrations. Furthermore, the DA client module (157) can communicate with a digital assistant server (not shown) using a communication subsystem (180).

[0077] In various embodiments, the DA client module (157) may collect additional information about the surrounding environment of the medical device (100) from various sensors, subsystems, and peripheral devices to construct a context associated with user input. For example, the DA client module (157) may provide context information along with user input to a digital assistant server to infer the user's intent. Here, context information that may accompany user input may include sensor information, e.g., lighting, ambient noise, ambient temperature, images, videos, etc. of the surrounding environment. As another example, context information may include the physical state of the medical device (100) (e.g., device orientation, device location, device temperature, power level, speed, acceleration, motion pattern, cellular signal strength, etc.). As another example, the situation information may include information related to the software status of the medical device (100) (e.g., processes running on the medical device (100), installed programs, past and present network activity, background services, error logs, resource usage, etc.).

[0078] In various embodiments, the memory (150) may include additional or deleted instructions, and furthermore, the medical device (100) may include additional configurations in addition to the configuration shown in 2a, or exclude some configurations.

[0079] The processor (120) can control the overall operation of the medical device (100) and can execute various commands to implement an interface that provides guidance for cardiac ultrasound measurement by running an application or program stored in memory (150).

[0080] The processor (120) may correspond to a computing device such as a CPU (Central Processing Unit) or an AP (Application Processor). Additionally, the processor (120) may be implemented in the form of an integrated chip (IC), such as a System on Chip (SoC) that integrates various computing devices such as a Neural Processing Unit (NPU).

[0081] The peripheral interface (130) is connected to various sensors, subsystems, and peripheral devices and can provide data to enable the medical device (100) to perform various functions. Here, it can be understood that the medical device (100) performs a function by the processor (120).

[0082] The peripheral interface (130) may receive data from a motion sensor (160), a light sensor (light sensor) (161), and a proximity sensor (162), thereby enabling the medical device (100) to perform orientation, light, and proximity detection functions, etc. As another example, the peripheral interface (130) may receive data from other sensors (163) (positioning system—GPS receiver, temperature sensor, biometric sensor), thereby enabling the medical device (100) to perform functions related to other sensors (163).

[0083] In various embodiments, the medical device (100) may include a camera subsystem (170) connected to a peripheral interface (130) and an optical sensor (171) connected thereto, thereby enabling the medical device (100) to perform various shooting functions such as taking photos and recording video clips.

[0084] In various embodiments, the medical device (100) may include a communication subsystem (180) connected to a peripheral interface (130). The communication subsystem (180) is composed of one or more wired / wireless networks and may include various communication ports, radio frequency transceivers, and optical transceivers.

[0085] In various embodiments, the medical device (100) includes an audio subsystem (190) connected to a peripheral interface (130), and the audio subsystem (190) includes one or more speakers (191) and one or more microphones (192), so that the medical device (100) can perform voice-operated functions, such as voice recognition, voice cloning, digital recording, and telephone functions.

[0086] In various embodiments, the medical device (100) may include an I / O subsystem (140) connected to a peripheral interface (130). For example, the I / O subsystem (140) may control a touch screen (143) included in the medical device (100) through a touch screen controller (141). As an example, the touch screen controller (141) may detect user contact and movement or interruption of contact and movement using any one of a plurality of touch sensing technologies, such as capacitive, resistive, infrared, surface acoustic wave technology, proximity sensor array, etc. As another example, the I / O subsystem (140) may control other input / control devices (144) included in the medical device (100) through other input controller(s) (142). As an example, other input controller(s) (142) can control one or more pointer devices such as buttons, rocker switches, thumb wheels, infrared ports, USB ports and styluses.

[0087] Next, referring to FIG. 2b, the guide server (300) may include a communication interface (310), memory (320), I / O interface (330), and a processor (340), and each component may communicate with one or more communication buses or signal lines.

[0088] The communication interface (310) can be connected to the medical staff device (100) and the cardiac ultrasound imaging diagnostic device (200) via a wired / wireless communication network to exchange data. For example, the communication interface (310) can receive cardiac ultrasound images from the cardiac ultrasound imaging diagnostic device (200) and transmit determined information to the medical staff device (100).

[0089] Meanwhile, a communication interface (310) that enables the transmission and reception of such data includes a communication pod (311) and a wireless circuit (312), wherein the wired communication port (311) may include one or more wired interfaces, for example, Ethernet, Universal Serial Bus (USB), FireWire, etc. Additionally, the wireless circuit (312) may transmit and receive data with an external device via an RF signal or an optical signal. Furthermore, wireless communication may use at least one of a plurality of communication standards, protocols, and technologies, such as GSM, EDGE, CDMA, TDMA, Bluetooth, Wi-Fi, VoIP, Wi-MAX, or any other suitable communication protocol.

[0090] The memory (320) can store various data used in the guide server (300). For example, the memory (320) can store cardiac ultrasound images, store models trained to classify and segment cross-sections of cardiac ultrasound images, or store models trained to evaluate and calculate a matching rate by comparing measurements obtained from the ultrasound cross-sections based on previously received standard cross-sections.

[0091] In various embodiments, the memory (320) may include a volatile or non-volatile recording medium capable of storing various data, commands and information. For example, the memory (320) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage, cloud, and blockchain data.

[0092] In various embodiments, the memory (320) may store at least one configuration of an operating system (321), a communication module (322), a user interface module (323), and one or more applications (324).

[0093] An operating system (321) (e.g., an embedded operating system such as LINUX, UNIX, MAC OS, WINDOWS, VxWorks, etc.) may include various software components and drivers for controlling and managing general system tasks (e.g., memory management, storage device control, power management, etc.) and may support communication between various hardware, firmware, and software components.

[0094] The communication module (323) can support communication with other devices through the communication interface (310). The communication module (320) may include various software components for processing data received by the wired communication port (311) or wireless circuit (312) of the communication interface (310).

[0095] The user interface module (323) can receive user requests or inputs from a keyboard, touch screen, microphone, etc. through the I / O interface (330) and provide a user interface on the display.

[0096] The application (324) may include a program or module configured to be executed by one or more processors (330). Here, the application for providing guidance on cardiac ultrasound measurements may be implemented on a server farm.

[0097] The I / O interface (330) can connect at least one of the input / output devices (not shown) of the guide server (300), such as a display, keyboard, touch screen, and microphone, to the user interface module (323). The I / O interface (330) can receive user input (e.g., voice input, keyboard input, touch input, etc.) together with the user interface module (323) and process commands based on the received input.

[0098] The processor (340) is connected to the communication interface (310), memory (320), and I / O interface (330) to control the overall operation of the guide server (300) and can execute various commands for the guide through an application or program stored in the memory (320).

[0099] The processor (340) may correspond to a computing device such as a CPU (Central Processing Unit) or an AP (Application Processor). Additionally, the processor (340) may be implemented in the form of an integrated chip (IC), such as a System on Chip (SoC) that integrates various computing devices. Alternatively, the processor (340) may include a module for computing artificial neural network models, such as a Neural Processing Unit (NPU).

[0100] In various embodiments, the processor (340) may be configured to receive a cardiac ultrasound image of an object, divide a plurality of cardiac cross-sectional regions in a cross-sectional view of the cardiac ultrasound image, calculate a matching rate for a cross-sectional view in which the plurality of cardiac cross-sectional regions are divided based on a previously received standard cross-sectional view, determine whether to provide a guide based on the matching rate for the cross-sectional view, and, in response to whether to provide a guide, provide a guide for obtaining a cross-sectional view having a pre-set matching rate or higher. Optionally, the processor (340) may be configured to provide a measurement guide for each cardiac ultrasound cross-sectional view.

[0101] In various embodiments, the processor (340) may be further configured to divide a plurality of heart cross-sectional regions using a first prediction model that is learned to divide a plurality of heart cross-sectional regions in the cross-sectional view.

[0102] In various embodiments, the processor (340) may be further configured to calculate a matching rate using a matching rate calculation model configured to output a measurement in the divided heart structure region and calculate a matching rate by comparing the measurement with a measurement determined in the cross-section based on a previously received standard cross-section.

[0103] At this time, the first prediction model is trained to divide a plurality of cardiac cross-sectional regions in the cross-sectional view, and may include a first feature extraction unit configured to divide a plurality of regions based on the anatomical structure within the cardiac ultrasound image using the received cardiac ultrasound image as input, and a second feature extraction unit configured to predict the location of a plurality of points within the cardiac ultrasound image using the received cardiac ultrasound image as input.

[0104] At this time, the first prediction model may be further configured to be trained to divide a plurality of cardiac cross-sectional regions in the cross-sectional view, and to evaluate the region division results by inputting mask information including entropy for the divided regions, an anatomical mask for each region (inferenced chamber mask anatomy), and an area for each region (inferenced chamber mask ratio).

[0105] At this time, the matching rate calculation model is configured to calculate measurements corresponding to the area and size of each divided cardiac cross-sectional region by inputting multiple points within the cardiac ultrasound image determined by the first prediction model, and may be further configured to calculate the matching rate by comparing measurements determined in the cross-sectional view based on the previously received standard cross-sectional view.

[0106] At this time, the above matching rate calculation model may be further configured to evaluate measurements taken in the divided heart cross-section region using data from an entropy meter, a capacity meter, and a connectivity meter as input, and to calculate the matching rate by comparing the measurements determined in the cross-section based on the previously received standard cross-section.

[0107] In various embodiments, the processor (340) may be further configured to provide a guide including movement information of a probe for obtaining a standard measurement cross-section (View) and a matching rate calculated by comparing the measurement determined in the cross-section based on the received standard cross-section.

[0109] Hereinafter, a guide method for cardiac ultrasound according to an embodiment of the present invention will be described in detail with reference to FIG. 3.

[0110] FIG. 3 illustrates the procedure of a guide method for cardiac ultrasound according to one embodiment of the present invention.

[0111] First, referring to FIG. 3, a guide procedure according to one embodiment of the present invention is as follows.

[0112] A guide method is provided comprising the steps of: receiving a cardiac ultrasound image of an object; dividing a plurality of cardiac cross-sectional regions in a cross-sectional view of the cardiac ultrasound image; calculating a matching rate for a cross-sectional view in which the plurality of cardiac cross-sectional regions are divided based on a previously received standard cross-sectional view; determining whether to provide a guide based on the matching rate for the cross-sectional view; and, in response to the determination of whether to provide a guide, providing a guide for obtaining a cross-sectional view having a pre-set matching rate or higher.

[0113] At this time, the step of dividing the cross-sectional area in the cross-sectional view may further include the step of dividing the multiple heart cross-sectional areas using a first prediction model that is trained to divide each of the multiple heart cross-sectional areas in the cross-sectional view.

[0114] Additionally, the step of calculating a matching rate for the cross-section based on the previously received standard cross-section may further include the step of calculating the matching rate using a matching rate calculation model configured to output a measurement in the segmented heart structure region and calculate the matching rate by comparing the measurement with a measurement determined in the cross-section based on the previously received standard cross-section.

[0115] In one embodiment of the present invention, the plurality of cardiac cross-sectional regions may be one or more selected from structures observable in a specific cross-section of the heart, such as the right ventricle (RV), left ventricle (LV), aorta, left atrium (LA), left ventricle posterior wall (LVPW), and ventricular septum (IVS).

[0116] In various embodiments of the present invention, the first prediction model is trained to divide a plurality of cardiac cross-sectional regions in the cross-sectional view, and may include a first feature extraction unit configured to divide a plurality of regions based on the anatomical structure within the cardiac ultrasound image using a received cardiac ultrasound image as input, and a second feature extraction unit configured to predict the location of a plurality of points within the cardiac ultrasound image using the received cardiac ultrasound image as input.

[0117] At this time, the first prediction model may be further configured to be trained to divide a plurality of heart cross-sectional regions in the cross-sectional view, and to evaluate the region division results by inputting mask information including entropy for the divided regions, an inferenced chamber mask anatomy for each region, and an inferenced chamber mask ratio for each region.

[0118] In various embodiments of the present invention, the matching rate calculation model is configured to calculate a measurement corresponding to the area and size of each divided cardiac cross-sectional region by taking a plurality of points within the cardiac ultrasound image determined by the first prediction model as input, and may be further configured to calculate a matching rate by comparing the measurement determined in the cross-sectional view based on a previously received standard cross-sectional view.

[0119] At this time, the matching rate calculation model may be further configured to calculate the matching rate by using measurements corresponding to the area and size of each divided cardiac cross-section region, using data from an entropy meter, a capacity meter, and a connectivity meter as inputs, evaluating measurements taken in the divided cardiac cross-section region, and comparing the measurements determined in the cross-section based on the previously received standard cross-section.

[0122] Hereinafter, a guide method for cardiac ultrasound according to an embodiment of the present invention will be specifically described with reference to FIGS. 4a and 4b.

[0123] According to the present invention, the result of dividing the region can be evaluated by inputting mask information data including entropy for the divided region, an inferenced chamber mask anatomy for each region, and an inferenced chamber mask ratio for each region, and providing an evaluation result.

[0124] FIG. 4a is a figure showing an example of a Chamber anatomy meter for the cardiac cross-sectional region segmentation result based on a previously received standard cross-sectional view according to one embodiment of the present invention.

[0125] FIG. 4b is a figure showing an example of a ratio meter for the result of segmenting a heart cross-section region based on a previously received standard cross-sectional view according to one embodiment of the present invention.

[0126] Referring to FIG. 4a, a Chamber anatomy meter for cardiac cross-sectional region segmentation results based on a previously received standard cross-sectional view according to one embodiment of the present invention can be predicted in advance to probabilistically distribute the coordinates of each point corresponding to the center of each region of the aorta, intect ventricular septum (IVS), left atrium (LA), left ventricle (LV), right ventricle (RV), and left ventricle posterior wall (lvpw), using the previously received standard measured cross-sectional view as input. For example, the coordinates where each point can be located are (X1, Y1) for the point corresponding to the center of the aorta, (X2, Y2) for the point corresponding to the center of the intect ventricular septum (IVS), (X3, Y3) for the point corresponding to the center of the left atrium (LA), and (left The point corresponding to the center of the ventricle (LV) may be (X4, Y4), the point corresponding to the center of the right ventricle (RV) may be (X5, Y5), and the point corresponding to the center of the left ventricle posterior wall (lvpw) may be (X6, Y6). In one embodiment, the cardiac cross-section may include cross-sections that can be taken at the parasternal window, apical window, subcostal window, and suprasternal notch window.

[0127] Referring to FIG. 4b, the area ratio of each of the multiple cardiac cross-sectional regions divided in the cross-section can be pre-measured as right ventricle (RV) 18%, left ventricle (LV) 32%, aorta 19%, left atrium (LA) 19%, left ventricle posterior wall (LVPW) 11%, and ventricular septum (IVS) 5% using a previously received standard measurement cross-section as input.

[0130] FIGS. 5A and 5B are figures showing an example in which the results of cardiac cross-sectional region segmentation according to one embodiment of the present invention are evaluated using an entropy meter.

[0131] FIGS. 6a to 6c are figures showing examples of evaluating the results of cardiac cross-sectional region segmentation according to one embodiment of the present invention using a capacity meter.

[0132] FIG. 7 is a figure showing an example in which the results of cardiac cross-sectional region segmentation according to one embodiment of the present invention are evaluated using a connectivity meter.

[0134] According to one embodiment of the present invention, the matching rate calculation model of the present invention is configured to calculate a measurement corresponding to the area and size of each divided cardiac cross-sectional region by inputting a plurality of points within a cardiac ultrasound image determined by the first prediction model, and may be further configured to calculate a matching rate by comparing the measurement determined in the cross-sectional view based on a previously received standard cross-sectional view.

[0135] At this time, the above matching rate calculation model may be configured to calculate the matching rate by using multiple points within the cardiac ultrasound image as inputs, using measurements corresponding to the area and size of each divided cardiac cross-section region, evaluating measurements taken in the divided cardiac cross-section region using data from an entropy meter, a capacity meter, and a connectivity meter as inputs, and comparing the measurements determined in the cross-section based on the previously received standard cross-section.

[0137] First, referring to FIGS. 5a and 5b, FIGS. 5a and 5b show an example in which the results of segmenting a cardiac cross-section region according to one embodiment of the present invention are evaluated using an entropy meter. By using data such as the entropy distribution in a standard measurement cross-section (standard image, View) as input, measuring the entropy in a plurality of segmented cardiac cross-section regions obtained from a real-time ultrasound image, and comparing it with the entropy distribution in the standard measurement cross-section (standard image, View), it is possible to provide a guideline for probe operation to obtain a cross-section such as the standard measurement cross-section (standard image, View).

[0138] At this time, entropy can be obtained as shown in the following mathematical formulas 1 and 2.

[0139]

[0140]

[0142] In the above mathematical formula 1, p may represent uncertainty, and

[0143] In the above mathematical formula 2, x t is pixels, c is classification, h is height, w is width, and p is probability.

[0144] Referring again to 5a and 5b, it is possible to compare the entropy of a standard cross-section received based on an entropy meter as described above with the entropy calculated from a cross-section in which the plurality of heart cross-section regions are divided.

[0145] Next, referring to FIG. 6a, FIG. 6a is a diagram showing an example in which the capacity of each divided heart region is measured as a result of dividing the heart cross-sectional region in a previously received standard cross-sectional view according to an embodiment of the present invention, and FIGs. 6b and 6c are diagrams showing an example in which the result of dividing the heart cross-sectional region according to an embodiment of the present invention is evaluated using a connectivity meter.

[0146] Referring again to FIG. 4a and 4b, the coordinates of multiple points within the cardiac ultrasound image in FIG. 4a can be predicted in advance using a previously received standard measurement cross-section as input, and referring again to FIG. 4b, the area ratios of each of the multiple cardiac cross-section regions divided in the cross-section can be predicted in advance using the previously received standard measurement cross-section as input to be 18% for the right ventricle (RV), 32% for the left ventricle (LV), 19% for the aorta, 19% for the left atrium (LA), 11% for the left ventricle posterior wall (lvpw), and 5% for the ventricular septum (IVS). Therefore, by comparing the coordinates of multiple points and the area of ​​each region measured in each divided region with the coordinates of points and the area of ​​each region in the previously received standard measurement cross-section, it is possible to provide a movement guide for the probe to obtain the standard measurement cross-section.

[0147] Specifically, referring to Fig. 6b, the matching rate with the capacity of each region predicted in advance using the previously received standard measurement cross-section as input—right ventricle (RV) 18%, left ventricle (LV) 32%, aorta 19%, left atrium (LA) 19%, left ventricle posterior wall (lvpw) 11%, and ventricular septum (IVS) 5%—is 93%, so it can be confirmed that the capacity matching rate with the previously received standard measurement cross-section is more than 90%.

[0148] Referring to Fig. 6c, when evaluated by comparing the pre-predicted capacity of each region—right ventricle (RV) 18%, left ventricle (LV) 32%, aorta 19%, left atrium (LA) 19%, left ventricle posterior wall (lvpw) 11%, and ventricular septum (IVS) 5%—with the previously received standard measurement cross-section as input, the cross-section of Fig. 6c shows a matching rate of only 6% when compared with the pre-predicted coordinates that are probabilistically distributed using the previously received standard measurement cross-section as input. Therefore, it can be seen that the transducer must be moved to obtain the pre-set matching rate.

[0149] Referring to the following Fig. 7, Fig. 7 is a figure showing an example in which the results of cardiac cross-sectional region segmentation according to one embodiment of the present invention are evaluated using a connectivity meter.

[0150] Referring again to FIG. 4a, the coordinates of each point corresponding to the center of each region—the aorta, the intect ventricular septum (IVS), the left atrium (LA), the left ventricle (LV), the right ventricle (RV), and the left ventricle posterior wall (lvpw)—can be predicted in advance by probabilistically distributing them using the previously received standard measurement cross-section as input. For example, the coordinates where each point can be located are (X1, Y1) for the center of the aorta, (X2, Y2) for the center of the intect ventricular septum (IVS), (X3, Y3) for the center of the left atrium (LA), (X4, Y4) for the center of the left ventricle (LV), and ( The point corresponding to the center of the ventricle (RV) may be (X5, Y5) and the point corresponding to the center of the left ventricle posterior wall (lvpw) may be (X6, Y6).

[0151] Referring to FIG. 7, according to the present invention, the connectivity of each point corresponding to the center of each region can be compared with that of a previously received standard measurement cross-section to calculate the matching rate. Since FIG. 7 shows that the point corresponding to the center of the aorta is enlarged compared to the point corresponding to the center of the aorta in FIG. 4a, it can be seen that the probe must be moved to the left to obtain a point close to FIG. 4a.

[0154] Hereinafter, with reference to FIGS. 8 to 10, a guideline presented using a guide method for cardiac ultrasound according to various embodiments of the present invention will be explained.

[0155] First, referring to FIG. 8, a movement guide for a probe is provided to obtain a standard measurement cross-section by receiving a real-time cardiac ultrasound image, dividing a plurality of cardiac cross-sectional regions in the cross-section, and predicting the positions of a plurality of points within the cardiac ultrasound image using the received cardiac ultrasound image as input.

[0156] Referring to FIG. 9, FIG. 9 shows a standard measurement cross-sectional view in which a plurality of cardiac cross-sectional regions are each divided and the positions and entropies of a plurality of points in each region are measured and shown. Referring to FIG. 10, FIG. 10 shows the results of dividing cardiac cross-sectional regions when the probe acquires a cardiac ultrasound image at an incorrect position, and the positions and entropies of a plurality of points are measured and shown.

[0157] Referring to FIGS. 9 and 10, the segmentation result of the heart cross-section region and a plurality of point prediction measurements are evaluated by comparing them with measurements determined from a cross-section based on a previously received standard cross-section using data from an entropy meter, a capacity meter, and a connectivity meter as input, and based on this, a matching rate with the standard cross-section can be calculated.

[0158] Referring to FIG. 9, FIG. 9 indicates that a cross-sectional view close to a standard cross-sectional view can be obtained when the matching rate is 99%, and referring to FIG. 10, FIG. 10 indicates a result where the matching rate is calculated as 35%. Since the matching rate in real-time cardiac ultrasound images can be verified, the present invention enables probe guidance to a clinically significant location.

[0161] Although embodiments of the present invention have been described in more detail with reference to the attached drawings, the present invention is not necessarily limited to these embodiments and may be modified in various ways within the scope of the technical spirit of the present invention. Accordingly, the embodiments disclosed in the present invention are intended to explain, not limit, the technical spirit of the present invention, and the scope of the technical spirit of the present invention is not limited by these embodiments. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. The scope of protection of the present invention shall be interpreted by the claims below, and all technical spirits within an equivalent scope shall be interpreted as being included within the scope of rights of the present invention. Explanation of the symbols

[0164] 100: Medical staff device 110: Memory interface 120: Processor 130: Peripheral Interfaces 140: I / O Subsystem 141: Touchscreen Controller 142: Other Input Controllers 143: Touch screen 144: Other Input Control Devices 150: Memory 151: Operating System 152: Communication Module 153: GUI Module 154: Sensor processing module 155: Phone module 156: Applications 156-1, 156-2: Application 157: Digital Assistant Client Module 158: User data 160: Motion sensor 161: Light sensor 162: Proximity sensor 163: Other sensors 170: Camera subsystem 171: Optical sensor 180: Communications subsystem 190: Audio Subsystem 191: Speaker 192: Microphone 300: Guide Server 310: Communication Interface 311: Wired communication port 312: Wireless circuit 320: Memory 321: Operating System 322: Communication Module 323: User Interface Module 324: Application 330: I / O interface 340: Processor

Claims

Claim 1 delete Claim 2 A guide method for cardiac ultrasound implemented by a processor, comprising: receiving a cardiac ultrasound image of an object; dividing a plurality of cardiac cross-sectional regions in a cross-sectional view of the cardiac ultrasound image; calculating a matching rate for a cross-sectional view in which the plurality of cardiac cross-sectional regions are divided based on a previously received standard cross-sectional view; determining whether to provide a guide based on the matching rate for the cross-sectional view; and, in response to the determination of whether to provide a guide, providing a guide for obtaining a cross-sectional view having a pre-set matching rate or higher, wherein the step of dividing the cross-sectional regions in the cross-sectional view further comprises the step of dividing the plurality of cardiac cross-sectional regions using a first prediction model learned to divide each of the plurality of cardiac cross-sectional regions in the cross-sectional view. Claim 3 A guide method for cardiac ultrasound implemented by a processor, comprising: receiving a cardiac ultrasound image of an object; dividing a plurality of cardiac cross-sectional regions in a cross-sectional view of the cardiac ultrasound image; calculating a matching rate for a cross-sectional view in which the plurality of cardiac cross-sectional regions are divided based on a previously received standard cross-sectional view; determining whether to provide a guide based on the matching rate for the cross-sectional view; and, in response to the determination of whether to provide a guide, providing a guide for obtaining a cross-sectional view having a matching rate greater than or equal to a preset matching rate, wherein the step of calculating a matching rate for the cross-sectional view based on a previously received standard cross-sectional view includes calculating a matching rate using a matching rate calculation model configured to output a measurement value in the divided cardiac structural region and calculate a matching rate by comparing the measurement value with a measurement value determined in the cross-sectional view based on a previously received standard cross-sectional view. Claim 4 A guide method for cardiac ultrasound according to claim 2, wherein the plurality of cardiac cross-sectional regions are one or more selected from the group consisting of the right ventricle (RV), left ventricle (LV), aorta, left atrium (LA), left ventricle posterior wall (LVPW), and ventricular septum (IVS). Claim 5 A guide method for cardiac ultrasound according to claim 2, wherein the first prediction model is trained to divide a plurality of cardiac cross-sectional regions in the cross-sectional view, and comprises a first feature extraction unit configured to divide a plurality of regions based on anatomical structures within a cardiac ultrasound image using a received cardiac ultrasound image as input, and a second feature extraction unit configured to predict the location of a plurality of points within a cardiac ultrasound image using the received cardiac ultrasound image as input. Claim 6 A guide method for cardiac ultrasound according to claim 2, wherein the first prediction model is trained to divide a plurality of cardiac cross-sectional regions in the cross-sectional view, and is further configured to evaluate the region division results by inputting mask information including entropy for the divided regions, an anatomical mask for each region (inferenced chamber mask anatomy), and an area for each region (inferenced chamber mask ratio). Claim 7 A guide method for cardiac ultrasound according to claim 3, wherein the matching rate calculation model is configured to calculate a measurement value corresponding to the area and size of each divided cardiac cross-sectional region by taking a plurality of points within a cardiac ultrasound image determined by a first prediction model that divides a plurality of cardiac cross-sectional regions in a cross-sectional view as input, and further configured to calculate a matching rate by comparing the measurement value determined in the cross-sectional view based on a previously received standard cross-sectional view. Claim 8 A guide method for cardiac ultrasound according to claim 7, wherein the matching rate calculation model is further configured to evaluate measurements taken in segmented cardiac cross-sectional areas using data from an entropy meter, a capacity meter, and a connectivity meter as input, and to calculate a matching rate by comparing measurements determined in a cross-sectional view based on a previously received standard cross-sectional view. Claim 9 delete Claim 10 A device for guiding cardiac ultrasound, comprising a communication unit configured to receive a cardiac ultrasound image of an object, and a processor functionally connected to the communication unit, wherein the processor divides a plurality of cardiac cross-sectional regions in a cross-sectional view of the cardiac ultrasound image, calculates a matching rate for a cross-sectional view in which the plurality of cardiac cross-sectional regions are divided based on a previously received standard cross-sectional view, determines whether to provide a guide based on the matching rate for the cross-sectional view, and in response to whether to provide a guide, provides a guide for obtaining a cross-sectional view having a pre-set matching rate or higher, and is further configured to divide a plurality of cardiac cross-sectional regions using a first prediction model learned to divide each of the plurality of cardiac cross-sectional regions in the cross-sectional view. Claim 11 A device for guiding cardiac ultrasound, comprising a communication unit configured to receive a cardiac ultrasound image of an object, and a processor functionally connected to the communication unit, wherein the processor divides a plurality of cardiac cross-sectional regions in a cross-sectional view of the cardiac ultrasound image, calculates a matching rate for a cross-sectional view in which the plurality of cardiac cross-sectional regions are divided based on a previously received standard cross-sectional view, determines whether to provide a guide based on the matching rate for the cross-sectional view, and in response to the determination of whether to provide a guide, provides a guide for obtaining a cross-sectional view having a pre-set matching rate or higher, and further comprises calculating a matching rate using a matching rate calculation model configured to output a measurement value in the divided cardiac structural region and calculate a matching rate by comparing the measurement value with a measurement value determined in the cross-sectional view based on a previously received standard cross-sectional view. Claim 12 A guide device for cardiac ultrasound according to claim 10, wherein the plurality of cardiac cross-sectional regions comprises the right ventricle (RV), left ventricle (LV), aorta, left atrium (LA), left ventricle posterior wall (LVPW), and ventricular septum (IVS). Claim 13 A device for guiding cardiac ultrasound according to claim 10, wherein the first prediction model is trained to divide a plurality of cardiac cross-sectional regions in the cross-sectional view, and comprises a first feature extraction unit configured to divide a plurality of regions based on anatomical structures within a cardiac ultrasound image using a received cardiac ultrasound image as input, and a second feature extraction unit configured to predict the location of a plurality of points within a cardiac ultrasound image using the received cardiac ultrasound image as input. Claim 14 A device for guiding cardiac ultrasound according to claim 10, wherein the first prediction model is trained to divide a plurality of cardiac cross-sectional regions in the cross-sectional view, and is further configured to evaluate the region division results by inputting mask information including entropy for the divided regions, an anatomical mask for each region (inferenced chamber mask anatomy), and an area for each region (inferenced chamber mask ratio). Claim 15 A device for guiding cardiac ultrasound according to claim 11, wherein the matching rate calculation model is configured to calculate a measurement value corresponding to the area and size of each divided cardiac cross-sectional region by taking a plurality of points within a cardiac ultrasound image determined by a first prediction model that divides a plurality of cardiac cross-sectional regions in a cross-sectional view as input, and further configured to calculate a matching rate by comparing the measurement value determined in the cross-sectional view based on a previously received standard cross-sectional view. Claim 16 A device for guiding cardiac ultrasound according to claim 15, wherein the matching rate calculation model is further configured to evaluate measurements taken in segmented cardiac cross-sectional areas using data from an entropy meter, a capacity meter, and a connectivity meter as input, and to calculate a matching rate by comparing measurements determined in a cross-sectional view based on a previously received standard cross-sectional view. Claim 17 A device for guiding cardiac ultrasound according to claim 10, wherein the processor is further configured to provide two-dimensional image-based navigation of the movement of the probe according to the position or direction of movement on a virtual three-dimensional structure of the entire heart.

Citation Information

Patent Citations

  • Automated segmentation of tri-plane image for real time ultrasound imaging

    JP2019022824A

  • Ultrasound Imaging Probe Positioning

    JP2019514476A

  • Automated detection of planes from three-dimensional echocardiographic data

    KR1020090029673A

  • Ultrasound system and method for providing standard view information

    KR1020100056240A

  • Method and apparatus for displaying ulrtasound image

    KR1020130056676A