Ultrasound diagnostic device and method for controlling the ultrasound diagnostic device

Abstract

The present invention provides an ultrasound diagnostic apparatus and a control method for the ultrasound diagnostic apparatus that can easily and accurately select an ultrasound image frame suitable for measuring the diameter of the left ventricular outflow tract. [Solution] The ultrasound diagnostic device is an ultrasound diagnostic device that guides a frame suitable for measuring the diameter of the left ventricular outflow tract from multiple ultrasound images of the heart of a subject, and comprises an image recognition unit (24) that image-recognizes the local anatomical structure of the heart in each of the multiple frames, a time-varying waveform generation unit (25) that generates a time-varying waveform of the anatomical structure state based on the image-recognized local anatomical structure, a candidate frame extraction unit (26) that extracts candidate frames for measurement from the multiple frames using the time-varying waveform, a monitor (23), and a display control unit (22) that highlights the candidate frames for measurement on the monitor (23).

Description

Technical Field

[0001] The present invention relates to an ultrasonic diagnostic apparatus for imaging the heart of a subject and a control method for an ultrasonic diagnostic apparatus.

Background Art

[0002] Conventionally, so-called cardiac output is calculated by capturing an ultrasonic image representing a tomographic plane of the heart of a subject using a so-called ultrasonic diagnostic apparatus and analyzing the captured ultrasonic image. Cardiac output is usually calculated through the following calculation steps: (1) measuring the diameter of the left ventricular outflow tract in an ultrasonic image of a frame representing the so-called parasternal left ventricular long-axis section at the mid-systolic phase of the heart, and calculating the cross-sectional area of the left ventricular outflow tract; (2) calculating the velocity-time integral of blood flow in the left ventricular outflow tract by the so-called pulsed Doppler method for the so-called apical five-chamber section or apical three-chamber section; (3) calculating the so-called stroke volume from the product of the cross-sectional area of the left ventricular outflow tract and the velocity-time integral of blood flow in the left ventricular outflow tract; and (4) calculating the cardiac output from the product of the stroke volume and the heart rate, which is the method commonly used in practice.

[0003] When calculating cardiac output in this manner, there have occasionally been problems such as different criteria for selecting an ultrasonic image of a frame representing the mid-systolic phase of the heart for each user of the ultrasonic diagnostic apparatus such as a doctor, or it takes a lot of time to select an ultrasonic image of a frame representing the mid-systolic phase of the heart. It is generally known that the mid-systolic phase of the heart tends to be located near the phase where the diameter of the left ventricular outflow tract reaches its maximum. Patent Document 1 discloses a technique for automatically selecting an ultrasonic image of a frame where the diameter of the left ventricular outflow tract is maximum, and for example, by using this technique, a frame near the phase where the diameter of the left ventricular outflow tract reaches its maximum can be selected.

Prior Art Literature

Patent Literature

[0004]

Patent Literature 1

Summary of Invention

[0005] Here, guidelines issued by the American Society of Echocardiography (ASE) and others define the phase when the aortic valve annulus is most open as the mid-systolic phase of the heart. However, the phase when the aortic valve annulus is most open does not necessarily coincide with the phase when the diameter of the left ventricular outflow tract is at its maximum. Therefore, when using the technology described in Patent Document 1, it is not always possible to select an ultrasound image representing the mid-systolic phase as a frame suitable for measuring the diameter of the left ventricular outflow tract. There was a risk of selecting an ultrasound image corresponding to a different phase each time an ultrasound image was selected.

[0006] This invention was made to solve the problems of the past, and aims to provide an ultrasound diagnostic device and a control method for the ultrasound diagnostic device that can easily and accurately select an ultrasound image frame suitable for measuring the diameter of the left ventricular outflow tract. [Means for solving the problem]

[0007] The above objective can be achieved with the following configuration. [1] An ultrasound diagnostic device that guides the user to a frame suitable for measuring the diameter of the left ventricular outflow tract from multiple ultrasound images of the subject's heart, An image recognition unit that recognizes the local anatomical structure of the heart in each of multiple frames, A time-varying waveform generation unit generates a time-varying waveform of the anatomical structure state based on the local anatomical structure recognized by the image recognition unit, A candidate frame extraction unit extracts candidate frames for measurement from multiple frames using time-varying waveforms generated by a time-varying waveform generation unit. Monitor and, A display control unit that highlights the measurement candidate frames extracted by the candidate frame extraction unit on the monitor. An ultrasound diagnostic device equipped with the following features. [2] The ultrasound diagnostic apparatus according to [1], comprising a memory that stores multiple candidate measurement frames extracted by a candidate frame extraction unit during multiple past heartbeat periods, and local anatomical structures corresponding to each candidate measurement frame and recognized by an image recognition unit. [3] The image recognition unit recognizes the aortic valve annulus as a local anatomical structure, The time-varying waveform generation unit generates a time-varying waveform of the angular difference of the aortic valve annulus with respect to the vascular axis. The ultrasound diagnostic apparatus according to [1] or [2], wherein the candidate frame extraction unit extracts the frame with the smallest angle difference in the time-varying waveform as a candidate frame for measurement. [4] The image recognition unit recognizes the mitral valve as a local anatomical structure, The time-varying waveform generation unit generates a time-varying waveform of the mitral valve distance. The ultrasonic diagnostic apparatus according to [1] or [2], wherein the candidate frame extraction unit extracts the frame in which the valve distance in the time-varying waveform is minimized as the measurement candidate frame. [5] The image recognition unit recognizes the left ventricle as a local anatomical structure, The time-varying waveform generation unit generates a time-varying waveform of the left ventricle area. The ultrasound diagnostic apparatus according to [1] or [2], wherein the candidate frame extraction unit extracts candidate frames based on the time-varying waveform of the area. [6] The image recognition unit recognizes the left ventricle as a local anatomical structure, The time-varying waveform generation unit generates a time-varying waveform of the curvature of the left ventricle contour. The ultrasound diagnostic apparatus according to [1] or [2], wherein the candidate frame extraction unit extracts candidate measurement frames based on the time-varying waveform of curvature. [7] An ultrasonic diagnostic apparatus according to any one of [1] to [6], wherein the display control unit highlights the measurement candidate frames by changing the brightness or color of the border lines of the measurement candidate frames extracted by the candidate frame extraction unit. [8] The ultrasound diagnostic apparatus according to any one of [1] to [6], wherein the display control unit highlights the measurement candidate frame by changing the brightness or color of the local anatomical structure in the measurement candidate frame extracted by the candidate frame extraction unit. [9] The time-varying waveform generation unit generates multiple time-varying waveforms for multiple indicators as anatomical structural states, The ultrasound diagnostic apparatus according to any one of [1] to [8], wherein the candidate frame extraction unit extracts measurement candidate frames based on a plurality of time-varying waveforms generated by the time-varying waveform generation unit.

[10] The ultrasound diagnostic apparatus according to [2], wherein the display control unit displays a list of multiple measurement candidate frames stored in memory on a monitor.

[11] The ultrasound diagnostic apparatus according to [2], further comprising a frame recommendation unit that selects a frame suitable for measurement from among multiple measurement candidate frames by comparing multiple measurement candidate frames stored in memory and recommends it to the user.

[12] A control method for an ultrasound diagnostic device that guides a frame suitable for measuring the diameter of the left ventricular outflow tract from multiple frames of ultrasound images taken of the heart of a subject, Image recognition is performed to identify the local anatomical structure of the heart in each of multiple frames. Based on image-recognized local anatomical structures, a time-varying waveform of the anatomical structure state is generated. Using the generated time-varying waveform, candidate frames for measurement are extracted from multiple frames. The extracted candidate frames for measurement are highlighted on the monitor. A method for controlling an ultrasound diagnostic device. [Effects of the Invention]

[0008] In the present invention, an ultrasound diagnostic apparatus comprises: an image recognition unit that performs image recognition on a local anatomical structure of a heart in each of a plurality of frames; a time-varying waveform generation unit that generates a time-varying waveform of an anatomical structure state based on the local anatomical structure image-recognized by the image recognition unit; a candidate frame extraction unit that extracts a measurement candidate frame representing a mid-systolic phase from the plurality of frames using the time-varying waveform generated by the time-varying waveform generation unit; a monitor; and a display control unit that highlights the measurement candidate frame extracted by the candidate frame extraction unit on the monitor, whereby an ultrasound image of a frame suitable for measuring the diameter of the left ventricular outflow tract can be selected easily and accurately. [BRIEF DESCRIPTION OF THE DRAWINGS]

[0009] [Figure 1] FIG. 1 is a block diagram showing the configuration of an ultrasound diagnostic apparatus according to Embodiment 1 of the present invention. [Figure 2] FIG. 2 is a block diagram showing the internal configuration of a transmission / reception circuit in Embodiment 1 of the present invention. [Figure 3] FIG. 3 is a block diagram showing the internal configuration of an image generation unit in Embodiment 1 of the present invention. [Figure 4] FIG. 4 is a diagram showing an example of an ultrasound image representing a parasternal left ventricular long-axis section. [Figure 5] FIG. 5 is a diagram showing an example of an ultrasound image of a highlighted measurement candidate frame [Figure 6] FIG. 6 is a flowchart showing the operation of the ultrasound diagnostic apparatus according to Embodiment 1 of the present invention. [Figure 7] FIG. 7 is a diagram showing an example of ultrasound images of a plurality of measurement candidate frames displayed in a list. [Figure 8] FIG. 8 is a diagram showing an example of a jump button for sequentially displaying measurement candidate frames on a monitor by skipping frames other than measurement candidate frames. [Figure 9] FIG. 9 is a block diagram showing the configuration of an ultrasound diagnostic apparatus according to Embodiment 2 of the present invention. [MODE FOR CARRYING OUT THE INVENTION]

[0010] Embodiments of this invention will be described below with reference to the attached drawings. The following description of the constituent elements is based on a typical embodiment of the present invention, but the present invention is not limited to such embodiments. In this specification, a numerical range represented by "~" means a range that includes the numbers written before and after "~" as the lower and upper limits, respectively. In this specification, “identical” and “same” include the range of error that is generally accepted in the art.

[0011] Embodiment 1 Figure 1 shows the configuration of an ultrasound diagnostic apparatus according to Embodiment 1 of the present invention. The ultrasound diagnostic apparatus comprises an ultrasound probe 1 and a device body 2 that are connected to each other by so-called wired communication or so-called wireless communication.

[0012] The ultrasonic probe 1 comprises a transducer array 11 and a transmitting / receiving circuit 12 connected thereto.

[0013] The main unit 2 of the device includes an image generation unit 21 connected to the transmitting / receiving circuit 12. In the main unit 2, the display control unit 22 and the monitor 23 are sequentially connected to the image generation unit 21. In addition, the image recognition unit 24, the time-varying waveform generation unit 25, and the candidate frame extraction unit 26 are sequentially connected to the image generation unit 21. The candidate frame extraction unit 26 is connected to the display control unit 22. A memory 27 is also connected to the image generation unit 21 and the candidate frame extraction unit 26. The memory 27 is also connected to the display control unit 22. Furthermore, a device control unit 28 is connected to the transmitting / receiving circuit 12, the image generation unit 21, the display control unit 22, the image recognition unit 24, the time-varying waveform generation unit 25, the candidate frame extraction unit 26, and the memory 27. An input device 29 is connected to the device control unit 28.

[0014] The image acquisition unit 30 is composed of a transmitting / receiving circuit 12 and an image generation unit 21. Furthermore, the processor 31 for the main unit 2 is composed of the image generation unit 21, a display control unit 22, an image recognition unit 24, a time-varying waveform generation unit 25, a candidate frame extraction unit 26, and a device control unit 28.

[0015] The transducer array 11 of the ultrasonic probe 1 has a plurality of ultrasonic transducers arranged in one or two dimensions. Each of these ultrasonic transducers transmits ultrasound according to a drive signal supplied from the transmitting / receiving circuit 12, and also receives ultrasonic echoes from the subject and outputs a signal based on the ultrasonic echoes. Each ultrasonic transducer is constructed by forming electrodes at both ends of a piezoelectric body made of, for example, a piezoelectric ceramic represented by PZT (Lead Zirconate Titanate), a polymer piezoelectric element represented by PVDF (Poly Vinylidene Di Fluoride), or a piezoelectric single crystal represented by PMN-PT (Lead Magnesium Niobate-Lead Titanate).

[0016] The image acquisition unit 30, which consists of a transmitting / receiving circuit 12 and an image generation unit 21, acquires multiple frames of ultrasound images as moving images of the subject's heart by transmitting and receiving an ultrasound beam using an ultrasound probe 1.

[0017] The transmitting / receiving circuit 12 transmits ultrasonic waves from the transducer array 11 and generates a sound line signal based on the received signal acquired by the transducer array 11, under the control of the device control unit 28. As shown in Figure 2, the transmitting / receiving circuit 12 includes a pulser 41 connected to the transducer array 11, and an amplifier 42, an AD (Analog to Digital) converter 43, and a beamformer 44 connected sequentially in series from the transducer array 11.

[0018] The pulser 41 includes, for example, multiple pulse generators, and based on a transmission delay pattern selected in accordance with a control signal from the device control unit 28, it supplies each drive signal to the multiple ultrasonic transducers of the transducer array 11, adjusting the delay amount, so that the ultrasonic waves transmitted from the transducers form an ultrasonic beam. In this way, when a pulsed or continuous wave voltage is applied to the electrodes of the ultrasonic transducers of the transducer array 11, the piezoelectric material expands and contracts, generating pulsed or continuous wave ultrasonic waves from each ultrasonic transducer, and an ultrasonic beam is formed from the combined wave of these ultrasonic waves.

[0019] The transmitted ultrasonic beam is reflected from a target, such as a part of the subject, and propagates toward the transducer array 11 of the ultrasonic probe 1. The ultrasonic echo propagating toward the transducer array 11 is received by each ultrasonic transducer that makes up the transducer array 11. At this time, each ultrasonic transducer that makes up the transducer array 11 expands and contracts upon receiving the propagating ultrasonic echo, generating a received signal which is an electrical signal, and outputs these received signals to the amplification unit 42.

[0020] The amplification unit 42 amplifies the signals input from each ultrasonic transducer constituting the transducer array 11 and transmits the amplified signals to the AD conversion unit 43. The AD conversion unit 43 converts the signals transmitted from the amplification unit 42 into digital received data. The beamformer 44 performs so-called receive focus processing by adding each received data received from the AD conversion unit 43 with a corresponding delay. Through this receive focus processing, each received data converted by the AD conversion unit 43 is phase-corrected and added together, and a sound ray signal with a focused ultrasonic echo is obtained.

[0021] As shown in Figure 3, the image generation unit 21 has a configuration in which a signal processing unit 45, a DSC (Digital Scan Converter) 46, and an image processing unit 47 are connected in series in sequence.

[0022] The signal processing unit 45 receives the sound line signal from the transmitting / receiving circuit 12, and after correcting for attenuation due to distance according to the depth of the ultrasonic reflection position using a sound velocity value set by the device control unit 28, it performs envelope detection processing to generate a B-mode image signal, which is tomographic image information of the tissue within the subject.

[0023] The DSC46 converts the B-mode image signal generated by the signal processing unit 45 into an image signal that follows the scanning method of a normal television signal (raster conversion). The image processing unit 47 performs various necessary image processing, such as gradation processing, on the B-mode image signal input from the DSC 46, and then sends the B-mode image signal to the display control unit 22, the image recognition unit 24, and the memory 27. Hereafter, the B-mode image signal processed by the image processing unit 47 will be referred to as the ultrasonic image.

[0024] In the present invention, the image acquisition unit 30 acquires multiple frames of ultrasound images representing the cross-sectional plane of the subject's heart. For example, as shown in Figure 4, an ultrasound image U representing a so-called parasternal left ventricular long-axis section that longitudinally crosses the so-called aortic valve annulus of the heart is acquired. The ultrasound image U representing the parasternal left ventricular long-axis section typically includes the left ventricular outflow tract T, the aortic valve annulus A, a portion of the left ventricle LV, and the mitral valve MV.

[0025] Incidentally, there is a known technique for calculating so-called cardiac output by using an ultrasound diagnostic device to capture an ultrasound image U representing a cross-sectional view of the subject's heart and analyzing the captured ultrasound image U. The calculation of cardiac output is usually performed in the following steps: (1) measure the diameter of the left ventricular outflow tract T in the ultrasound image U of a frame representing the so-called parasternal left ventricle long axis section during the mid-systolic phase of the heart, and calculate the cross-sectional area of ​​the left ventricular outflow tract T; (2) calculate the velocity-time integral of blood flow in the left ventricular outflow tract T using the so-called pulsed Doppler method for the so-called apical five-chamber section or apical three-chamber section; (3) calculate the stroke volume by product of the cross-sectional area of ​​the left ventricular outflow tract T and the velocity-time integral of blood flow in the left ventricular outflow tract T; and (4) calculate the cardiac output by product of the stroke volume and the heart rate.

[0026] When calculating cardiac output in this manner, problems sometimes arise where, for example, the criteria for selecting the ultrasound image U representing the mid-systolic phase of the heart differ among users of the ultrasound diagnostic equipment, such as physicians, or where it takes a lot of time to select the ultrasound image U representing the mid-systolic phase of the heart.

[0027] Here, guidelines issued by the American Society of Echocardiography (ASE) and others define the mid-systolic phase of the heart as the phase in which the aortic valve annulus A is most open during one heartbeat, i.e., the duration of one heartbeat. In the mid-systolic phase of the heart, the mitral valve MV is often closed, and the volume and curvature of the left ventricle LV gradually change. Therefore, the mid-systolic phase of the heart can be identified from the temporal changes in the local anatomical structure of the heart, such as the degree of opening of the aortic valve annulus A.

[0028] The image recognition unit 24 performs image recognition of local anatomical structures of the heart in each of the multiple frames acquired by the image acquisition unit 30. Here, local anatomical structures include the aortic valve annulus A, mitral valve MV, and left ventricle LV. The image recognition unit 24 pre-stores template image data, such as general images representing local anatomical structures of the heart, and can perform image recognition of local anatomical structures by a so-called template matching method, which searches within the ultrasound image U using the template image data. The image recognition unit 24 can also perform image recognition of local anatomical structures by inputting the ultrasound image U into a pre-trained model in so-called machine learning, which has been pre-trained on the local anatomical structures of the heart.

[0029] The time-varying waveform generation unit 25 generates a time-varying waveform of the anatomical structure based on the local anatomical structure of the heart recognized by the image recognition unit 24. As a time-varying waveform of the anatomical structure, the time-varying waveform generation unit 25 can generate, for example, a time-varying waveform of the angular difference of the aortic annulus A with respect to the vascular axis. The vascular axis refers to the axis along the direction of course of the aorta near the aortic annulus A. The angular difference of the aortic annulus A with respect to the vascular axis refers to the angle between the aortic annulus A and the vascular axis in the ultrasound image U. Typically, in an ultrasound image U representing a parasternal left ventricle long-axis section, a pair of aortic annulus A are visible on both sides of the vascular axis. In this case, for example, the average of the angular differences calculated for the pair of aortic annulus A can be calculated as the final angular difference value.

[0030] The term "time-varying waveform of anatomical structure" refers to a waveform that represents the time-series changes in the anatomical structure of the heart. The time-varying waveform generation unit 25 can generate a graph as a time-varying waveform of the anatomical structure, for example, by plotting the time at which multiple frames of ultrasound images U were acquired on the horizontal axis and the value of the anatomical structure of the heart corresponding to each time on the vertical axis.

[0031] The time-varying waveform generation unit 25 can also generate a time-varying waveform of the mitral valve MV as a time-varying waveform of the anatomical structure, for example, a time-varying waveform of the valve distance of the mitral valve MV. The mitral valve MV is anatomically composed of two valves, an anterior leaflet and a posterior leaflet, and the valve distance of the mitral valve MV refers to the distance between the anterior leaflet and the posterior leaflet in the ultrasound image U.

[0032] The time-varying waveform generation unit 25 can also generate a time-varying waveform of the area of ​​the left ventricle LV in the ultrasound image U, as an example of a time-varying waveform of an anatomical structure. The time-varying waveform generation unit 25 can also generate a time-varying waveform of the curvature of the contour of the left ventricle LV in the ultrasound image U, as an example of a time-varying waveform of an anatomical structure.

[0033] The candidate frame extraction unit 26 uses the time-varying waveform of the anatomical structure generated by the time-varying waveform generation unit 25 to extract a candidate measurement frame representing the mid-systolic phase, i.e., a frame suitable for measuring the diameter of the left ventricular outflow tract T, from multiple ultrasound image U frames. Guidelines issued by the American Society of Echocardiography and others define the mid-systolic phase of the heart as the phase in which the aortic valve annulus A is most open during one heartbeat. Therefore, the candidate frame extraction unit 26 can, for example, refer to the time-varying waveform of the angular difference of the aortic valve annulus A with respect to the vascular axis as the time-varying waveform of the anatomical structure, and extract the ultrasound image U of the frame in the phase where the angular difference of the aortic valve annulus A with respect to the vascular axis is minimized as the ultrasound image U of the candidate measurement frame representing the mid-systolic phase of the heart.

[0034] During the mid-systolic phase of the heart, the mitral valve MV is often in its most closed state during a single heartbeat. Therefore, the candidate frame extraction unit 26 can also extract the ultrasound image U of the frame in which the mitral valve MV has the minimum valve distance by referring to the time-varying waveform of the valve distance of the mitral valve MV as the ultrasound image U of the measurement candidate frame representing the mid-systolic phase of the heart.

[0035] Furthermore, during the mid-systolic phase of the heart, the volume of the left ventricular LV gradually decreases over the duration of one heartbeat. Therefore, the candidate frame extraction unit 26 can also extract ultrasound image U of a measurement candidate frame representing the mid-systolic phase of the heart by referring to the time-varying waveform of the area of ​​the left ventricular LV in the ultrasound image U as a time-varying waveform of the anatomical structure. In this case, the candidate frame extraction unit 26 can, for example, extract ultrasound image U of a mid-systolic phase frame from a trained model in machine learning, which has learned numerous time-varying waveforms of the area of ​​the left ventricular LV and numerous ultrasound image U representing the mid-systolic phase, by inputting the time-varying waveform of the area of ​​the left ventricular LV generated by the time-varying waveform generation unit 25 and multiple ultrasound image U frames acquired by the image acquisition unit 30.

[0036] Furthermore, the candidate frame extraction unit 26 can also extract ultrasound image U of a measurement candidate frame representing the mid-systolic phase of the heart by referring to the time-varying waveform of the curvature of the left ventricle LV in the ultrasound image U as a time-varying waveform of the anatomical structure. In this case, the candidate frame extraction unit 26 can, for example, extract an ultrasound image U of a mid-systolic phase frame from a trained machine learning model that has learned numerous time-varying waveforms of the curvature of the left ventricle LV and numerous ultrasound image U representing the mid-systolic phase by inputting the time-varying waveform of the curvature of the left ventricle LV generated by the time-varying waveform generation unit 25 and multiple ultrasound image U frames acquired by the image acquisition unit 30.

[0037] The candidate frame extraction unit 26 extracts ultrasound images U of measurement candidate frames representing the mid-systolic phase of the heart using the time-varying waveform of the anatomical structure in this manner. Therefore, even if the user is different, ultrasound images U of measurement candidate frames representing the mid-systolic phase can be extracted under the same conditions.

[0038] Memory 27 stores ultrasound images U of multiple measurement candidate frames extracted by the candidate frame extraction unit 26 during past multiple heartbeat periods, and local anatomical structures of the heart corresponding to each measurement candidate frame's ultrasound image U and recognized by the image recognition unit 24. For memory 27, recording media such as flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), FD (Flexible Disk), MO disk (Magneto-Optical disk), MT (Magnetic Tape), RAM (Random Access Memory), CD (Compact Disc), DVD (Digital Versatile Disc), SD card (Secure Digital card), or USB memory (Universal Serial Bus memory) can be used.

[0039] The display control unit 22, under the control of the device control unit 28, performs predetermined processing on the ultrasound image U acquired by the image acquisition unit 30 and displays it on the monitor 23. The display control unit 22 also highlights the measurement candidate frames extracted by the candidate frame extraction unit 26 on the monitor 23. As shown in Figure 5, for example, in so-called cine playback where multiple already acquired ultrasound image U frames are sequentially played back as a video, the display control unit 22 can highlight the ultrasound image U1 of the measurement candidate frame among the multiple ultrasound image U frames.

[0040] Figure 5 shows an example where the monitor 23 displays an ultrasound image U2 that is displayed sequentially in chronological order as a video, multiple frames of ultrasound image U that are displayed sequentially by scrolling in chronological order, a scroll bar B that has an elongated shape extending along the extension direction and whose positions in that extension direction correspond to each point in time from the start to the end of acquisition of the multiple frames of ultrasound image U, and a slider SL that moves along the extension direction on the scroll bar B in accordance with the point in time when the ultrasound image U2 displayed sequentially as a video is acquired. The display control unit 22 can highlight the ultrasound image U1 of the measurement candidate frame among the multiple frames of ultrasound image U that are displayed sequentially by scrolling. The display control unit 22 can also highlight the ultrasound image U1 of the measurement candidate frame at the moment when the ultrasound image U1 of the measurement candidate frame is displayed as ultrasound image U2 displayed sequentially as a video. In this case, the ultrasound image U2 corresponding to the ultrasound image U1 of the measurement candidate frame is also highlighted. In the example shown in Figure 5, four ultrasound images U representing the gradually changing anatomical structure of the heart over time are shown, along with ultrasound image U1, a candidate frame for measurement where the aortic valve annulus A is most open.

[0041] Furthermore, the display control unit 22 can highlight the ultrasound image U1 of a measurement candidate frame by differentiating the display pattern of the frame of the ultrasound image U1 of the measurement candidate frame from the display pattern of the frame of the ultrasound image U of other frames, differentiating the display color and brightness of the ultrasound image U1 of the measurement candidate frame from the display color and brightness of the ultrasound image U of other frames, and differentiating the display pattern of local anatomical structures in the ultrasound image U1 of the measurement candidate frame from the display pattern of local anatomical structures in the ultrasound image U of other frames.

[0042] The display method of the frame of the ultrasound image U includes the type of frame, such as a solid or dotted line, and the display color and brightness of the frame. The display method of local anatomical structures in the ultrasound image U includes the display color and brightness of the local anatomical structures and whether or not the contour lines of the local anatomical structures are displayed. The display control unit 22 can also highlight the ultrasound image U1 of a measurement candidate frame by displaying a message such as "This is a measurement candidate frame" only in the vicinity of the ultrasound image U1 of the measurement candidate frame using a so-called pop-up display.

[0043] The user can easily and accurately select the ultrasound image U representing the mid-systolic phase of the heart from several ultrasound image U frames, including the ultrasound image U1 of the measurement candidate frame, by moving the slider SL along the extension direction of the scroll bar B via the input device 29, and viewing several ultrasound image U frames, including the ultrasound image U1 of the measurement candidate frame, via the input device 29.

[0044] The monitor 23 displays ultrasound images U, etc., under the control of the display control unit 22, and has a display device such as an LCD (Liquid Crystal Display) or an organic EL display (Organic Electroluminescence Display).

[0045] The input device 29 is for the user to perform input operations and consists of devices such as a keyboard, mouse, trackball, touchpad, and touch sensor placed on top of the monitor 23.

[0046] In this embodiment, each process in the processor 31 is executed on any computer. Alternatively, any computer may execute these processes using a processor as hardware, a program as software, or a combination thereof. In that case, the processor is configured to work in cooperation with the program to execute the various processes in this embodiment, and can function as a unit or means in this embodiment. Furthermore, the execution order of the processes by the processor is not limited to the order described and may be changed as appropriate. Any computer may be a general-purpose computer, a computer designed for a specific purpose, a workstation, or any other system capable of executing each process.

[0047] The processor 31 may be composed of one or more hardware components, and the type of hardware is not limited. For example, the processor 31 may be composed of hardware such as a CPU (Central Processing Unit), MPU (Micro Processing Unit), FPGA (Field Programmable Gate Array) or other programmable logic devices, an ASIC (Application Specific Integrated Circuit) or other dedicated circuit for executing specific processing, a GPU (Graphic Processing Unit), or an NPU (Neural Processing Unit). Furthermore, the type of hardware may be a combination of different types of hardware. When multiple hardware components are configured to execute one or more processes of a given processor, these multiple hardware components may reside in physically separate devices or in the same device. Also, in any embodiment, the order of each process performed by the processor 31 is not limited to the order described above and may be changed as appropriate. The hardware is composed of electrical circuits (circuitry) that combine circuit elements such as semiconductor elements.

[0048] Furthermore, the program may be firmware or software such as microcode. Alternatively, the program may be, for example, a set of program modules, each function of which may be implemented by a processor configured to perform its respective function. The program may be program code or multiple code segments stored on one or more non-temporary computer-readable media (e.g., storage media or other storage). The program may be divided and stored on multiple non-temporary computer-readable media located on physically separate devices. Program code or code segments may represent any combination of procedures, functions, subprograms, routines, subroutines, modules, software packages, classes, or instructions, data structures, or program statements. Program code or code segments may be connected to other code segments or hardware circuits by sending and receiving information, data, arguments, parameters, or memory contents.

[0049] Next, the operation of the ultrasound diagnostic apparatus according to Embodiment 1 will be described with reference to the flowchart shown in Figure 6.

[0050] In step S1, the image acquisition unit 30 generates an ultrasound image U of the subject's heart, for example, representing a parasternal left ventricular long-axis cross-section. At this time, under the control of the device control unit 28, ultrasound transmission and reception are started from multiple transducers of the transducer array 11 according to the drive signal from the pulser 41 of the ultrasound probe 1's transmission / reception circuit 12. Ultrasound echoes from within the subject are received by multiple transducers of the transducer array 11, the received signal, which is an analog signal, is output to the amplification unit 42 for amplification, and then AD converted by the AD conversion unit 43 to acquire the received data.

[0051] The beamformer 44 performs reception focus processing on this received data, and the resulting sound line signal is sent to the image generation unit 21 of the main unit 2 of the device, where the image generation unit 21 generates an ultrasound image U representing the subject's heart. At this time, the signal processing unit 45 of the image generation unit 21 performs attenuation correction according to the depth of the ultrasound reflection position and envelope detection processing on the sound line signal, and the DSC 46 converts it into an image signal following the scanning method of a normal television signal, and the image processing unit 47 performs various necessary image processing such as gradation processing. The ultrasound image U generated in step S1 in this way is sent to the display control unit 22, the image recognition unit 24, and the memory 27.

[0052] In step S2, the image recognition unit 24 recognizes local anatomical structures of the heart, such as the aortic valve annulus A, mitral valve MV, and left ventricle LV, in the ultrasound image U acquired in step S1. The image recognition unit 24 can recognize local anatomical structures of the heart by methods such as template matching or using a trained model in machine learning.

[0053] In step S3, the time-varying waveform generation unit 25 measures the anatomical state of the local anatomical structure of the heart, which was image-recognized in step S2, on the ultrasound image U, and generates a time-varying waveform of the measured anatomical state. For example, the time-varying waveform generation unit 25 can measure the angular difference of the aortic valve annulus A with respect to the vascular axis in the ultrasound image U as an anatomical state, and generate a time-varying waveform of the measured angular difference.

[0054] The time-varying waveform generation unit 25 can, for example, measure the valve distance of the mitral valve MV in the ultrasound image U as an anatomical structure and generate a time-varying waveform of the measured valve distance. The time-varying waveform generation unit 25 can, for example, measure the area of ​​the left ventricle LV in the ultrasound image U as an anatomical structure and generate a time-varying waveform of the measured area. The time-varying waveform generation unit 25 can, for example, measure the curvature of the contour of the left ventricle LV in the ultrasound image U as an anatomical structure and generate a time-varying waveform of the measured curvature.

[0055] In step S4, the candidate frame extraction unit 26 refers to the time-varying waveform generated in step S3 to determine whether the processing in steps S1 to S3 was performed over one heartbeat period of the subject's heart, that is, whether a time-varying waveform of the anatomical structure corresponding to one heartbeat period was generated. The candidate frame extraction unit 26, for example, pre-stores template data representing typical time-varying waveforms of anatomical structures, and can identify the time-varying waveform obtained in step S3 as one heartbeat period of the heart if the similarity of the time-varying waveform obtained in step S3 to the template data is above a certain value. As long as it is determined in step S4 that processing was not performed over one heartbeat period, the processing in steps S1 to S4 is repeated. If it is determined in step S4 that processing was performed over one heartbeat period, the process proceeds to step S5.

[0056] In step S5, the candidate frame extraction unit 26 extracts an ultrasound image U1 of a candidate measurement frame representing the mid-systolic phase using the time-varying waveform of the anatomical structure generated in step S3. The candidate frame extraction unit 26 can extract, for example, an ultrasound image U of a frame representing the phase when the aortic valve annulus A is most open during one heartbeat, i.e., the phase when the angular difference of the aortic valve annulus A with respect to the vascular axis is smallest during one heartbeat. The candidate frame extraction unit 26 can also extract an ultrasound image U of a frame representing the mid-systolic phase of the heart as an ultrasound image U1 of a candidate measurement frame representing the mid-systolic phase of the heart based on the area or curvature of the left ventricular LV.

[0057] In this way, the ultrasound images U1 of the candidate measurement frames extracted in step S5 are stored in memory 27.

[0058] In step S6, the device control unit 28 determines whether or not to terminate the scanning of the subject's heart with the ultrasound probe 1. The device control unit 28 can determine to terminate the scanning if the user inputs an instruction to terminate the scanning via the input device 29, for example, by determining that the user has acquired a sufficient number of ultrasound images U. The device control unit 28 can also determine to continue scanning if the user does not input any specific instructions via the input device 29.

[0059] If it is determined in step S6 to continue scanning, the process returns to step S1, and the subsequent processes up to step S6 are repeated. In this way, as long as it is determined in step S6 to continue scanning, the processes from step S1 to step S6 are repeated.

[0060] Here, if it is determined in step S4 that processing has been performed over one heartbeat period and the process proceeds to step S5, and then the process in step S4 is performed again based on the determination in step S6, the candidate frame extraction unit 26 sets the target heartbeat period to the next heartbeat period in the time series. If it is determined that the processing in steps S1 to S3 has been performed over the set one heartbeat period, the process proceeds to step S5. In step S5, the candidate frame extraction unit 26 uses the time-varying waveform of the anatomical structure during the set one heartbeat period to extract the ultrasound image U1 of the measurement candidate frame for this one heartbeat period.

[0061] If it is determined in step S6 that the scan is finished, the process proceeds to step S7. In step S7, the display control unit 22 highlights the ultrasound image U1 of the measurement candidate frame extracted in step S5 on the monitor 23. The display control unit 22 can highlight the ultrasound image U1 of the measurement candidate frame from among the multiple ultrasound image U frames in so-called cine playback, which sequentially plays back the acquired ultrasound image U of multiple frames as a video, for example as shown in Figure 5.

[0062] The display control unit 22 can highlight the ultrasound image U1 of a measurement candidate frame by, for example, differentiating the display of the frame of the ultrasound image U1 of the measurement candidate frame and the display of local anatomical structures such as the aortic valve annulus A visible in the ultrasound image U1 of the measurement candidate frame from the ultrasound images U of other frames.

[0063] The user can view several ultrasound images U, including the highlighted frame U1, from among multiple ultrasound images U, and easily and accurately select the ultrasound image U of the measurement frame that represents the mid-systolic phase from among those frames.

[0064] Once the process in step S7 is completed, the operation of the ultrasound diagnostic device according to the flowchart in Figure 6 is complete.

[0065] As described above, according to the ultrasound diagnostic apparatus of Embodiment 1 of the present invention, the time-varying waveform generation unit 25 generates a time-varying waveform of the anatomical structure state based on the local anatomical structure of the heart recognized by the image recognition unit 24, the candidate frame extraction unit 26 extracts an ultrasound image U1 of a measurement candidate frame representing the mid-systolic phase from multiple ultrasound images U using the time-varying waveform, and the display control unit 22 highlights the ultrasound image U1 of the measurement candidate frame on the monitor 23, so that the user can easily and accurately select an ultrasound image U1 of a frame representing the mid-systolic phase of the heart.

[0066] Although it is explained that the transmitting / receiving circuit 12 is provided in the ultrasonic probe 1, the transmitting / receiving circuit 12 may also be provided in the main body of the device 2. Furthermore, although it is explained that the image generation unit 21 is provided in the main body 2 of the device, the image generation unit 21 may also be provided in the ultrasonic probe 1.

[0067] The main unit 2 of the device may be a stationary type, a portable type that is easy to carry, or a handheld type, for example, composed of a smartphone or tablet computer. Thus, the type of equipment that makes up the main unit 2 is not particularly limited.

[0068] An example is described in which the candidate frame extraction unit 26 determines the duration of one heartbeat of the subject's heart using pre-stored template data relating to the time-varying waveform of the anatomical structure. However, for example, in the time-varying waveform of periods corresponding to multiple heartbeat durations, the repeating unit of the waveform can be identified, and that repeating unit can be identified as each of the one heartbeat durations.

[0069] Furthermore, the candidate frame extraction unit 26 can calculate the similarity between the ultrasound image U1 of one extracted measurement candidate frame and the ultrasound images U of frames sequentially generated by the image acquisition unit 30, and extract the ultrasound images U of frames whose calculated similarity is equal to or greater than the similarity threshold as the ultrasound images U1 of the measurement candidate frames for each heart rate period.

[0070] Furthermore, when this process is performed in real time while acquiring ultrasound images U, the display control unit 22 can sequentially highlight the ultrasound images U1 of the candidate measurement frames on the monitor 23 in real time. By checking the ultrasound images U1 of the candidate measurement frames highlighted for each heart rate period in this way, the user can proceed with the examination while confirming that the examination is appropriate.

[0071] Furthermore, after a sufficient number of ultrasound image U frames have been acquired by the image acquisition unit 30, the image recognition unit 24 can perform image recognition of the local anatomical structure of the heart in each ultrasound image U, the time-varying waveform generation unit 25 can generate time-varying waveforms of the anatomical structure, and the candidate frame extraction unit 26 can extract ultrasound image U1 of candidate frames for measurement. In this case, for example, multiple ultrasound image U frames acquired in past examinations can be stored in the memory 27, and the image recognition unit 24, time-varying waveform generation unit 25, and candidate frame extraction unit 26 can be used to process the multiple ultrasound image U frames stored in the memory 27.

[0072] Furthermore, while an example is described in which the candidate frame extraction unit 26 extracts an ultrasound image U1 of a measurement candidate frame using a time-varying waveform of one indicator from among multiple anatomical structural states such as the angular difference of the aortic valve annulus A with respect to the vascular axis, the valve distance of the mitral valve MV, the area of ​​the left ventricular LV, and the curvature of the left ventricular LV, it is also possible to extract a measurement candidate frame based on multiple time-varying waveforms relating to multiple indicators as anatomical structural states. For example, the candidate frame extraction unit 26 can extract an ultrasound image U1 of a measurement candidate frame during one heartbeat period based on each of the multiple time-varying waveforms, and then select the ultrasound image U of the frame extracted as the ultrasound image U1 of the measurement candidate frame from the time-varying waveforms that make up the most number of ultrasound images U of the multiple frames as the final ultrasound image U1 of the measurement candidate frame.

[0073] Furthermore, the display control unit 22 can display a list of ultrasound images U1 of multiple measurement candidate frames stored in the memory 27 on the monitor 23, as shown in Figure 7, for example. The user can select the ultrasound image U of the measurement frame that represents the mid-systolic phase from the list of ultrasound images U1 of multiple measurement candidate frames.

[0074] Furthermore, the display control unit 22 can display a jump button J on the monitor 23, for example, as shown in Figure 8. When the jump button J is selected by the user, the ultrasound image U1 of the measurement candidate frame and its enlarged image, ultrasound image U2, are immediately displayed on the monitor 23 from among multiple ultrasound image U frames. This eliminates the need for the user to search for the ultrasound image U1 of the measurement candidate frame among multiple ultrasound image U frames, and allows the user to easily select the ultrasound image U of the measurement frame by checking several ultrasound image U frames, including the ultrasound image U1 of the measurement candidate frame.

[0075] Embodiment 2 The ultrasound diagnostic device can also recommend one ultrasound image U from a given frame to the user if an ultrasound image U1 is extracted from each of the candidate frames during multiple heartbeat periods.

[0076] Figure 9 shows the configuration of the ultrasound diagnostic apparatus of Embodiment 2. The ultrasound diagnostic apparatus of Embodiment 2 is equipped with a device body 2A in place of the device body 2 shown in Figure 1 of the ultrasound diagnostic apparatus of Embodiment 1. The device body 2A further includes a frame recommendation unit 51 in the device body 2 of Embodiment 1, and is equipped with a device control unit 28A in place of the device control unit 28.

[0077] In the main unit 2A of the device, the frame recommendation unit 51 is connected to the time-varying waveform generation unit 25 and the memory 27. The frame recommendation unit 51 is connected to the display control unit 22 and the device control unit 28A. Furthermore, the image generation unit 21, the display control unit 22, the image recognition unit 24, the time-varying waveform generation unit 25, the candidate frame extraction unit 26, the device control unit 28A, and the frame recommendation unit 51 constitute the processor 31A for the main unit 2A.

[0078] The frame recommendation unit 51 compares the ultrasound images U1 of multiple measurement candidate frames stored in the memory 27, and selects an ultrasound image U of a frame suitable for measurement from among the ultrasound images U1 of multiple measurement candidate frames and recommends it to the user.

[0079] When the time-varying waveform generation unit 25 generates a time-varying waveform of the angular difference of the aortic valve annulus A with respect to the vascular axis, the frame recommendation unit 51 can, for example, select the ultrasound image U1 of the frame with the smallest angular difference from among multiple candidate ultrasound images U1 for measurement and recommend it to the user as the ultrasound image U of the frame suitable for measurement.

[0080] Furthermore, when the time-varying waveform generation unit 25 generates a time-varying waveform of the valve distance of the mitral valve MV, the frame recommendation unit 51 can, for example, select the ultrasonic image U1 of the frame with the smallest valve distance from among multiple candidate ultrasonic images U1 of measurement frames and recommend it to the user as the ultrasonic image U of the frame suitable for measurement.

[0081] Furthermore, when the time-varying waveform generation unit 25 generates a time-varying waveform of the area of ​​the left ventricular LV in the ultrasound image U, the candidate frame extraction unit 26 can use a trained model in machine learning to calculate the ultrasound image U1 of the measurement candidate frame that represents the mid-systolic time phase in each heartbeat period, and the accuracy, which is an index representing the likelihood of its selection. The frame recommendation unit 51 can, for example, select the ultrasound image U1 of the frame with the highest accuracy from among multiple measurement candidate frames and recommend it to the user as the ultrasound image U of the frame suitable for measurement.

[0082] Furthermore, when the time-varying waveform generation unit 25 generates a time-varying waveform of the curvature of the left ventricular LV in the ultrasound image U, the candidate frame extraction unit 26 can use a trained model in machine learning to calculate the ultrasound image U1 of the measurement candidate frame that represents the mid-systolic time phase in each heartbeat period, and the accuracy, which is an index representing the likelihood of its selection. The frame recommendation unit 51 can, for example, select the ultrasound image U1 of the frame with the highest accuracy from among multiple measurement candidate frames and recommend it to the user as the ultrasound image U of the frame suitable for measurement.

[0083] The frame recommendation unit 51 selects and recommends to the user an ultrasound image U of a frame suitable for measurement. By reviewing several ultrasound image Us, including the recommended frame's ultrasound image U, the user can easily and accurately select an ultrasound image U of a measurement frame that represents the mid-systolic phase of the heart. [Explanation of Symbols]

[0084] 1 Ultrasound probe, 2,2A Main unit, 11 Transducer array, 12 Transmit / receive circuit, 21 Image generation unit, 22 Display control unit, 23 Monitor, 24 Image recognition unit, 25 Time-varying waveform generation unit, 26 Candidate frame extraction unit, 27 Memory, 28,28A Device control unit, 29 Input device, 30 Image acquisition unit, 31,31A Processor, 41 Pulsar, 42 Amplifier unit, 43 AD conversion unit, 44 Beamformer, 45 Signal processing unit, 46 DSC, 47 Image processing unit, 51 Frame recommendation unit, A Aortic valve annulus, B Scroll bar, J Jump button, LV Left ventricle, MV Mitral valve, SL Slider, T Left ventricular outflow tract, U,U1,U2 Ultrasound image.

Claims

1. An ultrasound diagnostic device that guides the user to a frame suitable for measuring the diameter of the left ventricular outflow tract from multiple ultrasound images of the subject's heart, An image recognition unit that image-recognizes the local anatomical structure of the heart in each of the aforementioned multiple frames, A time-varying waveform generation unit generates a time-varying waveform of the anatomical structure state based on the local anatomical structure recognized by the image recognition unit, A candidate frame extraction unit extracts candidate frames from the plurality of frames using the time-varying waveform generated by the time-varying waveform generation unit, Monitor and, A display control unit that highlights the measurement candidate frames extracted by the candidate frame extraction unit on the monitor. An ultrasound diagnostic device equipped with the following features.

2. The ultrasound diagnostic apparatus according to claim 1, comprising a memory that stores a plurality of measurement candidate frames extracted by the candidate frame extraction unit during multiple past heartbeat periods, and the local anatomical structures corresponding to each of the measurement candidate frames and recognized by the image recognition unit.

3. The image recognition unit recognizes the aortic valve annulus as the local anatomical structure, The time-varying waveform generation unit generates the time-varying waveform of the angular difference of the aortic valve annulus with respect to the vascular axis, The ultrasonic diagnostic apparatus according to claim 1, wherein the candidate frame extraction unit extracts the frame in which the angle difference in the time-varying waveform is minimized as the measurement candidate frame.

4. The image recognition unit recognizes the mitral valve as the local anatomical structure, The time-varying waveform generation unit generates the time-varying waveform of the valve distance of the mitral valve, The ultrasonic diagnostic apparatus according to claim 1, wherein the candidate frame extraction unit extracts the frame in which the valve distance in the time-varying waveform is minimized as the measurement candidate frame.

5. The image recognition unit recognizes the left ventricle as the local anatomical structure, The time-varying waveform generation unit generates the time-varying waveform of the area of ​​the left ventricle, The ultrasonic diagnostic apparatus according to claim 1, wherein the candidate frame extraction unit extracts the measurement candidate frame based on the time-varying waveform of the area.

6. The image recognition unit recognizes the left ventricle as the local anatomical structure, The time-varying waveform generation unit generates the time-varying waveform of the curvature of the left ventricle contour, The ultrasonic diagnostic apparatus according to claim 1, wherein the candidate frame extraction unit extracts the measurement candidate frames based on the time-varying waveform of the curvature.

7. The ultrasonic diagnostic apparatus according to claim 1, wherein the display control unit highlights the measurement candidate frame by changing the brightness or color of the border line of the measurement candidate frame extracted by the candidate frame extraction unit.

8. The ultrasound diagnostic apparatus according to claim 1, wherein the display control unit highlights the measurement candidate frame by changing the brightness or color of the local anatomical structure in the measurement candidate frame extracted by the candidate frame extraction unit.

9. The time-varying waveform generation unit generates multiple time-varying waveforms relating to multiple indicators as the anatomical structure state, The ultrasonic diagnostic apparatus according to claim 1, wherein the candidate frame extraction unit extracts the measurement candidate frames based on the plurality of time-varying waveforms generated by the time-varying waveform generation unit.

10. The ultrasonic diagnostic apparatus according to claim 2, wherein the display control unit displays a plurality of measurement candidate frames stored in the memory on the monitor in a list.

11. The ultrasound diagnostic apparatus according to claim 2, further comprising a frame recommendation unit that selects a frame suitable for measurement from among the multiple measurement candidate frames by comparing the multiple measurement candidate frames stored in the memory and recommends it to the user.

12. A control method for an ultrasound diagnostic device that guides the user to a frame suitable for measuring the diameter of the left ventricular outflow tract from multiple ultrasound images of the subject's heart, The local anatomical structure of the heart in each of the aforementioned multiple frames is recognized by image recognition. Based on the image-recognized local anatomical structure, a time-varying waveform of the anatomical structure state is generated. Using the generated time-varying waveform, candidate frames for measurement are extracted from the multiple frames. The extracted candidate frames for measurement are highlighted on the monitor. A method for controlling an ultrasound diagnostic device.

Images