Medical information processing device, ultrasound diagnostic device, and program

Abstract

To obtain high-resolution ultrasound data with high responsiveness.SOLUTION: A medical information processing device according to an embodiment includes an acquisition unit, an extraction unit, and an output unit. The acquisition unit acquires first ultrasound data obtained on the basis of the result of an ultrasound scan of a subject. The extraction unit continuously extracts signal components representing an object from the first ultrasound data. The output unit outputs second ultrasound data on the basis of the signal components representing the object which is continuously extracted.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The embodiments disclosed in this specification and the drawings relate to a medical information processing device, an ultrasound diagnostic device, and a program. [Background technology]

[0002] Ultrasound diagnostic devices are widely used to observe and diagnose blood flow in living bodies. Ultrasound diagnostic devices generate and display blood flow information from reflected ultrasonic waves using the Doppler method based on the Doppler effect. Examples of blood flow information generated and displayed by ultrasound diagnostic devices include color Doppler images and Doppler waveforms (Doppler spectra).

[0003] Color Doppler images are captured using the Color Flow Mapping (CFM) method. In the CFM method, ultrasonic waves are transmitted and received multiple times on multiple scanning lines. Then, a Moving Target Indicator (MTI) filter is applied to the data sequence at the same position to suppress signals (clutter signals) originating from stationary or slow-moving tissues and extract signals originating from blood flow. The CFM method estimates blood flow information such as blood flow velocity, variance, and power values ​​from the blood flow signals, and displays the distribution of the estimated results as a Doppler image.

[0004] It is known that the resolution of B-mode data and Doppler data decreases due to the point spread function (PSF), which is determined by the wavelength of the transmitted ultrasound, the transmit / receive aperture width, etc. Although there are solutions such as increasing the frequency of the transmitted ultrasound, there is a limit to the resolution of the image that can be obtained because there is also a limit to the frequency band of the probe.

[0005] Non-Patent Document 1 describes a method of generating blood flow data with improved resolution by extracting and accumulating high signal values ​​(amplitude values) from multiple blood flow data that are continuous in the time direction. More specifically, Non-Patent Document 1 describes a method of utilizing the fact that the amplitude distribution characteristics of the speckle pattern of blood flow data can be approximately approximated by a probability distribution called Rayleigh distribution. As a result, high-intensity, spatially sparse signals that have a low occurrence probability but a large signal value (amplitude value) are extracted from each blood flow data and are accumulated.

[0006] However, in the method described in Non-Patent Document 1, if the number of frames used to extract the object is small, the object is extracted discretely (discontinuously), and high-resolution blood flow data (ultrasound data) cannot be obtained. On the other hand, if the number of frames used is large, the load of the calculation process increases and the responsiveness deteriorates. [Prior art documents] [Non-patent literature]

[0007] [Non-Patent Document 1] Jorgen Arendt Jensen et al., “Fast super resolution ultrasound imaging using the erythrocytes,” Proc. SPIE 12038, Medical Imaging 2022: Ultrasonic Imaging and Tomography,120380E, April 4, 2022 Summary of the Invention [Problem to be solved by the invention]

[0008] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to obtain high-resolution ultrasound data with high responsiveness. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]

[0009] A medical image processing device according to an embodiment includes an acquisition unit, an extraction unit, and an output unit. The acquisition unit acquires first ultrasound data obtained based on a result of an ultrasound scan of a subject. The extraction unit continuously extracts signal components representing an object from the first ultrasound data. The output unit outputs second ultrasound data based on the continuously extracted signal components representing the object. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram showing the configuration of an ultrasonic diagnostic apparatus according to an embodiment. [Diagram 2] FIG. 2 is a diagram for explaining the Rayleigh distribution. [Diagram 3] FIG. 3 is a flowchart showing the flow of processing executed by the medical image processing apparatus shown in FIG. [Figure 4] FIG. 4 is a schematic diagram for explaining the processing performed by the medical image processing apparatus according to the embodiment. [Diagram 5] FIG. 5 is a schematic diagram for explaining a process according to a comparative example. [Figure 6] FIG. 6 is a diagram showing how an object is extracted by a kernel according to the embodiment. [Figure 7A] FIG. 7A is a diagram showing a configuration of the first ultrasound data. [Figure 7B] FIG. 7B is a diagram showing the result of object extraction when a kernel according to a comparative example is used. [Figure 7C] FIG. 7C is a diagram showing a result of extraction of an object when the kernel according to the embodiment is used. [Figure 8] FIG. 8 is a diagram for explaining signal processing according to a comparative example. [Figure 9] FIG. 9 is a diagram for explaining signal processing according to the embodiment. [Figure 10A] FIG. 10A is a diagram showing ultrasound data according to a first comparative example. [Figure 10B] FIG. 10B is a diagram showing ultrasound data according to the second comparative example. [Figure 10C] FIG. 10C is a diagram showing second ultrasound data (high-resolution image data) according to the embodiment. [Figure 11] FIG. 11 is a diagram showing how an object is extracted by a kernel according to another embodiment. [Figure 12] FIG. 12 is a diagram illustrating the process according to the second embodiment. [Figure 13] FIG. 13 is a diagram illustrating a process according to a modification of the second embodiment. [Figure 14] FIG. 14 is a flowchart illustrating an example of a procedure according to the third embodiment. [Figure 15] FIG. 15 is a diagram illustrating an example of processing according to the third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] (First embodiment) Hereinafter, embodiments of a medical image processing device, an ultrasound diagnostic device, and a program will be described in detail with reference to the drawings.

[0012] The ultrasound diagnostic apparatus according to this embodiment causes an ultrasound probe to perform an ultrasound scan, and collects multiple frame data (multiple frame data within a predetermined time) that are continuous in the time direction and obtained by performing the ultrasound scan. The frame data is collected at a predetermined frame rate by performing the ultrasound scan. The frame data refers to any of reception data, measurement data, blood flow data, and tissue data. The reception data is, for example, a reception signal of ultrasound received by an ultrasound probe (e.g., CH data). The measurement data is data (e.g., IQ data) obtained by performing phasing addition and quadrature detection processing on the reception signal of ultrasound. The blood flow data is data (e.g., power signal data) in which information derived from blood flow in the measurement data is extracted or emphasized. The tissue data is data (e.g., B-mode data) in which information derived from tissue is extracted or emphasized.

[0013] The measurement data includes, for example, information derived from tissue (tissue signal components (clutter)) and information derived from blood flow (blood flow signal components). The information derived from blood flow may include not only information derived from blood but also information derived from contrast agents in blood. Furthermore, the blood flow data is data in which information derived from blood flow is extracted or emphasized, and includes blood flow velocity values, variance values, and power values.

[0014] The extraction of information derived from blood flow is, for example, an operation of extracting blood flow signal components from the measurement data. The emphasis of information derived from blood flow is, for example, an operation of making the blood flow signal components more prominent than the tissue signal components. Note that the blood flow data may be obtained by a process of extracting or emphasizing information derived from blood flow, or by a process of removing or reducing information derived from tissue.

[0015] The ultrasound diagnostic device also acquires sum data obtained by summing a plurality of frame data as first ultrasound data. The first ultrasound data is, for example, data having a higher SN ratio (signal-noise ratio) than each frame data. The ultrasound diagnostic device performs processing to continuously extract signal components representing an object from the first ultrasound data. The object includes, for example, any of blood, body tissue, and contrast agent.

[0016] The ultrasound diagnostic device outputs second ultrasound data based on the signal components representing the continuously extracted objects. The second ultrasound data may be any of synthetic data obtained by synthesizing the signal components representing the continuously extracted objects and the first ultrasound data, corrected data obtained by correcting the first ultrasound data based on the signal components representing the continuously extracted objects, and data including the signal components representing the continuously extracted objects.

[0017] According to the ultrasonic diagnostic device of this embodiment, even if the number of frames used for extracting the object is small, the object can be extracted continuously. This allows high-response, high-resolution ultrasonic data (high-resolution data) to be obtained. Furthermore, according to the ultrasonic diagnostic device of this embodiment, the process for extracting the signal components representing the object can be suppressed to 1 / the number of frames compared to the conventional method, and the calculation load can be significantly reduced.

[0018] Although the above description has been given of an example in which the present invention is applied to an ultrasonic diagnostic device, the present invention may be applied to a modality (medical information processing device) other than an ultrasonic diagnostic device. For example, the present invention may be applied to a medical information processing device such as a workstation or server that acquires ultrasonic data obtained based on the results of an ultrasonic scan of a subject.

[0019] FIG. 1 is a block diagram showing the configuration of an ultrasonic diagnostic device according to an embodiment. The ultrasonic diagnostic device 10 is a device that generates ultrasonic data based on a reception signal (reflected wave signal) received from an ultrasonic probe 5. The ultrasonic diagnostic device 10 shown in FIG. 1 is a device that can generate two-dimensional ultrasonic data based on a two-dimensional reception signal and can generate three-dimensional ultrasonic data based on a three-dimensional reception signal. However, the embodiment is also applicable to cases where the ultrasonic diagnostic device 10 is a device dedicated to two-dimensional data. The ultrasonic diagnostic device 10 includes a transmission circuit 9, a reception circuit 11, and a medical information processing device 100.

[0020] The ultrasonic probe 5 is, for example, an electronic scanning type probe, and has a plurality of transducers 101 arranged one-dimensionally or two-dimensionally at its tip. The transducer 101 is a piezoelectric element (electromechanical conversion element) that performs mutual conversion between an electric signal (voltage pulse signal) and an ultrasonic wave (acoustic wave). The ultrasonic probe 5 transmits ultrasonic waves from the plurality of transducers 101 to a subject, and receives reflected ultrasonic waves from the subject by the plurality of transducers 101. The reflected acoustic wave reflects the difference in acoustic impedance within the subject. Note that when a transmitted ultrasonic pulse is reflected by the surface of a moving blood flow, a heart wall, or the like, the reflected ultrasonic wave undergoes a frequency shift due to the Doppler effect depending on a velocity signal component in the ultrasonic transmission direction of the moving body.

[0021] The probe connection unit 103 connects to the ultrasonic probe 5 and transmits and receives ultrasonic waves to and from the ultrasonic probe 5. The connection means of the ultrasonic probe 5 by the probe connection unit 103 may be either wired or wireless. In the case of a wired connection, the probe connection unit 5 has a connector unit (receptacle) for connecting a connector (plug) of the ultrasonic probe 5. In the case of a wireless connection, the probe connection unit 5 has a communication unit for wireless communication with the ultrasonic probe 5.

[0022] The transmission circuit 9 is a transmission unit that outputs a pulse signal (drive signal) to the multiple transducers 101. By applying a pulse signal to the multiple transducers 101 with a time difference, ultrasonic waves with different delay times are transmitted from the multiple transducers 101, and a transmitted ultrasonic beam is formed. The direction and focus of the transmitted ultrasonic beam can be controlled by selectively changing the transducer 101 to which the pulse signal is applied (i.e., the transducer 101 to be driven) or by changing the delay time (application timing) of the pulse signal. By sequentially changing the direction and focus of the transmitted ultrasonic beam, an observation area inside the subject is scanned. In addition, by changing the delay time of the pulse signal, a transmitted ultrasonic beam that is a plane wave (focus is far away) or a diverging wave (focus point is the opposite ultrasonic transmission direction for the multiple transducers 101) may be formed. Alternatively, a transmitted ultrasonic beam may be formed using one transducer or a part of the multiple transducers 101. The transmission circuit 9 transmits a pulse signal of a predetermined drive waveform to the transducer 101, causing the transducer 101 to generate a transmitted ultrasonic wave having a predetermined transmission waveform.

[0023] The receiving circuit 11 is a receiving section that inputs, as a received signal, an electrical signal output from the transducer 101 that has received a reflected ultrasonic wave. The received signal is input to the processing circuit 110. In this embodiment, the analog signal output from the transducer 101 and the digital data obtained by sampling (digital conversion) the analog signal are both referred to as received signals without any particular distinction. However, depending on the context, the received signal may be referred to as received data or measured data in order to clearly indicate that it is digital data.

[0024] The medical information processing device 100 is connected to a transmission circuit 9 and a reception circuit 11, and processes signals received from the reception circuit 11 and controls the transmission circuit 9. The medical information processing device 100 includes a processing circuit 110, a memory 132, an input device 134, and a display 135.

[0025] The memory 132 is composed of a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, an optical disk, etc. The memory 132 is a memory that stores data such as image data for display generated by the processing circuit 110. The memory 132 can also store a reception signal (reflected wave signal) output by the reception circuit 11. In addition, the memory 132 stores, as necessary, a control program for performing ultrasonic transmission / reception, image processing, and display processing, diagnostic information (e.g., patient ID, doctor's findings, etc.), diagnostic protocols, various body marks, and other various data.

[0026] The input device 134 receives various instructions and information input from an operator and is composed of an input interface device such as a mouse, a keyboard, a button, a trackball, etc.

[0027] The display 135 displays a GUI (Graphical User Interface) for receiving input of imaging conditions and various images under the control of the processing circuitry 110. The display 135 is configured, for example, from a display interface device such as a liquid crystal display.

[0028] The processing circuit 110 controls each part of the ultrasound diagnostic device 10, thereby controlling the entire ultrasound diagnostic device 10. Although the processing circuit 110 is described as being realized as a single circuit in Fig. 1, it may be realized as a large number of circuits by combining a plurality of independent processors. Also, a specific function may be configured as an independent circuit dedicated to a specific function, such as an ASIC (Application Specific Integrated Circuit).

[0029] Furthermore, the term "processor" used in the above description refers to circuits such as a CPU (Central Processing Unit), a GPU (Graphical Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). The processor realizes functions by reading and executing a program stored in memory 132.

[0030] The processing circuit 110 causes the ultrasonic probe 5 to execute an ultrasonic scan, and collects a plurality of frame data (a plurality of frame data within a predetermined time) that are continuous in the time direction and obtained by executing the ultrasonic scan. The processing circuit 110 performs delay-and-sum processing and quadrature detection processing on the reception signal (CH data) collected via the reception circuit 11. The delay-and-sum processing is processing in which the reception signals of the plurality of transducers 101 are added together by changing the delay time and weight for each transducer 101, and is also called delay and sum (DAS) beamforming. The quadrature detection processing is processing in which the reception signal is converted into an in-phase signal and a quadrature signal (IQ data (measurement data)) in the baseband. In addition, adaptive beamforming, model-based processing, processing using machine learning, and the like may be performed on the reception signal.

[0031] Furthermore, the processing circuitry 110 may estimate the amount of tissue displacement caused by the subject's body movement or the like between multiple frame data, and correct each frame data based on the estimated result. Specifically, the processing circuitry 110 calculates the amount of tissue displacement caused by the body movement or the like between frames from multiple frame data. The processing circuitry 110 corrects the frame data based on the calculated amount of displacement.

[0032] The processing circuitry 110 also performs envelope detection processing, logarithmic compression processing, etc. to generate B-mode data (data in which information derived from tissue is extracted or emphasized) in which the signal intensity at each point in the observation region is expressed as brightness. The processing circuitry 110 also generates blood flow data (power signal data) in which information derived from blood flow in the measurement data is extracted or emphasized.

[0033] For example, the processing circuit 110 applies an MTI (Moving Target Indicator) filter to the multiple frame data. This reduces information (tissue signal components (clutter)) derived from tissues that are stationary between frames or tissues with little movement, and extracts information derived from blood flow (blood flow signal components). The MTI filter may be a filter with fixed filter coefficients, such as a Butterworth type IIR (infinite impulse response) filter or a polynomial regression filter. The MTI filter may be an adaptive filter that changes coefficients according to an input signal using eigenvalue decomposition or singular value decomposition.

[0034] The processing circuitry 110 may also decompose the frame data into a plurality of bases by eigenvalue decomposition or singular value decomposition, and may extract information derived from the blood flow by removing information derived from tissues by extracting a specific base. The processing circuitry 110 may also use a method such as a vector Doppler method, a speckle tracking method, or a vector flow mapping method to obtain a velocity vector for each coordinate in the received signal data, and obtain a blood flow vector representing the magnitude and direction of the blood flow. In addition to the methods exemplified here, any method may be used as long as it can extract or emphasize information derived from the blood flow contained in the frame data (received data, measured data), or can remove or reduce information derived from tissues.

[0035] Furthermore, the processing circuit 110 reads out and executes a program stored in the memory 132, thereby causing the acquisition function 111, the extraction function 112, and the output function 113 to function, and performs processing to output high-resolution ultrasound data (high-resolution image data 29 shown in FIG. 4).

[0036] Before describing the process of outputting high-resolution ultrasound data using the ultrasound diagnostic device 10 configured as above, a method of generating high-resolution data according to the conventional technology (for example, the method described in Non-Patent Document 1) will be described.

[0037] It is known that the amplitude distribution characteristic 50 of the speckle pattern of blood flow data can be approximately approximated by a probability distribution called a Rayleigh distribution, as shown in Fig. 2. In the method of generating high-resolution data according to the conventional technology, as shown in Fig. 5, high-intensity and spatially sparse signals 32 (points 51 shown in Fig. 2) that have a low occurrence probability but a large signal value (amplitude value) are extracted from a plurality of blood flow data 31 corresponding to each of a plurality of frame data 30, and ultrasonic data 33 (ultrasonic image 39) is generated by accumulating these.

[0038] However, the number of frames required to generate a single high-resolution blood flow data (ultrasound data 33 shown in Figure 5) using this method is several thousand to several tens of thousands. With this method, if the number of frames used to extract the object is small, the object is extracted discretely (discontinuously), and high-resolution blood flow data cannot be obtained. On the other hand, using a large number of frames increases the computational processing load and reduces responsiveness.

[0039] Hereinafter, the processing performed by the medical information processing device 100 will be described with reference to Fig. 3 and Fig. 4. The processing circuit 110 collects and acquires a plurality of frame data 20 (received signals, measurement data, etc.) that are continuous in the time direction and obtained by performing an ultrasound scan, as shown in Fig. 4, by using the acquisition function 111 (step S100). The number of frames of the frame data 20 when generating high-resolution data is approximately the same as when generating general Doppler data. For example, the number of frames (number of packets) when generating Doppler data is about several tens. On the other hand, the number of frame data 20 collected by the acquisition function 111 is about several tens to several hundreds, which is significantly smaller than the number of frame data collected by the method according to the conventional technology (about several thousands to tens of thousands).

[0040] Furthermore, the processing circuit 110 estimates the amount of tissue displacement caused by the subject's body movement between multiple frame data, and corrects each frame data based on the estimated result (step S150). Specifically, the processing circuit 110 calculates the amount of tissue displacement caused by body movement between frames from a received signal including a data sequence of multiple frames. The processing circuit 110 corrects the amount of displacement by using the calculated amount of displacement and moving the received signal so that the positions are aligned within the frame in which the integration process described below is performed. Here, the reference frame for calculating the amount of displacement may be only one frame in the entire data sequence, or the reference frame may be changed depending on the time direction position (i.e., multiple reference frames may be provided), or the previous frame in the adjacent frame may be used as the reference frame. The reference frame may be selected arbitrarily from the data sequence, and for example, any of the first frame, the middle frame, and the last frame may be used as the reference frame.

[0041] The processing circuitry 110 also applies an MTI filter to the plurality of frame data whose displacements have been corrected, thereby reducing information (tissue signal components (clutter)) derived from tissues that are stationary or move little between frames, and extracting information derived from blood flow (blood flow signal components) (step S170).

[0042] As shown in FIG. 4, the acquisition function 111 performs an addition process on a plurality of frame data 20, and acquires the single added data obtained as the first ultrasound data 21 (step S200). That is, the acquisition function 111 acquires the first ultrasound data 21 obtained based on the result of an ultrasound scan on the subject. The first ultrasound data 21 has a higher SN ratio (signal-noise ratio) than each of the frame data 20 before addition. The first ultrasound data 21 is blood flow data (power signal data) from which information derived from blood flow is extracted. Note that, as shown in FIG. 5, in the method of generating high-resolution data according to the conventional technology, the addition process shown in step S200 is not performed, and blood flow data 31 corresponding to each of the plurality of frame data 30 is generated.

[0043] The extraction function 112 performs a process of continuously extracting signal components representing an object from the first ultrasound data 21 (step S300). The object here is something that is to be highly resolved, and includes at least one of blood, body tissue, and contrast agent. Furthermore, continuously extracting signal components representing an object means extracting the positions of signals (pixels) representing the object without leaving a predetermined interval in the signal space or image space. For example, when the object is blood, the extraction function 112 extracts the positions of signals (pixels) representing blood without leaving a predetermined interval in the signal space or image space. As a result, the extraction function 112 acquires signal components 22, which are extracted data representing the object, as shown in FIG. 4.

[0044] Here, an example of a method for continuously extracting signal components representing an object will be described with reference to FIG. 6 and FIG. 7A to FIG. 7C. For each of a plurality of positions of interest included in the first ultrasound data 21, the extraction function 112 extracts the signal component of the position of interest as a signal component representing the object based on a comparison result between a signal value located in a predetermined direction and range of interest relative to the position of interest and the signal value of the position of interest. If the signal value of the position of interest is greater than or equal to a signal value located in a predetermined direction and range, the extraction function 112 extracts the signal component of the position of interest as a signal component representing the object. For example, as shown in FIG. 6, the extraction function 112 extracts the position of a signal (pixel) representing blood using a kernel 40 based on a ratio of 3 vertical x 1 horizontal. Note that, for convenience of explanation, an example is shown here in which the pixel value (luminance value) of the position of interest is compared with the pixel value located in a predetermined range for each direction of interest relative to the position of interest on a two-dimensional image, but the signal value of the position of interest may be compared with the signal value located in a predetermined range one-dimensionally for the first ultrasound data 21. That is, the signal components representing the object may be extracted without developing the first ultrasound data 21 into an image.

[0045] Each square in Fig. 7A represents a pixel value (brightness value) of the image represented by the first ultrasound data 21. When extracting a position having a relatively high pixel value from the first ultrasound data 21, for example, as shown in Fig. 7B, a kernel of 3 x 3, totaling 9 squares, including the position of interest and 8 squares adjacent to the position of interest, is used. In this case, when the pixel value of the position of interest is higher than any of the 8 adjacent squares, the processing circuit 110 extracts the position of interest as the position of a pixel (signal) representing blood.

[0046] However, when the kernel shown in FIG. 7B is used, the object (blood vessel, etc.) is extracted discretely, and its structure is not fully expressed. On the other hand, when the kernel 40 shown in FIG. 6 is used, the object is extracted continuously, as shown in FIG. 7C. Specifically, the kernel 40 has three squares in one row, and each square corresponds to one pixel. The pixel corresponding to the central square is set as the position of interest, and the pixels corresponding to the two squares adjacent to the central square are set as positions to be compared. More specifically, when the kernel 40 is set at the position shown in FIG. 6, the pixel value of the position of interest is higher than the pixel values ​​of the adjacent positions, so that position of interest is extracted as the object.

[0047] In the above example, the kernel 40 extracts signal components representing an object in four directions: vertical, horizontal, diagonally upper right, and diagonally upper left, but the shape and size of the kernel are not limited to this. Also, the extraction function 112 may extract the target position as the object even if the pixel value of the target position is equal to the pixel value of pixels located in a predetermined direction and range.

[0048] In other words, in the embodiment, since signal components representing the object can be continuously extracted from the first ultrasound data 21, it can be said that the extraction conditions for the signal components representing the object are looser than those in the conventional method. The extraction conditions can be loosened because the data (first ultrasound data 21) with a high S / N ratio obtained by the addition process in step S200 is used as the extraction target.

[0049] In the above example, an example of extracting an object in units of pixels has been shown, but an object may be continuously extracted in units of groups having a plurality of pixels. When extracting an object in units of groups having a plurality of pixels, the average value or integrated value of each pixel constituting the group may be set as the pixel value (signal value) of the group. In this case, the extraction function 112 extracts a signal component representing an object for each group having a plurality of pixels based on the result of comparison between the pixel values ​​of other groups located in a predetermined direction and range and the pixel values ​​of the group at the position of interest.

[0050] As another example, the extraction function 112 may compare the signal value (pixel value) of each of the positions of interest included in the first ultrasound data 29 with the signal value (pixel value) of a position within a predetermined range for each direction of interest relative to the position of interest, and weight the signal component of the position of interest based on the comparison result and a weighting factor previously determined for each direction of interest. For example, when four directions of vertical, horizontal, diagonally upper right, and diagonally lower left are set as directions of interest, a weighting factor is set in advance for each direction. Then, if the pixel value of the position of interest in the three directions of vertical, horizontal, and diagonally upper right is greater than or equal to the adjacent pixel value, the extraction function 112 weights the pixel value of the position of interest by the weighting factor determined for each of the three directions (multiplying the pixel value by the weighting factor). As a result, the pixel value of the position of interest is changed and emphasized based on the comparison result and the weighting factor determined for each direction.

[0051] Next, the output function 113 performs a process of outputting the second ultrasound data 23 based on the signal components 22 (extracted data) representing the object continuously extracted in step S300 (step S400). For example, the output function 113 outputs the composite data or the corrected data as the second ultrasound data 23. As shown in FIG. 4, the composite data is obtained by a composite process (addition) of the signal components 22 (extracted data) representing the object continuously extracted and the first ultrasound data 21 (power signal data). The corrected data is obtained by a correction process of the first ultrasound data 21 (power signal data) based on the signal components 22 (extracted data) representing the object continuously extracted. The first ultrasound data 29, which is a high-resolution image shown in FIG. 4, is obtained by imaging the second ultrasound data 23 by the output function 113.

[0052] Next, the signal processing according to the comparative example and the embodiment will be compared with reference to FIG. 8 and FIG. 9. As shown in FIG. 8, in the comparative example, the addition processing according to the present embodiment is not performed on several thousands to several tens of thousands of frame data 30, and a plurality of blood flow data 31 (power signal data) corresponding to the frame data 30 are generated. In addition, in the comparative example, a high-luminance, spatially sparse signal having a large signal value (amplitude value) is extracted from each of the plurality of blood flow data 31, and a plurality of frames of extracted data 32 are obtained. Then, in the comparative example, the extracted plurality of extracted data 32 are integrated. As described above, in this method, if the number of frames used to extract the object is small, the object is extracted discretely (discontinuously), and high-resolution blood flow data cannot be obtained. On the other hand, if the number of frames used is increased, the load of the calculation processing increases, and the responsiveness deteriorates.

[0053] On the other hand, as shown in FIG. 9, in the medical information processing apparatus 100 according to the embodiment, the acquisition function 111 performs an addition process on several tens to several hundreds of frame data 20, and acquires the single addition data obtained as the first ultrasound data 21. In addition, in the medical information processing apparatus 100, the extraction function 112 performs a process of continuously extracting signal components representing the object from the first ultrasound data 21, and acquires the signal components 22 that are extracted data representing the object. Then, in the medical information processing apparatus 100, the output function 113 outputs the second ultrasound data 23 based on the signal components representing the continuously extracted object. According to this method, even if the number of frames used to extract the object is small, the object can be continuously extracted. As a result, ultrasound data (high-resolution data) with high responsiveness can be obtained. In addition, according to the ultrasound diagnostic apparatus according to the present embodiment, the process of extracting the signal components representing the object can be suppressed to 1 / the number of frames compared to the conventional method, and the calculation load can be significantly reduced.

[0054] 10A to 10C, the blood flow data according to the comparative example and the embodiment will be compared. FIG. 10A is an ultrasound image (blood flow data) according to the first comparative example, which was obtained using the SMI (superb micro-vascular imaging) method. FIG. 10B is an ultrasound image (blood flow data) according to the second comparative example, which was obtained by the conventional method shown in FIG. 5. FIG. 10C is first ultrasound data 29, which is a high-resolution image obtained by the method according to the embodiment shown in FIG. 4. The high-resolution image 29 depicts the blood flow with higher resolution than the ultrasound image shown in FIG. 10A. Moreover, the high-resolution image 29 shown in FIG. 10C depicts the peripheral blood flow in detail and with continuity than the ultrasound image shown in FIG. 10B.

[0055] As described above, according to the medical image processing device 100 of the embodiment, even if the number of frames used for extracting the object is small, the object (blood, contrast agent, etc.) can be continuously extracted. This allows high-response, high-resolution ultrasound data (high-resolution data) to be obtained. Furthermore, according to the ultrasound diagnostic device of the present embodiment, the process for extracting the signal component representing the object can be suppressed to 1 / the number of frames compared to the conventional method, and the calculation load can be significantly reduced.

[0056] The embodiments are not limited to the above examples, and various modifications are possible without departing from the spirit of the invention.

[0057] For example, in the above embodiment, the acquisition function 111 acquires single added data with an improved S / N ratio by adding multiple frame data as the first ultrasound data. However, ultrasound data with an improved S / N ratio may be acquired without performing this addition process. For example, the acquisition function 111 may input multiple frame data 20 consecutive in the time direction obtained by performing an ultrasound scan on a subject to a trained model that outputs single ultrasound data with a higher S / N ratio than multiple frame data obtained by performing an ultrasound scan, and acquire the single ultrasound data output from the trained model as the first ultrasound data 21. This trained model is trained by a data set in which multiple frame data is input data and single ultrasound data with a higher S / N ratio than each frame data is used as teacher data. The acquisition function 111 inputs multiple frame data 20 to the trained model and acquires the single ultrasound data with a higher S / N ratio than the multiple frame data output from the trained model as the first ultrasound data 21.

[0058] In addition, the acquisition function 111 may not perform processing to improve the S / N ratio, and may acquire the first ultrasound data 21 obtained based on the result of an ultrasound scan on the subject. For example, the acquisition function 111 may acquire ultrasound data with a high S / N ratio received from an external workstation or the like as the first ultrasound data 21.

[0059] In the above embodiment, the extraction function 112 performs the process of continuously extracting signal components representing an object from the first ultrasound data 21 by using the kernel 40 shown in FIG. 6, for example. However, the process of extracting signal components representing an object may be performed without using a kernel. For example, the extraction function 112 may input the first ultrasound data 21 to a trained model that continuously outputs signal components representing an object contained in ultrasound data by inputting a single piece of ultrasound data having a higher S / N ratio than a plurality of frame data consecutive in the time direction obtained by executing an ultrasound scan, and acquire signal components 22 (extracted data) representing an object continuously extracted from the trained model. This trained model is trained by a data set or the like in which ultrasound data with an improved S / N ratio is used as input data and signal components in the ultrasound data that continuously represent an object are used as teacher data. The extraction function 112 inputs the first ultrasound data acquired by the acquisition function 111 to the trained model and acquires the signal components that continuously represent an object output from the trained model. This allows the signal components representing an object to be continuously extracted from the first ultrasound data 21 without using a kernel.

[0060] In addition, the kernel according to the embodiment is described with an example of a kernel based on a ratio of 3 vertical x 1 horizontal, but is not limited thereto. For example, as shown in FIG. 11, a kernel based on a ratio of 5 vertical x 1 horizontal may be used, in which only the first, third, and fifth squares from the left of the 5 x 1 squares are used. For example, when the kernel 61 is applied to the pre-extraction signal 60, a signal value of "10" is extracted. When the kernel 62 is applied to the pre-extraction signal 60 (when the kernel 61 is shifted one square to the right), a signal value of "8" is extracted. Therefore, by using such kernels 61 and 62, even if relatively large signal values ​​exist adjacent to each other in the direction in which the kernels are arranged, the signal components (signal values ​​"10" and "8") representing the object can be continuously extracted.

[0061] In the above explanation, an example of generating high-resolution blood flow data has been mainly described, but the method according to the embodiment can also generate high-resolution internal tissue data and contrast data.

[0062] Second embodiment In the second embodiment, in step S400, when the output function 133 outputs the second ultrasound data based on the signal components representing the continuously extracted object, an inappropriate signal point or an inappropriate frame is identified from the signal components representing the continuously extracted object, and the second ultrasound data is output based on the identification result of the inappropriate signal point or the inappropriate frame. In the second embodiment and the modified example of the second embodiment, for example, Patent Application No. 2023-164256 filed on September 27, 2023 is cited.

[0063] 12 shows a plurality of second signal data extracted in step S400. Here, frames 521 to 524 represent each frame of the first ultrasound data of the plurality of frames, or each frame of the blood flow signal data obtained by performing the process of step S400 on the first ultrasound data of the plurality of frames and performing clutter removal processing. For example, the data of frame 521 represents the first signal data in the first frame, or the blood flow signal data after the first signal data in the first frame has been subjected to clutter removal processing. Moreover, the data of frame 522 represents the first ultrasound data in the second frame.

[0064] Moreover, in frames 521 to 524, pixels shown in gray or black represent signal data extracted by extraction function 112 in step S300. For example, in Fig. 12, points 531a to 531d are signal data extracted as the second signal data in frame 521, which is the first frame. Moreover, points 531e, 531f, 531g, 531h and area 532a are signal data extracted in frame 522, which is the second frame. Moreover, in frames 521 to 524, gray pixels represent signal points that are not extracted as inappropriate signal points, and black pixels represent signal points that are extracted as inappropriate signal points.

[0065] Next, the output function 113 identifies inappropriate signal points from the signal data extracted in step S300. Here, an inappropriate signal point is a signal point that is thought not to be a blood flow signal of the observation target, such as clutter. Here, since clutter and the like are thought to have a tendency not to be extracted as a high signal point across multiple frames at the same position, the output function 113 identifies inappropriate signal points based on the number of signal extractions across multiple frames. As an example, the output function 113 identifies a signal point at a position where the number of signal extractions is less than a criterion as an inappropriate signal point.

[0066] For example, in Fig. 12, integrated signal data 530 indicates second signal data that has been subjected to integration processing in the processing described below. Output function 113 generates table 40 that counts how many times each point has been extracted as a high signal point. For example, points 531a, 531b, 531c, etc. are extracted as high signal points in two or more frames, so the signal extraction count is "2". On the other hand, points belonging to region 532a are extracted as high signal points only in frame 522, which is the second frame, i.e., only in one frame, so the signal extraction count is "1".

[0067] Here, the processing circuit 110 sets the reference signal extraction count to "2", for example. In this case, the output function 113 determines signal points in the region 531, such as points 531a, 531b, 531c, where the signal extraction count is 2 or more, as appropriate signal points. On the other hand, the output function 113 identifies signal points in the region 532, where the signal extraction count is 1, as inappropriate signal points.

[0068] Next, output function 113 accumulates the second signal data in the multiple frames extracted in step S300 to generate accumulated signal data that integrates the data of each frame. As an example, in Fig. 12, output function 113 accumulates multiple pieces of second signal data that are high signal points shown in gray or black in frames 521 to 524 to generate accumulated signal data 530.

[0069] Next, the output function 113 generates third signal data from which inappropriate signals are removed, based on the result of identifying the inappropriate signal points and the second signal data extracted in step S300. As an example, the output function 113 generates the third signal data by removing inappropriate signal points from the integrated signal data 530 obtained by integrating the second signal data. In other words, the output function 113 generates the third signal data as ultrasonic data by removing inappropriate signal points from the integrated signal points. As an example, in FIG. 12, the output function 113 removes signal points in an area 532, which is a signal point at a position where the number of times of extraction of the signal point is less than a reference, from the integrated signal data 530 obtained by integrating the second signal data, as inappropriate signal points from the integrated signal points, and generates third signal data 50 in which only signal points in an appropriate area 531 are integrated.

[0070] As described above, in the second embodiment, the output function 113 generates the third signal data by identifying inappropriate signal points based on the number of times the signal points are extracted. This makes it possible to remove signal points that become noise, thereby improving image quality.

[0071] (Modification of the second embodiment) In the second embodiment, a case has been described in which processing circuit 110 identifies inappropriate signal points and generates third signal data by excluding the identified inappropriate signal points from the signal points after accumulation. In a modification of the second embodiment, a case will be described in which the third signal data is generated by identifying inappropriate frames instead of identifying inappropriate signal points.

[0072] In a modified example of the second embodiment, the output function 113 identifies an inappropriate frame from the second signal data extracted in step S300. Here, an inappropriate frame is a frame that is estimated to include a signal point that is not considered to be a blood flow signal of an observation target, such as clutter. Here, it is considered that the number of extracted signals extracted as high signal points changes suddenly when viewed in the frame direction near a frame where clutter occurs, so the output function 113 identifies an inappropriate frame based on the number of extracted signals in the frame direction. As an example, the output function 113 identifies a frame in which the change in the number of extracted signals in the frame direction is larger than a reference as an inappropriate frame.

[0073] For example, in FIG. 13, frames 521 to 524 indicate each frame of the first signal data of a plurality of frames. Among frames 521 to 524, signal points indicated in gray or black indicate signal points of high signal values ​​extracted as parts with high signal values ​​in step S300. Here, the output function 113 identifies a frame in which the change in the number of extracted signals in the frame direction is greater than the reference as an inappropriate frame. In the example of FIG. 13, the number of signal points extracted as signal points of high signal values ​​in frame 522 is "12". In contrast, the number of signal points extracted as signal points of high signal values ​​in frames 521 and 523 is "4". Therefore, since the change in the number of extracted signals in the frame direction exceeds the reference near frame 522, the output function 113 identifies frame 522 as an inappropriate frame.

[0074] The output function 113 generates third signal data from which the inappropriate frames have been excluded, based on the identified inappropriate frames and the second signal data identified in step S300. As an example, the output function 113 generates the third signal data by integrating the second signal data while excluding the inappropriate frames from the integration target. As an example, in FIG. 13, the output function 113 generates third signal data 560 by integrating the second signal data while excluding frame 522, which is an inappropriate frame, from the integration target.

[0075] In the above embodiment, the processing circuit 110 extracts an inappropriate frame based on a change in the number of extracted signals in the frame direction, but the embodiment is not limited to this. The processing circuit 110 may identify an inappropriate frame based on the number of extracted signals in the frame direction itself. As an example, the processing circuit 110 may identify a frame in which the number of extracted signals in the frame direction exceeds a reference value as an inappropriate frame.

[0076] As described above, in the modification of the second embodiment, the processing circuit 110 generates the third signal data by identifying inappropriate signal points based on the number of times the signal points are extracted. This makes it possible to remove signal points that become noise, thereby improving image quality.

[0077] (Third embodiment) In the third embodiment, a case where the processing of steps S300 and S400 in the first embodiment is performed differently from the first embodiment will be described. Specifically, in the third embodiment, instead of steps S300 and S400 in the first embodiment, the output function 113 divides the first ultrasonic data into a plurality of ultrasonic data, extracts third ultrasonic data by performing peak extraction from each ultrasonic data, assigns the third ultrasonic data to a corresponding position on the first ultrasonic data to generate fourth ultrasonic data, and integrates the fourth ultrasonic data to generate the second ultrasonic data. In the third embodiment, for example, a patent application of Japanese Patent Application No. 2023-213406 filed on December 18, 2023 is cited.

[0078] This process will be described with reference to Fig. 14 and Fig. 15. Fig. 14 is a diagram for explaining in more detail the process performed in place of steps S300 and S400 in Fig. 3 in the third embodiment. Fig. 15 is a diagram for explaining the flow of the process in Fig. 14.

[0079] 15, image data 1020 indicates the first ultrasound data to be processed in step S400. Pixels 1020a, 1020b, 1020c, 1020d, 1020e, 1020f, 1020g, 1020h, 1020i, 1020j, 1020k, and 1020l indicate the respective pixels of the image data 1020.

[0080] First, in step S1410, the output function 113 divides the first ultrasonic image data into a plurality of second ultrasonic image data. As an example, the output function 113 performs data division processing on the image data 1020, which is the first ultrasonic image data, while thinning out the data at equal intervals, and divides the data into four pieces of second ultrasonic image data. As an example, the output function 113 performs data division processing on the image data 1020, which is the first ultrasonic image data, while skipping one piece of data vertically and horizontally, and divides the image data 1021a including pixels 1020a, 1020c, 1020e, 1020g, etc., image data 1021b including pixels 1020b, 1020d, 1020f, 1020h, etc., image data 1021c including pixels 1020i, 1020k, etc., and image data 1021d including pixels 1020j, 1020l, etc., as shown in the figure. That is, the output function 113 divides the image data 1020, which is the first ultrasound image data, into two pieces vertically and horizontally, that is, 2×2, to divide the image data 1020 into four pieces of ultrasound data, namely, image data 1021a, 1021b, 1021c, and 1021d.

[0081] In the above example, the output function 113 divides the image data 1020 into two pieces of second ultrasound image data by dividing the image data 1020 vertically and horizontally into two pieces of 2×2, but the embodiment is not limited to this, and the output function 113 may divide the image data into three pieces of 3×3 vertically and horizontally, for example, to divide the image data into nine pieces of ultrasound data, or may divide the image data into four pieces of 4×4 vertically and horizontally, for example, to divide the image data into 16 pieces of ultrasound data. Also, the embodiment is not limited to this, and the output function 113 may divide the image data into two pieces of ultrasound data by dividing the image data into two pieces of 2×1 vertically only, or may divide the image data into two pieces of ultrasound data by dividing the image data into two pieces of 1×2 horizontally only.

[0082] Next, in step S1420, the output function 113 extracts a third ultrasound data by performing peak extraction from each ultrasound data.

[0083] As an example of the peak detection process in step S1420, the output function 113 extracts a high signal point using a kernel that spreads over a total of nine signal points (3×3) including a point of interest and eight signal points adjacent to the point of interest. In this case, the output function 113 extracts the point of interest as a high signal point only when the point of interest has a higher signal value than any of the eight adjacent signal points.

[0084] As another example of the peak detection process in step S1420, the output function 113 extracts the third ultrasound data from the second ultrasound data using a kernel extending in a particular direction, for example, kernel 4 having a size of 3×1.

[0085] As another example of the peak detection process in step S1420, the output function 113 extracts the third ultrasound data from the second ultrasound data using a trained model based on machine learning.

[0086] In this manner, the output function 113 extracts image data 1022a, 1022b, 1022c, and 1022d, which are the third ultrasound data, from image data 1021a, 1021b, 1021c, and 1021d, which are the second ultrasound data, respectively.

[0087] Next, in step S1430, the output function 113 allocates the third ultrasound data to corresponding positions on the first ultrasound data to generate fourth ultrasound data. That is, the output function 113 allocates the image data 1022a, 1022b, 1022c, and 1022d, which are the third ultrasound data, to corresponding positions on the first ultrasound data to generate image data 1023, which is the fourth ultrasound data.

[0088] Then, in step S1440, the output function 113 integrates the fourth ultrasound image data to generate second ultrasound data, and then, in step S1450, the output function 113 outputs the second ultrasound data.

[0089] As described above, in the third embodiment, the output function 113 applies the above-mentioned extraction process to each frame. That is, the output function 113 applies a kernel that extracts high signal points to each of a plurality of frames to extract second ultrasound data. The processing circuitry 110 adds the second ultrasound data in each frame as necessary to generate image data 1024 to be output.

[0090] By using the method of the third embodiment, it becomes possible to extract high-luminance signal regions over a wider range.

[0091] (Other embodiments) Furthermore, the extraction of the local peak position in the first to third embodiments and the like is not limited to the above-mentioned method, and may be performed by other methods. For example, the local peak position may be extracted by performing peak sharpening by applying a nonlinear function to the signal value in the frame. In such a case, for example, the extraction function 110g first performs a process of resampling the first ultrasonic image data to increase the pixel density and increase the effective resolution. Here, the resampling may be, for example, replacing each pixel with a plurality of smaller pixels. Furthermore, the signal value of each pixel after replacement may be interpolated from the original signal value (the signal value before replacement) by, for example, bicubic interpolation or the like.

[0092] Furthermore, the extraction function 110g sharpens the local peaks by raising each signal value of the first ultrasound data after resampling to a power (for example, the 8th power, the 12th power, etc.). The extraction function 110g extracts local peak positions by, for example, performing threshold processing on the signal values ​​after the power. That is, the extraction function 110g extracts identification information in which positions extracted as local peaks are represented by "1" and positions not extracted as local peaks are represented by "0". The extraction function 110g performs the above-mentioned local peak sharpening process on a plurality of first ultrasound data, thereby extracting identification information from each of the first ultrasound data. Note that the target of the above-mentioned local peak sharpening process is not limited to the first ultrasound data, and may be frame data.

[0093] Furthermore, the above-described embodiments may be combined with each other as appropriate.

[0094] Regarding the above embodiment, the following supplementary notes are disclosed as one aspect and optional features of the invention.

[0095] (Appendix 1) An ultrasound diagnostic device 10 as a medical information processing device provided in one aspect of the present invention includes a processing circuit 110. The processing circuit 110 acquires first ultrasound data 21 obtained based on the result of an ultrasound scan of a subject by an acquisition function 111. The processing circuit 110 continuously extracts signal components 22 representing the object from the first ultrasound data 21 by an extraction function 112. The processing circuit 110 outputs second ultrasound data 23 by an output function 113 based on the continuously extracted signal components 22 representing the object.

[0096] (Appendix 2) The processing circuit 110 may use the acquisition function 111 to collect multiple frame data 20 that are consecutive in the time direction obtained by performing an ultrasound scan, and acquire added data obtained by adding together the multiple frame data 20 as first ultrasound data 21.

[0097] (Appendix 3) The processing circuit 110 may output, via the output function 113, composite data obtained by performing a composite process on the first ultrasound data 21 and the signal components 22 representing the continuously extracted object as second ultrasound data 23.

[0098] (Appendix 4) The processing circuit 110 may output, via the output function 113, corrected data obtained by performing correction processing on the first ultrasound data 21 based on the signal components 22 representing the continuously extracted object as second ultrasound data 23.

[0099] (Appendix 5) The processing circuit 110 may use the extraction function 112 to extract, for each of a plurality of positions of interest contained in the first ultrasound data 21, a signal component of the position of interest as a signal component 22 representing the target object, based on a comparison result between a signal value located in a predetermined direction and range of interest relative to the position of interest and a signal value of the position of interest.

[0100] (Appendix 6) The processing circuit 110 may use the extraction function 112 to extract the signal component at the position of interest as the signal component 22 representing the object if the signal value at the position of interest is greater than or equal to the signal value located in a predetermined direction and range.

[0101] (Appendix 7) The processing circuit 110 may use the extraction function 112 to compare, for each of a plurality of positions of interest included in the first ultrasound data 21, the signal value of the position of interest with the signal value of a position within a predetermined range for each direction of interest relative to the position of interest, and weight the signal component of the position of interest based on the comparison result and a weighting coefficient predetermined for each direction of interest.

[0102] (Appendix 8) The processing circuit 110 may input first ultrasound data 21 to a trained model that continuously outputs signal components representing an object contained in a single piece of ultrasound data having a higher signal-to-noise ratio than multiple frame data consecutive in the time direction obtained by executing an ultrasound scan, using the extraction function 112, and obtain signal components 22 representing the object continuously extracted from the trained model.

[0103] (Appendix 9) The object may include at least one of blood, body tissue, and a contrast agent.

[0104] (Appendix 10) An ultrasound diagnostic device 10 provided in one aspect of the present invention includes an execution unit that causes an ultrasound probe 5 to execute an ultrasound scan, and a processing circuit 110. The processing circuit 110 acquires, by an acquisition function 111, first ultrasound data 21 obtained based on the result of an ultrasound scan of a subject. The processing circuit 110 continuously extracts, by an extraction function 112, signal components 22 representing the object from the first ultrasound data 21. The processing circuit 110 outputs, by an output function 113, second ultrasound data 23 based on the continuously extracted signal components 22 representing the object.

[0105] (Appendix 11) A program provided in one aspect of the present invention causes a computer to execute a process of acquiring first ultrasound data 21 obtained based on the results of an ultrasound scan on a subject, continuously extracting signal components 22 representing the object from the first ultrasound data 21, and outputting second ultrasound data 23 based on the continuously extracted signal components 22 representing the object.

[0106] According to at least one of the embodiments described above, it is possible to obtain high-resolution ultrasound data with high responsiveness.

[0107] Although some embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0108] 110 Processing circuit 111 Acquisition Function 112 Extraction function 113 Output Function

Claims

1. an acquisition unit that acquires first ultrasound data obtained based on a result of an ultrasound scan of a subject; an extractor that continuously extracts signal components representing an object from the first ultrasound data; and an output unit that outputs second ultrasound data based on the continuously extracted signal components representing the object. Medical information processing equipment.

2. the acquisition unit acquires a plurality of frame data successive in a time direction obtained by executing the ultrasound scan, and acquires sum data obtained by adding up the plurality of frame data as the first ultrasound data. The medical information processing device according to claim 1 .

3. The medical image processing device according to claim 1 , wherein the output unit outputs, as the second ultrasound data, composite data obtained by performing a synthesis process on the first ultrasound data and the continuously extracted signal components representing the object.

4. The output unit outputs, as the second ultrasound data, corrected data obtained by performing a correction process on the first ultrasound data based on the continuously extracted signal components representing the object. The medical information processing device according to claim 1 .

5. the extraction unit extracts, for each of a plurality of positions of interest included in the first ultrasound data, a signal component of the position of interest as a signal component representing the object, based on a comparison result between a signal value located in a predetermined direction and range of interest with respect to the position of interest and a signal value of the position of interest; The medical information processing device according to claim 1 .

6. the extraction unit extracts the signal component at the target position as a signal component representing the object if the signal value at the target position is greater than or equal to a signal value located in the predetermined direction and range. The medical information processing device according to claim 5 .

7. the extraction unit compares, for each of a plurality of positions of interest included in the first ultrasound data, a signal value of the position of interest with a signal value of a position within the predetermined range for each direction of interest relative to the position of interest, and weights the signal component of the position of interest based on a result of the comparison and a weighting coefficient predetermined for each direction of interest. The medical information processing device according to claim 5 .

8. the acquisition unit inputs a plurality of frame data consecutive in the time direction obtained by performing an ultrasound scan on the subject to a trained model that outputs a single ultrasound data set having a higher S / N ratio than a plurality of frame data consecutive in the time direction obtained by performing an ultrasound scan, and acquires the single ultrasound data set output from the trained model as the first ultrasound data; The medical information processing device according to claim 1 .

9. The extraction unit inputs the first ultrasound data to a trained model that continuously outputs signal components representing an object included in a single piece of ultrasound data having a higher S / N ratio than a plurality of frame data consecutive in a time direction obtained by executing an ultrasound scan, and acquires signal components representing the object continuously extracted from the trained model. The medical information processing device according to claim 1 .

10. The object includes at least one of blood, body tissue, and contrast agent; The medical information processing device according to claim 1 .

11. 2. The medical image processing device according to claim 1, wherein the output unit identifies inappropriate signal points or inappropriate frames from the signal components representing the object that are continuously extracted, and outputs the second ultrasound data based on a result of identifying the inappropriate signal points or the inappropriate frames.

12. The medical image processing device according to claim 11 , wherein the output unit generates the second ultrasound data by excluding the inappropriate signal points from the signal points after integration.

13. The medical image processing device according to claim 11 , wherein the output unit identifies a signal point at a position where a signal has been extracted fewer times than a reference number as the inappropriate signal point.

14. The medical image processing apparatus according to claim 11 , wherein the output unit identifies a frame in which a change in the number of extracted signals in the frame direction is larger than a reference value as the inappropriate frame.

15. The output unit divides the first ultrasonic data into a plurality of ultrasonic data, and extracts third ultrasonic data by performing peak extraction from each of the ultrasonic data; Allocating the third ultrasound data to a corresponding position on the first ultrasound data to generate fourth ultrasound data; The medical image processing apparatus according to claim 1 , wherein the second ultrasound data is generated by integrating the fourth ultrasound data.

16. an execution unit that causes the ultrasound probe to execute an ultrasound scan; an acquisition unit that acquires first ultrasound data obtained based on a result of the ultrasound scan of the subject; an extractor that continuously extracts signal components representing an object from the first ultrasound data; and an output unit that outputs second ultrasound data based on the continuously extracted signal components representing the object. Ultrasound diagnostic equipment.

17. On the computer, acquiring first ultrasound data based on a result of an ultrasound scan of a subject; Continuously extracting signal components representative of an object from the first ultrasound data; A program that executes a process of outputting second ultrasound data based on the continuously extracted signal components representing the object.

Images