Ultrasound diagnostic device, medical information processing device, and medical information processing method

Abstract

To improve the image quality of an ultrasound image by providing high time resolution and low computational load.SOLUTION: An ultrasound diagnostic device according to an embodiment comprises an ultrasound probe, an acquisition unit, an extraction unit, and an output unit. The ultrasonic probe transmits ultrasonic waves to a subject and receives ultrasonic waves reflected by the subject. The acquisition unit acquires first ultrasonic data of the subject on the basis of the ultrasonic waves received by the ultrasonic probe. The extraction unit extracts identification information that identifies a local peak position for each predetermined area of a frame represented by the first ultrasonic data. The output unit outputs second ultrasonic data on the basis of the identification information extracted by the extraction unit and the ultrasonic data representing a processing target.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The embodiments disclosed in this specification relate to an ultrasound diagnostic apparatus, a medical information processing apparatus, and a medical information processing method. [Background technology]

[0002] Conventionally, techniques for improving the image quality of ultrasound images including fine flow paths and fluids (e.g., blood flow, contrast agent, etc.) are known. For example, Patent Document 1 discloses a method for generating an image showing the boundary of a flow path (e.g., the shape of a blood vessel) by removing clutter contained in continuous ultrasound reception signals within a predetermined time and averaging the fluid signals after clutter removal over a predetermined time. Patent Document 2 also discloses a method for performing a super-resolution process that improves the resolution (pixel density) of an ultrasound image and sharpens the peaks of a speckle pattern in the ultrasound image.

[0003] However, in the technology of Patent Document 1, the finer the flow path, the more the speckle pattern cannot be contained within the flow path due to the resolution limit of the ultrasound diagnostic device, and the flow path cannot be expressed with high image quality. Also, in the technology of Patent Document 2, the calculation load of the super-resolution process is high, and it is difficult to generate an image in response to the operation of the ultrasound probe (the time resolution is poor). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2016-20881 A [Patent Document 2] Special Publication No. 2019-526350 Summary of the Invention [Problem to be solved by the invention]

[0005] One of the problems that the embodiments disclosed in the present specification are intended to solve is to improve the image quality of ultrasound images by providing high time resolution and low computational load. However, the problems solved by the embodiments disclosed in the present specification are not limited to the above problems. Problems corresponding to the effects of the configurations shown in the embodiments described later can also be considered as other problems solved by the embodiments disclosed in the present specification. [Means for solving the problem]

[0006] An ultrasonic diagnostic apparatus according to an embodiment includes an ultrasonic probe, an acquisition unit, an extraction unit, and an output unit. The ultrasonic probe transmits ultrasonic waves to a subject and receives ultrasonic waves reflected by the subject. The acquisition unit acquires first ultrasonic data of the subject based on the ultrasonic waves received by the ultrasonic probe. The extraction unit extracts identification information for identifying a local peak position for each predetermined region of a frame represented by the first ultrasonic data. The output unit outputs second ultrasonic data based on the identification information extracted by the extraction unit and ultrasonic data representing a processing target. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of an ultrasound diagnostic apparatus according to the first embodiment. [Diagram 2] FIG. 2 is a flowchart showing the procedure of processing performed by the ultrasonic diagnostic apparatus according to the first embodiment. [Diagram 3] FIG. 3 is a diagram for explaining the first ultrasound data according to the first embodiment. [Figure 4] FIG. 4 is a diagram for explaining extraction of signal components according to the first embodiment. [Diagram 5] FIG. 5 is a diagram for explaining an example of the extraction process according to the first embodiment. [Figure 6] FIG. 6 is a diagram for explaining filter information according to the first embodiment. [Figure 7A]FIG. 7A is a diagram for explaining an example of generation of filter information according to the first embodiment. [Figure 7B] FIG. 7B is a diagram for explaining an example of generation of filter information according to the first embodiment. [Figure 8] FIG. 8 is a diagram for explaining the second ultrasound data according to the first embodiment. [Figure 9A] FIG. 9A is a diagram showing ultrasound data according to a comparative example. [Figure 9B] FIG. 9B is a diagram showing second ultrasound data obtained by the processing according to the first embodiment. [Figure 10] FIG. 10 is a diagram for explaining an example of a process according to another embodiment. [Figure 11A] FIG. 11A is a diagram for explaining an example of a process according to another embodiment. [Figure 11B] FIG. 11B is a diagram for explaining an example of a process according to another embodiment. [Figure 12] FIG. 12 is a diagram for explaining an example of a process according to another embodiment. [Figure 13] FIG. 13 is a diagram for explaining an example of a processing result of the processing according to the comparative example. [Figure 14] FIG. 14 is a diagram for explaining an example of a processing result of the processing according to the other embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, embodiments of an ultrasound diagnostic apparatus, a medical information processing apparatus, and a medical information processing method according to the present application will be described in detail with reference to the accompanying drawings. Note that the ultrasound diagnostic apparatus, the medical information processing apparatus, and the medical information processing method according to the present application are not limited to the embodiments shown below.

[0009] (First embodiment) Fig. 1 is a block diagram showing an example of the configuration of an ultrasound diagnostic device 10 according to the first embodiment. The ultrasound diagnostic device 10 is a device that generates ultrasound data based on a reception signal (reflected wave signal) received from an ultrasound probe 5. The ultrasound diagnostic device 10 shown in Fig. 1 is a device that can generate two-dimensional ultrasound data based on a reception signal received from a one-dimensional ultrasound probe 5 (an ultrasound probe in which transducers are arranged in one dimension) and can generate three-dimensional ultrasound data based on a reception signal received from a two-dimensional ultrasound probe 5 (an ultrasound probe in which transducers are arranged in two dimensions).

[0010] 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.

[0011] 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 103 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 103 has a communication unit for wireless communication with the ultrasonic probe 5.

[0012] The ultrasonic diagnostic apparatus 10 includes a transmission circuit 9, a reception circuit 11, and a medical information processing apparatus 100.

[0013] 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.

[0014] 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 a 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 the received signal without any particular distinction.

[0015] 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.

[0016] 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.

[0017] The input device 134 accepts various instructions and information input from an operator. The input device 134 is composed of input interface devices such as a trackball, a switch button, a mouse, a keyboard, a touch pad that performs input operations by touching the operation surface, a touch monitor in which a display screen and a touch pad are integrated, a non-contact input circuit using an optical sensor, and a voice input circuit. The input interface device is connected to a processing circuit 110 described later, and converts an input operation received from an operator into an electrical signal and outputs it to the processing circuit 110. In this specification, the input interface device is not limited to only those having physical operating parts such as a mouse and a keyboard. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs the electrical signal to the processing circuit 110 is also included as an example of an input interface device.

[0018] 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.

[0019] The processing circuit 110 controls each part of the ultrasonic diagnostic device 10, thereby controlling the entire ultrasonic diagnostic device 10. For example, the processing circuit 110 executes a program stored in the memory 132, thereby functioning as a control function 111, a signal processing function 112, an acquisition function 113, an extraction function 114, a generation function 115, and an output function 116. Here, the control function 111 is an example of an execution unit. The acquisition function 113 is an example of an acquisition unit. The extraction function 114 is an example of an extraction unit. The generation function 115 is an example of a generation unit. The output function 116 is an example of an output unit. Note that, although the processing circuit 110 is described in FIG. 1 as being realized as a single circuit, it may be realized as a large number of circuits by combining multiple independent processors. Also, a specific function, such as an ASIC (Application Specific Integrated Circuit), may be configured as a dedicated independent circuit.

[0020] 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.

[0021] The ultrasonic diagnostic apparatus 10 configured as above performs the following processes, which can be roughly divided. (Process 1) A process of acquiring, as first ultrasound data, summation data obtained by summing a plurality of frames of data that are successive in the time direction and that are obtained by an ultrasound scan of a subject. (Process 2) A process of extracting, for each position of a frame (image) represented by the first ultrasound data, identification information for identifying the magnitude relationship between a signal value corresponding to that position and signal values ​​corresponding to the surroundings of that position from each of the plurality of first ultrasound data. (Process 3) A process of generating filter information corresponding to each position of a frame (image) based on the identification information extracted from each of the plurality of first ultrasound data. (Process 4) A process of outputting second ultrasound data based on at least one of the plurality of first ultrasound data (for example, the most recent first ultrasound data) and filter information.

[0022] The ultrasonic diagnostic device 10 performing processes 1 to 4 improves the image quality of ultrasonic images (especially ultrasonic images including fine flow paths and fluids) with high time resolution and low computational load.

[0023] Hereinafter, the operation of the ultrasound diagnostic device 10 will be described in detail with reference to FIG.

[0024] The control function 111 controls the transmission circuit 9 and the reception circuit 11 to cause the ultrasonic probe 5 to execute an ultrasonic scan and acquire a plurality of frames of reception signals (e.g., CH data) (step S101). Specifically, the control function 111 collects a plurality of frames of data (a plurality of frames of data within a predetermined time) that are continuous in the time direction and obtained by executing an ultrasonic scan at a predetermined frame rate. The frame data includes the amplitude value (signal value) of a signal corresponding to each pixel that constitutes one image (frame).

[0025] The signal processing function 112 performs delay-and-sum processing and quadrature detection processing on the collected reception signals. The delay-and-sum processing is processing for adding reception signals of multiple transducers 101 by changing the delay time and weight for each transducer 101, and is also called DAS (Delay and Sum) beamforming. The quadrature detection processing is processing for converting the reception signals into in-phase signals and quadrature signals in the baseband and acquiring measurement data representing IQ data and absolute values ​​of the IQ data. In addition, adaptive beamforming, model-based processing, processing using machine learning, and the like may be performed on the reception signals.

[0026] Furthermore, the signal processing function 112 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 estimation result (step S102). Specifically, the signal processing function 112 calculates the amount of tissue displacement caused by the body movement between frames from multiple frame data, and corrects the frame data based on the calculated amount of displacement.

[0027] Moreover, the signal processing function 112 performs an envelope detection process, a logarithmic compression process, and the like, and generates B-mode data in which the signal intensity at each point in the observation region is represented by brightness. Moreover, the signal processing function 112 generates blood flow data by extracting information derived from blood flow of the measurement data. For example, the signal processing function 112 applies an MTI (Moving Target Indicator) filter to a plurality of frame data (step S103). This reduces information derived from tissue that is stationary between frames or tissue with little movement (tissue signal components (clutter)), and extracts information derived from blood flow (blood flow signal components). As the MTI filter, a filter with fixed filter information, such as a Butterworth type IIR (Infinite Impulse Response) filter or a polynomial regression filter, may be used. The MTI filter may be an adaptive filter that changes a coefficient according to an input signal using eigenvalue decomposition or singular value decomposition, or the like.

[0028] The signal processing function 112 can also decompose the frame data into a plurality of bases by eigenvalue decomposition or singular value decomposition, and extract a specific base to remove information derived from tissues and extract information derived from blood flow. The signal processing function 112 can also obtain a velocity vector for each coordinate in the received signal data by using a method such as a vector Doppler method, a speckle tracking method, or a vector flow mapping method to obtain a blood flow vector that indicates the magnitude and direction of blood flow. In addition to the methods exemplified here, other methods can be used to extract information derived from blood flow contained in the frame data (measurement data) or to remove information derived from tissues.

[0029] The acquiring function 113 acquires a plurality of first ultrasound data within a predetermined time based on the result of an ultrasound scan on the subject. For example, the acquiring function 113 acquires a plurality of frame data that are obtained by an ultrasound scan on the subject and are continuous in the time direction, and performs an addition process on the frame data (step S104). For example, as shown in FIG. 3, the acquiring function 113 adds a plurality of frame data 20 that are continuous in the time direction, from which clutter components have been removed by the process of step S103, for every certain number of frames. The certain number of frames (number of packets) referred to here is, for example, several tens to several hundred. The acquiring function 113 acquires the added data obtained by this addition process as the first ultrasound data 21.

[0030] The first ultrasound data 21 has a higher SN ratio (signal-noise ratio) than each frame data 20 before addition. The first ultrasound data 21 (added data) is, for example, blood flow data (power Doppler data) in which information derived from blood flow is emphasized. The first ultrasound data 21 represents a boundary of a flow path (for example, the shape of a blood vessel) by averaging a signal of a fluid after clutter removal over a predetermined time. The frame represented by the first ultrasound data 21 includes a signal value (amplitude value) representing a speckle pattern caused by constructive interference and destructive interference between ultrasonic waves reflected from the fluid, and a signal value representing other noises (artifacts, etc.) that occur instantaneously or intermittently on the time axis.

[0031] 4, the extraction function 114 extracts identification information 22 from each of the multiple first ultrasound data 21 (step S105). The identification information is information for identifying, for each position of a frame (image) represented by the first ultrasound data 21, the magnitude relationship between a signal value corresponding to that position and signal values ​​corresponding to the surroundings of that position.

[0032] 5, the extraction function 114 places the kernel 40 at a position of interest in the frame (image) represented by the first ultrasound data 21, and compares the magnitude relationship between a signal value corresponding to the position of interest and a signal value corresponding to a position of the image in the range where the kernel 40 is placed (around the position of interest). The extraction function 114 obtains, for example, information for identifying whether or not each position of the frame is larger than the signal value corresponding to the surroundings of the position, as identification information. In other words, the identification information can be said to be information for identifying a position (local peak position) with a relatively large signal value for each local region of the frame.

[0033] Specifically, when a kernel based on a ratio of 3 vertical by 1 horizontal is used, the extraction function 114 places the center (second square) of the kernel 40 as a position of interest, and identifies whether or not the signal value corresponding to that position is greater than the signal values ​​corresponding to the positions at both ends (first square, third square) of the kernel 40. If the signal value corresponding to the position of interest is greater than the signal values ​​corresponding to the surroundings of the position, the extraction function 114 represents the position of interest, for example, as "1". On the other hand, if the signal value corresponding to the position of interest is smaller than the signal values ​​corresponding to the surroundings of the position, the extraction function 114 represents the position of interest, for example, as "0". Then, the extraction function 114 performs this process for each position of the frame, thereby extracting identification information for the frame (image) represented by the first ultrasound data 21.

[0034] In other words, this extraction process converts the first ultrasound data 21 into a binary image in which each pixel of the frame (image) is represented by a “0” or a “1”, and the amplitude values ​​(signal values) of the signals corresponding to each pixel constituting the first ultrasound data 21 are lost.

[0035] In the example of Fig. 5, the kernel 40 is arranged in four directions, vertically, horizontally, diagonally to the upper right, and diagonally to the upper left, for each position of the frame represented by the first ultrasound data to extract the identification information, but the shape and size of the kernel are not limited to this. In addition, in the example of Fig. 5, an example is shown in which the object is extracted in units of pixels, but the identification information may be extracted for each position of the frame in units of groups having multiple pixels. When extracting the identification information in units of groups having multiple pixels, the average value or integrated value of the signal values ​​of each position constituting the group may be set as the signal value corresponding to each position of the frame.

[0036] The generating function 115 generates filter information corresponding to each position of the frame based on the identification information 22 extracted from each of the plurality of first ultrasound data 21 by the extracting function 114 (step S106). For example, as shown in FIG. 6 and FIG. 7A, the generating function 115 generates filter information 23 using the identification information 22 (1 to 3 shown in FIG. 6) for three frames. The filter information 23 is obtained according to the value represented by each identification information 22 at the corresponding positions (coordinates (x, y)) between the frames, as shown in FIG. 7B. For example, when the identification information 22 is all "1" at the corresponding positions in three frames, the filter information at that position is "1". When the identification information 22 is "1" once and "0" twice at the corresponding positions in three frames, the filter information at that position is "0.33". When the identification information 22 is all "0" at the corresponding positions in three frames, the filter information at that position is "0".

[0037] In this way, the more the number of times that the identification information 22 become "1" at corresponding positions within a predetermined time, the larger the value of the filter information 23 is set. In other words, the more the number of times that the identification information 22 become "1" at corresponding positions, the more likely it is that a signal value larger than the surroundings is continuously obtained at that position and that a fluid is present, so that a higher weighting factor as filter information is set to a higher value ("1") at such positions. On the other hand, when the identification information 22 contain "0" at corresponding positions, the more likely it is that noise (artifacts, etc.) that occurs instantaneously or intermittently on the time axis is present at that position, so that a lower weighting factor as filter information is set to a higher value ("0.67", "0.33", "0") at such positions.

[0038] The output function 116 outputs the second ultrasound data based on the filter information 23 generated by the generation function 115 and at least one of the plurality of first ultrasound data 21 (S107). For example, the output function 116 outputs the second ultrasound data 24 based on the most recent first ultrasound data 21 of the plurality of first ultrasound data 21 and the filter information 23, as shown in FIG.

[0039] Specifically, the output function 116 generates and outputs the second ultrasound data 24 by multiplying a signal value (amplitude value) representing each position of the frame represented by the most recent first ultrasound data 21 by filter information (weighting coefficient) set for each corresponding position of the filter information 23. The second ultrasound data 24 is multiplied by a weighting coefficient of a large value for a position in the frame represented by the first ultrasound data 21 where a fluid is likely to exist, and the position of the fluid is emphasized by the filter information 23. On the other hand, the second ultrasound data 24 is multiplied by a weighting coefficient of a small value for a position in the frame represented by the first ultrasound data 21 where a noise (artifact, etc.) occurring momentarily or intermittently is likely to exist, and noise is reduced by the filter information 23.

[0040] 9A and 9B, the ultrasound image (blood flow image) represented by the second ultrasound data 24 will be compared with a conventional ultrasound image. FIG. 9A is a diagram showing a conventional ultrasound image. FIG. 9B is a diagram showing an ultrasound image represented by the second ultrasound data 24. The ultrasound image shown in FIG. 9A is obtained by averaging the fluid signal after clutter removal over a predetermined time period, but the finer the flow path, the less the image quality of the flow path can be displayed. On the other hand, the ultrasound image shown in FIG. 9B can display the fine blood vessel running with high image quality.

[0041] As described above, the ultrasound diagnostic apparatus 10 according to the first embodiment can improve the image quality of ultrasound images with high time resolution and low computational load.

[0042] Furthermore, according to the first embodiment, the acquisition function 113 acquires sum data obtained by adding together a plurality of frames of data that are obtained by an ultrasound scan of the subject and are continuous in the time direction, as the first ultrasound data 21. This reduces the number of frames to be used for extracting the identification information 22, and allows the use of ultrasound data with a high S / N ratio.

[0043] In the first embodiment, an example has been described in which the output function 116 outputs the second ultrasound data 24 based on the most recent first ultrasound data 21 among the multiple first ultrasound data 21 and the filter information 23. However, this is not limited to this, and the second ultrasound data 24 may be output based on other first ultrasound data 21 that is not the most recent among the multiple first ultrasound data 21 and the filter information 23.

[0044] Furthermore, the output function 116 may perform an addition process similar to that in step S104 on a plurality of first ultrasound data 21, and output the second ultrasound data 24 based on the data obtained thereby and the filter information 23. In this case, by multiplying the filter information 23 by data having a higher S / N ratio than the first ultrasound data 21, it is expected that the image quality of the ultrasound image can be further improved compared to that described in the embodiment.

[0045] In the first embodiment, the output function 116 outputs the second ultrasound data 24 based on the filter information 23 and the first ultrasound data 21 generated by the generation function 115, but the present invention is not limited to this. For example, the output function 116 may output the second ultrasound data 24 based on the identification information 22 extracted from each of the multiple first ultrasound data 21 by the extraction function 114 and at least one of the multiple first ultrasound data 21, or ultrasound data obtained by performing a predetermined process on the first ultrasound data 21.

[0046] In this case, the output function 116 may utilize a pre-trained trained model to input, to the trained model, the identification information 22 extracted from each of the multiple first ultrasound data 21 and at least one of the multiple first ultrasound data 21, or ultrasound data obtained by performing a predetermined processing on the first ultrasound data 21, and obtain the data output by the trained model as the second ultrasound data 24.

[0047] Furthermore, when extracting the identification information in step S105, the extraction function 114 may perform an extraction process for extracting a signal value with a relatively large signal value (a signal value having a local peak) for each local region of the frame (a process for extracting a signal value corresponding to each position of the frame represented by the first ultrasound data 21 based on the magnitude relationship between the signal value corresponding to the position and the signal values ​​corresponding to the surroundings of the position). In this case, the output function 116 may treat the ultrasound data obtained as a result of the extraction process by the extraction function 114 as ultrasound data that has been subjected to a predetermined process, and output the second ultrasound data 24 based on the ultrasound data and the filter information 23.

[0048] In addition, the output function 116 may combine the ultrasound data obtained by the extraction process performed by the extraction function 114 with the most recent first ultrasound data 21 to produce synthesized data that has been subjected to a predetermined process, and output the second ultrasound data 24 based on the ultrasound data and the filter information 23.

[0049] In the first embodiment, the identification information 22 is expressed by binarizing each position of the frame represented by the first ultrasound data 21 with "0" or "1", but a list of positions having signal values ​​higher than the signal values ​​corresponding to the surroundings may be extracted as the identification information.

[0050] Furthermore, the identification information extracted from each of the plurality of first ultrasound data by the extraction function 114 may be assigned weight information determined according to each of the plurality of first ultrasound data. For example, according to each of the plurality of first ultrasound data, the shorter the elapsed time of the first ultrasound data 21, the higher the weight information value may be assigned to the identification information extracted from the first ultrasound data. This allows the identification information extracted from each of the plurality of first ultrasound data to be weighted according to the elapsed time.

[0051] In the first embodiment, the extraction function 114 uses the kernel 40 based on a ratio of 3 vertical x 1 horizontal, and is arranged in four directions, vertical, horizontal, diagonally upper right, and diagonally upper left, and extracts identification information for identifying the magnitude relationship between the signal value corresponding to each position of the frame and the signal values ​​corresponding to surrounding positions within each direction and distance, but this is not limited to the above example. The surroundings for which the magnitude relationship of the signal value is identified by the extraction function 114 may be positions within a predetermined direction and distance from each position of the frame represented by the first ultrasound data 21. The extraction function 114 may also assign weight information determined according to at least one of the direction and distance to the identification information. This allows the identification information extracted from each of the multiple first ultrasound data to be weighted according to at least one of the direction and distance of the signal value to be compared. The kernel 40 may be any one that can specify the extraction range of the identification information, and its shape, size, etc. are set appropriately.

[0052] In the first embodiment, the case where the sum data obtained by adding a plurality of frame data is acquired as the first ultrasound data has been described. However, the embodiment is not limited to this, and each of the plurality of frame data may be acquired as the first ultrasound data. That is, the acquisition function 113 may acquire each of a plurality of frames consecutive in the time direction obtained by an ultrasound scan as the first ultrasound data. For example, the acquisition function 113 may set each of the five frame data 20 shown in FIG. 3 as the first ultrasound data. In this case, the extraction function 114 may extract identification information from each of the five frame data 20. Furthermore, the generation function 115 may generate filter information corresponding to each position of the frame based on the identification information extracted from each of the five frame data 20. Furthermore, the output function 116 may output the second ultrasound data based on at least one frame data 20 (for example, the most recent frame data) of the five frame data 20, or ultrasound data obtained by performing a predetermined process on the frame data 20, and the filter information generated by the generation function 115.

[0053] In the above-mentioned first embodiment, the case where the signal values ​​between pixels in a single first ultrasound data are compared has been described. However, the embodiment is not limited to this, and for example, the signal values ​​between a plurality of first ultrasound data that are consecutive in time may be compared. In such a case, the extraction function 114 may compare the signal values ​​at the same coordinates between the first ultrasound data that are consecutive in time.

[0054] In the above embodiment, the acquisition function 113 acquires, as the first ultrasound data, single added data with an improved SN ratio by adding multiple frame data together. However, ultrasound data with an improved SN ratio may be acquired without adding. In such a case, for example, the acquisition function 113 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 SN ratio than multiple frame data consecutive in the time direction 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 SN ratio than each frame data is used as teacher data. The acquisition function 113 inputs multiple frame data 20 to the trained model and acquires, as the first ultrasound data 21, single ultrasound data with a higher SN ratio than the multiple frame data output from the trained model.

[0055] In addition, the acquisition function 113 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 113 may acquire ultrasound data with a high S / N ratio received from an external workstation or the like as the first ultrasound data 21.

[0056] In the above-mentioned first embodiment, an example in which the present invention is applied to an ultrasonic diagnostic device has been described, but the present invention is not limited thereto, and may be applied to a 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 a server that acquires ultrasonic data obtained based on the result of an ultrasonic scan of a subject. For example, the medical information processing device such as a workstation or a server may execute the above-mentioned process using a plurality of frame data collected in the past.

[0057] In addition, in the above description, the fluid represented by the ultrasound image is blood flow, and therefore, the acquisition function 113 acquires the first ultrasound data obtained by an ultrasound scan in the absence of a contrast agent, but the fluid may be a contrast agent. In this case, the acquisition function 113 may acquire the first ultrasound data obtained by an ultrasound scan in the presence of a contrast agent.

[0058] Note that the components of each device illustrated in the above description of the embodiments are conceptual and functional, and are not necessarily physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to that illustrated, and all or a part of the devices can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0059] The method described in the above embodiment can be realized by executing a prepared program on a computer such as a personal computer or a workstation. This program can be distributed via a network such as the Internet. This program can also be recorded on a non-transitory recording medium readable by a computer, such as a hard disk, a flexible disk (FD), a CD-ROM, an MO, a DVD, a USB memory, or a flash memory such as an SD card memory, and can be executed by being read from the non-transitory recording medium by a computer.

[0060] As described above, according to the embodiment, it is possible to obtain ultrasound data with high visibility and high resolution.

[0061] 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.

[0062] (Other embodiments) In the above embodiment, it has been described that the shape and size of the kernel used to extract the local peak position are arbitrary. For example, in addition to the kernel 40 based on the ratio of 3 vertical x 1 horizontal shown in FIG. 5, kernels such as 4 x 1, 5 x 1, 3 x 2, and 3 x 3 may be used. Here, the above kernels may be used according to the SN ratio of the data to be extracted from the local peak. For example, when the first ultrasound data with a high SN ratio obtained by performing an addition process on a plurality of frame data is the extraction target, a kernel with a large size difference in the aspect ratio (3 x 1, 4 x 1, 5 x 1, etc.) may be used. This is because an image with a high SN ratio tends to clearly depict point-like noise and vascular structures although they are discrete, so that point-like noise that appears isolated can be efficiently suppressed by widening the observation range. On the other hand, when each frame data in which the addition process is not performed and the SN ratio is not increased is the extraction target of the local peak, a kernel with a small size difference in the aspect ratio (2 x 1, 3 x 2, 3 x 3, etc.) may be used. Also, when obtaining the first ultrasound data, the more the number of frame data to be added together, the more the S / N ratio improves. Therefore, when extracting the first ultrasound data, the more the number of frame data to be added together, the more the kernel to be used may be associated with the number of frame data to be added together, so that a kernel having a larger size difference between the aspect ratios of the frames is used.

[0063] In the above embodiment, the case where the local peak position is extracted using one type of kernel has been described, but the embodiment is not limited thereto, and the local peak position may be extracted by combining two or more types of kernels. For example, the extraction function 114 extracts a position where the signal value is relatively large in a frame using a 5×1 kernel, and further extracts a position where the signal value is relatively high for the same frame using a 3×3 kernel. Here, the extraction function 114 can set the position extracted by either the 5×1 kernel or the 3×3 kernel as the local peak position, or can set the position extracted by both the 5×1 kernel and the 3×3 kernel as the local peak position. That is, the extraction function 114 may extract the local peak position by combining two or more types of kernels. As described above, two or more types of kernels may be combined according to the S / N ratio of the data from which the local peak is extracted. For example, when the first ultrasound data with a high S / N ratio obtained by performing an addition process on a plurality of frame data is the extraction target, multiple types of kernels with a large difference in size between the horizontal and vertical ratios (3×1, 4×1, 5×1 kernels) may be combined, and the position extracted by any one of the types of kernels may be set as the local peak position. On the other hand, when the addition process is not performed and each frame data with an unenhanced S / N ratio is the extraction target for the local peak, multiple types of kernels with a small difference in size between the horizontal and vertical ratios (2×1, 3×2, 3×3 kernels) may be combined, and the position extracted by all the types of kernels may be set as the local peak position.

[0064] In the above embodiment, in the extraction of the local peak position using the kernel, when the signal value of the attention position is larger than or equal to the signal value around the attention position, the attention position is represented by "1". However, the embodiment is not limited to this. For example, the signal value of the attention position or the signal value around the attention position may be multiplied by a predetermined coefficient before comparison. As an example, the extraction function 114 may compare the signal value of the surrounding positions with the signal value of the attention position after multiplying the signal value of the surrounding positions by X times (for example, 1.5 times or 0.9 times). Also, for example, when the signal value of the attention position is larger than the average value of the signal values ​​of the surrounding positions, the attention position may be represented by "1". Also, for example, the local peak position may be extracted using the variance (standard deviation) of the signal values ​​of the positions included in the kernel. As an example, the extraction function 114 may represent the attention position by "1" when the signal value of the attention position is larger than or equal to the signal value around the surrounding positions and the variance of the signal values ​​of the positions included in the kernel (the attention position and the surrounding positions) is equal to or less than a threshold value. In this case, even if the signal value of the position of interest is greater than or equal to the surrounding signal values, if the variance exceeds a threshold, the position of interest may be represented as "0". This is because in an area where point noise is scattered, the point noise is depicted as having a higher luminance value than the surrounding pixels, but the variance value is also large due to the large variation with the surrounding pixels. In this way, by combining the comparison with the surrounding pixel values ​​with variance evaluation, it is possible to efficiently suppress the point noise and extract local peaks.

[0065] In the above embodiment, an example in which three frames of first ultrasound data are used has been described, but the number of frames may be less than three (for example, two frames) or more than three (for example, five frames). The number of frames may be a single frame. For example, the acquisition function 113 may acquire first ultrasound data of the subject, and the extraction function 114 may extract identification information for identifying a local peak position for each predetermined region of one frame represented by the first ultrasound data. In this case, the output function 116 may output the second ultrasound data based on the identification information extracted from one frame by the extraction function 114 and the ultrasound data representing the processing target. The extraction function 114 may also identify whether or not each position of interest in one frame represented by the first ultrasound data is a local peak position by comparing the position of interest with other positions within a predetermined range for each of a plurality of spatial directions (for example, four directions: vertical, horizontal, diagonally upper right, and diagonally upper left) of the position of interest in the frame. In this case, the generating function 115 may set a weighting factor as the filter information 23 for each position of interest of one frame represented by the first ultrasound data according to the number of times the extracting function 114 has identified the position of interest as a local peak in each direction. For example, when the generating function 115 has identified the position of interest of one frame represented by the first ultrasound data as a local peak in two directions, vertical and horizontal, the generating function 115 sets a weighting factor of "0.5" for the position of interest, and when the position of interest of one frame represented by the first ultrasound data has identified the position of interest as a local peak in two directions, vertical, horizontal, diagonally upper right, and diagonally upper left (all directions), the generating function 115 sets a weighting factor of "1" for the position of interest. Thereafter, the output function 116 may output the second ultrasound data based on the filter information 23 generated by the generating function 115 and the ultrasound data representing the processing target. The number of frames used for the first ultrasound data can be changed by a user's direct designation, or alternatively, the number of frames may be associated in advance with the imaging target, examination type, and imaging mode designated by the user, and may be determined in conjunction with the user's designation of the imaging target, examination type, and imaging mode. For example, imaging regions located away from circulatory system organs, such as finger joints, are less susceptible to the effects of body movement, and blurring of the imaging subject tends to occur less even during long-term imaging.Therefore, in the case of such an imaging target, a large number of frames such as 5 or 10 can be specified to increase the number of frames to be added and improve the SN ratio of the first ultrasound data. On the other hand, in an image of an abdominal region such as the liver, the object also moves with the imaging time due to slight influence of the movement of circulatory system organs. Therefore, in the case of such an imaging target, a small number of frames such as 3 can be specified to prevent deterioration of the image quality of the first ultrasound data caused by the blur of the imaging target. Alternatively, the total number of pixels depicted in each frame may be counted for each frame, and if the count number changes significantly between frames, it may be determined that the imaging target or the ultrasound probe 5 has blurred, and the number of frames to be added may be reduced to a minimum value (e.g., 3). On the other hand, if the total number depicted in each frame does not fluctuate beyond a predetermined threshold range for a predetermined time period or more, a process of increasing the number of frames to be added may be performed. This increases the number of frames to be added during the time period when the imaging target is detected, and improves the SN ratio of the first ultrasound data.

[0066] In the above embodiment, when extracting a local peak position, it is not only possible to compare the position of interest with other positions in a predetermined direction and range at the same time position, but also possible to compare signal values ​​between a plurality of first ultrasound data that are continuous in time. In other words, it is also possible to compare the position of interest with other positions in a predetermined direction and range at the same spatial position.

[0067] In such a case, the kernels arranged for the multiple first ultrasound data are arranged so as to include a time point of interest and surrounding time points in the time direction at the same spatial position. For example, when comparing signal values ​​at the same coordinates between three temporally consecutive frames (first frame, second frame, and third frame) of first ultrasound data, the second frame may be set as the time point of interest, and the first and third frames may be set as surrounding time points, and the signal values ​​may be compared. In this case, the extraction function 114 extracts the first coordinate of the second frame as a local peak position when the signal value of the first coordinate in the second frame is greater than or equal to the signal value of the first coordinate in the first and third frames. The extraction of the local peak position described above may be performed not only based on the magnitude relationship of the signal values, but also by extracting the coordinates compared at the time point of interest as the local peak position when the variance of the signal values ​​at each time point included in the kernel is equal to or less than a threshold value. The same coordinates described above may be a single pixel, or may be a plurality of pixels. When comparing signal values ​​at a plurality of pixels, for example, an average value of the signal values ​​of the plurality of pixels in each frame may be compared.

[0068] The extraction of the local peak positions in the plurality of first ultrasound data consecutive in time is not limited to the method using the kernel described above, and may be, for example, a trained model that outputs the local peak positions in response to the input of the plurality of first ultrasound data consecutive in the time direction. In such a case, the trained model is trained by a data set or the like in which the plurality of first ultrasound data consecutive in time is used as input data and the local peak positions extracted in the target data among the plurality of first ultrasound data are used as teacher data. The extraction function 114 inputs the plurality of first ultrasound data consecutive in time to the trained model, thereby extracting the local peak positions in the target data. Note that the above-mentioned process (process of extracting the local peak positions using the plurality of data consecutive in time) may be performed on the plurality of first ultrasound data consecutive in time as described above, or may be performed on the frame data consecutive in time.

[0069] In addition, in the above-mentioned case where local peak positions are extracted from temporally consecutive frames and identification information is extracted, weight information may be assigned to the identification information. That is, similar to the case where the position of interest is compared with other positions in a spatially predetermined direction and range at the same time position, weight information determined according to at least one of the direction and distance (time difference from the time of interest to the time of comparison target) may be assigned to the identification information. For example, dot noise tends to flash randomly while changing its location in a short time, while blood flow tends to appear in a lump within a certain time domain in accordance with pulsation. Therefore, when extracting local peak positions from consecutive frames, weight information for identification information at a time point serving as a starting point can be set to 1, while weights for identification information of frames at time points distant from the time point serving as a starting point can be set to 0.8, 0.6, etc., so that the more distant the time, the lower the weight. In this way, dot noise can be efficiently suppressed by utilizing the difference in properties between dot noise and blood flow.

[0070] In the above embodiment, the case where the identification information is extracted, the filter information is generated, and the second ultrasonic data is outputted for two-dimensional ultrasonic data has been described. However, the embodiment is not limited to this, and the identification information may be extracted, the filter information may be generated, and the second ultrasonic data may be outputted for three-dimensional ultrasonic data. In such a case, for example, a one-dimensional ultrasonic probe may be swung or moved to acquire a reception signal from a three-dimensional space to generate three-dimensional ultrasonic data. Alternatively, a two-dimensional ultrasonic probe may be used to acquire a reception signal from a three-dimensional space to generate three-dimensional ultrasonic data. In addition, a kernel may be three-dimensionally arranged for the three-dimensional ultrasonic data, and local peak positions may be extracted (identification information is extracted), filter information may be generated, and the second ultrasonic data may be outputted in the same manner as in the above embodiment.

[0071] The extraction of the local peak position 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 114 first performs a process of resampling the first ultrasound 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 pixels of a smaller size. In addition, 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.

[0072] Furthermore, the extraction function 114 sharpens the local peaks by raising each signal value of the first ultrasound data after resampling to a power (e.g., 8th power, 12th power, etc.). The extraction function 114 extracts local peak positions by performing, for example, threshold processing on the signal values ​​after the power. That is, the extraction function 114 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 114 performs the 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 local peak sharpening process described above is not limited to the first ultrasound data, and may be frame data.

[0073] Alternatively, the pixel density may be increased by performing resampling to generate frame data with an increased effective resolution, and the frame data may then be synthesized and a kernel applied to obtain the first ultrasound data. In this case, it is desirable to enlarge the size of the kernel to match the magnification of the effective resolution improvement of the resampling. For example, when the effective resolution of the image is doubled (i.e., the resolution of an image of 512 pixels x 512 pixels is increased to an image of 1024 pixels x 1024 pixels) for a kernel size of (3 x 1), a kernel size of (6 x 2) may be used.

[0074] The generating function 115 generates filter information based on a plurality of pieces of identification information extracted by the local peak sharpening process.

[0075] Furthermore, the ultrasound diagnostic device 10 according to this embodiment can change the scan conditions of the ultrasound scan when performing the above-mentioned (Process 2) to (Process 4). Specifically, when switched to a mode in which the above-mentioned (Process 2) to (Process 4) are performed (hereinafter, referred to as a process application mode), the ultrasound diagnostic device 10 can change the scan conditions so as to increase the scan line density (number of scan lines).

[0076] For example, when switching from a mode in which multiple frame data are added and displayed, or from a normal color Doppler mode to a processing application mode, the control function 111 controls the transmission circuit 9 and the reception circuit 11 to cause the ultrasound probe 5 to execute an ultrasound scan with an increased scanning line density, thereby acquiring a reception signal with an increased number of scanning lines in the frame data. In this way, the control function 111 sequentially acquires multiple frame data with a larger number of scanning lines in the frame data, compared to the mode before the switch.

[0077] Furthermore, the change to increase the scanning line density can also be made within the processing application mode. For example, two processing application modes, processing application mode 1 and processing application mode 2, are further applied to the processing application mode. The control function 111 may perform control so that the scanning line density is not changed when switching to processing application mode 1, and the scanning line density is increased when switching to processing application mode 2.

[0078] In the above embodiment, the second ultrasound data 24 is generated and output by multiplying the signal value representing each position of the frame represented by the first ultrasound data 21 by the filter information (weighting coefficient) set for each corresponding position of the filter information 23. However, the embodiment is not limited to this, and the second ultrasound data may be generated and output by applying other formulas.

[0079] For example, the output function 116 may generate and output the second ultrasound data 24 by exponentiating the signal value (amplitude value) representing each position of the frame represented by the first ultrasound data 21 by the filter information (weighting coefficient) set for each corresponding position in the filter information 23. That is, when the signal value of each position is "A" and the weighting coefficient is "a", the output function 116 outputs "A" for all positions. a " is calculated to generate and output second ultrasound data 24.

[0080] In the above embodiment, the generated filter information is multiplied by the signal value of the corresponding position (pixel) in the first ultrasound data (i.e., one weighting factor is multiplied by only one pixel signal value). However, the embodiment is not limited to this, and may be multiplied by one weighting factor by the signal values ​​of multiple pixels. As an example, one weighting factor may be multiplied by each of the signal values ​​of 3×3 pixels centered on the pixel at the corresponding position.

[0081] In the above embodiment, a case has been described in which, in generating filter information, weighting coefficients are calculated according to the number of times "1" appears at corresponding positions in each piece of identification information 22. However, the embodiment is not limited to this, and the weighting coefficient may be set to "1" when "1" appears even once in the identification information.

[0082] Moreover, the ultrasound diagnostic apparatus, medical information processing apparatus, and medical information processing method according to the present application can apply various techniques in addition to the above-described embodiments. These will be described below.

[0083] For example, the ultrasound diagnostic device, medical information processing device, and medical information processing method according to the present application may apply the process of deleting inappropriate signal points and deleting inappropriate frame data described in Japanese Patent Application No. 2023-164256. In such a case, for example, the extraction function 114 extracts inappropriate signal points in the plurality of frame data based on the signal values ​​in the plurality of frame data. For example, the acquisition function 113 may acquire the first ultrasound data of the subject by deleting the inappropriate signal points extracted by the extraction function 114 in step S104 shown in FIG. 2 and then performing an addition process on the plurality of frame data.

[0084] An example of processing by extraction function 114 will be described below with reference to Fig. 10. Here, frame data 25-28 shown in Fig. 10 indicate frame data after the processing of step S103 in Fig. 2 has been performed. For example, extraction function 114 performs local peak extraction processing on frame data 25-28, and extracts pixels indicating signals whose signal values ​​are locally maximum values ​​(pixels shown in gray or black in the figure). Note that the local peak extraction processing can appropriately use the processing used to extract local peak positions described in the embodiments of the present application.

[0085] Next, the extraction function 114 extracts inappropriate signal points based on the results of the local peak extraction process. Here, the inappropriate signal points are signal points that are thought not to be blood flow signals of the observation target, such as clutter. Since clutter and the like tend not to be extracted as high signal points across multiple frames at the same position, the extraction function 114 identifies inappropriate signal points based on the number of signal extractions across multiple frame data. For example, the extraction function 114 identifies signal points at positions where the number of signal extractions is less than a criterion as inappropriate signal points.

[0086] 10, the extraction function 114 generates a table T1 that counts how many times each point in frame data 25 to 28 has been extracted as a local peak signal point. Here, the pixels 31a, 31b, 31c, etc. shown in gray have been extracted as local peaks in two or more frame data, so the signal extraction count is "2." On the other hand, the pixels belonging to region 32a shown in black have been extracted as local peaks only in frame data 26, i.e., only in one frame data, so the signal extraction count is "1."

[0087] Here, the processing circuit 110 sets the reference signal extraction count to "2", for example. In this case, the processing circuit 110 uses the identification function 110h to determine that the signal points in the region 31, such as points 31a, 31b, 31c, etc., whose signal extraction count is 2 or more, are appropriate signal points. On the other hand, the extraction function 114 identifies the signal points in the region 32 whose signal extraction count is 1, as inappropriate signal points. The acquisition function 113 deletes the signal points extracted by the extraction function 114 (signal points included in the region 32a) and then performs addition processing of the frame data 25 to 28 to acquire the first ultrasound data of the subject. In the above example, the case where the determination processing of inappropriate signal points is performed based on the signal extraction count has been described, but the embodiment is not limited to this, and the inappropriate signal points may be identified using a neural network.

[0088] Also, for example, the extraction function 114 extracts inappropriate frame data from the plurality of frame data based on signal values ​​in the plurality of frame data. The acquisition function 113 acquires first ultrasound data of the subject by deleting the frame data extracted by the extraction function 114 and then performing an addition process on the plurality of frame data. Here, the inappropriate frame data refers to frame data that is estimated to include signal points that are not considered to be blood flow signals of the observation target, such as clutter. In the vicinity of a frame where clutter occurs, it is considered that the number of extracted signals extracted as local peaks changes rapidly when viewed in the frame direction, so the extraction function 114 identifies inappropriate frame data based on the number of extracted signals in the frame direction. For example, the extraction function 114 identifies frame data in which the change in the number of extracted signals in the frame direction is greater than a reference as inappropriate frame data.

[0089] As an example, in the frame data 26 in FIG. 10, the number of signal points extracted as local peak signal points is "12". In contrast, in the frame data 25, 27, and 28, the number of signal points extracted as local peak signal points is "4". Here, if the number of reference signal points is "6", the change in the number of extracted signals in the frame direction near the frame data 26 exceeds the reference, so the extraction function 114 identifies the frame data 26 as an inappropriate frame. The acquisition function 113 deletes the inappropriate frame data 26 extracted by the extraction function 114, and then performs an addition process on the frame data 25, 27, and 28 to acquire the first ultrasound data of the subject. In the above example, the case where the process of determining inappropriate frame data is performed based on the change in the number of extracted signals in the frame direction has been described, but the embodiment is not limited to this, and inappropriate frame data may be identified by a comprehensive determination criterion using a neural network.

[0090] As described above, the extraction function 114 extracts identification information by performing an extraction process of local peak positions on the first ultrasound data acquired after deleting inappropriate signal points or the first ultrasound data acquired after deleting inappropriate frame data.

[0091] In addition, for example, the ultrasound diagnostic device, medical information processing device, and medical information processing method according to the present application can extract the local peak position by applying the local peak detection process described in Japanese Patent Application No. 2023-164256 to the first ultrasound data or frame data. In such a case, for example, the extraction function 114 extracts the local peak position by threshold processing or local maximum value extraction processing in step S105 shown in FIG. 2. Hereinafter, an example of the processing by the extraction function 114 will be described with reference to FIGS. 11A and 11B. Note that the points 90a to 90k shown in FIGS. 11A and 11B are schematic diagrams showing the signal points of each signal data in one frame, and the vertical direction of the paper represents the size of each signal data.

[0092] For example, as shown in Fig. 11A, the extraction function 114 extracts points 90b, 90c, 90d, 90e, 90g, 90h, and 90i whose signal values ​​are equal to or greater than the thresholds (horizontal lines in the figure) shown in Fig. 11A as local peak positions. Also, for example, the extraction function 114 extracts points 90d and 90h, which are local maximum values, as local peak positions as shown in Fig. 11B.

[0093] 11A and 11B, for the sake of simplicity, the signal data is shown as one-dimensional signal data, but the signal data of each frame is usually two-dimensional signal data. Even if the signal data is two-dimensional or more dimensional signal data, the extraction function 114 can extract the local peak positions by performing the same process as described above.

[0094] In addition, for example, the ultrasound diagnostic device, medical information processing device, and medical information processing method according to the present application can apply the high signal point extraction process described in Japanese Patent Application No. 2023-213406 to the extraction of local peak positions. Hereinafter, this process will be described with reference to FIG. 12. Here, in FIG. 12, image data 30 indicates data (first ultrasound data or frame data) that is the target of the local peak position extraction process. Pixels 40a, 40b, 40c, 40d, 40e, 40f, 40g, 40h, 40i, 40j, 40k, and 40l indicate each pixel of the image data 30. For example, in step S105 shown in FIG. 2, the extraction function 114 performs a process of extracting identification information from data (for example, first ultrasound data) that is the target of the local peak position extraction process as follows.

[0095] For example, the extraction function 114 performs a data division process on the image data 30 (hereinafter, sometimes referred to as the first ultrasound data) to thin out the data at equal intervals, thereby generating four divided data from the first ultrasound data (dividing the first ultrasound data into four). As an example, the extraction function 114 performs a data division process on the image data 30, which is the first ultrasound data, while skipping one data vertically and horizontally, and divides the data into image data 41a including pixels 40a, 40c, 40e, 40g, etc., image data 41b including pixels 40b, 40d, 40f, 40h, etc., image data 41c including pixels 40i, 40k, etc., and image data 41d including pixels 40j, 40l, etc., as shown in the figure. That is, the extraction function 114 divides the image data 30, which is the first ultrasound data, into two parts vertically and horizontally, into 2×2 parts, thereby generating four image data 41a, 41b, 41c, and 41d (divided data) from the first ultrasound data.

[0096] In the above example, the image data 30 is divided into two parts vertically and horizontally, that is, 2×2 division, and the first ultrasound data is divided into four parts, but the embodiment is not limited to this. For example, the image data may be divided into three parts vertically and horizontally, that is, 3×3 division, and the first ultrasound data may be divided into nine parts, or the image data may be divided into four parts vertically and horizontally, that is, 4×4 division, and the first ultrasound data may be divided into 16 parts. Also, for example, the image data may be divided into two parts vertically only, that is, 2×1 division, and the first ultrasound data may be divided into two parts, or the image data may be divided into two parts horizontally only, that is, 1×2 division, and the first ultrasound data may be divided into two parts.

[0097] Next, the extraction function 114 extracts local peak positions from each of the divided data. The peak extraction process may be performed using the process for extracting local peak positions described in the embodiments of the present application. The extraction function 114 extracts division identification information 42a, 42b, 42c, and 42d representing the extraction results of the local peak positions from each of the multiple divided data.

[0098] The extraction function 114 assigns the divided identification information 42a, 42b, 42c, and 42d to corresponding positions on the first ultrasound data to generate image data 43. The image data 43 is the extraction result of the positions of high signal points, and corresponds to the identification information.

[0099] The effect of the above-mentioned high signal point extraction process will be described with reference to Fig. 13 and Fig. 14. Fig. 13 is a conceptual diagram showing a high signal point extraction method according to a comparative example, and Fig. 8 is a conceptual diagram showing a high signal point extraction method according to another embodiment.

[0100] Fig. 13 shows a comparative example of a high signal point extraction method, which does not perform space division and extracts high signal points. Each point in Fig. 13 represents a signal point, and curve 50 is a line connecting signal values. As shown in Fig. 13, when signal extraction is performed without space division, signal point 50a and signal point 50b are extracted as the positions of high signal points.

[0101] In contrast, FIG. 14 shows a high signal point extraction method according to another embodiment, which performs spatial division to extract high signal points. Each point in FIG. 14 represents a signal point, and curves 51 and 52 are lines connecting signal values ​​in each image data that has been subjected to division processing. When signal extraction is performed on each image data that has been subjected to division processing, signal points 51a, 51b and signal points 52a, 52b are extracted as positions of high signal points. That is, when the method according to the other embodiment is used, it is possible to extract a high luminance signal area in a wider range than in the comparative example. That is, in the method according to the other embodiment, the image components representing the object are continuously extracted, and peak pixel values ​​can be continuously extracted. The position of interest for peak determination is basically in pixel units, but may be in group units having multiple pixels. When peak determination is performed in group units, the pixel value of the group may be the average value or the integrated value of the pixel values ​​of the pixels included in the multiple groups.

[0102] In the above embodiment, the case where identification information is extracted at each position of the frame represented by the first ultrasound data has been described. However, the embodiment is not limited to this, and may be, for example, a case where identification information is extracted only for positions included in a partial area of ​​the first ultrasound data. That is, the extraction function 114 extracts, as identification information, information identifying a position having a higher signal value than the surroundings within a predetermined range of the frame.

[0103] In the above embodiment, a case has been described in which at least one of the plurality of first ultrasound data or ultrasound data obtained by performing a predetermined process on the first ultrasound data is treated as a processing target, and processing using identification information is performed. However, the embodiment is not limited to this, and the ultrasound data representing the processing target may be other than at least one of the plurality of first ultrasound data and ultrasound data obtained by performing a predetermined process on the first ultrasound data.

[0104] In addition, the above-mentioned processes related to the deletion of inappropriate signal points and the deletion of inappropriate frame data, the detection process of local peaks, and the extraction process of high-luminance points may be combined and selected according to the imaging target, imaging mode, or input process by the user. For example, the extraction process of high-luminance points may be applied when the imaging mode is changed to one in which the effective resolution of frame data is finer than a certain level.

[0105] In addition, for example, the ultrasound diagnostic device, medical information processing device, and medical information processing method according to the present application can use the kernel described in Patent Application No. 2023-213405 to extract the local peak position. Specifically, a kernel in which only limited positions of the masses included in the kernel are used may be used to extract the local peak position. For example, the extraction function 114 uses a filter that is a 5×1 kernel and extracts only the 1st, 3rd, and 5th masses from the left of the 5×1 masses as the kernel, and compares the extracted signal value with the adjacent signal value to extract the local peak position. As an example, the extraction function 114 extracts the local peak position by comparing the signal values ​​of the 3rd mass as the position of interest and the 1st and 5th masses as the surroundings.

[0106] Regarding the above-described embodiments, the following supplementary notes are disclosed as one aspect and optional features of the invention.

[0107] (Appendix 1) The medical information processing device includes: an acquisition unit that acquires a plurality of first ultrasound data within a predetermined time; An extractor that extracts, for each position of a frame represented by the first ultrasound data, identification information that identifies a magnitude relationship between a signal value corresponding to the position and signal values ​​corresponding to a periphery of the position from each of the plurality of first ultrasound data; and an output unit that outputs second ultrasound data based on at least one of the plurality of first ultrasound data, or ultrasound data obtained by performing a predetermined process on the first ultrasound data, and the identification information extracted from each of the plurality of first ultrasound data.

[0108] (Appendix 2) The extraction section may extract, for each position of the frame, information identifying whether or not a signal value corresponding to that position is greater than signal values ​​corresponding to surrounding areas of that position, as the identification information.

[0109] (Appendix 3) a generating unit that generates filter information corresponding to each position of the frame based on the identification information extracted from each of the plurality of first ultrasound data by the extracting unit, The output unit may output the second ultrasound data based on at least one of the plurality of first ultrasound data, or ultrasound data obtained by performing a predetermined process on the first ultrasound data, and the filter information.

[0110] (Appendix 4) The extraction section may assign weight information determined in accordance with each of the plurality of first ultrasound data to the identification information.

[0111] (Appendix 5) the surroundings, the magnitude relationship of the signal values ​​of which is identified by the extraction unit, are positions within a predetermined direction and distance from the position; The extraction section may assign weight information determined according to at least one of the direction and the distance to the identification information.

[0112] (Appendix 6) The acquisition unit may acquire, as the first ultrasound data, sum data obtained by summing a plurality of frame data that are obtained by an ultrasound scan of a subject and are continuous in a time direction.

[0113] (Appendix 7) The output unit may treat the ultrasound data that has been processed to extract a signal value corresponding to each position of a frame represented by the first ultrasound data based on a magnitude relationship between a signal value corresponding to the position and signal values ​​corresponding to the surroundings of the position as the ultrasound data that has been processed in the predetermined manner, and output the second ultrasound data based on the ultrasound data and the identification information.

[0114] (Appendix 8) The output unit may combine ultrasound data that has been processed to extract a signal value corresponding to each position of a frame represented by the first ultrasound data based on a magnitude relationship between a signal value corresponding to the position and signal values ​​corresponding to the surroundings of the position, and the first ultrasound data to obtain synthetic data, and output the second ultrasound data based on the ultrasound data and the identification information.

[0115] (Appendix 9) The acquisition unit may acquire the first ultrasound data obtained by an ultrasound scan in the presence of a contrast agent.

[0116] (Appendix 10) The acquisition unit may acquire the first ultrasound data obtained by an ultrasound scan in the absence of a contrast agent.

[0117] (Appendix 11) Ultrasound diagnostic equipment: an execution unit that causes an ultrasound probe to execute an ultrasound scan; an acquisition unit that acquires a plurality of first ultrasound data within a predetermined time; An extractor that extracts, for each position of a frame represented by the first ultrasound data, identification information that identifies a magnitude relationship between a signal value corresponding to the position and signal values ​​corresponding to a periphery of the position from each of the plurality of first ultrasound data; and an output unit that outputs second ultrasound data based on at least one of the plurality of first ultrasound data, or ultrasound data obtained by performing a predetermined process on the first ultrasound data, and the identification information extracted from each of the plurality of first ultrasound data.

[0118] (Appendix 12) The medical information processing method includes: An acquisition step of acquiring a plurality of first ultrasound data within a predetermined time period; an extraction step of extracting, from each of the plurality of first ultrasound data, identification information for identifying a magnitude relationship between a signal value corresponding to each position of a frame represented by the first ultrasound data and signal values ​​corresponding to the surroundings of the position; and an output step of outputting second ultrasound data based on at least one of the plurality of first ultrasound data or ultrasound data obtained by performing a predetermined process on the first ultrasound data, and the identification information extracted from each of the plurality of first ultrasound data.

[0119] (Appendix 13) Ultrasound diagnostic equipment: an ultrasonic probe that transmits ultrasonic waves to a subject and receives ultrasonic waves reflected by the subject; an acquisition unit that acquires first ultrasound data of the subject based on the ultrasound received by the ultrasound probe; an extracting unit that extracts identification information that identifies a local peak position for each predetermined region of a frame represented by the first ultrasound data; The apparatus further includes an output unit that outputs second ultrasound data based on the identification information extracted by the extraction unit and ultrasound data representing a processing target.

[0120] (Appendix 14) The extraction unit may identify a position where a signal value is relatively large for each local region of a frame represented by the first ultrasound data as the peak position, and extract the identification information.

[0121] (Appendix 15) The acquisition unit acquires a plurality of first ultrasound data within a predetermined time period, The extraction unit extracts identification information for identifying a position of a local peak for each frame represented by the plurality of first ultrasound data; The output section may output the second ultrasound data based on the identification information extracted for each of the frames and the ultrasound data.

[0122] (Appendix 16) The extraction section may extract, for each position of the frame, information that identifies a magnitude relationship between a signal value corresponding to that position and signal values ​​corresponding to surrounding areas of that position, as the identification information.

[0123] (Appendix 17) The extraction section may extract, for each position of the frame, information identifying whether or not a signal value corresponding to that position is greater than signal values ​​corresponding to surrounding areas of that position, as the identification information.

[0124] (Appendix 18) The surroundings may be locations within a spatial direction and range relative to the location, or locations within a temporal direction and range relative to the location.

[0125] (Appendix 19) The extraction section may extract, as the identification information, information identifying a position having a higher signal value than surrounding areas within a predetermined range of the frame.

[0126] (Appendix 20) The surroundings may be locations within a spatial direction and range relative to the location, or locations within a temporal direction and range relative to the location.

[0127] (Appendix 21) The extractor may extract the identification information for each position of a frame represented by the first ultrasound data.

[0128] (Appendix 22) The ultrasound data representing the processing target may be at least one first ultrasound data of the plurality of first ultrasound data, or ultrasound data obtained by performing a predetermined processing on the first ultrasound data.

[0129] (Appendix 23) a generating unit that generates filter information corresponding to each position of the frame based on the identification information extracted from each of the plurality of first ultrasound data by the extracting unit, The output section may output the second ultrasound data based on the filter information and ultrasound data representing the processing object.

[0130] (Appendix 24) The extraction section may assign weight information determined in accordance with each of the plurality of first ultrasound data to the identification information.

[0131] (Appendix 25) The surroundings, the magnitude relationship of the signal values ​​of which is identified by the extraction unit, are positions within a predetermined direction and distance in space relative to the position, or positions within a predetermined direction and distance in time relative to the position, The extraction section may assign weight information determined according to at least one of the direction and the distance to the identification information.

[0132] (Appendix 26) The acquisition unit may acquire, as the first ultrasound data, sum data obtained by summing a plurality of frame data that are obtained by an ultrasound scan of a subject and are continuous in a time direction.

[0133] (Appendix 27) The output unit may treat the ultrasound data that has been processed to extract a signal value corresponding to each position of a frame represented by the first ultrasound data based on a magnitude relationship between a signal value corresponding to the position and signal values ​​corresponding to the surroundings of the position as the ultrasound data that has been processed in the predetermined manner, and output the second ultrasound data based on the ultrasound data and the identification information.

[0134] (Appendix 28) The output unit may combine ultrasound data that has been processed to extract a signal value corresponding to each position of a frame represented by the first ultrasound data based on a magnitude relationship between a signal value corresponding to the position and signal values ​​corresponding to the surroundings of the position, and the first ultrasound data to obtain synthetic data, and output the second ultrasound data based on the ultrasound data and the identification information.

[0135] (Appendix 29) The acquisition unit may acquire the first ultrasound data obtained by an ultrasound scan in the presence of a contrast agent.

[0136] (Appendix 30) The acquisition unit may acquire the first ultrasound data obtained by an ultrasound scan in the absence of a contrast agent.

[0137] (Appendix 31) The extraction unit may extract, for each position of the frame, information that identifies the magnitude relationship after multiplying a predetermined coefficient between a signal value corresponding to that position or a signal value corresponding to the surrounding area of ​​that position, as the identification information.

[0138] (Appendix 32) The extraction section may extract, for each position of the frame, information that identifies a variance between a signal value corresponding to that position and signal values ​​corresponding to a periphery of that position, as the identification information.

[0139] (Appendix 33) The acquisition section may acquire three-dimensional ultrasound data as the plurality of first ultrasound data within the predetermined time period.

[0140] (Appendix 34) The acquisition unit may acquire a plurality of first ultrasound data collected by increasing a scan line density in a mode in which the identification information is extracted.

[0141] (Appendix 35) The extraction unit may extract the identification information by dividing the first ultrasound data into a plurality of divided data, generating extracted data by extracting positions of local peaks for each divided data, and assigning each extracted data to a corresponding position on the first ultrasound data.

[0142] (Appendix 36) The medical information processing device includes: an acquisition unit that acquires first ultrasound data of a subject; an extracting unit that extracts identification information that identifies a local peak position for each predetermined region of a frame represented by the first ultrasound data; The apparatus further includes an output unit that outputs second ultrasound data based on the identification information extracted by the extraction unit and ultrasound data representing a processing target.

[0143] (Appendix 37) The medical information processing method includes: acquiring first ultrasound data of the subject; an extraction step of extracting identification information for identifying a local peak position for each predetermined region of a frame represented by the first ultrasound data; The method further includes an output step of outputting second ultrasound data based on the identification information extracted by the extraction section and ultrasound data representing a processing target. [Explanation of symbols]

[0144] 10. Ultrasound diagnostic equipment 100 Medical information processing device 111 Control Functions 112 Signal Processing Functions 113 Acquisition Function 114 Extraction Function 115 Generation function 116 Output Function

Claims

1. an ultrasonic probe that transmits ultrasonic waves to a subject and receives ultrasonic waves reflected by the subject; an acquisition unit that acquires first ultrasound data of the subject based on the ultrasound received by the ultrasound probe; an extracting unit that extracts identification information for identifying a local peak position for each predetermined region of a frame represented by the first ultrasound data; an output unit that outputs second ultrasound data based on the identification information extracted by the extraction unit and ultrasound data representing a processing target. Ultrasound diagnostic equipment.

2. the extraction unit identifies a position where a signal value is relatively large for each local region of a frame represented by the first ultrasound data as the local peak position, and extracts the identification information. The ultrasonic diagnostic apparatus according to claim 1 .

3. The acquisition unit acquires a plurality of first ultrasound data within a predetermined time period, The extraction unit extracts, for each frame represented by the plurality of first ultrasound data, identification information that identifies a position of a local peak; the output unit outputs the second ultrasound data based on the identification information extracted for each of the frames and the ultrasound data. The ultrasonic diagnostic apparatus according to claim 1 .

4. the extraction unit extracts, for each position of the frame, information for identifying a magnitude relationship between a signal value corresponding to the position and signal values ​​corresponding to a periphery of the position, as the identification information; The ultrasonic diagnostic apparatus according to claim 1 .

5. the extraction unit extracts, for each position of the frame, information identifying whether a signal value corresponding to the position is greater than signal values ​​corresponding to surrounding areas of the position as the identification information; The ultrasonic diagnostic apparatus according to claim 4.

6. The surroundings are locations within a spatial direction and range relative to the location, or locations within a temporal direction and range relative to the location. The ultrasonic diagnostic apparatus according to claim 4.

7. The extraction unit extracts, as the identification information, information identifying a position having a higher signal value than surrounding positions within a predetermined range of the frame. The ultrasonic diagnostic apparatus according to claim 1 .

8. The surroundings are locations within a spatial direction and range relative to the location, or locations within a temporal direction and range relative to the location. The ultrasonic diagnostic apparatus according to claim 7.

9. The extraction unit extracts the identification information for each position of a frame represented by the first ultrasound data. The ultrasonic diagnostic apparatus according to claim 1 .

10. The ultrasound data representing the processing target is at least one first ultrasound data of a plurality of first ultrasound data, or ultrasound data obtained by performing a predetermined process on the first ultrasound data. The ultrasonic diagnostic apparatus according to claim 1 .

11. a generating unit that generates filter information corresponding to each position of the frame based on the identification information extracted from each of the plurality of first ultrasound data by the extracting unit, The output unit outputs the second ultrasound data based on the filter information and the ultrasound data representing the processing target. The ultrasonic diagnostic apparatus according to claim 1 .

12. The ultrasound diagnostic apparatus according to claim 11 , wherein the extraction unit assigns weight information determined in accordance with each of the plurality of first ultrasound data to the identification information.

13. The surroundings, the magnitude relationship of the signal values ​​of which is identified by the extraction unit, are positions within a predetermined direction and distance in space relative to the position, or positions within a predetermined direction and distance in time relative to the position, the extraction unit assigns weight information determined according to at least one of the direction and the distance to the identification information; The ultrasonic diagnostic apparatus according to claim 5 .

14. the acquisition unit acquires, as the first ultrasound data, sum data obtained by summing a plurality of frame data that are obtained by an ultrasound scan of a subject and are continuous in a time direction; The ultrasonic diagnostic apparatus according to claim 1 .

15. the output unit extracts, for each position of a frame represented by the first ultrasound data, a signal value corresponding to the position based on a magnitude relationship between a signal value corresponding to the position and signal values ​​corresponding to the surroundings of the position, as the ultrasound data subjected to the predetermined processing, and outputs the second ultrasound data based on the ultrasound data and the identification information. The ultrasonic diagnostic apparatus according to claim 10.

16. the output unit extracts, for each position of the frame represented by the first ultrasound data, a signal value corresponding to the position based on a magnitude relationship between a signal value corresponding to the position and signal values ​​corresponding to the surroundings of the position, and combines the first ultrasound data to obtain the predetermined processed ultrasound data, and outputs the second ultrasound data based on the ultrasound data and the identification information. The ultrasonic diagnostic apparatus according to claim 10.

17. The acquisition unit acquires the first ultrasound data obtained by an ultrasound scan in the presence of a contrast agent. The ultrasonic diagnostic apparatus according to claim 1 .

18. The acquisition unit acquires the first ultrasound data obtained by an ultrasound scan in the absence of a contrast agent. The ultrasonic diagnostic apparatus according to claim 1 .

19. the extraction unit extracts, for each position of the frame, information for identifying a magnitude relationship after multiplying a signal value corresponding to the position or a signal value corresponding to a periphery of the position by a predetermined coefficient, as the identification information; The ultrasonic diagnostic apparatus according to claim 4.

20. the extraction unit extracts, for each position of the frame, information identifying a variance between a signal value corresponding to the position and signal values ​​corresponding to a periphery of the position, as the identification information; The ultrasonic diagnostic apparatus according to claim 1 .

21. The acquisition unit acquires three-dimensional ultrasound data as first ultrasound data of the subject. The ultrasonic diagnostic apparatus according to claim 1 .

22. The acquisition unit acquires first ultrasound data collected by increasing a scan line density in a mode for extracting the identification information. The ultrasonic diagnostic apparatus according to claim 1 .

23. the extraction unit divides the first ultrasound data into a plurality of divided data, generates extracted data by extracting positions of local peaks for each divided data, and assigns each extracted data to a corresponding position on the first ultrasound data, thereby extracting the identification information. The ultrasonic diagnostic apparatus according to claim 1 .

24. an acquisition unit that acquires a plurality of first ultrasound data within a predetermined time; an extracting unit that extracts, for each position of a frame represented by the first ultrasound data, identification information that identifies a magnitude relationship between a signal value corresponding to the position and signal values ​​corresponding to a periphery of the position from each of the plurality of first ultrasound data; and an output unit that outputs second ultrasound data based on at least one of the plurality of first ultrasound data, or ultrasound data obtained by performing a predetermined process on the first ultrasound data, and the identification information extracted from each of the plurality of first ultrasound data. Ultrasound diagnostic equipment.

25. an acquisition unit that acquires first ultrasound data of a subject; an extracting unit that extracts identification information for identifying a local peak position for each predetermined region of a frame represented by the first ultrasound data; an output unit that outputs second ultrasound data based on the identification information extracted by the extraction unit and ultrasound data representing a processing target. Medical information processing equipment.

26. acquiring first ultrasound data of a subject; an extraction step of extracting identification information for identifying a local peak position for each predetermined region of a frame represented by the first ultrasound data; and an output step of outputting second ultrasound data based on the identification information extracted by the extraction step and ultrasound data representing a processing target. Medical information processing method.

Images