Ultrasonic diagnostic apparatus

Abstract

The purpose of the present invention is to provide an ultrasonic diagnostic device that reduces the number of times ultrasonic pulses are transmitted during Doppler measurement while suppressing unnecessary components included in information obtained by Doppler measurement. An information processing unit (26) is provided with: a Doppler measurement unit (40) that generates Doppler measurement information on the basis of a received Doppler signal output from a wall filter (38); and the machine learning model (44) is constructed according to the training information and the target information. The training information is information obtained from K received Doppler signals. The target information is information obtained from J reception Doppler signals for the same object to be measured as when obtained from K reception Doppler signals. Here, J and K are integers of 2 or more, and J is greater than K. A machine learning model (44) generates Doppler measurement information from the input information. The input information is information generated from K reception Doppler signals for an object to be measured in a subject (18).

Description

Technical Field

[0001] The present invention relates to an ultrasonic diagnostic apparatus, and more particularly to an apparatus for performing Doppler measurement. Background Art

[0002] An ultrasonic diagnostic apparatus that observes a subject by transmitting and receiving ultrasonic waves is widely used. Among the operation modes of the ultrasonic diagnostic apparatus, there is a Doppler mode for measuring the blood flow velocity of an observed part. In the measurement in the Doppler mode, ultrasonic pulses are continuously transmitted to the subject multiple times, and reflected waves continuously generated multiple times in the subject are received. A plurality of received signals having Doppler frequency components (hereinafter, referred to as received Doppler signals) are generated from a plurality of received pulse signals based on the continuously received reflected waves. Further, high-pass filter processing (wall filter processing) is performed on the plurality of received Doppler signals, and based on the plurality of received Doppler signals after the high-pass filter processing, the blood flow velocity in a region of interest set on the ultrasonic beam formed by the ultrasonic pulses is obtained.

[0003] As the high-pass filter, a filter such as an FIR filter (Finite Impulse Response Filter) or an IIR filter (Infinite Impulse Response Filter) is used. The larger the number of received Doppler signals to be processed by the high-pass filter, the larger the number of tap coefficients of the high-pass filter can be increased. Therefore, the larger the number of received Doppler signals to be processed by the high-pass filter, the steeper the filter characteristics, and while ensuring the high-frequency passband, the low-frequency attenuation amount can also be increased. Thereby, noise such as clutter in the displayed ultrasonic image is suppressed.

[0004] In addition, as the technology related to the present invention, an ultrasonic diagnostic apparatus operating in the Doppler mode is described in Patent Documents 1 to 3 below. Patent Documents 4 to 6 describe a wall filter.

[0005] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2005-102718

[0006] Patent Document 2: Japanese Unexamined Patent Application Publication No. 8-154935

[0007] Patent Document 3: Japanese Unexamined Patent Application Publication No. 2016-87302

[0008] Patent Document 4: Japanese Unexamined Patent Application Publication No. 2009-5737

[0009] Patent Document 5: Japanese Unexamined Patent Application Publication No. 7-16227

[0010] Patent Document 6: Japanese Patent Application Laid-Open No. 2004-532711 Summary of the Invention

[0011] As described above, in Doppler measurement, the more ultrasonic pulses are transmitted, the more Doppler signals are received, making the filter characteristics steeper and increasing the effect of suppressing unnecessary components such as clutter. However, the more ultrasonic pulses are transmitted, the smaller the frame rate and the fewer the number of ultrasonic images displayed per fixed time.

[0012] An object of the present invention is to suppress unnecessary components contained in information obtained by Doppler measurement while reducing the number of ultrasonic pulses transmitted in Doppler measurement.

[0013] The ultrasonic diagnostic apparatus according to the present invention is characterized by comprising: a transmission unit that sets N as an integer of 2 or more and continuously transmits ultrasonic pulses N times through an ultrasonic probe; a reception unit that receives reflected waves continuously generated N times in a measurement object through the ultrasonic probe; and an information processing unit that generates N received Doppler signals from N received pulse signals output from the reception unit based on the reflected waves continuously generated N times in the measurement object and performs processing on each of the received Doppler signals. The information processing unit includes: a filter that performs high-pass filter processing on the N received Doppler signals; a Doppler measurement unit that generates Doppler measurement information of the measurement object based on the N received Doppler signals that have undergone the high-pass filter processing; and a machine learning model that is constructed based on teaching data. Under the condition that J and K are integers of 2 or more and J is greater than K, the teaching data includes: training information, at least one of reception characteristic information derived from each of the received Doppler signals when N is set to K and the Doppler measurement information generated by the Doppler measurement unit when N is set to K; and target information, at least one of the reception characteristic information derived from each of the received Doppler signals when N is set to J for the same measurement object as when N is set to K and the Doppler measurement information generated by the Doppler measurement unit when N is set to J. The machine learning model generates the Doppler measurement information of the measurement object in the subject based on input information, and the input information is at least one of the reception characteristic information derived from each of the received Doppler signals when N is set to K and the Doppler measurement information generated by the Doppler measurement unit when N is set to K.

[0014] In one embodiment, the reception characteristic information includes at least one of the following: the N received Doppler signals before the high-pass filter processing; and the N received Doppler signals after the high-pass filter processing.

[0015] In one embodiment, the Doppler measurement information includes at least one of the following: the autocorrelation values of the N received Doppler signals processed by the high-pass filter; the velocity of the measurement object obtained from the N received Doppler signals processed by the high-pass filter; the Doppler frequency deviation degree for the N received Doppler signals processed by the high-pass filter; and the value representing the magnitude of the N received Doppler signals processed by the high-pass filter.

[0016] In one embodiment, the transmitting unit transmits ultrasonic waves for B-mode image generation through the ultrasonic probe, the receiving unit receives the reflected waves for B-mode image generation generated in the measurement object through the ultrasonic probe, the information processing unit includes a B-mode image generation unit, and the B-mode image generation unit generates B-mode image data based on the reflected waves for B-mode image generation and based on the B-mode image reception signals output from the receiving unit. Based on the reflected waves for B-mode image generation, the B-mode image reception signals output from the receiving unit are cited as any one of the N received pulse signals output from the receiving unit.

[0017] In one embodiment, the transmitting unit forms a plurality of transmission frequency bands for the ultrasonic pulses at different positions or in different directions. For two adjacent transmission frequency bands, the ultrasonic pulses are alternately transmitted in such a way that the ultrasonic pulses are transmitted in one transmission frequency band during the period when the ultrasonic pulses are not transmitted in the other transmission frequency band. For two adjacent transmission frequency band pairs each including two adjacent transmission frequency bands, a series of the ultrasonic pulses alternately transmitted on the two transmission frequency bands included in one transmission frequency band pair is regarded as an ultrasonic pulse group, and the ultrasonic pulse groups are alternately transmitted in such a way that the ultrasonic pulse groups are transmitted in one transmission frequency band pair during the period when the ultrasonic pulse groups are not transmitted in the other transmission frequency band pair. Each time K ultrasonic pulses are transmitted in each transmission frequency band, the machine learning model generates one frame amount of the Doppler measurement information for each transmission frequency band.

[0018] In one embodiment, during the period of generating one frame amount of the Doppler measurement information, the action of alternately transmitting the ultrasonic pulse groups is continuously performed for two adjacent transmission frequency band pairs.

[0019] Advantageous Effects of the Invention

[0020] According to the present invention, while suppressing the unnecessary components included in the information obtained by Doppler measurement, it is also possible to reduce the number of times of transmitting ultrasonic pulses in Doppler measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a diagram showing the structure of an ultrasonic diagnostic apparatus.

[0022] Figure 2 It is a diagram showing the action of inputting training information into the machine learning unit.

[0023] Figure 3 It is a diagram showing the action of inputting target information into the machine learning unit.

[0024] Figure 4 It is a diagram showing the model application action.

[0025] Figure 5 It is a diagram showing an example of an ultrasonic pulse transmitted from an ultrasonic probe during normal operation.

[0026] Figure 6 It is a diagram showing an example of an ultrasonic pulse transmitted from an ultrasonic probe during the model application action.

[0027] Figure 7 It is a diagram showing the model application action.

[0028] Symbol Explanation

[0029] 10 - Beam control unit, 12 - Transmission unit, 14 - Ultrasonic probe, 16 - Vibration element, 18 - Subject, 20 - Reception unit, 22 - Control unit, 24 - Operation unit, 26 - Information processing unit, 28 - Phased addition unit, 32 - B - mode image generation unit, 34 - Image processing unit, 36 - Quadrature detection unit, 38 - Wall filter, 40 - Doppler measurement unit, 42 - Machine learning unit, 44 - Machine learning model, 46 - Display unit, 100 - Ultrasonic diagnostic device. Detailed Embodiments

[0030] Each embodiment of the present invention will be described with reference to the respective figures. For the same constituent elements shown in multiple figures, the same symbols are marked and their descriptions are omitted. In Figure 1 the structure of the ultrasonic diagnostic device 100 according to the embodiment of the present invention is shown. The ultrasonic diagnostic device 100 includes a beam control unit 10, a transmission unit 12, an ultrasonic probe 14, a reception unit 20, a control unit 22, an operation unit 24, an information processing unit 26, and a display unit 46.

[0031] The information processing unit 26 includes a phased addition unit 28, a B-mode image generation unit 32, an image processing unit 34, a quadrature detection unit 36, a wall filter 38, a Doppler measurement unit 40, and a machine learning unit 42. The information processing unit 26 can be constituted by one or more processors that implement the respective functions of these components (the phased addition unit 28, the B-mode image generation unit 32, the image processing unit 34, the quadrature detection unit 36, the wall filter 38, the Doppler measurement unit 40, and the machine learning unit 42) by executing a program. The control unit 22 performs overall control of the ultrasonic diagnostic apparatus 100. The operation unit 24 includes a keyboard, a mouse, a lever, buttons, a voice recognition device, etc., and outputs information related to user operations to the control unit 22. The control unit 22 controls the ultrasonic diagnostic apparatus 100 according to the operations in the operation unit 24.

[0032] The operation unit 24 can constitute a user interface for operating the ultrasonic diagnostic apparatus 100 together with the display unit 46. For example, the operation unit 24 can include a touch panel on the display screen of the display unit 46. Also, the operation unit 24 can have the function of operating a keyboard, a lever, buttons, etc. virtually formed on the display screen.

[0033] An overview of the operation of the ultrasonic diagnostic apparatus 100 will be described. The ultrasonic diagnostic apparatus 100 transmits ultrasonic waves from the ultrasonic probe 14 to the subject 18, and receives the ultrasonic waves reflected within the subject 18, that is, the reflected waves generated within the subject 18, by the ultrasonic probe 14. The ultrasonic diagnostic apparatus 100 performs respective measurements based on the B-mode and the Doppler mode.

[0034] In the operation of the B-mode, the ultrasonic diagnostic apparatus 100 generates B-mode image data based on the reflected waves received from the subject 18, and displays the B-mode image on the display unit 46. In the operation of the Doppler mode, the ultrasonic diagnostic apparatus 100 generates B-mode color Doppler image data representing an image in which colors corresponding to blood flow velocities are added to the B-mode image, and displays the B-mode color Doppler image on the display unit 46.

[0035] The specific structure of the ultrasonic diagnostic apparatus 100 and the specific processes performed by the ultrasonic diagnostic apparatus 100 will be described. The ultrasonic probe 14 is set in a state of being in contact with the surface of the subject 18. The ultrasonic probe 14 includes a plurality of vibration elements 16. The transmission unit 12 outputs transmission signals to the respective vibration elements 16 of the ultrasonic probe 14 according to the control based on the beam control unit 10. Thereby, ultrasonic waves are transmitted from the ultrasonic probe 14. The beam control unit 10 can form a transmission beam in the ultrasonic probe 14 and scan the transmission beam over the subject 18 by controlling the transmission unit 12. That is, the transmission unit 12 can adjust the delay time or level of each transmission signal according to the control of the beam control unit 10, form a transmission beam in the ultrasonic probe 14, and scan the transmission beam over the subject 18. Further, the transmission unit 12 can adjust the delay time or level of each transmission signal according to the control of the beam control unit 10, and form a transmission frequency band composed of a plurality of transmission beams in the ultrasonic probe 14.

[0036] When the respective vibration elements 16 of the ultrasonic probe 14 receive the reflected waves generated within the subject 18, each vibration element 16 outputs a reception signal corresponding to the received ultrasonic wave to the reception unit 20. The reception unit 20 performs processes such as amplification and band limitation on the reception signals output from the respective vibration elements 16 according to the control based on the beam control unit 10, and outputs them to the information processing unit 26. The information processing unit 26 performs processes executed by each component (the phased addition unit 28, the B-mode image generation unit 32, the image processing unit 34, the quadrature detection unit 36, the wall filter 38, the Doppler measurement unit 40, and the machine learning unit 42) on each reception signal.

[0037] The phased addition unit 28 performs phased addition on the plurality of reception signals output from the reception unit 20 by the plurality of vibration elements 16 to generate a phased reception signal. Thereby, a phased reception signal that is phase-adjusted and added is generated so that the reception signals based on the ultrasonic waves received from a specific direction are enhanced with each other, and a reception beam is formed in the specific direction. The phased addition unit 28 outputs the phased reception signal to the B-mode image generation unit 32 during the operation in the B mode. Further, the phased addition unit 28 outputs the phased reception signal to the quadrature detection unit 36 during the operation in the Doppler mode.

[0038] The operations in the B mode will be described. The phased summation unit 28 generates respective phased received signals based on the ultrasonic waves received in respective directions of the received beams scanned within the subject 18, and outputs the same as B mode image received signals to the B mode image generation unit 32. The B mode image generation unit 32 generates B mode image data based on the B mode image received signals obtained for respective received beam directions, and outputs the same to the image processing unit 34. The B mode image data for one scan of the transmit beam and the receive beam (hereinafter referred to as the transceiver beam) is image data for one frame amount, and corresponds to one B mode image.

[0039] The beam control unit 10, the transmit unit 12, the ultrasonic probe 14, the receive unit 20, the phased summation unit 28, and the B mode image generation unit 32 successively generate B mode image data in conjunction with repeated scans of the transceiver beam, and output respective B mode image data to the image processing unit 34. The image processing unit 34 generates a video signal for displaying the B mode image based on the B mode image data, and outputs the same to the display unit 46. The display unit 46 displays the B mode image based on the video signal.

[0040] The B mode may be a phase inversion B mode. In the phase inversion B mode, ultrasonic pulses are continuously transmitted in the same direction twice with a phase difference of 180°. The B mode image generation unit 32 adds two phased received signals based on the reflected waves continuously received twice according to the ultrasonic pulses continuously transmitted twice to generate a harmonic received signal, and generates phase inversion B mode image data based on the harmonic received signal. The harmonic received signal represents the harmonic component generated in the two phased received signals due to the Doppler frequency not being 0. The phase inversion B mode image data represents an image of a moving measurement object such as blood.

[0041] The operations in the Doppler mode will be described. The operations of the Doppler mode according to the present embodiment include a normal operation, a learning operation, and a model application operation. In the normal operation, the Doppler measurement unit 40 generates Doppler measurement information based on the received Doppler signal obtained by quadrature detection of the phased received signal.

[0042] The Doppler measurement information may include color Doppler data. The color Doppler data is data representing the blood flow velocity by coloring on the B mode image of the area scanned by the transceiver beam. The color Doppler data may be, for example, data that marks the area where the blood flows away from the ultrasonic probe 14 in blue, marks the area where the blood flows toward the ultrasonic probe 14 in red, and the brighter the area, the greater the blood flow velocity.

[0043] Among the Doppler measurement information generated by the Doppler measurement unit 40, in addition to color Doppler data, it may also include various information related to the blood flow velocity in the area scanned by the transmitting and receiving beam. The information other than color Doppler data contained in the Doppler measurement information will be described later.

[0044] The learning operation is an operation of generating teaching data for machine learning and constructing a machine learning model 44 in the machine learning unit 42 through machine learning. The teaching data is generated through normal operations. In the model application operation, the machine learning model 44 constructed by the machine learning unit 42 through machine learning generates Doppler measurement information.

[0045] The normal operation will be described. In the normal operation, ultrasonic pulses are transmitted and received N times continuously for one transmitting and receiving beam. Here, N is an integer of 2 or more. N received pulse signals are output from the phased addition unit 28 to the quadrature detection unit 36 as N post-phased received signals. The quadrature detection unit 36 performs quadrature detection on the N received pulse signals with a local signal having the frequency of the transmitted ultrasonic pulse to generate N received Doppler signals. The N received Doppler signals are output from the quadrature detection unit 36 to the wall filter 38. The wall filter 38 performs high-pass filter processing on the N received Doppler signals and outputs the N received Doppler signals after high-pass filter processing to the Doppler measurement unit 40.

[0046] The Doppler measurement unit 40 generates color Doppler data as one piece of information contained in the Doppler measurement information based on the N received Doppler signals obtained for each of a plurality of transmitting and receiving beams with different positions or directions.

[0047] The Doppler measurement unit 40 obtains the blood flow velocity v(r) in the depth direction of the transmitting and receiving beam by autocorrelation processing as shown in Patent Document 3, for example, based on the N received Doppler signals. Here, v(r) represents the blood flow velocity at the position of depth r. The Doppler measurement unit 40 generates color Doppler data based on the blood flow velocity v(r) in the depth direction at each depth r obtained for each of a plurality of transmitting and receiving beams with different positions or directions, and outputs it to the image processing unit 34. Hereinafter, the specific processing for obtaining the blood flow velocity v(r) will be described.

[0048] The received Doppler signal obtained in the q-th (q = 1 to N) of the first to N-th is represented by the following formula (Equation 1).

[0049] [Equation 1]

[0050]

[0051] r is the coordinate value in the depth direction. I(r, q) represents the in-phase component of the received Doppler signal, and Q(r, q) represents the quadrature component of the received Doppler signal. j is the imaginary unit. The Doppler measurement unit 40 obtains the autocorrelation value A(r) with respect to N received Doppler signals z(r, 1), z(r, 2), …… z(r, N) according to (Equation 2).

[0052] [Equation 2]

[0053]

[0054] Here, the superscript "*" represents the conjugate complex number. The Doppler measurement unit 40 uses the real part Re[A(r)] and the imaginary part Im[A(r)] of the autocorrelation value A(r) and obtains the blood flow velocity v(r) according to (Equation 3).

[0055] [Equation 3]

[0056]

[0057] c is the propagation speed of the ultrasonic pulse propagating in the subject 18. f0 is the frequency of the ultrasonic pulse transmitted from the ultrasonic probe 14. T is the time interval for transmitting N ultrasonic pulses. The part on the right side of c / (2f0) in the right side of (Equation 3) represents the Doppler frequency. The blood flow velocity v(r) represents the component in the depth direction of the blood flow velocity at the depth r. When the angle φ formed by the blood flow direction with respect to the depth direction is known, v(r) / cosφ is the blood flow velocity.

[0058] In cases such as when measuring the blood flow velocity distribution where it is not necessary to obtain the absolute value of the blood flow velocity (for example, the value in the MKSA unit system), the blood flow velocity can be a value obtained by multiplying an arbitrary constant by the value obtained from Equation (Equation 3). Also, instead of the blood flow velocity, the Doppler frequency shift measurement value, which is the part on the right side of c / (2f0) in the right side of (Equation 3), can be used.

[0059] The image processing unit 34 generates data representing a B-mode color Doppler image obtained by assigning a color corresponding to the blood flow velocity to the B-mode image based on the B-mode image data and the color Doppler data. The image processing unit 34 generates a video signal based on the B-mode color Doppler image data and outputs it to the display unit 46. The display unit 46 displays the B-mode color Doppler image based on the video signal.

[0060] The Doppler measurement unit 40 can use the autocorrelation value A(r) at each depth r obtained for each of a plurality of transceiver beams with different positions or directions as one of the Doppler measurement information.

[0061] Further, the Doppler measurement unit 40 can use the velocity v(r) at each depth r obtained for each of a plurality of transmission / reception beams with different positions or directions as one of the Doppler measurement information.

[0062] The Doppler measurement unit 40 can generate the blood flow power P(r) at each depth r obtained for each of the transmission / reception beams with different positions or directions as one of the Doppler measurement information. The blood flow power P(r) is represented by the magnitude of the received Doppler signal shown in (Equation 1). To obtain the blood flow power P(r), an appropriate filter such as an SVD (Singular Value Decomposition) filter can be used as the wall filter 38.

[0063] Further, the Doppler measurement unit 40 can generate the degree of deviation of the Doppler frequency (hereinafter referred to as the Doppler frequency deviation degree) of the received Doppler signals acquired N times continuously for one transmission / reception beam as one of the information included in the Doppler measurement information.

[0064] When the blood flow velocity v(r) is obtained according to the above (Equation 1) to (Equation 3), the Doppler frequency deviation degree can be obtained from the N - 1 adjacent-time Doppler frequencies obtained according to (Equation 4).

[0065] That is, the Doppler measurement unit 40 uses the real part and the imaginary part of z(r, q)·z(r, q + 1) summed up on the right side of (Equation 2), and obtains the adjacent-time Doppler frequency fa(r, q) for each of q = 1 to N - 1 according to (Equation 4). * The Doppler measurement unit 40 obtains the Doppler frequency deviation degree for the N - 1 adjacent-time Doppler frequencies fa(r, 1), fa(r, 2),..., fa(r, N - 1), and outputs it to the image processing unit 34. The Doppler frequency deviation degree can be a value representing the deviation such as the dispersion or standard deviation of the N - 1 adjacent-time Doppler frequencies.

[0066] [Equation 4]

[0067]

[0068] The image processing unit 34 can adjust the color added to the B-mode image according to the Doppler frequency deviation degree. For example, when areas where blood flows away from the ultrasonic probe 14 are marked blue and areas where blood flows toward the ultrasonic probe 14 are marked red, the greater the Doppler frequency deviation degree, the closer the color can be to purple or white.

[0069]

[0070] ​As described above, among the Doppler measurement information generated by the Doppler measurement unit 40, in addition to the color Doppler data, there are also the autocorrelation value A(r), blood flow velocity v(r), blood flow power P(r), Doppler frequency deviation degree, etc. obtained for each of the transmission and reception beams with different positions or directions. The Doppler measurement information can be information including at least one of the autocorrelation value A(r), blood flow velocity v(r), blood flow power P(r), and Doppler frequency deviation degree.

[0071] In this way, during normal operation, based on the N received Doppler signals that have undergone high-pass filter processing by the wall filter 38, the Doppler measurement unit 40 generates Doppler measurement information. The received Doppler signal output from the quadrature detection unit 36 includes low-frequency noise based on the movement of tissues within the subject 18, which causes the unwanted components contained in the Doppler measurement information. For example, it causes the generation of noise called clutter for the color Doppler data. Therefore, the wall filter 38 suppresses the unwanted components contained in the Doppler measurement information.

[0072] Next, the learning operation will be described. During the learning operation, the following processing is performed for the case where ultrasonic pulses are transmitted and received continuously K times for each transmission and reception beam. Here, K is an integer of 2 or more that is smaller than the above-mentioned N. Along with the continuous transmission and reception of ultrasonic pulses K times for each transmission and reception beam, K received Doppler signals are output from the quadrature detection unit 36 to the machine learning unit 42 and the wall filter 38.

[0073] The wall filter 38 performs high-pass filter processing on the K received Doppler signals and outputs the K received Doppler signals after the high-pass filter processing to the Doppler measurement unit 40 and the machine learning unit 42. The Doppler measurement unit 40 generates Doppler measurement information based on the received Doppler signals obtained continuously K times for each of the plurality of transmission and reception beams with different positions or directions and outputs it to the machine learning unit 42.

[0074] In this way, in the machine learning unit 42, for the case where ultrasonic pulses are transmitted and received continuously K times for each transmission and reception beam (hereinafter, sometimes referred to as K - time transmission and reception), the following information is input as training information. That is, the received Doppler signal before the high-pass filter processing by the wall filter 38, the received Doppler signal after the high-pass filter processing by the wall filter 38, and the Doppler measurement information generated by the Doppler measurement unit 40 are input to the machine learning unit 42.

[0075] The training information may include at least one of the following: the received Doppler signal before high-pass filter processing is performed by the wall filter 38; the received Doppler signal after high-pass filter processing is performed by the wall filter 38; and the Doppler measurement information generated by the Doppler measurement unit 40. The Doppler measurement information may be at least one of the various types of information included in the Doppler measurement information.

[0076] Next, for the case where ultrasonic pulses are transmitted and received J times for each transceiver beam (hereinafter sometimes referred to as J times of transmission and reception), the following information is input to the machine learning unit 42 as target information. Here, J is an integer of 2 or more that is larger than K. Compared with the case of K times of transmission and reception, the tap coefficients of the wall filter 38 are more in the case of J times of transmission and reception. Therefore, compared with the case of K times of transmission and reception, the low-pass filter characteristics become steeper, and the characteristics of smaller attenuation in the high frequency and larger attenuation in the low frequency become significant.

[0077] The received Doppler signal before high-pass filter processing is performed by the wall filter 38, the received Doppler signal after high-pass filter processing is performed by the wall filter 38, and further the Doppler measurement information generated by the Doppler measurement unit 40 are input to the machine learning unit 42. However, the region (measurement object) where ultrasonic pulses are transmitted and received in the case of J times of transmission and reception is the same as the region (measurement object) where ultrasonic pulses are transmitted and received in the case of K times of transmission and reception. The Doppler measurement information as the target information may be at least one of the various types of information included in the Doppler measurement information.

[0078] In the learning operation, the above-mentioned K times of transmission and reception and J times of transmission and reception are performed on the blood flow in different multiple measurement objects, for example, different multiple observation sites. The machine learning unit 42 obtains a set of the training information generated by K times of transmission and reception and the target information generated by J times of transmission and reception for different multiple subjects 18 or different multiple observation sites as teaching data, and constructs a machine learning model 44. For at least one of the different multiple measurement objects, the target information includes at least the Doppler measurement information. The learning operation may be performed using machine learning algorithms such as CNN, AdaBoost, and SVN. The machine learning algorithm may include a deep learning algorithm.

[0079] The constructed machine learning model 44 is a model that generates the same Doppler measurement information as in the case of J times of transmission and reception when ultrasonic pulses are transmitted and received K times for each transceiver beam and the following input information is input. That is, the machine learning model 44 is a model that, when ultrasonic pulses are transmitted and received K times continuously, can predict the obtainable Doppler measurement information assuming J times of transmission and reception.

[0080] The input information may be at least one of the following: the received Doppler signal before high-pass filtering is performed by the wall filter 38; the received Doppler signal after high-pass filtering is performed by the wall filter 38; and the Doppler measurement information generated by the Doppler measurement unit 40. The Doppler measurement information may be at least one of the various types of information included in the Doppler measurement information.

[0081] Next, the model application operation will be described. In the model application operation, an ultrasonic beam is scanned at the observation site of the subject 18, and ultrasonic pulses are transmitted and received for a plurality of transmitting and receiving beams having different positions or directions. For each transmitting and receiving beam, ultrasonic pulses are transmitted and received K times continuously, and K received Doppler signals are output from the quadrature detector 36 to the wall filter 38 and the machine learning model 44.

[0082] The wall filter 38 performs high-pass filtering on the K received Doppler signals, and outputs the K received Doppler signals after high-pass filtering to the Doppler measurement unit 40 and the machine learning model 44. The Doppler measurement unit 40 generates Doppler measurement information based on the received Doppler signals obtained continuously K times for each of the plurality of transmitting and receiving beams having different positions or directions, and outputs it to the machine learning model 44.

[0083] Thus, in the machine learning model 44, the input information is input for the case where ultrasonic pulses are transmitted and received K times continuously for each transmitting and receiving beam, and the machine learning model 44 generates the same Doppler measurement information as the case where the input information is transmitted and received J times.

[0084] When the Doppler measurement information includes color Doppler data, the machine learning model 44 outputs the color Doppler data to the image processing unit 34. The image processing unit 34 generates data representing a B-mode color Doppler image based on the B-mode image data and the color Doppler data. The image processing unit 34 generates a video signal for displaying the B-mode color Doppler image based on the B-mode color Doppler image data, and outputs it to the display unit 46. The display unit 46 displays the B-mode color Doppler image based on the video signal.

[0085] In addition, the image processing unit 34 can generate composite image data that displays side by side an image based on B-mode color Doppler image data obtained through normal operation and an image based on B-mode color Doppler image data obtained through model application operation. Also, the image processing unit 34 can generate composite image data that represents an image in which one of an image based on B-mode color Doppler image data obtained through normal operation and an image based on B-mode color Doppler image data obtained through model application operation is seen through the other. The image processing unit 34 generates a video signal for displaying the composite image based on the composite image data and outputs it to the display unit 46. The display unit 46 displays the composite image based on the video signal.

[0086] Thus, the ultrasonic diagnostic apparatus 100 according to the present embodiment includes a transmission unit 12, a reception unit 20, and an information processing unit 26. The transmission unit 12 continuously transmits ultrasonic pulses N times through the ultrasonic probe 14. The reception unit 20 receives reflected waves continuously generated N times in the measurement object through the ultrasonic probe 14. The information processing unit 26 generates N reception Doppler signals by orthogonal detection from the N reception pulse signals output from the reception unit 20 based on the reflected waves continuously generated N times, and performs processing on the N reception Doppler signals. The measurement object in the present embodiment is an observation site where blood flows in the subject 18.

[0087] The information processing unit 26 may include a wall filter 38 (filter) that performs high-pass filter processing on the N reception Doppler signals, a Doppler measurement unit 40 that generates Doppler measurement information of the measurement object based on the N reception Doppler signals on which high-pass filter processing has been performed, and a machine learning model 44 constructed based on teaching data.

[0088] The teaching data includes training information and target information. The training information is at least one of the following: reception characteristic information derived from each reception Doppler signal with N set to K; and Doppler measurement information generated by the Doppler measurement unit 40 when N is set to K. Here, the reception characteristic information includes at least one of the following: the reception Doppler signal before high-pass filter processing; and the reception Doppler signal after high-pass filter processing.

[0089] The target information is at least one of the following: reception characteristic information derived from each reception Doppler signal with N set to J for the same measurement object as when N is set to K; and Doppler measurement information generated by the Doppler measurement unit 40 when N is set to J. Here, J and K are integers of 2 or more, and J is greater than K.

[0090] The machine learning model (44) generates Doppler measurement information based on the input information. The input information is at least one of the following: reception characteristic information derived from each received Doppler signal with N set to K for the object to be measured in the subject 18; and the Doppler measurement information generated by the Doppler measurement unit 40 when N is set to K.

[0091] As described above, compared with the case of J - time transmission and reception with N set to J, the tap coefficients of the wall filter 38 are more numerous in the case of K - time transmission and reception with N set to K. Therefore, compared with the case of K - time transmission and reception, the low - pass filter characteristic becomes steeper in the case of J - time transmission and reception, and the characteristic that the attenuation amount is smaller at high frequencies and larger at low frequencies becomes significant. Thus, the unwanted components contained in the Doppler measurement information are suppressed to a greater extent in the case of J - time transmission and reception compared with K - time transmission and reception. Regarding the color Doppler data contained in the Doppler measurement information, the effect of suppressing clutter is greater in the case of J - time transmission and reception compared with K - time transmission and reception.

[0092] According to the ultrasonic diagnostic apparatus 100 according to the present embodiment, by applying the machine learning model 44, Doppler measurement information similar to that in the case of J - time transmission and reception can also be obtained for the case of K - time transmission and reception. Thus, even when the number of ultrasonic pulse transmissions is relatively small, the unwanted components contained in the Doppler measurement information can be suppressed by the wall filter 38. For the case of displaying a B - mode color Doppler image, even when the number of ultrasonic pulse transmissions is relatively small, clutter can be suppressed by the wall filter 38.

[0093] Moreover, in the ultrasonic diagnostic apparatus 100 according to the present embodiment, by maintaining the effect of suppressing the unwanted components contained in the Doppler measurement information while reducing the number of ultrasonic pulse transmissions, the frame rate when generating color Doppler data is increased.

[0094] In Figure 2 the operation of inputting training information to the machine learning unit 42 is shown. In this figure, it is shown that J = 3K holds, and for a series of J - time ultrasonic pulse transmissions and receptions, the training information is continuously input to the machine learning unit 42 three times. That is, along with J ultrasonic pulses being transmitted from the ultrasonic probe 14 and J reflected waves being received by the ultrasonic probe 14, J received Doppler signals are input to the wall filter 38 and the machine learning unit 42.

[0095] The wall filter 38, the Doppler measurement unit 40, and the machine learning unit 42 input training information into the machine learning unit 42 for each of the K received Doppler signals. That is, each time K received Doppler signals are input, the wall filter 38 outputs the K received Doppler signals after high-pass filter processing to the Doppler measurement unit 40 and the machine learning unit 42. Each time the K received Doppler signals after high-pass filter processing are input, the Doppler measurement unit 40 outputs Doppler measurement information to the machine learning unit 42. In this way, the training information corresponding to K times of transmission and reception is continuously input into the machine learning unit 42 three times by inputting K received Doppler signals, the K received Doppler signals before high-pass filter processing, the K received Doppler signals after high-pass filter processing, and the Doppler measurement information generated based on the K received Doppler signals.

[0096] In Figure 3 FIG. shows the operation of inputting target information into the machine learning unit 42. In this figure, it is shown that for J consecutive transmissions and receptions of ultrasonic pulses, the target information is input into the machine learning unit 42 once. That is, along with the transmission of J ultrasonic pulses from the ultrasonic probe 14 and the reception of J reflected waves by the ultrasonic probe 14, J received Doppler signals are input into the wall filter 38 and the machine learning unit 42. Figure 3 The J received Doppler signals shown can be the same as Figure 2 the J received Doppler signals shown. That is, the J received Doppler signals obtained through J = 3K times of transmission and reception in the operation of inputting training information into the machine learning unit 42 can be used for the operation of inputting target information into the machine learning unit 42.

[0097] The wall filter 38, the Doppler measurement unit 40, and the machine learning unit 42 input target information based on the J received Doppler signals into the machine learning unit 42. That is, the wall filter 38 outputs the J received Doppler signals after high-pass filter processing to the Doppler measurement unit 40 and the machine learning unit 42 according to the J received Doppler signals. The Doppler measurement unit 40 outputs Doppler measurement information to the machine learning unit 42 according to the J received Doppler signals after high-pass filter processing. In this way, the J received Doppler signals, the J received Doppler signals before high-pass filter processing, the J received Doppler signals after high-pass filter processing, and the Doppler measurement information generated based on the J received Doppler signals are input into the machine learning unit 42 as target information corresponding to J times of transmission and reception.

[0098] For different multiple subjects 18 or different multiple observation sites, Figure 2 and Figure 3 the operations shown are performed, and the machine learning unit 42 constructs the machine learning model 44 based on the continuously input training information and the continuously input target information.

[0099] InFigure 4 The model applicable operations are shown. In this figure, the following is shown: The transmission and reception of K consecutive ultrasonic pulses, the K received Doppler signals before the high-pass filter processing, the K received Doppler signals after the high-pass filter processing, and the Doppler measurement information are input into the machine learning model 44 once. That is, along with the transmission of K ultrasonic pulses from the ultrasonic probe 14 and the reception of K reflected waves by the ultrasonic probe 14, the K received Doppler signals are input into the wall filter 38 and the machine learning model 44. The wall filter 38 outputs the K received Doppler signals after the high-pass filter processing to the Doppler measurement unit 40 and the machine learning model 44 based on the K received Doppler signals. The Doppler measurement unit 40 outputs the Doppler measurement information to the machine learning model 44 by inputting the K received Doppler signals after the high-pass filter processing. Thus, the K received Doppler signals before the high-pass filter processing, the K received Doppler signals after the high-pass filter processing, and the Doppler measurement information generated based on the K received Doppler signals are input into the machine learning model 44 as input information, and the machine learning model 44 generates the same Doppler measurement information as the case of J times of transmission and reception based on the input information.

[0100] In Figure 5 An example of the ultrasonic pulses transmitted from the ultrasonic probe 14 during normal operation is shown. The plurality of vibration elements 16 provided in the ultrasonic probe 14 are arranged along Figure 5 the left-right direction. The vertical axis represents time. In Figure 5 the embodiment shown, four transmission frequency bands TX1 to TX4 are formed at different positions in the lateral direction by the plurality of vibration elements 16 arranged along the left-right direction. Each of the transmission frequency bands TX1 to TX4 is formed by a plurality of transmission beams. In each of the transmission frequency bands TX1 to TX4, N ultrasonic pulses are transmitted, and N reflected waves generated by reflection from the subject 18 are received. A series of N ultrasonic pulses is set as an ultrasonic pulse group, and the ultrasonic pulse group is transmitted at a prescribed time interval.

[0101] In the adjacent transmission frequency bands TX1 and TX2, the ultrasonic pulses are alternately transmitted, and N ultrasonic pulses are transmitted in each of the transmission frequency bands TX1 and TX2. Similarly, in the adjacent transmission frequency bands TX3 and TX4, the ultrasonic pulses are alternately transmitted, and N ultrasonic pulses are transmitted in each of the transmission frequency bands TX3 and TX4.

[0102] After transmitting the ultrasonic pulse group SP1 in the adjacent transmission frequency bands TX1 and TX2, the ultrasonic pulse group SP2 is transmitted in the adjacent transmission frequency bands TX3 and TX4. The transmission of the ultrasonic pulse group SP1 in the adjacent transmission frequency bands TX1 and TX2 and the transmission of the ultrasonic pulse group SP2 in the adjacent transmission frequency bands TX3 and TX4 are alternately repeated. In the following description, the adjacent transmission frequency bands TX1 and TX2 are referred to as the transmission frequency band pair PTX1, and the adjacent transmission frequency bands TX3 and TX4 are referred to as the transmission frequency band pair PTX2.

[0103] During the period from transmitting the ultrasonic pulse group SP2 in the transmission frequency band pair PTX2 to transmitting the ultrasonic pulse group SP1 in the transmission frequency band pair PTX1, ultrasonic pulses for B-mode image generation are transmitted in the ultrasonic probe 14 and reflected waves for B-mode image generation are received. In Figure 5 In the illustrated embodiment, a half-transmission frequency band for B-mode image generation is formed with a width that is half the width of each of the transmission frequency bands TX1 to TX4. Two ultrasonic pulses for B-mode image generation are transmitted in each of two adjacent half-transmission frequency bands within the transmission frequency band TX1, and the ultrasonic pulses for B-mode image generation are alternately transmitted in the two adjacent half-transmission frequency bands within the transmission frequency band TX1. In the present embodiment, the B-mode is a phase-inversion B-mode, and the phase difference between the two ultrasonic pulses for B-mode image generation transmitted in each half-transmission frequency band is 180°.

[0104] In the present embodiment, in the order of the transmission frequency bands TX1, TX2, TX3, and TX4, the operation of alternately transmitting ultrasonic pulses for B-mode image generation in two half-transmission frequency bands in each transmission frequency band is performed. In Figure 5 When alternately transmitting ultrasonic pulses for B-mode image generation in two half-transmission frequency bands in each of the transmission frequency bands TX1, TX2, TX3, and TX4, the ultrasonic pulse group for B-mode image generation is represented as the ultrasonic pulse group PIB.

[0105] The ultrasonic pulse group SP1 is transmitted in the transmission frequency band pair PTX1, the ultrasonic pulse group SP2 is transmitted in the transmission frequency band pair PTX2, and the ultrasonic pulse group PIB is transmitted in each of the transmission frequency bands TX1, TX2, TX3, and TX4. By performing reception processing on the reflected waves generated by each ultrasonic pulse group, processing of one frame of FR amount is executed. Processing of one frame of FR amount is equivalent to processing for generating Doppler measurement information corresponding to one color Doppler image.

[0106] Regarding each of the transmission frequency bands TX1 to TX4, in the processing of one frame of FR amount, normal operation is performed when transmitting N ultrasonic pulses and receiving N reflected waves generated by reflection from the subject 18, and the Doppler measurement unit 40 generates Doppler measurement information that does not depend on the machine learning model 44.

[0107] In Figure 6 an example of an ultrasonic pulse transmitted from the ultrasonic probe 14 in the model application operation is shown. In Figure 6 the illustrated embodiment, similar to Figure 5 the illustrated embodiment, four transmission frequency bands TX1 to TX4 are formed at different lateral positions of the ultrasonic pulse by a plurality of vibration elements 16 arranged in the left - right direction.

[0108] In each of the adjacent transmission frequency bands TX1 and TX2, two ultrasonic pulses are transmitted, and the ultrasonic pulses are transmitted alternately in the adjacent transmission frequency bands TX1 and TX2. Similarly, in each of the adjacent transmission frequency bands TX3 and TX4, two ultrasonic pulses are transmitted, and the ultrasonic pulses are transmitted alternately in the adjacent transmission frequency bands TX3 and TX4. Thus, in each of the transmission frequency bands TX1, TX2, TX3, and TX4, an ultrasonic pulse group SP1 composed of two ultrasonic pulses is respectively transmitted. Similarly, in each of the transmission frequency bands TX1, TX2, TX3, and TX4, ultrasonic pulse groups SP2, SP3, and SP4 composed of two ultrasonic pulses are sequentially transmitted over time.

[0109] In the present embodiment, in each of the transmission frequency bands TX1, TX2, TX3, and TX4, a series of transmission processes of sequentially transmitting the ultrasonic pulse groups SP1 to SP4 over time is repeated. In each of the transmission frequency bands TX1, TX2, TX3, and TX4, by transmitting the ultrasonic pulse groups SP1 to SP4, K ultrasonic pulses are transmitted in each of the transmission frequency bands TX1, TX2, TX3, and TX4. In Figure 6 the illustrated example, K = 8.

[0110] The transmission of the ultrasonic pulses for generating the B - mode image accompanying Figure 6 the initial series of transmissions of the ultrasonic pulse groups SP1 to SP4 is described. During the period from transmitting the ultrasonic pulse group SP1 in the transmission frequency band TX4 to transmitting the ultrasonic pulse group SP2 in the transmission frequency band TX1, the ultrasonic pulse group PIB1 for generating the B - mode image is transmitted in the left half - transmission frequency band of the transmission frequency band TX1. During the period from transmitting the ultrasonic pulse group SP2 in the transmission frequency band TX4 to transmitting the ultrasonic pulse group SP3 in the transmission frequency band TX1, the ultrasonic pulse group PIB2 for generating the B - mode image is transmitted in the right half - transmission frequency band of the transmission frequency band TX1.

[0111] After transmitting the ultrasonic pulse group SP3 in the transmission band TX4 and until transmitting the ultrasonic pulse group SP4 in the transmission band TX1, the ultrasonic pulse group PIB3 for B-mode image generation is transmitted in the left half of the transmission band of the transmission band TX2. After transmitting the ultrasonic pulse group SP4 in the transmission band TX4 and until transmitting the ultrasonic pulse group SP1 in the transmission band TX1, the ultrasonic pulse group PIB4 for B-mode image generation is transmitted in the right half of the transmission band of the transmission band TX2.

[0112] Explanation is given for the transmission of the ultrasonic pulses for B-mode image generation transmitted accompanying Figure 6 the transmission of the second series of ultrasonic pulse groups SP1 to SP4. After transmitting the ultrasonic pulse group SP1 in the transmission band TX4 and until transmitting the ultrasonic pulse group SP2 in the transmission band TX1, the ultrasonic pulse group PIB5 for B-mode image generation is transmitted in the left half of the transmission band of the transmission band TX3. After transmitting the ultrasonic pulse group SP2 in the transmission band TX4 and until transmitting the ultrasonic pulse group SP3 in the transmission band TX1, the ultrasonic pulse group PIB6 for B-mode image generation is transmitted in the right half of the transmission band of the transmission band TX3. After transmitting the ultrasonic pulse group SP3 in the transmission band TX4 and until transmitting the ultrasonic pulse group SP4 in the transmission band TX1, the ultrasonic pulse group PIB7 for B-mode image generation is transmitted in the left half of the transmission band of the transmission band TX4. After transmitting the ultrasonic pulse group SP4 in the transmission band TX4 and until transmitting the ultrasonic pulse group SP1 in the transmission band TX1, the ultrasonic pulse group PIB8 for B-mode image generation is transmitted in the right half of the transmission band of the transmission band TX4.

[0113] Hereinafter, accompanying Figure 6 the transmission of the odd-numbered series of ultrasonic pulse groups SP1 to SP4, the ultrasonic pulse groups PIB1 to PIB4 are transmitted at the same time as the ultrasonic pulse groups PIB1 to PIB4 transmitted accompanying the transmission of the first series of ultrasonic pulse groups SP1 to SP4. And, accompanying Figure 6 the transmission of the even-numbered series of ultrasonic pulse groups SP1 to SP4, the ultrasonic pulse groups PIB5 to PIB8 are transmitted at the same time as the ultrasonic pulse groups PIB5 to PIB8 transmitted accompanying the transmission of the second series of ultrasonic pulse groups SP1 to SP4.

[0114] Ultrasonic pulse groups SP1 to SP4 are transmitted in each of transmission bands TX1 to TX4, and by receiving and processing the reflected waves generated by each ultrasonic pulse group, processing of the FR amount for one frame of color Doppler data is performed. The processing of the FR amount for one frame is equivalent to the processing of generating Doppler measurement information corresponding to one color Doppler image.

[0115] Moreover, ultrasonic pulse groups PIB1 to PIB8 for generating B-mode images are transmitted from half transmission bands formed by each of transmission bands TX1 to TX4, and by receiving and processing the reflected waves generated by each ultrasonic pulse group, processing of the FRB amount for one frame of phase-inverted B-mode data is performed. The processing of the FRB amount for one frame is equivalent to the processing of generating phase-inverted B-mode data corresponding to one phase-inverted B-mode image.

[0116] In Figure 5 the transmission of ultrasonic pulses in the normal operation shown, during the period of generating the Doppler measurement information of the FR amount for one frame, the operation of alternately transmitting ultrasonic pulse groups to the adjacent two transmission bands PTX1 and PTX2 is performed only once.

[0117] In contrast, in Figure 6 the model application operation shown, during the period of generating the Doppler measurement information of the FR amount for one frame, the operation of alternately transmitting ultrasonic pulse groups to the adjacent two transmission bands PTX1 and PTX2 is continuously performed multiple times. In Figure 6 the example shown, during the period of generating the Doppler measurement information of the FR amount for one frame, the operation of alternately transmitting ultrasonic pulse groups to the adjacent two transmission bands PTX1 and PTX2 is continuously performed 4 times.

[0118] Therefore, compared with Figure 5 , the time interval for transmitting ultrasonic pulse groups in one frame of FR becomes larger, and the phase change of multiple received Doppler signals obtained in one frame of FR becomes sufficiently large. That is, the phase angle (multiple deflection angles) of the autocorrelation value A(r) represented by (Equation 2) becomes sufficiently large. Thereby, the measurement accuracy of Doppler measurement information is improved. In addition, by alternately transmitting ultrasonic pulse groups to the adjacent two transmission bands PTX1 and PTX2, the region for obtaining Doppler measurement information within each fixed time becomes wider. In addition, compared with Figure 5 , the time for generating the Doppler measurement information of the FR amount for one frame becomes shorter, and the frame rate becomes larger.

[0119] Here, an embodiment is shown in which the ultrasonic probe 14 includes a plurality of vibrating elements 16 arranged linearly, and a plurality of transmission frequency bands are formed in a direction perpendicular to the arrangement direction of the vibrating elements 16. The plurality of vibrating elements 16 may be arranged in a curved shape at the front end of the ultrasonic probe 14. In this case, a plurality of transmission frequency bands may be formed so as to radially extend from the front end of the ultrasonic probe 14.

[0120] In Figure 7 is shown the model application operation Figure 6 when transmitting ultrasonic pulses from the ultrasonic probe 14. In this figure, the following is shown: the transmission and reception of a series of K ultrasonic pulses of 1 frame FR amount, the K received Doppler signals before performing high-pass filter processing, the K received Doppler signals after performing high-pass filter processing, and the Doppler measurement information are input into the machine learning model 44 once. That is, as K ultrasonic pulses are transmitted from the ultrasonic probe 14 and K reflected waves are received by the ultrasonic probe 14, the K received Doppler signals are input into the wall filter 38 and the machine learning model 44. The wall filter 38 outputs the K received Doppler signals after high-pass filter processing to the Doppler measurement unit 40 and the machine learning model 44. The Doppler measurement unit 40 outputs the Doppler measurement information to the machine learning model 44 by inputting the K received Doppler signals after high-pass filter processing. In this way, the K received Doppler signals, the K received Doppler signals before high-pass filter processing, the K received Doppler signals after high-pass filter processing, and the Doppler measurement information generated based on the K received Doppler signals are input into the machine learning model 44 as input information. The machine learning model 44 generates Doppler measurement information similar to the case of J transmissions and receptions based on the input information. For at least one of the time intervals between adjacent received pulse signals among the K received Doppler signals, a time interval capable of detecting the Doppler frequency may be used.

[0121] In addition, Figure 5 the ultrasonic pulse group PIB shown or Figure 6 the ultrasonic pulse groups PIB1 to PIB8 shown can be cited as ultrasonic pulse groups for the Doppler mode in addition to the B mode. In this case, according to the transmission and reception of the ultrasonic pulses belonging to the ultrasonic pulse group PIB or the ultrasonic pulse groups PIB1 to PIB8, the received pulse signal output from the phased addition unit 28 is output not only to the B mode image generation unit 32 but also to the quadrature detection unit 36. For example, by using ultrasonic pulses having the same waveform for both the B mode and the Doppler mode, the ultrasonic pulses in the B mode can be used in the Doppler mode. For ultrasonic pulses using phase inversion, a phase difference of 180° is given to the two received Doppler signals based on the two ultrasonic pulses by the quadrature detection unit 36.

[0122] The reflected wave generated according to the B-mode image is used as one of the K received pulse signals output from the receiving unit 20, i.e., the received pulse signal after in-phase processing (B-mode image received signal), and is referred to the operation in the Doppler mode. The ultrasonic pulse group PIB or the ultrasonic pulse groups PIB1 to PIB8 are, in addition to the B mode, also referred to as the ultrasonic pulse group for the Doppler mode, whereby the same effect as the case of increasing the number of times of transmitting and receiving ultrasonic pulses in the operation of the Doppler mode can be obtained.

[0123] [Structure of the present invention]

[0124] Structure 1:

[0125] An ultrasonic diagnostic apparatus, comprising:

[0126] A transmitting unit that sets N as an integer of 2 or more and continuously transmits ultrasonic pulses N times through an ultrasonic probe;

[0127] A receiving unit that receives the reflected waves continuously generated N times in the measurement object through the ultrasonic probe; and

[0128] An information processing unit that generates N received Doppler signals from the N received pulse signals output from the receiving unit according to the reflected waves continuously generated N times in the measurement object, and performs processing on each of the received Doppler signals.

[0129] The information processing unit includes:

[0130] A filter that performs high-pass filter processing on the N received Doppler signals;

[0131] A Doppler measurement unit that generates Doppler measurement information of the measurement object according to the N received Doppler signals on which the high-pass filter processing has been performed; and

[0132] A machine learning model constructed according to teaching data.

[0133] Under the condition that J and K are set as integers of 2 or more and J is greater than K,

[0134] The teaching data includes:

[0135] Training information, at least one of the received characteristic information derived from each of the received Doppler signals by setting N as K and the Doppler measurement information generated by the Doppler measurement unit when N is set as K; and

[0136] Target information, at least one of the received characteristic information derived from each of the received Doppler signals with N set to J for the same measurement object as when N is set to K and the Doppler measurement information generated by the Doppler measurement unit when N is set to J,

[0137] The machine learning model generates the Doppler measurement information for a measurement object in a subject based on input information, which is at least one of the received characteristic information derived from each of the received Doppler signals with N set to K and the Doppler measurement information generated by the Doppler measurement unit when N is set to K.

[0138] Structure 2:

[0139] The ultrasonic diagnostic apparatus according to Structure 1, characterized in that,

[0140] The received characteristic information includes at least one of the following:

[0141] The N received Doppler signals before high-pass filter processing; and

[0142] The N received Doppler signals after high-pass filter processing.

[0143] Structure 3:

[0144] The ultrasonic diagnostic apparatus according to Structure 1 or Structure 2, characterized in that,

[0145] The Doppler measurement information includes at least one of the following:

[0146] The autocorrelation values of the N received Doppler signals after high-pass filter processing;

[0147] The velocity of the measurement object obtained from the N received Doppler signals after high-pass filter processing;

[0148] The Doppler frequency deviation degree for the N received Doppler signals after high-pass filter processing; and

[0149] The value representing the magnitude of the N received Doppler signals after high-pass filter processing.

[0150] Structure 4:

[0151] The ultrasonic diagnostic apparatus according to any one of Structures 1 to 3, characterized in that,

[0152] The transmission unit transmits ultrasonic waves for B-mode image generation through the ultrasonic probe,

[0153] The receiving unit receives, via the ultrasonic probe, the reflected waves for generating a B-mode image generated in the measurement object.

[0154] The information processing unit includes a B-mode image generation unit, which generates B-mode image data based on the reflected waves for generating a B-mode image and the B-mode image reception signals output from the receiving unit.

[0155] Based on the reflected waves for generating a B-mode image, the B-mode image reception signals output from the receiving unit are referred to as any one of the N reception pulse signals output from the receiving unit.

[0156] Structure 5:

[0157] The ultrasonic diagnostic apparatus according to any one of Structures 1 to 4, characterized in that

[0158] The transmitting unit forms a plurality of transmission frequency bands for the ultrasonic pulses at different positions or in different directions.

[0159] For two adjacent transmission frequency bands, the ultrasonic pulses are alternately transmitted in such a way that the ultrasonic pulses are transmitted in one transmission frequency band during the period when the ultrasonic pulses are not transmitted in the other transmission frequency band.

[0160] For two adjacent transmission frequency band pairs each including two adjacent transmission frequency bands, a series of the ultrasonic pulses alternately transmitted on the two transmission frequency bands included in one transmission frequency band pair are regarded as an ultrasonic pulse group, and the ultrasonic pulse groups are alternately transmitted in such a way that the ultrasonic pulse groups are transmitted in one transmission frequency band pair during the period when the ultrasonic pulse groups are not transmitted in the other transmission frequency band pair.

[0161] Each time K ultrasonic pulses are transmitted in each transmission frequency band, the machine learning model generates one frame amount of the Doppler measurement information for each transmission frequency band.

[0162] Structure 6:

[0163] The ultrasonic diagnostic apparatus according to Structure 5, characterized in that

[0164] During the period of generating one frame amount of the Doppler measurement information, the action of alternately transmitting the ultrasonic pulse groups is continuously performed multiple times for two adjacent transmission frequency band pairs.

Claims

1. An ultrasonic diagnostic device, characterized in that: have: The transmitting unit sets N to an integer greater than 2 and transmits ultrasonic pulses N times continuously through the ultrasonic probe; A receiving unit receives, through the ultrasonic probe, reflected waves generated N times in the measurement object; and an information processing unit that generates N reception Doppler signals from the N reception pulse signals output from the receiving unit based on the reflected waves generated N times continuously in the measurement object, and performs processing on each of the reception Doppler signals; The information processing unit includes: A filter, performing high-pass filter processing on the N received Doppler signals; a Doppler measurement unit that generates Doppler measurement information of a measurement object based on the N received Doppler signals that have been subjected to the high-pass filter processing; and Machine learning models, built from teaching data, Under the condition that J and K are set to integers greater than 2 and J is greater than K, The teaching data includes: training information is at least one of reception characteristic information derived from each of the received Doppler signals when N is set to K and the Doppler measurement information generated by the Doppler measurement unit when N is set to K; and The target information is at least one of the reception characteristic information derived from each of the reception Doppler signals when N is set to J for the same measurement object as when N is set to K, and the Doppler measurement information generated by the Doppler measurement unit when N is set to J, The machine learning model generates the Doppler measurement information for the measurement object in the subject based on input information, and the input information is at least one of the reception characteristic information derived from each of the received Doppler signals when N is set to K and the Doppler measurement information generated by the Doppler measurement unit when N is set to K.

2. The ultrasonic diagnostic apparatus according to claim 1, wherein: The receiving characteristic information includes at least one of the following: The N received Doppler signals before being processed by the high-pass filter; and The N received Doppler signals are processed by the high-pass filter.

3. The ultrasonic diagnostic apparatus according to claim 1, wherein: The Doppler measurement information includes at least one of the following: autocorrelation values ​​of the N received Doppler signals after being processed by the high-pass filter; a velocity of the object to be measured obtained from the N received Doppler signals processed by the high-pass filter; Doppler frequency deviations of the N received Doppler signals after being processed by the high-pass filter; and A value representing the magnitudes of the N received Doppler signals after being processed by the high-pass filter.

4. The ultrasonic diagnostic apparatus according to any one of claims 1 to 3, characterized in that: The transmitting unit transmits ultrasonic waves for generating a B-mode image through the ultrasonic probe. The receiving unit receives the reflected wave for generating a B-mode image generated in the measurement object through the ultrasonic probe. The information processing unit includes a B-mode image generating unit that generates B-mode image data based on a B-mode image receiving signal output from the receiving unit and based on a reflected wave for B-mode image generation. Based on the reflected wave for B-mode image generation, the B-mode image reception signal output from the receiving unit is cited as any one of the N reception pulse signals output from the receiving unit.

5. The ultrasonic diagnostic apparatus according to any one of claims 1 to 3, characterized in that: The transmitting unit forms a plurality of transmission frequency bands at different positions or in different directions for the ultrasonic pulse. The ultrasonic pulses are transmitted alternately in two adjacent transmission frequency bands such that the ultrasonic pulses are transmitted in one transmission frequency band during a period in which the ultrasonic pulses are not transmitted in the other transmission frequency band. For two adjacent transmission band pairs each including two adjacent transmission bands, a series of ultrasonic pulses alternately transmitted on two transmission bands included in one transmission band pair is used as an ultrasonic pulse group, and ultrasonic pulse groups are alternately transmitted in a manner that ultrasonic pulse groups are transmitted on the other transmission band pair during a period when ultrasonic pulse groups are not transmitted on one transmission band pair, Each time K of the ultrasonic pulses are transmitted in each transmission frequency band, the machine learning model generates one frame of the Doppler measurement information for each transmission frequency band.

6. The ultrasonic diagnostic apparatus according to claim 5, characterized in that: While one frame of the Doppler measurement information is being generated, the operation of alternately transmitting ultrasonic pulse groups is continued multiple times for two adjacent transmission frequency band pairs.

Images