Ultrasonic diagnosis apparatus, information processing apparatus, ultrasonic diagnosis system, ultrasonic image generation method, ultrasonic image learning method and program

Abstract

To obtain an ultrasonic image of favorable image quality, and to reduce the material amount and cost of an ultrasonic diagnosis apparatus.SOLUTION: An ultrasonic diagnosis apparatus 100A comprises a control unit 18A. The control unit 18A estimates and generates weighted image data from unweighted image data of ultrasonic transmission voltages of a plurality of vibrators 211 of an ultrasonic probe 2 by using estimation data. The estimation data is data machine-learned by using weighted image data and unweighted transmission image data. The estimation data is data for estimating weighted image data from unweighted image data.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to an ultrasonic diagnostic apparatus, an information processing apparatus, an ultrasonic diagnostic system, an ultrasonic image generation method, an ultrasonic image learning method, and a program.

Background Art

[0002] Conventionally, an ultrasonic diagnostic apparatus is known which irradiates ultrasonic waves into a subject by an ultrasonic probe, receives the reflected waves thereof, and analyzes them to display an ultrasonic image inside the subject. The subject is a living body of a patient or the like.

[0003] The ultrasonic probe has a plurality of vibrators. The ultrasonic diagnostic apparatus causes each vibrator to emit ultrasonic waves by outputting a transmission signal of a voltage pulse (transmission pulse) to each vibrator. Further, in order to change the voltage of the transmission pulse applied to each vibrator, an ultrasonic diagnostic apparatus having a plurality of positive power supplies and negative power supplies with different voltages, and a switching element for selecting and switching them is known (see Patent Document 1). This ultrasonic diagnostic apparatus generates a transmission pulse of an arbitrary voltage by switching the switching element and outputs it to each vibrator.

[0004] Also, a method of weighting the transmission voltage of a transmission pulse input to a plurality of vibrators of an ultrasonic probe is known. Here, with reference to FIGS. 12 and 13, a configuration for weighting a transmission pulse (drive voltage waveform) input to the vibrator 211 of the ultrasonic probe will be described. FIG. 12 is a block diagram showing a conventional vibrator 211 and a transmission unit 32. FIG. 13 is a diagram showing the intensity of ultrasonic waves with respect to the position x in the scanning direction of the ultrasonic probe 2.

[0005] The ultrasonic diagnostic apparatus has an ultrasonic probe connected to the ultrasonic diagnostic apparatus main body. The ultrasonic probe has a vibrator 211. The vibrator 211 has vibrators 211a to 211l arranged in order in the scanning direction. The ultrasonic diagnostic apparatus main body includes a transmission unit 32. The transmission unit 32 has a trigger circuit 321, a transmission power supply circuit 322, and a pulsar 323. The pulsar 323 has pulsars 323a to 323l respectively connected in order to the vibrators 211a to 211l.

[0006] The trigger circuit 321 generates a trigger signal for generating a transmission pulse under the control of a control unit (not shown) and outputs it to each of the pulsars 323a to 323l. The trigger circuit 321 gives the delay time set for each of the pulsars 323a to 323l to the trigger signal.

[0007] The transmission power supply circuit 322 is composed of a plurality of independent power supplies corresponding to each of the pulsars 323a to 323l. The transmission power supply circuit 322 supplies independent and variable power supply voltages to each of the pulsars 323a to 323l under the control of the control unit. The pulsars 323a to 323l generate respective transmission pulses according to the respective power supply voltages supplied from the transmission power supply circuit 322 under the control of the control unit and transmit them to the respective vibrators 211a to 211l. Therefore, the amplitude of the transmission pulses generated by the pulsars 323a to 323l changes according to the magnitude of the power supply voltage.

[0008] Here, the aperture of the ultrasonic probe is set to the width of the vibrators 211a to 211h. As an example, when focusing the transmission beam, the trigger circuit 321 advances the transmission pulse timing at the aperture end and delays the transmission pulse timing at the aperture center. In an ultrasonic diagnostic apparatus, in order to obtain two-dimensional ultrasonic image data, it is necessary to change the position of the transmission beam little by little to generate a drive signal for the transmission pulse and obtain a reception signal. For example, from a state where an ultrasonic beam is generated using the vibrators 211a to 211h of the aperture, the aperture is shifted in the scanning direction, and a transmission beam is generated using the vibrators 211b to 211i. Then, the position of the aperture is shifted by one vibrator pitch. The position of the transmission beam is also shifted by one vibrator pitch. Note that the timing of the generation of the trigger signal by the trigger circuit 321 is also appropriately changed according to the position of the vibrator used.

[0009] As shown in FIG. 12, the weighting of the transmission pulse is usually such that the drive voltage waveform of the transmission pulse is set so as to have a small amplitude at the end of the aperture and the maximum amplitude at the center of the aperture. FIG. 13 shows the intensity [dB] of the ultrasonic wave with the weighting of the transmission pulse and the ultrasonic wave without the weighting of the transmission pulse with respect to the position x [mm] in the scanning direction of the ultrasonic probe. That is, FIG. 13 shows the directivity of the transmission beam of the ultrasonic wave with the weighting of the transmission pulse and the ultrasonic wave without the weighting. Assume that the graphs without weighting and with weighting are normalized at their respective maximum intensities. In the case where there is no weighting of the transmission pulse, the amplitudes of the transmission pulses input to each vibrator are equal. The amplitudes of the ultrasonic pulses generated from each of the vibrators are also equal. In the case without weighting, the side lobes at the "{", "}" parts on both shoulders of the graph in FIG. 13 are larger than those in the case with weighting. For this reason, artifacts are likely to occur.

[0010] When there is no weighting of the transmission pulse, ultrasonic waves are also irradiated in a direction different from the direction of the original transmission beam. This is called a side lobe. Even when there is no reflector in the direction of the original transmission beam, if there is a reflector in the side lobe direction, the reflection of the reflector on the side lobe side occurs. This is called an artifact, which is not desirable because it degrades the image quality or causes misdiagnosis. When there is weighting of the transmission pulse, the level of the side lobe of the ultrasonic image can be reduced, and by suppressing the amount of artifacts generated, good image quality can be obtained.

[0011] In addition, there are those that use machine learning to improve the image quality of ultrasonic waves. For example, an ultrasonic diagnostic apparatus having a model machine-learned with learning data including image data obtained by transmitting a plane wave beam or a converging beam of ultrasonic waves is known (see Patent Document 2). This ultrasonic diagnostic apparatus generates estimated image data corresponding to image data based on a converging beam using the model for image data based on a plane wave beam.

Prior Art Documents

Patent Documents

[0012]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0013] However, in the ultrasonic diagnostic apparatus of FIG. 12, the power supply voltage for weighting the transmission pulse needs to be changed each time the aperture position changes. Usually, a capacitor for stabilization is included in the power supply output. For this reason, the transmission unit 32 of the ultrasonic diagnostic apparatus of FIG. 12 has power loss due to charging and discharging of the capacitor, and is accompanied by heat generation. Further, the transmission unit 32 also increases the circuit material amount and manufacturing cost for weighting. In addition, the ultrasonic diagnostic apparatus of Patent Document 2 does not perform weighting of the transmission pulse.

[0014] An object of the present invention is to obtain an ultrasonic image with good image quality and to reduce the material amount and cost of the ultrasonic diagnostic apparatus.

Means for Solving the Problems

[0015] In order to solve the above problems, the ultrasonic diagnostic apparatus according to the invention described in claim 1 is provided with a first control unit that performs machine learning using image data obtained with transmission weighting of a plurality of vibrators of an ultrasonic probe and image data obtained without transmission weighting, and uses estimation data for estimating image data with transmission weighting from image data without transmission weighting, and estimates and generates image data with transmission weighting from the image data obtained without transmission weighting.

[0016] The invention described in claim 2 is the ultrasonic diagnostic apparatus according to claim 1, wherein the image data with transmission weighting for machine learning is image data generated by synthesizing a plurality of pieces of image data obtained by changing transmission parameters without transmission weighting.

[0017] The invention described in claim 3 is the ultrasonic diagnostic apparatus according to claim 2, wherein the transmission parameters are transmission voltage and focusing conditions.

[0018] The information processing apparatus according to the invention described in claim 4 A second control unit is provided that generates estimation data for estimating image data with transmission weighting from image data without transmission weighting by performing machine learning using image data obtained with transmission weighting of a plurality of vibrators of an ultrasonic probe and image data obtained without transmission weighting.

[0019] The invention according to claim 5 is the information processing apparatus according to claim 4, wherein The image data with transmission weighting for machine learning is image data generated by synthesizing a plurality of pieces of image data obtained by changing transmission parameters without transmission weighting.

[0020] The invention according to claim 6 is the information processing apparatus according to claim 5, wherein The transmission parameters are transmission voltage and focusing conditions.

[0021] The ultrasonic diagnostic system according to claim 7 is An ultrasonic diagnostic apparatus according to any one of claims 1 to 3, and An information processing apparatus, and The information processing apparatus is A second control unit is provided that generates estimation data for estimating image data with transmission weighting from image data without transmission weighting by performing machine learning using image data obtained with transmission weighting of a plurality of vibrators of an ultrasonic probe and image data obtained without transmission weighting.

[0022] The ultrasonic image generation method according to claim 8 is A first control step of estimating and generating image data with transmission weighting from image data obtained without transmission weighting using estimation data for estimating image data with transmission weighting from image data without transmission weighting, which is obtained by performing machine learning using image data obtained with transmission weighting of ultrasonic waves and image data obtained without transmission weighting.

[0023] The ultrasonic image learning method according to claim 9 is A second control step is included for generating estimation data for estimating image data with transmission weighting from image data without transmission weighting by performing machine learning using the image data obtained with transmission weighting of ultrasonic waves of a plurality of vibrators of an ultrasonic probe and the image data obtained without transmission weighting.

[0024] The program of the invention according to claim 10 causes a computer to function as a first control unit that generates, by performing machine learning using the image data obtained with transmission weighting of ultrasonic waves of a plurality of vibrators of an ultrasonic probe and the image data obtained without transmission weighting, and using the estimation data for estimating the image data with transmission weighting from the image data without transmission weighting, the image data with transmission weighting from the image data obtained without transmission weighting. to function as.

[0025] The program of the invention according to claim 11 causes a computer to function as a second control unit that generates, by performing machine learning using the image data obtained with transmission weighting of ultrasonic waves of a plurality of vibrators of an ultrasonic probe and the image data obtained without transmission weighting, the estimation data for estimating the image data with transmission weighting from the image data without transmission weighting. to function as.

Advantages of the Invention

[0026] According to the present invention, an ultrasonic image with good image quality can be obtained, and the quantity of goods and cost of the ultrasonic diagnostic apparatus can be reduced.

Brief Description of the Drawings

[0027]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Embodiments for Carrying Out the Invention

[0028] Hereinafter, with reference to the drawings, the first and second embodiments of the present invention will be described in detail in order. However, the scope of the invention is not limited to the illustrated examples.

[0029] (First Embodiment) Referring to FIGS. 1 to 8, a first embodiment of the present invention will be described. First, referring to FIGS. 1 to 5, the device configuration of this embodiment will be described. FIG. 1 is a block diagram showing an ultrasonic diagnostic system 1000 according to the first embodiment of the present invention. FIG. 2 is a schematic diagram of an ultrasonic diagnostic apparatus 100A that generates an estimated image using the generated learning data. FIG. 3 is a block diagram showing the functional configuration of the ultrasonic diagnostic apparatus 100A. FIG. 4 is a block diagram of the ultrasonic diagnostic apparatus 100A showing the internal configuration of the transmission unit 12A. FIG. 5 is a block diagram of an ultrasonic diagnostic apparatus 100B for generating learning data of this embodiment showing the internal configuration of the transmission unit 12B.

[0030] As shown in FIG. 1, the ultrasonic diagnostic system 1000 is a system provided in a medical device development manufacturer or a medical facility such as a hospital, and estimates ultrasonic image data using a learned model of machine learning. The ultrasonic diagnostic system 1000 includes ultrasonic diagnostic apparatuses 100A and 100B. The communication network N is, for example, a LAN (Local Area Network) of a medical facility, and at least the ultrasonic diagnostic apparatuses 100A and 100B are connected thereto.

[0031] The ultrasonic diagnostic apparatuses 100A and 100B emit ultrasonic waves to a subject such as a patient's living body to generate ultrasonic image data. The ultrasonic diagnostic apparatus 100A is an ultrasonic diagnostic apparatus for generating an estimated image. The ultrasonic diagnostic apparatus 100A generates and displays estimated image data using the estimation data as a learned model obtained by the ultrasonic diagnostic apparatus 100B. The ultrasonic diagnostic apparatus 100B is an ultrasonic diagnostic apparatus for learning. The ultrasonic diagnostic apparatus 100B performs machine learning on ultrasonic image data with / without weighting of the transmission voltage to generate estimation data as a learned model.

[0032] As shown in FIG. 2, the ultrasonic diagnostic apparatus 100A includes an ultrasonic diagnostic apparatus main body 1A and an ultrasonic probe 2. The ultrasonic probe 2 is connected to the ultrasonic diagnostic apparatus main body 1A. The ultrasonic probe 2 transmits ultrasonic waves (transmission ultrasonic waves) into the subject and receives reflected waves (reflection ultrasonic waves: echoes) of the ultrasonic waves reflected in the subject. The ultrasonic probe 2 includes an ultrasonic probe main body 21, a cable 22, and a connector 23. The ultrasonic probe main body 21 is the header part of the ultrasonic probe 2 and transmits and receives ultrasonic waves. The cable 22 is connected to the ultrasonic probe main body 21 and the connector 23. The cable 22 is a cable through which a drive signal for the ultrasonic probe main body 21 and a reception signal of ultrasonic waves flow. The connector 23 is a plug connector for connecting to a connector (not shown) of a receptacle of the ultrasonic diagnostic apparatus main body 1A.

[0033] The ultrasonic diagnostic apparatus main body 1A is connected to the ultrasonic probe main body 21 via the connector 23 and the cable 22. The ultrasonic diagnostic apparatus main body 1A transmits a drive signal of an electrical signal to the ultrasonic probe main body 21 to cause the ultrasonic probe main body 21 to transmit transmission ultrasonic waves to the subject. The ultrasonic probe 2 generates a reception signal, which is an electrical signal, in response to the reflection ultrasonic waves from the subject received by the ultrasonic probe main body 21. The ultrasonic diagnostic apparatus main body 1A images the internal state of the subject as ultrasonic image data based on the reception signal generated by the ultrasonic probe 2.

[0034] The ultrasonic probe main body 21 has a vibrator 211 (FIG. 3) on the tip side. The vibrator 211 has vibrators 211a to 211h (FIG. 4). However, the eight vibrators 211a to 211h are representative of each vibrator of the vibrator 211 for simplicity of explanation. The number of each vibrator of the vibrator 211 can be arbitrarily set and is, for example, 192 in actuality.

[0035] Each oscillator of the oscillator 211 is, for example, arranged in a one-dimensional array in the scanning direction (azimuth direction). Note that each oscillator of the oscillator 211 may be arranged in a two-dimensional array. In the present embodiment, a linear scanning type electronic scan probe is adopted as the ultrasonic probe 2. However, the ultrasonic probe 2 may be either an electronic scanning type or a mechanical scanning type. Further, the ultrasonic probe 2 may be any of a linear scanning type, a sector scanning type, or a convex scanning type. The ultrasonic diagnostic apparatus main body 1A and the ultrasonic probe 2 may be configured to perform wireless communication instead of wired communication via the cable 22. This wireless communication is, for example, UWB (Ultra Wide Band).

[0036] The operation input unit 11 is a control panel or the like that receives various operation inputs from users such as doctors and technicians. The operation input unit 11 has operation elements such as push buttons, encoders, lever switches, joysticks, trackballs, keyboards, touch pads, and multi-function switches.

[0037] The display unit 17 has a display panel such as an LCD (Liquid Crystal Display), an organic EL (Electro-Luminescence) display, or an inorganic EL display. The display unit 17 displays display information such as ultrasonic image data on the display panel.

[0038] As shown in FIG. 3, the ultrasonic diagnostic apparatus main body 1A includes an operation input unit 11, a transmission unit 12A, a reception unit 13, a signal processing unit 14, an image processing unit 15, a display control unit 16, a display unit 17, a control unit 18A, a storage unit 191, and a communication unit 192. The control unit 18A functions as a first control unit.

[0039] The operation input unit 11 receives various operation inputs from the user and outputs the operation signal to the control unit 18A. The operation input unit 11 may include a touch panel that is integrally formed on the display screen of the display unit 17 and receives touch inputs from the user.

[0040] The transmission unit 12A supplies a drive signal, which is an electrical signal, to the ultrasonic probe 2 in accordance with the control of the control unit 18A to generate transmitted ultrasonic waves in the ultrasonic probe 2. Here, with reference to FIG. 4, the internal configuration of the transmission unit 12A will be described. The transmission unit 12A includes a trigger circuit 121, a transmission power supply circuit 122A, and a pulsar 123.

[0041] For the sake of simplicity in explanation, the pulsar 123 is typically assumed to have eight independent pulsars 123a to 123h. However, the number of each pulsar in the pulsar 123 is not limited to eight. The pulsars 123a to 123h are respectively connected to the vibrators 211a to 211h in sequence.

[0042] The trigger circuit 121 has a delay circuit and generates a trigger signal for transmission pulse generation under the control of the control unit 18A and outputs it to the pulsars 123a to 123h. The trigger circuit 121 sets a delay time for each individual path corresponding to each vibrator 211, and the delay circuit generates a trigger signal delayed by the set delay time. The trigger circuit 121 delays the transmission of each transmission pulse of the drive signals of the pulsars 123a to 123h by the trigger signal. The trigger circuit 121 focuses the transmission beam composed of the transmitted ultrasonic waves by the delay.

[0043] The transmission power supply circuit 122A is composed of one power supply corresponding to the pulsars 123a to 123h. The transmission power supply circuit 122A supplies a common and variable power supply voltage to each of the pulsars 123a to 123h in accordance with the control of the control unit 18A. The pulsars 123a to 123h generate each transmission pulse based on the power supply voltage supplied from the transmission power supply circuit 122A in accordance with the control of the control unit 18A and transmit it to each of the vibrators 211a to 211h. The vibrators 211a to 211h serve as transmission apertures. That is, the transmission pulses generated by the pulsars 123a to 123h have different timings (delays), for example, as shown in FIG. 4. And the transmission pulses generated by the pulsars 123a to 123h have a common amplitude. For this reason, the transmission unit 12A cannot perform voltage weighting of the transmission of the transmission pulses.

[0044] The transmission unit 12A drives a continuous part (for example, 64) of a plurality (for example, 192) of vibrators 211 arranged in the ultrasonic probe 2 to generate transmission ultrasonic waves. Then, each time the transmission unit 12A generates transmission ultrasonic waves, it scans by shifting the vibrator 211 to be driven in the scanning direction.

[0045] As shown in FIGS. 3 and 4, the receiving unit 13 receives a received signal, which is an electrical signal, from the ultrasonic probe 2 according to the control of the control unit 18A. The receiving unit 13 includes, for example, an amplifier, an A / D conversion circuit, and a phased addition circuit. The amplifier amplifies the received signal at a preset amplification factor for each individual path corresponding to each vibrator 211. The A / D conversion circuit performs analog-digital conversion (A / D conversion) on the amplified received signal. The phased addition circuit gives a delay time to the A / D-converted received signal for each individual path corresponding to each vibrator 211 to adjust the phase. The phased addition circuit adds (phased adds) the received signals after these processes to generate beam data.

[0046] The signal processing unit 14 performs envelope detection processing, logarithmic compression, etc. on the beam data from the receiving unit 13 according to the control of the control unit 18A. The signal processing unit 14 further adjusts the dynamic range and gain of the beam data after these processes to perform luminance conversion. The signal processing unit 14 generates B (Brightness) mode image data composed of pixels having luminance values as received energy by this luminance conversion. That is, the B mode image data represents the strength of the received signal by luminance. Note that the signal processing unit 14 may be configured to be able to generate image data of other image modes other than the B mode, such as the M (Motion) mode and the color Doppler mode.

[0047] The image processing unit 15 has an image memory unit 15a. The image memory unit 15a is composed of a semiconductor memory such as a DRAM (Dynamic Random Access Memory), for example. The image processing unit 15 stores the B-mode image data transmitted from the signal processing unit 14 in the image memory unit 15a in frame units according to the control of the control unit 18A. The B-mode image data in frame units may be referred to as ultrasonic image data. The image processing unit 15 transmits the ultrasonic image data stored in the image memory unit 15a to the display control unit 16 one frame at a time at predetermined intervals according to the control of the control unit 18A.

[0048] The display control unit 16 is, for example, a DSC (Digital Scan Converter). The display control unit 16 performs processes such as coordinate conversion on the B-mode image data input from the image processing unit 15 according to the control of the control unit 18A and converts it into an image signal for display. The display control unit 16 outputs the image signal to the display unit 17.

[0049] The display unit 17 displays the ultrasonic image on the display panel according to the image signal output from the display control unit 16 according to the control of the control unit 18A. Also, the display unit 17 displays various display information input from the control unit 18A on the display panel.

[0050] The control unit 18A includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). The control unit 18A reads out various processing programs stored in the ROM and expands them in the RAM, and controls each part of the ultrasonic diagnostic apparatus 100A in cooperation with the expanded programs and the CPU. The ROM is composed of a non-volatile memory such as a semiconductor. The ROM stores a system program corresponding to the ultrasonic diagnostic apparatus 100A, various processing programs executable on the system program, and various data such as a gamma table. In particular, the ROM stores an image display program for executing the image display processing described later. These programs are stored in the RAM in the form of computer-readable program codes. The CPU sequentially executes operations according to the program codes on the RAM. The RAM forms a work area for temporarily storing various programs executed by the CPU and data related to these programs.

[0051] The storage unit 191 is a storage unit such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive) that can write and read information such as ultrasonic image data. The storage unit 191 stores estimation data as a learned model for estimating weighted ultrasonic image data from ultrasonic image data without voltage weighting for transmission.

[0052] The communication unit 192 is a communication interface such as a network card connected to the communication network N. The control unit 18A transmits and receives information to and from devices such as the ultrasonic diagnostic apparatus 100B on the communication network N via the communication unit 192.

[0053] Next, with reference to FIG. 5, the configuration of the ultrasonic diagnostic apparatus 100B for learning will be described. The ultrasonic diagnostic apparatus 100B has a configuration in which, in the ultrasonic diagnostic apparatus 100A, the transmission unit 12A and the control unit 18A are replaced with a transmission unit 12B and a control unit 18B, respectively. The control unit 18B functions as a second control unit. The transmission unit 12B includes a trigger circuit 121, a transmission power supply circuit 122B, and a pulsar 123. Also, in the ultrasonic diagnostic apparatus 100B, the same reference numerals are given to the parts common to the ultrasonic diagnostic apparatus 100A, and the description thereof will be omitted.

[0054] The transmission power supply circuit 122B is a power supply circuit capable of supplying independent power supply voltages different from each other to each of the pulsars 123a to 123h. That is, the transmission power supply circuit 122B can output both a power supply voltage for weighting the transmission voltage and a power supply voltage without weighting to each of the pulsars 123a to 123h. For this reason, the pulsar 123 can generate both a transmission pulse for a transmission beam with voltage weighting in transmission and a transmission pulse for a transmission beam without weighting. That is, the weighted transmission pulses generated by the pulsars 123a to 123h of the transmission unit 12B are different from each other with their timings (delays) and amplitudes shifted as shown in FIG. 5, for example. For this reason, the transmission unit 12B can weight the voltage of the transmission of the transmission pulse.

[0055] Also, the transmission power supply circuit 122B and the pulsar 123 can switch between weighting with and without weighting in a short period. For example, it is possible to switch between weighting with and without weighting for each frame or for each transmission. For this reason, even in a subject in which movement occurs, such as a human body, the ultrasonic diagnostic apparatus 100B can obtain ultrasonic image data by switching between weighting with and without weighting.

[0056] The control unit 18B has the same configuration as the control unit 18A. However, the ROM of the control unit 18B stores a first learning program for executing a first learning process described later instead of the image display program.

[0057] Next, with reference to FIGS. 6 to 8, the operations of the ultrasonic diagnostic apparatuses 100A and 100B according to the present embodiment will be described. FIG. 6 is a flowchart showing the first learning process. FIG. 7 is a flowchart showing the image display process. FIG. 8 is a schematic diagram of the first learning process and the image display process.

[0058] First, with reference to FIG. 6, the first learning process executed by the ultrasonic diagnostic apparatus 100B will be described. The first learning process is a process of acquiring ultrasonic image data with / without voltage weighting for transmission as teacher data for a subject such as a patient serving as a learning sample and performing machine learning.

[0059] In the ultrasonic diagnostic apparatus 100B, for example, an execution instruction for the first learning process is input from a user via the operation input unit 11. The control unit 18B executes the first learning process according to the execution instruction in accordance with the first learning program stored in the ROM.

[0060] First, the control unit 18B acquires ultrasonic image data without voltage weighting for transmission under the control of the transmission unit 12B to the display control unit 16 and stores it in the storage unit 191 (step S11). The control unit 18B acquires ultrasonic image data with voltage weighting for transmission under the control of the transmission unit 12B to the display control unit 16 and stores it in the storage unit 191 (step S12).

[0061] The control unit 18B determines whether the accumulated data number of the ultrasonic image data with and without weighting stored in the storage unit 191 is equal to or greater than a predetermined number (step S13). The predetermined number in step S13 is an accumulated data number sufficient for machine learning of the ultrasonic image data with and without weighting. Machine learning, for example, estimates the boundary of the feature amounts using the ultrasonic image data with and without weighting stored in the storage unit 191 as teacher data. Further, machine learning generates estimation data for estimating the ultrasonic image data with weighting from the ultrasonic image data without weighting using the boundary.

[0062] If it is less than the predetermined number (step S13; NO), the process proceeds to step S11. If it is equal to or more than the predetermined number (step S13; YES), the control unit 18B performs machine learning using the weighted and unweighted ultrasonic image data in the storage unit 191 (step S14). The control unit 18B extracts estimation data from the learning result of the machine learning in step S14 and stores it in the storage unit 191 (step S15). The first learning process ends. As shown on the left side of the dotted line in FIG. 8, estimation data is obtained by machine learning of the weighted and unweighted ultrasonic image data of the sample subject.

[0063] The control unit 18B transmits the estimation data stored in the storage unit 191 to the ultrasonic diagnostic apparatus 100A for generating an estimation image, for example, via the communication unit 192. The control unit 18A receives the estimation data received from the ultrasonic diagnostic apparatus 100B via the communication unit 192 and stores it in the storage unit 191 of its own device. Note that the transmission of the estimation data from the ultrasonic diagnostic apparatus 100B to the ultrasonic diagnostic apparatus 100A is not limited to the configuration via the communication network N. For example, the ultrasonic diagnostic apparatuses 100A and 100B may be configured to have a connection portion for a recording medium such as a USB (Universal Serial Bus) memory. The user connects the recording medium to the ultrasonic diagnostic apparatus 100B and records the generated estimation data on the recording medium. The user connects the recording medium to the ultrasonic diagnostic apparatus 100A and stores the estimation data in the storage unit 191. Further, the configuration may be such that the pre-generated estimation data is incorporated into a part of the system of the ultrasonic diagnostic apparatus 100A. For example, the estimation data is included in an image display program.

[0064] Next, with reference to FIG. 7, the image display process executed by the ultrasonic diagnostic apparatus 100A will be described. The image display process is a process of acquiring ultrasonic image data without weighting the transmission voltage of a subject such as a patient to be diagnosed, and estimating and generating estimation image data for display.

[0065] In the ultrasonic diagnostic apparatus 100A, after the first learning process, for example, an execution instruction for image display processing is input from a user via the operation input unit 11. In response to the execution instruction, the control unit 18A executes image display processing according to an image display program stored in the ROM.

[0066] First, the control unit 18A acquires ultrasonic image data without voltage weighting for transmission of a subject to be diagnosed under the control of the transmission unit 12A to the display control unit 16 (step S21). The control unit 18A reads out estimation data from the storage unit 191 (step S22). The control unit 18A uses the read estimation data to estimate and generate ultrasonic image data with weighting from the ultrasonic image data without weighting in step S21 (step S23). The estimated and generated ultrasonic image data with weighting is used as estimated image data. In step S23, the control unit 18A displays the generated ultrasonic estimated image data with weighting on the display unit 17. The image display processing ends. As shown on the right side of the dotted line in FIG. 8, estimated image data with weighting for the subject to be diagnosed is obtained and displayed from the ultrasonic image data without weighting for the subject to be diagnosed based on the estimation data.

[0067] The image generation conditions for the ultrasonic image data with / without weighting in the first learning process are preferably made to correspond to the image generation conditions for the ultrasonic image data without weighting in the image display processing. The image generation conditions are various processing conditions related to the generation of ultrasonic image data, such as transmission conditions other than voltage weighting for transmission, reception conditions, image modes, and image processing. These image generation conditions may include the type and part of the subject.

[0068] As described above, according to the present embodiment, the ultrasonic diagnostic system includes ultrasonic diagnostic apparatuses 100A and 100B. The ultrasonic diagnostic apparatus 100A includes a control unit 18A. The control unit 18A estimates and generates weighted image data from image data without voltage weighting for transmission of a plurality of vibrators 211 of the ultrasonic probe 2 using estimation data. The estimation data is data obtained by machine learning using weighted image data and image data without transmission weighting as teacher data. The estimation data is data for estimating weighted image data from image data without weighting.

[0069] Therefore, the ultrasonic diagnostic apparatus 100A can obtain an ultrasonic image with good image quality using the estimated weighted image data. Further, the ultrasonic diagnostic apparatus 100A does not require a transmission power supply circuit 122B for weighting and has a transmission power supply circuit 122A for without weighting. For this reason, the quantity, cost, and heat generation of the ultrasonic diagnostic apparatus 100A can be reduced.

[0070] The ultrasonic diagnostic apparatus 100B includes a control unit 18B. The control unit 18B performs machine learning using teacher data including image data obtained with weighting of ultrasonic waves of a plurality of vibrators 211 and image data obtained without weighting. The control unit 18B generates estimation data for estimating weighted image data from image data without weighting by the machine learning.

[0071] Therefore, the ultrasonic diagnostic apparatus 100B can cause the ultrasonic diagnostic apparatus 100A to obtain an ultrasonic image with good image quality using the weighted image data estimated by the estimation data.

[0072] (Second Embodiment) With reference to FIGS. 9 to 11, a second embodiment of the present invention will be described. FIG. 9 is a flowchart showing a second learning process. FIG. 10 is a diagram showing the transmission state of the transmission unit 12A in the first to fourth transmissions and receptions and the superimposition of ultrasonic image data in the present embodiment. FIG. 11 is a diagram showing the voltages of the weighted equivalent pulses of the first to fourth transmissions of the transmission unit 12A in FIG. 10.

[0073] The first embodiment was configured to perform machine learning of ultrasonic data with / without weighting of transmission voltage by the ultrasonic diagnostic apparatus 100B. In this embodiment, the ultrasonic diagnostic apparatus 100A is configured to equivalently generate weighted ultrasonic data by superimposing unweighted ultrasonic data and perform machine learning.

[0074] In this embodiment, the ultrasonic diagnostic apparatus 100A is used as the apparatus configuration. However, the ROM of the control unit 18A stores an image display program and a second learning program for executing a second learning process described later. Note that the ultrasonic diagnostic apparatus 100B may be used as the apparatus configuration.

[0075] Next, with reference to FIGS. 9 to 11, the operation of the ultrasonic diagnostic apparatus 100A of this embodiment will be described. With reference to FIG. 9, the second learning process executed by the ultrasonic diagnostic apparatus 100A will be described. The second learning process is a process of acquiring ultrasonic image data with / without weighting of transmission voltage of a subject such as a patient serving as a learning sample as teacher data and performing machine learning. However, the weighted ultrasonic image data is image data obtained by superimposing a plurality of unweighted ultrasonic image data.

[0076] In the ultrasonic diagnostic apparatus 100A, for example, an execution instruction for the second learning process is input from a user via the operation input unit 11. The control unit 18A executes the second learning process according to the second learning program stored in the ROM in response to the execution instruction.

[0077] First, the control unit 18A acquires ultrasonic image data without weighting the transmission voltage under the control of the transmission unit 12A to the display control unit 16 and stores it in the storage unit 191 (step S31). The control unit 18A sets and adjusts the transmission aperture and delay amount corresponding to the current number of transmission and reception times in the trigger circuit 121, the transmission power supply circuit 122A, and the pulsar 123 (step S32). That is, in step S32, the focusing conditions (transmission aperture, delay amount) are set as transmission parameters. The control unit 18A sets and adjusts the amplitude of the transmission pulse corresponding to the current number of transmission and reception times in the transmission power supply circuit 122A (step S33). That is, in step S33, the transmission voltage is set as a transmission parameter.

[0078] Here, regarding steps S32 and S33, with reference to FIG. 10, an example of transmitting a transmission pulse with a predetermined number of transmission and reception times of 4 times will be described. The predetermined number of transmission and reception times is the maximum value of the number of times of transmitting and receiving ultrasonic waves for ultrasonic image data without weighting, in order to generate superimposed image data equivalent to one piece of weighted ultrasonic image data.

[0079] Corresponding to step S32, the state of the transmission unit 12A for each number of transmission and reception times will be described. For the first number of transmission and reception times, the transmission unit 12A turns on only the pulsars 123d and 123e of the transmission aperture among the pulsars 123 and transmits a transmission pulse only to the vibrators 211d and 211e. For the second number of transmission and reception times, the transmission unit 12A turns on only the pulsars 123c to 123f of the transmission aperture among the pulsars 123 and transmits a transmission pulse only to the vibrators 211c to 211f. For the third number of transmission and reception times, the transmission unit 12A turns on only the pulsars 123b to 123g of the transmission aperture among the pulsars 123 and transmits a transmission pulse only to the vibrators 211b to 211g. For the fourth number of transmission and reception times, the transmission unit 12A turns on the pulsars 123a to 123h of the transmission aperture among the pulsars 123 and transmits a transmission pulse to the vibrators 211a to 211h.

[0080] Also, corresponding to step S33, it is assumed that the amplitudes of the transmission pulses for the 1st to 4th transmission and reception times are the same. However, the ultrasonic image data obtained by the 1st to 4th ultrasonic transmission and reception becomes equivalent to the transmission of the equivalent pulses shown in FIG. 10 when these are superimposed. The equivalent pulses have a small amplitude at the end in the scanning direction of the transmission aperture of the vibrator 211. The equivalent pulses also have a large amplitude at the center of the transmission aperture.

[0081] As shown in FIG. 11, let the amplitudes of the transmission pulses for the 1st to 4th transmission and reception times be voltages V1, V2, V3, and V4, respectively. Here, V1 = V2 = V3 = V4. The horizontal axis of the graph in FIG. 11 indicates the vibrators 211a to 211h. Similarly, the vertical axis indicates the voltage of the equivalent pulses. The voltage of the equivalent pulses corresponding to the vibrator 211 for the 1st to 4th transmission and reception times is the highest at 4V1 for the vibrators 211d and 211e and the lowest at V1 for the vibrators 211a and 211h. In step S33, the weighted curve may be changed by changing the voltage of the amplitude of the transmission pulse for each transmission and reception time.

[0082] Returning to FIG. 9, the control unit 18A controls the transmission unit 12B to the display control unit 16 based on the transmission aperture and the amplitude of the transmission pulse adjusted in steps S32 and S33 (step S34). In step S34, the control unit 18A obtains ultrasonic image data without voltage weighting of the transmission by this control.

[0083] The control unit 18A superimposes the ultrasonic image data without weighting obtained in step S35 and the ultrasonic image data without weighting stored in the storage unit 191 (step S35). In step S35, the control unit 18A stores the superimposed ultrasonic image data in the storage unit 191 as ultrasonic image data with weighting.

[0084] The control unit 18A determines whether the current number of transmissions and receptions is equal to a predetermined number of transmissions and receptions (step S36). If it is less than the predetermined number of transmissions and receptions (step S36; NO), the process proceeds to step S32. If it is equal to the predetermined number of transmissions and receptions (step S36; YES), the control unit 18A determines whether the number of accumulated data of the weighted and unweighted ultrasonic image data stored in the storage unit 191 is equal to or greater than a predetermined number (step S37).

[0085] If it is less than the predetermined number (step S37; NO), the process proceeds to step S31. If it is equal to or greater than the predetermined number (step S37; YES), the control unit 18A executes steps S38 and S39 to end the second learning process. Steps S38 and S39 are the same as steps S14 and S15 of the first learning process in FIG. 6, respectively. Also, after the second learning process, image display processing is executed in the ultrasonic diagnostic apparatus 100A.

[0086] As described above, according to the present embodiment, the control unit 18A of the ultrasonic diagnostic apparatus 100A generates image data with weighted transmission voltages for machine learning. The weighted image data is image data generated by synthesizing (superimposing) a plurality of image data obtained by changing the transmission parameters without weighting. The transmission parameters are the transmission voltage and the focusing conditions (transmission aperture, delay). Therefore, in machine learning, a plurality of weighted image data for learning can be generated without providing a special device (transmission power supply circuit 122B). When performing this method, it is not desirable for the positional relationship between the vibrator and the subject to change during multiple transmissions and receptions in terms of accurately generating the weighting signal. Therefore, measures such as using an ultrasonic phantom for the subject are taken.

[0087] In the above description, an example in which the ROMs of the control units 18A and 18B are used as the computer-readable medium of the program according to the present invention has been disclosed, but the present invention is not limited to this example. As other computer-readable media, non-volatile memories such as flash memories and portable recording media such as CD-ROMs can be applied. In addition, a carrier wave is also applied to the present invention as a medium for providing the data of the program according to the present invention via a communication line.

[0088] Note that the description in the above embodiment is an example of an ultrasonic diagnostic apparatus, an information processing apparatus, an ultrasonic diagnostic system, an ultrasonic image generation method, an ultrasonic image learning method, and a program according to the present invention. However, the present invention is not limited to these.

[0089] In each of the above embodiments, ultrasonic image data is machine-learned as image data to generate estimation data. Further, each of the above embodiments is configured to generate weighted estimated image data from ultrasonic image data without weighting the transmission voltage as image data. However, the present invention is not limited to this configuration. The image data for machine learning and estimation may be configured as sound line data or intermediate data generated between sound line data generation and ultrasonic image data generation. The intermediate data is, for example, sound line data after envelope detection processing or sound line data after logarithmic compression.

[0090] Also, in the above first embodiment, the ultrasonic diagnostic apparatus 100B as an information processing apparatus is configured to perform machine learning using ultrasonic image data with / without weighting of the transmission voltage. However, the present invention is not limited to this configuration. For example, a configuration may be adopted in which a server as an information processing apparatus is provided on the communication network N. The server acquires the ultrasonic image data with / without weighting generated by the ultrasonic diagnostic apparatus 100B, performs machine learning, and generates estimation data. The server transmits the estimation data to the ultrasonic diagnostic apparatus 100A for storage.

[0091] Similarly, in the above-described second embodiment, a server may be provided on the communication network N connected to the ultrasonic diagnostic apparatus 100A. The server acquires the weighted / non-weighted ultrasonic image data generated by the ultrasonic diagnostic apparatus 100A, performs machine learning, and generates estimation data. The server transmits the estimation data to the ultrasonic diagnostic apparatus 100A for storage.

[0092] Further, in the above-described second embodiment, a configuration may be adopted in which an ultrasonic diagnostic apparatus 100A for generating an estimated image and an ultrasonic diagnostic apparatus 100A for learning are provided on the communication network N.

[0093] In addition, regarding the detailed configurations and detailed operations of the ultrasonic diagnostic system 1000 and the ultrasonic diagnostic apparatuses 100A and 100B in the above-described embodiment, appropriate changes can be made without departing from the spirit of the present invention.

Description of Reference Numerals

[0094] 1000 Ultrasonic diagnostic system 100A, 100B Ultrasonic diagnostic apparatus 1A Ultrasonic diagnostic apparatus main body 11 Operation input unit 12A, 12B, 32 Transmission unit 121, 321 Trigger circuit 122A, 122B, 322 Transmission power supply circuit 123, 123a~123h, 323, 323a~323l Pulser 13 Reception unit 14 Signal processing unit 15 Image processing unit 151 Image memory unit 16 Display control unit 17 Display unit 18A, 18B Control unit 191 Storage unit 192 Communication unit 2 Ultrasonic probe 21 Ultrasonic probe main body 211, 211a~211l Vibrator 22 Cable 23 Connector

Claims

1. An ultrasonic diagnostic apparatus comprising a first control unit that performs machine learning using image data obtained with ultrasonic transmission weighting of a plurality of vibrators of an ultrasonic probe and image data obtained without transmission weighting, and uses estimation data for estimating image data with transmission weighting from image data without transmission weighting to estimate and generate image data with transmission weighting from the image data obtained without transmission weighting.

2. The ultrasonic diagnostic apparatus according to claim 1, wherein the image data with transmission weighting for machine learning is image data generated by synthesizing a plurality of pieces of image data obtained by changing transmission parameters without transmission weighting.

3. The ultrasonic diagnostic apparatus according to claim 2, wherein the transmission parameters are transmission voltage and focusing conditions.

4. An information processing apparatus comprising a second control unit that performs machine learning using image data obtained with ultrasonic transmission weighting of a plurality of vibrators of an ultrasonic probe and image data obtained without transmission weighting, and generates estimation data for estimating image data with transmission weighting from image data without transmission weighting.

5. The information processing apparatus according to claim 4, wherein the image data with transmission weighting for machine learning is image data generated by synthesizing a plurality of pieces of image data obtained by changing transmission parameters without transmission weighting.

6. The information processing apparatus according to claim 5, wherein the transmission parameters are transmission voltage and focusing conditions.

7. An ultrasonic diagnostic system comprising the ultrasonic diagnostic apparatus according to any one of claims 1 to 3, and an information processing apparatus, wherein the information processing apparatus comprises a second control unit that performs machine learning using image data obtained with ultrasonic transmission weighting of a plurality of vibrators of an ultrasonic probe and image data obtained without transmission weighting, and generates estimation data for estimating image data with transmission weighting from image data without transmission weighting.

8. An ultrasonic image generation method including a first control step of performing machine learning using image data obtained with ultrasonic transmission weighting and image data obtained without transmission weighting, and using estimation data for estimating image data with transmission weighting from image data without transmission weighting to estimate and generate image data with transmission weighting from the image data obtained without transmission weighting.

9. An ultrasonic image learning method including a second control step of generating estimation data for estimating image data with transmission weighting from image data without transmission weighting by performing machine learning using image data obtained with transmission weighting of ultrasonic waves of a plurality of vibrators of an ultrasonic probe and image data obtained without transmission weighting.

10. A computer, A first control unit that is machine-learned using image data obtained with transmission weighting of ultrasonic waves of a plurality of vibrators of an ultrasonic probe and image data obtained without transmission weighting, and estimates and generates image data with transmission weighting from image data obtained without transmission weighting using the estimation data for estimating image data with transmission weighting from image data without transmission weighting, A program for causing the computer to function as such.

11. A computer, A second control unit that performs machine learning using image data obtained with transmission weighting of ultrasonic waves of a plurality of vibrators of an ultrasonic probe and image data obtained without transmission weighting, and generates estimation data for estimating image data with transmission weighting from image data without transmission weighting, A program for causing the computer to function as such.

Images