Ultrasonic time series data processing device and ultrasonic time series data processing program

Abstract

To generate an ultrasonic image based on time-series data in which artifacts are reduced, or to allow types of artifacts generated in the ultrasonic image based on the time-series data to be grasped by a user easily.SOLUTION: A Doppler processing unit 18 or a beam data processing unit 20 generates object time-series data on the basis of a reception beam data string from a reception unit 16. An artifact prediction unit 38 predicts a type of artifacts generated by the object time-series data by inputting the object time-series data to an artifact prediction learning unit 32 that has executed learning. An artifact reduction unit 40 executes artifact reduction processing on the basis of the predicted type of artifacts. A display control unit 24 notifies a user of a corrected ultrasonic image 62 subjected to the artifact reduction processing, or of a result of the prediction by the artifact prediction unit 38.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] This specification discloses an ultrasound time-series data processing device and an ultrasound time-series data processing program. [Background technology]

[0002] Conventionally, ultrasonic waves are repeatedly transmitted and received from the same position (same direction as seen from the ultrasound probe) within the subject, and the time-series data obtained thereby, which is a time-series received beam data sequence, is imaged or analyzed.

[0003] Examples of images of time-series data include M-mode images, in which the horizontal axis represents time and the vertical axis represents depth, and the movement of tissue in the depth direction is shown by brightness lines extending in the time axis direction; and Doppler waveform images, in which the horizontal axis represents time and the vertical axis represents velocity, and in which the velocity of blood flowing through or within the test site is calculated based on the difference between the frequency of the transmitted ultrasound and the frequency of the received ultrasound.

[0004] Patent Document 1 discloses a method for analyzing time-series data that is a non-invasive method for determining vascular diseases, particularly arteriosclerosis, vascular stenosis, and aneurysms with high accuracy, in which ultrasound waves (with a frequency of f) are transmitted to the pulsating vascular wall of a subject, a reflected echo whose frequency has changed to f0 is received, the reflected echo is subjected to a wavelet transform to obtain a wavelet spectrum, the wavelet spectrum is subjected to mode decomposition to obtain spectra by mode, waveforms by mode on the time axis are obtained by an inverse wavelet transform, a norm value is calculated for each mode, and the calculated norm value is compared with a norm distribution obtained from a normal individual, thereby determining the presence or absence of a vascular disease or the incidence rate of a specific vascular disease. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] International Publication No. 2012 / 008173 Summary of the Invention [Problem to be solved by the invention]

[0006] However, in ultrasound images obtained by imaging time-series data, artifacts due to the time-series data may occur. In this specification, artifacts are those that prevent the display of desired waveforms in ultrasound images obtained by imaging time-series data. Artifacts may be caused by the operating conditions of the ultrasound diagnostic device, the subject, or the electrical circuits within the ultrasound diagnostic device. For example, artifacts include aliasing in Doppler waveform images, clutter caused by unwanted signals due to the subject's body movement, the Miller effect caused by saturation of Doppler data, and electrical noise in Doppler waveform images and M-mode images generated by the electrical circuits of the ultrasound diagnostic device.

[0007] An object of the ultrasound time-series data processing device disclosed in this specification is to generate an ultrasound image based on time-series data with reduced artifacts, or to enable a user to easily understand the type of artifacts that have occurred in an ultrasound image based on time-series data. [Means for solving the problem]

[0008] The ultrasound time-series data processing device disclosed in the present specification is a device for processing ultrasound time-series data, which is generated based on waves reflected from the test site or blood flowing within the test site by repeatedly transmitting and receiving ultrasound waves to and from the same position within the test site a plurality of times, and which uses, as training data, a combination of training time-series data, which is time-series data in which artifacts occur in ultrasound images based on the time-series data, and information indicating the type of the artifacts, and inputs the training data to an artifact prediction learning device that has been trained to predict and output the type of artifacts that will be generated by the time-series data based on the input time-series data. and an artifact prediction unit that inputs target time series data, which is time series data generated by repeatedly transmitting and receiving ultrasonic waves to and from the same position within a certain region, and predicts a type of artifact that will be generated by the target time series data based on the output of the artifact prediction learning device in response to the input; an artifact reduction unit that executes artifact reduction processing to reduce the artifact based on the type of artifact predicted by the artifact prediction unit; and a display control unit that displays an ultrasound image based on the target time series data to which the artifact reduction processing has been applied on a display unit.

[0009] According to this configuration, the artifact prediction unit predicts the type of artifact that the target time-series data will cause in the ultrasound image, and then the artifact reduction unit executes artifact reduction processing based on the predicted type of artifact, thereby reducing artifacts in the ultrasound image based on the target time-series data.

[0010] As the artifact reduction process, the artifact reduction unit may generate an ultrasound image in which artifacts have been reduced by inputting the target time series data into an image generation model that generates an ultrasound image in which artifacts have been reduced based on the time series data that causes the artifacts.

[0011] Even if the artifacts that the target time series data causes in the ultrasound image cannot be reduced by changing the settings of the ultrasound diagnostic device, this configuration makes it possible to generate an ultrasound image with reduced artifacts by inputting the target time series data into a trained image generation model.

[0012] The image processing device may further include a notification unit that notifies a user that the artifact reduction process has been executed.

[0013] According to this configuration, the user can easily understand that artifact reduction processing has been performed on the ultrasound image.

[0014] The ultrasound system may further include a time series data generation unit that generates the target time series data, wherein the artifact prediction unit predicts, in real time, the type of artifact that will be generated by the target time series data in response to generation of the target time series data by the time series data generation unit, the artifact reduction unit executes, in real time, the artifact reduction process in response to the prediction of the type of artifact by the artifact prediction unit, and the display control unit causes the display unit to display, in real time, an ultrasound image based on the target time series data to which the artifact reduction process has been applied.

[0015] In the ultrasound time-series data processing device disclosed in this specification, the artifact prediction unit can predict the type of artifact caused by the target time-series data simply by inputting the target time-series data into a trained artifact prediction learner. In other words, the amount of calculation required to predict the type of artifact caused by the target time-series data can be reduced, thereby enabling faster prediction of the type of artifact caused by the target time-series data. Therefore, when displaying an ultrasound image with reduced artifacts in real time, as in this configuration, the delay in displaying the ultrasound image relative to the time of acquisition of the target time-series data can be reduced.

[0016] The ultrasound time series data processing device disclosed in the present specification is an ultrasound time series data processing device comprising: an artifact prediction unit that inputs target time series data, which is time series data generated by repeatedly transmitting and receiving ultrasound waves to and from the same position within a target test site multiple times, to an artifact prediction learner that is trained to predict and output the type of artifact caused by the time series data based on the input time series data, using a combination of training time series data, which is time series data indicating time changes of signals, generated based on reflected waves from the test site or blood flowing within the test site, by repeatedly transmitting and receiving ultrasound waves to and from the same position within the test site multiple times, and information indicating the type of artifact, as training data; and a notification unit that notifies a user of the prediction result of the artifact prediction unit.

[0017] According to this configuration, the user can easily understand the type of artifact that the target time-series data causes in the ultrasound image.

[0018] The system may further include a time series data generation unit that generates the target time series data, wherein the artifact prediction unit predicts, in real time, the type of artifact that the target time series data will produce in response to the generation of the target time series data by the time series data generation unit, and the notification unit notifies the user of the prediction result of the artifact prediction unit in real time in response to the prediction of the type of artifact by the artifact prediction unit.

[0019] In the ultrasound time-series data processing device disclosed in this specification, even when a new ultrasound image with reduced artifacts is generated as artifact reduction processing by simply inputting target time-series data into an image generation model, the ultrasound image with reduced artifacts can be generated. In other words, the amount of calculation required to generate a corrected ultrasound image can be reduced, thereby enabling the generation of a corrected ultrasound image at a higher speed. Furthermore, when the settings of the ultrasound diagnostic device are changed as artifact reduction processing, the change of settings does not take much time. Therefore, when the predicted results of the artifact type are notified to the user in real time as in this configuration, the delay in notifying the predicted results relative to the time of acquisition of the target time-series data can be reduced.

[0020] The target test area and the test area may be pulsating areas, and the target time series data and the learning time series data may be time series data corresponding to the same period in the pulsation cycle of the target test area and the test area.

[0021] According to this configuration, the output accuracy of the artifact prediction learning device is improved by making the periods of the learning time series data and the target time series data in the pulsation cycle the same, thereby improving the prediction accuracy of the type of artifact indicated by the target time series data.

[0022] The ultrasound time series data processing program disclosed in the present specification causes a computer to repeatedly transmit and receive ultrasound to and from the same position within a test site multiple times, and generates time series data indicating time changes in signals based on reflected waves from the test site or blood flowing within the test site, and the time series data is time series data in which artifacts occur in ultrasound images based on the time series data. The time series data is a combination of training time series data, which is time series data in which artifacts occur in ultrasound images based on the time series data, and information indicating the type of the artifact. The program causes a computer to perform the following steps on an artifact prediction learning device that has been trained to predict and output the type of artifact that will be generated by the time series data based on the input time series data: The device functions as an artifact prediction unit that inputs target time series data, which is time series data generated by repeatedly transmitting and receiving ultrasonic waves to and from the same position within a target examination area multiple times, and predicts the type of artifact that will be generated by the target time series data based on the output of the artifact prediction learning device in response to the input; an artifact reduction unit that executes artifact reduction processing to reduce the artifact based on the type of artifact predicted by the artifact prediction unit; and a display control unit that displays an ultrasound image based on the target time series data to which the artifact reduction processing has been applied on a display unit.

[0023] The ultrasound time series data processing program disclosed in this specification causes a computer to function as an artifact prediction unit that inputs target time series data, which is time series data generated by repeatedly transmitting and receiving ultrasound waves to and from the same position within a target test site multiple times, into an artifact prediction learner that is trained to predict and output the type of artifact caused by the time series data based on the input time series data, using a combination of training time series data, which is time series data indicating time changes of signals, generated based on reflected waves from the test site or blood flowing within the test site, by repeatedly transmitting and receiving ultrasound waves to and from the same position within the test site multiple times, and information indicating the type of artifact, and a notification unit that notifies a user of the prediction result of the artifact prediction unit. [Effects of the Invention]

[0024] The ultrasound time-series data processing device disclosed in this specification can generate an ultrasound image based on time-series data with reduced artifacts. Alternatively, the ultrasound time-series data processing device disclosed in this specification can allow a user to easily understand the type of artifacts that have occurred in the ultrasound image based on the time-series data. [Brief explanation of the drawings]

[0025] [Figure 1] 1 is a block diagram of an ultrasonic diagnostic apparatus according to an embodiment of the present invention. [Figure 2] FIG. 2 is a conceptual diagram showing the relationship between received beam data and received frame data. [Figure 3] FIG. 10 is a conceptual diagram illustrating the learning process of an artifact prediction learning device. [Figure 4]FIG. 10 is a conceptual diagram illustrating a prediction process using an artifact prediction learning device. [Figure 5] FIG. 10 is a diagram showing an example of a notification screen for notifying a prediction result of an artifact prediction unit. [Figure 6] FIG. 10 is a diagram showing a first display example of an ultrasound image in which artifacts have been reduced. [Figure 7] FIG. 10 is a diagram showing a second display example of an ultrasound image in which artifacts have been reduced. [Figure 8] 4 is a flowchart showing the flow of processing performed by the ultrasound diagnostic apparatus according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0026] 1 is a block diagram of an ultrasound diagnostic apparatus 10 serving as an ultrasound time-series data processing apparatus according to this embodiment. The ultrasound diagnostic apparatus 10 is a medical device installed in a medical institution such as a hospital and used during ultrasound examinations.

[0027] The ultrasound diagnostic device 10 can operate in multiple operating modes, including B-mode, Doppler mode, and M-mode. B-mode is a mode in which a tomographic image (B-mode image) is generated and displayed based on reception frame data consisting of multiple reception beam data obtained by scanning an ultrasound beam (transmission beam). The amplitude intensity of a reflected wave from a scanning plane is converted into brightness. Doppler mode is a mode in which a waveform (Doppler waveform) indicating the tissue motion velocity along an observation line set within a subject is generated and displayed based on the difference in frequency between the transmission wave and the reflection wave along the observation line. Doppler modes may include continuous wave mode, pulse Doppler mode, color Doppler mode, and tissue Doppler mode. M-mode is a mode in which an M-mode image indicating the tissue motion along an observation line set within a subject is generated and displayed based on reception beam data corresponding to the observation line. This embodiment particularly focuses on the case in which the ultrasound diagnostic device 10 operates in Doppler mode or M mode.

[0028] The probe 12, which is an ultrasonic probe, is a device that transmits ultrasonic waves and receives reflected waves. Specifically, the probe 12 is placed in contact with the body surface of a subject, transmits ultrasonic waves toward the subject, and receives the reflected waves reflected by tissue within the subject. A transducer element array consisting of a plurality of transducer elements is provided within the probe 12. A transmission signal, which is an electrical signal, is supplied to each transducer element included in the transducer element array from a transmitter 14, which will be described later, thereby generating an ultrasonic beam (transmission beam). Furthermore, each transducer element included in the transducer element array receives reflected waves from the subject, converts the reflected waves into a reception signal, which is an electrical signal, and transmits the received signal to a receiver 16, which will be described later.

[0029] When transmitting ultrasonic waves, the transmitter 14 supplies a plurality of transmission signals in parallel to the probe 12 (specifically, the transducer element array) under the control of a processor 36, which will be described later. As a result, ultrasonic waves are transmitted from the transducer element array.

[0030] In Doppler mode or M mode, the transmitter 14 supplies a transmission signal to the probe 12 so that the probe 12 repeatedly transmits a transmission beam toward the same position within the region of interest of the subject, which position is determined by a user such as a doctor or medical technician. In other words, the transmitter 14 supplies a transmission signal to the probe 12 so that the probe 12 repeatedly transmits a transmission beam toward the same position within the region of interest. In B mode, the transmitter 14 supplies a transmission signal to the probe 12 so that the transmission beam transmitted from the probe 12 is electronically scanned within the scanning plane. Alternatively, time-division scanning can be performed so that the transmission beam is repeatedly transmitted toward the same position determined by the user while the transmission beam is electronically scanned within the scanning plane.

[0031] When receiving reflected waves, the receiving unit 16 receives multiple received signals in parallel from the probe 12 (specifically, the transducer array). The receiving unit 16 performs phasing addition (delay addition) on the multiple received signals, thereby generating received beam data.

[0032] In the Doppler mode or M mode, the probe 12 repeatedly transmits a transmission beam to the same position within the test area, and the receiver 16 receives multiple reflected waves from the test area or the blood flowing within the test area, and generates a time-series received beam data string based on the multiple reflected waves.In addition, in the B mode, the receiver 16 composes received frame data from multiple received beam data aligned in the scanning direction.

[0033] FIG. 2 is a conceptual diagram showing the relationship between receive beam data BD and receive frame data F. In Doppler mode or M mode, ultrasound is transmitted and received toward a position (direction) specified by the user. This generates a plurality of receive beam data DBs (i.e., receive beam data strings) in time series. The receive beam data DB contains information indicating the intensity and frequency of the reflected waves from each depth. In B mode, the transmit beam is scanned in the scanning direction θ, and receive frame data F is generated from a plurality of receive beam data aligned in the scanning direction θ.

[0034] In the Doppler mode, the receive beam data sequence is sent to a Doppler processor 18, and in the M mode, the receive beam data sequence is sent to a beam data processor 20.

[0035] Returning to FIG. 1 , in Doppler mode, the Doppler processing unit 18 generates Doppler data as time-series data indicating the temporal change in the velocity of the test site or the blood flowing within the test site based on the received beam data sequence from the receiving unit 16. Specifically, the Doppler processing unit 18 generates Doppler data by multiplying each received beam data by a reference frequency and performing quadrature detection to extract Doppler shift through a low-pass filter, sample gate processing (in pulse Doppler mode) to extract only signals at the position of the sample volume, A / D conversion of the signal, and frequency analysis using the fast Fourier transform (FFT) method. The generated Doppler data is sent to the image generating unit 22 and the processor 36. In Doppler mode, the receiving unit 16 and Doppler processing unit 18 correspond to a time-series data generating unit.

[0036] In M mode, the beam data processing unit 20 performs various signal processing such as gain correction, logarithmic amplification, and filtering on the received beam data sequence from the receiver 16. The processed received beam data sequence is sent to the image generator 22 and processor 36. In this embodiment, in M ​​mode, the received beam data sequence processed by the beam data processing unit 20 corresponds to time-series data indicating changes in the position of the subject region over time. In this case, the receiver 16 and the beam data processing unit 20 correspond to a time-series data generator. Note that in B mode as well, the beam data processing unit 20 performs the above-mentioned various signal processing on the received frame data from the receiver 16.

[0037] The image generating unit 22 is configured by a digital scan converter and has a coordinate conversion function, a pixel interpolation function, a frame rate conversion function, and the like.

[0038] In the Doppler mode, the image generator 22 generates a Doppler waveform image based on the Doppler data from the Doppler processor 18. The Doppler waveform is a waveform displayed on a two-dimensional plane of time and velocity, and shows the change over time in the velocity of the test area on the observation line corresponding to the received beam data sequence or the velocity of blood flowing within the test area.

[0039] In the M-mode, the image generating unit 22 generates an M-mode image based on the received beam data sequence from the beam data processing unit 20. The M-mode image is a waveform displayed on a two-dimensional plane of time and depth, and shows the change over time in the position of the subject area on the observation line corresponding to the received beam data sequence.

[0040] Artifacts may occur in ultrasound images (Doppler waveform images or M-mode images) generated by the image generator 22 based on time-series data (Doppler data or a received beam data sequence after signal processing). As described above, artifacts in this specification refer to artifacts that prevent the display of desired waveforms in ultrasound images obtained by visualizing time-series data. Examples of such artifacts include aliasing and mirror effects caused by the operating conditions (settings) of the ultrasound diagnostic device 10, clutter caused by the subject, and electrical noise caused by electrical circuits within the ultrasound diagnostic device. Clutter, for example, caused by the movement of a cardiac valve, has a wide range of components from high to low speeds, and appears as bright lines approximately parallel to the vertical axis in a Doppler waveform image in which the horizontal axis represents time and the vertical axis represents velocity. Furthermore, clutter, for example, caused by the movement of the cardiac wall, has low-speed components with high signal strength, and appears as bright lines extending horizontally near the zero velocity line in a Doppler waveform image in which the horizontal axis represents time and the vertical axis represents velocity. Of course, the types of artifacts are not limited to those described above.

[0041] In the B mode, the image generator 22 generates a B mode image in which the amplitude (intensity) of the reflected wave is expressed as brightness, based on the received frame data from the beam data processor 20.

[0042] The display control unit 24 causes various images such as Doppler waveform images, M-mode images, or B-mode images generated by the image generation unit 22 to be displayed on a display 26 serving as a display unit configured, for example, with a liquid crystal panel. The display control unit 24 also causes the display 26 to display an ultrasound image that is a prediction result by an artifact prediction unit 38 (described later) or a processing result by an artifact reduction unit 40 (described later).

[0043] Each of the transmitter 14, receiver 16, Doppler processor 18, beam data processor 20, image generator 22, and display controller 24 is configured with one or more processors, chips, electric circuits, etc. Each of the components may be realized by a combination of hardware and software.

[0044] The input interface 28 is configured by, for example, a button, a trackball, a touch panel, etc. The input interface 28 is used to input user instructions to the ultrasound diagnostic apparatus 10.

[0045] The memory 30 includes a hard disk drive (HDD), a solid state drive (SSD), an embedded multimedia card (eMMC), a read-only memory (ROM), or a random access memory (RAM). The memory 30 stores an ultrasound time-series data processing program for operating each component of the ultrasound diagnostic device 10. The ultrasound time-series data processing program may also be stored in a computer-readable non-transitory storage medium such as a universal serial bus (USB) memory or a CD-ROM. The ultrasound diagnostic device 10 or another computer can read and execute the ultrasound time-series data processing program from such a storage medium. As shown in FIG. 1 , the memory 30 also stores an artifact prediction learner 32 and an image generation model 34.

[0046] The artifact prediction learner 32 is configured with a learning model such as an RNN (Recurrent Neural Network), an LSTM (Long Short Term Memory) which is a type of RNN, a CNN (Convolutional Neural Network), or a DQN (Deep Q-Network) using a deep reinforcement learning algorithm. The artifact prediction learner 32 is trained to predict and output the type of artifact caused by input time series data based on the time series data using a combination of training time series data, which is time series data generated based on reflected waves from the test site or blood flowing within the test site by repeatedly transmitting and receiving ultrasound waves to and from the test site multiple times, and information (label) indicating the type of artifact.

[0047] FIG. 3 is a conceptual diagram illustrating the learning process of the artifact prediction learner 32. For example, the artifact prediction learner 32 receives training time-series data that causes "aliasing" as a type of artifact to appear in a Doppler waveform image. In this case, the artifact prediction learner 32 predicts and outputs the artifacts that the training time-series data will cause. An activation function such as a softmax function may be provided in the final stage (output layer) of the artifact prediction learner 32, so that the artifact prediction learner 32 outputs, as output data, the possibility (probability) that each of multiple types of artifacts will be caused by the training time-series data. The computer that performs the learning process calculates the error between the output data and the label ("aliasing" in this case) attached to the training time-series data using a predetermined loss function, and adjusts each parameter of the artifact prediction learner 32 (e.g., the weight and bias of each neuron) to reduce the error. By repeating such learning processing, the artifact prediction learning device 32 becomes able to predict and output the type of artifact that will be generated by the input time-series data, based on the input time-series data.

[0048] The subject's target region for the training time series data may be a pulsating region. In this case, the training time series data may be data corresponding to a predetermined period in the pulsation cycle of the subject's region. For example, the training time series data may be time series data based on a received beam data sequence acquired during the period between R waves in the electrocardiogram waveform obtained from an electrocardiograph attached to the subject.

[0049] In this embodiment, the learning time series data is data before imaging (corresponding to the above-mentioned Doppler data or received beam data sequence), but the learning time series data may also be a Doppler waveform image or an M-mode image visualized based on the Doppler data or received beam data sequence (more specifically, data that quantifies the characteristics of the Doppler waveform image or M-mode image).

[0050] 3 includes time-series data (normal) that does not produce artifacts as learning data, but normal time-series data does not have to be included in the learning data. Furthermore, the artifact prediction learning device 32 may be provided with a separate learning device for each type of artifact. In this case, each learning device is trained to output the probability that input time-series data exhibits the corresponding type of artifact.

[0051] In this embodiment, the artifact prediction learner 32 is trained by a computer other than the ultrasound diagnostic apparatus 10, and the trained artifact prediction learner 32 is stored in the memory 30. However, the time-series data acquired by the ultrasound diagnostic apparatus 10 may be used as learning time-series data, and the learning process of the artifact prediction learner 32 may be performed by the ultrasound diagnostic apparatus 10. In this case, the processor 36 functions as a learning processing unit that performs the learning process of the artifact prediction learner 32.

[0052] The image generation model 34 is a learning model that receives latent variables as input and generates a two-dimensional image based on the latent variables. The image generation model 34 is configured, for example, by a GAN (generative adversarial network). A GAN is configured by a pair of an image generator that generates a two-dimensional image based on latent variables and an image classifier that classifies whether an image to be classified is a generated image generated by the image generator. The image classifier is trained to be able to more accurately classify whether an image to be classified is a generated image. For example, the image classifier is trained using, as training data, a combination of a generated image and information (label) indicating that it is a generated image, and a combination of a true image (an image that is not a generated image) and information indicating that it is a true image. Meanwhile, the image generator is trained to generate a generated image that is close to a real image so as to fool the image classifier (causing the image classifier to misclassify it). For example, the image generator is trained so that a generated image generated based on latent variables is determined to be a true image by the image classifier. A well-trained GAN (more specifically, the image generator contained within the GAN) will be able to generate images that are more realistic.

[0053] In this embodiment, the image generation model 34 uses time-series data that cause artifacts as latent variables (input data) and is trained to generate, from the latent variables, an ultrasound image (specifically, a Doppler waveform image or an M-mode image) based on the time-series data, in which artifacts have been reduced. For example, the image generation model 34 uses time-series data that cause clutter as input data and is trained to generate an ultrasound image in which the clutter has been reduced.

[0054] Returning to FIG. 1 , the processor 36 includes at least one of a general-purpose processing device (e.g., a CPU (Central Processing Unit)) and a dedicated processing device (e.g., a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a programmable logic device). The processor 36 may not be a single processing device, but may be configured by the cooperation of multiple processing devices located in physically separate locations. As shown in FIG. 1 , the processor 36 functions as an artifact prediction unit 38 and an artifact reduction unit 40 in accordance with an ultrasound time-series data processing program stored in the memory 30.

[0055] FIG. 4 is a conceptual diagram illustrating the prediction process using the artifact prediction learning device 32. The artifact prediction unit 38 inputs time series data (referred to herein as "target time series data") obtained by repeatedly transmitting and receiving ultrasonic waves to and from the same position within a target examination region into the trained artifact prediction learning device 32. The target examination region is a region of a target subject where ultrasonic waves are transmitted and received to obtain the target time series data (time series data for predicting the type of artifact generated by the transmitted and received ultrasonic waves). As described above, the target time series data is generated by the receiving unit 16 and the Doppler processing unit 18 (in the case of Doppler mode) or the receiving unit 16 and the beam data processing unit 20 (in the case of M mode). The target time series data may also be a Doppler waveform image or an M-mode image (more specifically, data that quantifies the features of the Doppler waveform image or the M-mode image) visualized based on Doppler data or a received beam data sequence.

[0056] The artifact prediction learner 32 predicts the type of artifact caused by the target time series data based on the input target time series data and outputs output data indicating the prediction result. The artifact prediction unit 38 predicts the type of artifact caused by the target time series data based on the output data of the artifact prediction learner 32. When the artifact prediction learner 32 outputs the possibility that the target time series data will cause each of multiple types of artifacts as output data, the artifact prediction unit 38 can predict the possibility that the target time series data will cause each of the multiple types of artifacts.

[0057] If multiple artifact prediction learners 32 are prepared for different types of artifacts, the artifact prediction unit 38 sequentially passes the target time series data to the multiple artifact prediction learners 32, and predicts the possibility that the target time series data will cause each of the multiple types of artifacts based on the output data of each of the multiple artifact prediction learners 32.

[0058] When the target test site and the test site that is the subject of the training time series data are pulsating sites, the target time series data and the training time series data may be time series data corresponding to the same period in the pulsation cycle of the target test site and the test site. For example, when the training time series data is time series data based on a receive beam data sequence acquired during the period between R waves in an electrocardiogram waveform, the artifact prediction unit 38 may also set the target time series data to be time series data based on a receive beam data sequence acquired during the period between R waves in an electrocardiogram waveform. By making the training time series data and the target time series data have the same period in the pulsation cycle, the output accuracy of the artifact prediction learner 32 can be improved. In other words, the artifact prediction unit 38 can predict with improved accuracy the type of artifact caused by the target time series data.

[0059] The artifact reduction section 40 executes an artifact reduction process for reducing the artifact based on the type of artifact predicted by the artifact prediction section 38.

[0060] If the artifacts that the target time series data causes in the ultrasound image can be reduced by changing the operating conditions (settings) of the ultrasound diagnostic device 10, the artifact reduction unit 40 performs a process of changing the settings of the ultrasound diagnostic device 10 as the artifact reduction process.

[0061] For example, if the type of artifact predicted by the artifact prediction unit 38, i.e., the type of artifact caused by the target time-series data, is "aliasing," the artifact reduction unit 40 performs zero shift, which shifts the zero Hertz line of the Doppler waveform up or down, to eliminate aliasing. Alternatively, the artifact reduction unit 40 adjusts the PRF (Pulse Repetition Frequency) to eliminate aliasing. Furthermore, if the type of artifact predicted by the artifact prediction unit 38 is "mirror effect," the artifact reduction unit 40 performs gain adjustment to reduce the mirror effect. Furthermore, if the type of artifact predicted by the artifact prediction unit 38 is "electrical noise," the artifact reduction unit 40 performs gain adjustment to reduce the electrical noise.

[0062] On the other hand, if the artifacts caused by the target time series data in the ultrasound image cannot be reduced by changing the settings of the ultrasound diagnostic device 10, the artifact reduction unit 40 inputs the target time series data to the trained image generation model 34 as an artifact reduction process. The image generation model 34 outputs an ultrasound image based on the target time series data, in which artifacts have been reduced, based on the target time series data input as latent variables. In this manner, an ultrasound image in which artifacts have been reduced is generated. Note that the input to the image generation model 34 may be a Doppler waveform image or an M-mode image (more specifically, data that quantifies the features of the Doppler waveform image or M-mode image) that has been generated based on the target time series data.

[0063] The display control unit 24 notifies the user of the prediction result of the artifact prediction unit 38. That is, the display control unit 24 functions as a notification unit. Note that in this embodiment, the prediction result of the artifact prediction unit 38 is displayed on the display 26 by the display control unit 24, as described below, but in addition to or instead of this, the prediction result of the artifact prediction unit 38 may be notified to the user by audio output or the like.

[0064] 5 is a diagram showing an example of a notification screen 50 displayed on the display 26 to notify the user of the prediction result of the artifact prediction unit 38. The notification screen 50 displays an ultrasound image 52 generated based on the target time-series data and a prediction result 54 of the artifact prediction unit 38, i.e., the type of artifact predicted to be generated by the target time-series data. Note that the notification screen 50 is in Doppler mode, and a Doppler waveform image is displayed as the ultrasound image 52; however, in the case of M-mode, an M-mode image is displayed as the ultrasound image 52.

[0065] When the artifact prediction unit 38 predicts the possibility that the target time series data corresponds to each of the multiple types of artifacts, the display control unit 24 may notify the user of the possibility that the target time series data corresponds to each of the multiple types of artifacts.

[0066] In this way, by notifying the user of the prediction result of the artifact prediction unit 38, the user can easily understand whether or not an artifact has occurred in the ultrasound image 52 based on the target time-series data, and the type of artifact that has occurred. In particular, a user who is unfamiliar with viewing ultrasound images 52 may find it difficult to determine whether or not an artifact has occurred in the displayed ultrasound image 52. For such a user, it is particularly useful to be notified of whether or not an artifact has occurred in the displayed ultrasound image 52, or to be notified of the predicted type of artifact.

[0067] 6 and 7 are diagrams showing a display screen 60 including a corrected ultrasound image 62 in which artifacts have been reduced, displayed on the display 26. When the artifact reduction unit 40 has performed the above-described artifact reduction processing, the display control unit 24 causes the display 26 to display the corrected ultrasound image 62 based on the target time-series data to which the artifact reduction processing has been applied.

[0068] 6, the display controller 24 displays a corrected ultrasound image 62, which is an ultrasound image based on target time-series data that causes aliasing and in which the aliasing has been eliminated by a zero shift. When image generation is performed by the image generation model 34 as artifact reduction processing, the display controller 24 displays the corrected ultrasound image 62 generated by the image generation model 34, as shown in FIG.

[0069] The display controller 24 may notify the user that the artifact reduction process has been performed on the corrected ultrasound image 62, in addition to displaying the corrected ultrasound image 62. Furthermore, the display controller 24 may notify the user of the type of artifact reduced by the artifact reduction process. For example, since aliasing has been eliminated in the corrected ultrasound image 62 shown in FIG. 6, the display controller 24 displays a notification message 64 notifying the user that aliasing correction (more specifically, zero shift) has been performed on the corrected ultrasound image 62. Similarly, since clutter has been reduced in the corrected ultrasound image 62 shown in FIG. 7, the display controller 24 displays a notification message 64 notifying the user that clutter has been reduced.

[0070] This allows the user to easily understand that the displayed corrected ultrasound image 62 is an image that has been subjected to artifact reduction processing.

[0071] As described above, in this embodiment, the artifact prediction unit 38 can predict the type of artifact caused by the target time series data simply by inputting the target time series data to the trained artifact prediction learner 32. In other words, the amount of calculation required to predict the type of artifact caused by the target time series data can be kept low, thereby enabling faster prediction of the type of artifact caused by the target time series data.

[0072] Therefore, the artifact prediction unit 38 may predict the type of artifact that will be generated by the target time-series data in real time as the target time-series data is generated, and the display control unit 24 may notify the user in real time of the prediction result of the artifact prediction unit 38 in response to the prediction of the type of artifact that will be generated by the target time-series data by the artifact prediction unit 38. According to this embodiment, even when such real-time processing is performed, the prediction result of the artifact prediction unit 38 can be smoothly notified to the user without any delay.

[0073] Furthermore, even when the artifact reduction unit 40 generates a new corrected ultrasound image as artifact reduction processing, the artifact reduction unit 40 can generate a corrected ultrasound image with reduced artifacts simply by inputting the target time-series data to the image generation model 34. That is, the amount of calculation required to generate a corrected ultrasound image can be kept low, thereby enabling the generation of a corrected ultrasound image at higher speed. Note that when the settings of the ultrasound diagnostic apparatus 10 are changed as artifact reduction processing, the change of the settings does not take much time.

[0074] Therefore, the artifact prediction unit 38 may predict the type of artifact caused by the target time series data in real time as the target time series data is generated, the artifact reduction unit 40 may execute the artifact reduction process in real time in response to the artifact type predicted by the artifact prediction unit 38, and the display control unit 24 may display the corrected ultrasound image 62 based on the target time series data in real time as a result of the artifact reduction process on the display 26. According to this embodiment, even when such real-time processing is performed, the corrected ultrasound image 62 can be displayed smoothly on the display 26 without any delay.

[0075] The flow of processing performed by the ultrasound diagnostic apparatus 10 according to this embodiment will be described below with reference to the flowchart shown in FIG.

[0076] In step S10, in response to a user instruction from the input interface 28, the ultrasound diagnostic apparatus 10 starts the Doppler mode or the M mode.

[0077] In step S12, in the Doppler mode, the Doppler processing unit 18 generates Doppler data as target time-series data based on the received beam data sequence from the receiving unit 16. In the M mode, the beam data processing unit 20 generates, as target time-series data, a received beam data sequence that has been subjected to various signal processes.

[0078] In step S14, the artifact prediction unit 38 inputs the target time series data (Doppler data or receive beam data sequence) generated in step S12 to the trained artifact prediction learner 32. Then, the artifact prediction unit 38 predicts the type of artifact caused by the target time series data based on the output data of the artifact prediction learner 32 for the target time series data.

[0079] In step S16, the artifact reduction section 40 executes an artifact reduction process for reducing the artifact based on the type of artifact predicted by the artifact prediction section 38. Note that step S16 may be bypassed.

[0080] In step S18, the display control unit 24 displays the corrected ultrasound image that has been subjected to the artifact reduction process in step S16 and the type of reduced artifact on the display 26. If step S16 is bypassed, the display control unit 24 notifies the user of the prediction result by the artifact prediction unit 38 (the type of artifact occurring in the ultrasound image 52).

[0081] In step S20, processor 36 determines whether Doppler mode or M mode has ended in response to a user instruction. If Doppler mode or M mode is continuing, the process returns to step S12 and repeats steps S12 to S20. If Doppler mode or M mode has ended, the process ends.

[0082] Although the embodiment of the present invention has been described above, the present invention is not limited to the above embodiment, and various modifications are possible without departing from the spirit of the present invention.

[0083] For example, in this embodiment, the ultrasound time-series data processing device is the ultrasound diagnostic device 10, but the ultrasound time-series data processing device is not limited to the ultrasound diagnostic device 10 and may be another computer. In this case, the trained artifact prediction learner 32 is stored in a memory accessible from the computer serving as the ultrasound time-series data processing device, and the processor of the computer fulfills the functions of the artifact prediction unit 38, the artifact reduction unit 40, and the display control unit 24. [Explanation of symbols]

[0084] 10 Ultrasound diagnostic device, 12 Probe, 14 Transmitter, 16 Receiver, 18 Doppler processor, 20 Beam data processor, 22 Image generator, 24 Display controller, 26 Display, 28 Input interface, 30 Memory, 32 Artifact prediction learner, 34 Image generation model, 36 Processor, 38 Artifact prediction unit, 40 Artifact reduction unit.

Claims

1. an artifact prediction unit that inputs target time series data, which is time series data generated by repeatedly transmitting and receiving ultrasonic waves to and from the same position within a target test site multiple times, to an artifact prediction learner that has been trained to predict and output the type of artifact caused by the time series data based on the input time series data using a combination of training time series data, which is time series data that indicates time changes in signals and is generated based on reflected waves from the test site or blood flowing within the test site by repeatedly transmitting and receiving ultrasonic waves multiple times to and from the same position within the test site, and information indicating the type of artifact; an artifact reduction unit that executes an artifact reduction process to reduce the artifact based on the type of artifact predicted by the artifact prediction unit; a display control unit that displays, on a display unit, an ultrasound image based on the target time-series data to which the artifact reduction processing has been applied; Equipped with If the predicted type of artifact can be reduced by changing the operating conditions of the ultrasound diagnostic device that generated the target time series data, the artifact reduction unit changes the settings of the ultrasound diagnostic device as the artifact reduction processing; if the predicted type of artifact cannot be reduced by changing the operating conditions of the ultrasound diagnostic device that generated the target time series data, the artifact reduction unit generates an ultrasound image in which the artifact has been reduced by inputting the target time series data into an image generation model that generates an ultrasound image in which the artifact has been reduced based on the time series data that causes the artifact.

1. An ultrasonic time-series data processing device comprising:

2. The ultrasound time-series data processing apparatus according to claim 1 , further comprising a notification unit that notifies a user that the artifact reduction processing has been executed.

3. further comprising a time series data generation unit that generates the target time series data; the artifact prediction unit predicts, in real time, a type of artifact that will be generated by the target time series data when the target time series data is generated by the time series data generation unit; the artifact reduction unit executes the artifact reduction process in real time in response to the artifact type predicted by the artifact prediction unit; the display control unit causes a display unit to display, in real time, an ultrasound image based on the target time-series data to which the artifact reduction processing has been applied, in response to the artifact reduction processing.

2. The ultrasonic time-series data processing device according to claim 1,

4. the target test site and the test site are pulsating sites, the target time series data and the learning time series data are time series data corresponding to the same period in the pulsation cycle of the target test site and the test site, 2. The ultrasonic time-series data processing device according to claim 1,

5. Computer, an artifact prediction unit that inputs target time series data, which is time series data generated by repeatedly transmitting and receiving ultrasonic waves to and from the same position within a target test site multiple times, to an artifact prediction learner that has been trained to predict and output the type of artifact caused by the time series data based on the input time series data using a combination of training time series data, which is time series data that indicates time changes in signals and is generated based on reflected waves from the test site or blood flowing within the test site by repeatedly transmitting and receiving ultrasonic waves multiple times to and from the same position within the test site, and information indicating the type of artifact; an artifact reduction unit that executes an artifact reduction process to reduce the artifact based on the type of artifact predicted by the artifact prediction unit; a display control unit that displays, on a display unit, an ultrasound image based on the target time-series data to which the artifact reduction processing has been applied; It functions as If the predicted type of artifact can be reduced by changing the operating conditions of the ultrasound diagnostic device that generated the target time series data, the artifact reduction unit changes the settings of the ultrasound diagnostic device as the artifact reduction processing; if the predicted type of artifact cannot be reduced by changing the operating conditions of the ultrasound diagnostic device that generated the target time series data, the artifact reduction unit generates an ultrasound image in which the artifact has been reduced by inputting the target time series data into an image generation model that generates an ultrasound image in which the artifact has been reduced based on the time series data that causes the artifact.

1. An ultrasonic time series data processing program comprising:

Images