Ultrasound diagnostic apparatus, method, and program
The ultrasound diagnostic apparatus addresses the challenge of analyzing index values by calculating a reliability index based on tissue attribute parameters, enhancing the accuracy and reliability of diagnoses like NASH through regression and machine learning models.
Patent Information
- Application Number
- JP2024027458
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-02-27
- Publication Date
- 2025-09-08
AI Technical Summary
Existing ultrasound diagnostic methods face challenges in appropriately analyzing index values due to subjectivity and uncertainty in data reliability, particularly in non-invasive diagnosis of conditions like non-alcoholic steatohepatitis (NASH), where multiple tissue characterization parameters are used.
An ultrasound diagnostic apparatus that includes a measurement unit to measure tissue attribute parameters and a calculation unit to calculate a reliability index based on the reliability of each parameter, using models like regression and machine learning, to enhance the analysis of index values.
Enables accurate and reliable analysis of index values by determining high-reliability regions, reducing subjectivity and improving the diagnostic accuracy of conditions like NASH.
Smart Images

Figure 2025130344000001_ABST
Abstract
Description
[Technical Field]
[0001] The embodiments disclosed in this specification relate to an ultrasound diagnostic apparatus, a method, and a program. [Background technology]
[0002] An ultrasound diagnostic device has the function of visualizing the morphology of biological tissue based on reflected wave signals of ultrasound transmitted from an ultrasound probe, as well as the function of quantifying tissue properties. For example, an ultrasound diagnostic device can measure tissue property parameters indicating the elasticity, viscosity, etc. of biological tissue by measuring the propagation velocity of shear waves generated by push pulses. Furthermore, an ultrasound diagnostic device can measure tissue property parameters indicating the amount of attenuation of ultrasound in biological tissue by analyzing the attenuation state of reflected wave signals. Such tissue property parameters are used as index values for determining the degree of, for example, liver fibrosis, hepatitis, fatty liver, etc.
[0003] In recent years, methods for diagnosing non-alcoholic steatohepatitis (NASH) noninvasively, instead of liver biopsy, have been investigated using statistical analysis and machine learning using the above-mentioned tissue characterization parameters. For example, diagnostic methods using index values that use multiple tissue characterization parameters are being investigated. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Patent Publication No. 2021-073017 [Patent Document 2] U.S. Patent No. 9,830,699 [Patent Document 3] U.S. Patent No. 10,226,227 [Patent Document 4] Japanese Patent Application Publication No. 2019-024682 Summary of the Invention [Problem to be solved by the invention]
[0005] One of the problems that the embodiments disclosed herein aim to solve is to appropriately analyze index values. However, the problems solved by the embodiments disclosed herein are not limited to the above problem. Problems corresponding to the effects of the configurations described in the embodiments below can also be considered as other problems that the embodiments disclosed herein aim to solve. [Means for solving the problem]
[0006] An ultrasound diagnostic apparatus according to an embodiment includes a measurement unit and a calculation unit. The measurement unit measures a plurality of tissue attribute parameters based on a reflected wave signal received from a subject. The calculation unit calculates a reliability index of an index value based on the plurality of tissue attribute parameters based on the reliability of each of the plurality of tissue attribute parameters. [Brief explanation of the drawings]
[0007] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of an ultrasound diagnostic apparatus according to the first embodiment. [Figure 2] FIG. 2 is a flowchart showing the procedure of processing performed by the ultrasonic diagnostic apparatus according to the first embodiment. [Figure 3A] FIG. 3A is a diagram showing an example of a result of the measurement process according to the first embodiment. [Figure 3B] FIG. 3B is a diagram showing an example of a result of the measurement process according to the first embodiment. [Figure 3C] FIG. 3C is a diagram showing an example of a result of the measurement process according to the first embodiment. [Figure 4A] FIG. 4A is a diagram for explaining an example of obtaining a reliability according to the first embodiment. [Figure 4B] FIG. 4B is a diagram for explaining an example of obtaining the reliability according to the first embodiment. [Figure 5] FIG. 5 is a diagram for explaining an example of extraction of a high-reliability region according to the first embodiment. [Figure 6] FIG. 6 is a diagram showing an example of display information according to the first embodiment. [Figure 7] FIG. 7 is a diagram showing an example of display information according to the first embodiment. DETAILED DESCRIPTION OF THE INVENTION
[0008] Hereinafter, embodiments of an ultrasound diagnostic apparatus, method, and program according to the present application will be described in detail with reference to the accompanying drawings. Note that the ultrasound diagnostic apparatus, method, and program according to the present application are not limited to the following embodiments.
[0009] (First embodiment) Fig. 1 is a block diagram showing an example of the configuration of an ultrasound diagnostic apparatus 10 according to the first embodiment. As shown in Fig. 1, the ultrasound diagnostic apparatus 10 according to this embodiment includes an ultrasound probe 1, a display 2, an input interface 3, and a device main body 4, and the ultrasound probe 1, the display 2, and the input interface 3 are connected to the device main body 4 so as to be able to communicate with each other.
[0010] The ultrasonic probe 1 has multiple piezoelectric vibrators that generate ultrasonic waves based on drive signals supplied from a transmission / reception circuit 41. The ultrasonic probe 1 also receives reflected waves from the subject and converts them into electrical signals. The ultrasonic probe 1 also has a matching layer provided on the piezoelectric vibrators, a backing material that prevents ultrasonic waves from propagating backward from the piezoelectric vibrators, and the like. The ultrasonic probe 1 is detachably connected to the device main body 4.
[0011] When ultrasonic waves are transmitted from the ultrasonic probe 1 to the subject, the transmitted ultrasonic waves are reflected successively by discontinuous surfaces of acoustic impedance in the subject's internal tissues and are received as reflected wave signals by the multiple piezoelectric transducers of the ultrasonic probe 1. The amplitude of the received reflected wave signals depends on the difference in acoustic impedance at the discontinuous surfaces where the ultrasonic waves are reflected. When the transmitted ultrasonic pulses are reflected by the surface of a moving blood flow or heart wall, the reflected wave signals undergo a frequency shift due to the Doppler effect, depending on the velocity component of the moving object relative to the direction of ultrasonic transmission.
[0012] The ultrasonic probe 1 may be a one-dimensional ultrasonic probe in which a plurality of piezoelectric vibrators are arranged in a row, or may be an ultrasonic probe in which a plurality of piezoelectric vibrators of a one-dimensional ultrasonic probe are mechanically vibrated, or a two-dimensional ultrasonic probe in which a plurality of piezoelectric vibrators are arranged two-dimensionally in a lattice pattern.
[0013] The display 2 displays a GUI (Graphical User Interface) that allows the operator of the ultrasound diagnostic apparatus 10 to input various setting requests using the input interface 3, as well as ultrasound images generated in the apparatus main body 4. The display 2 also displays various messages and display information to notify the operator of the processing status and results of the apparatus main body 4. The display 2 also has a speaker and can output sound.
[0014] The input interface 3 is operated to set a predetermined position (e.g., the position of a region of interest (ROI)), and is realized by, for example, a trackball, a switch button, a mouse, a keyboard, a touchpad that performs input operations by touching the operation surface, a touch monitor that integrates a display screen and a touchpad, a non-contact input circuit using an optical sensor, and a voice input circuit. The input interface 3 is connected to a processing circuit 45 (described later) and converts input operations received from an operator into electrical signals and outputs the electrical signals to the processing circuit 45. Note that, in this specification, the input interface 3 is not limited to those having physical operation components such as a mouse and a keyboard. For example, an electrical signal processing circuit that receives electrical signals corresponding to input operations from an external input device provided separately from the device and outputs the electrical signals to the processing circuit 45 is also included as an example of an input interface.
[0015] The device main body 4 is a device that generates an ultrasound image based on a reflected wave signal received by the ultrasound probe 1, and as shown in FIG. 1, includes a transmission / reception circuit 41, a signal processing circuit 42, an image memory 43, a storage circuit 44, and a processing circuit 45. The transmission / reception circuit 41, the signal processing circuit 42, the image memory 43, the storage circuit 44, and the processing circuit 45 are connected so as to be able to communicate with each other. In the ultrasound diagnostic device 10 shown in FIG. 1, each processing function is stored in the storage circuit 44 in the form of a program executable by a computer. The transmission / reception circuit 41, the signal processing circuit 42, and the processing circuit 45 are processors that realize the function corresponding to each program by reading and executing the program from the storage circuit 44. In other words, when each program is read, each circuit has the function corresponding to the read program.
[0016] The transmission / reception circuit 41 has a pulse generator, a transmission delay unit, a pulser, etc., and supplies a drive signal to the ultrasonic probe 1. The pulse generator repeatedly generates rate pulses at a predetermined rate frequency to form transmitted ultrasonic waves. The transmission delay unit focuses the ultrasonic waves generated from the ultrasonic probe 1 into a beam and provides a delay time for each piezoelectric transducer required to determine the transmission directivity to each rate pulse generated by the pulse generator. The pulser applies a drive signal (drive pulse) to the ultrasonic probe 1 at a timing based on the rate pulse. In other words, the transmission delay unit changes the delay time provided to each rate pulse to arbitrarily adjust the transmission direction of the ultrasonic waves transmitted from the piezoelectric transducer surface.
[0017] The transmitter / receiver circuit 41 has a function of being able to instantaneously change the transmission frequency, transmission drive voltage, etc. in order to execute a predetermined scan sequence based on instructions from the processing circuit 45, which will be described later. In particular, the change in transmission drive voltage is realized by a linear amplifier type oscillation circuit that can instantaneously switch its value, or a mechanism that electrically switches between multiple power supply units.
[0018] The transmission / reception circuit 41 also has a preamplifier, an A / D (Analog / Digital) converter, a reception delay unit, an adder, etc., and performs various processes on the reflected wave signals received by the ultrasound probe 1 to generate reflected wave data. The preamplifier amplifies the reflected wave signals for each channel. The A / D converter performs A / D conversion on the amplified reflected wave signals. The reception delay unit provides the delay time required to determine the reception directivity. The adder performs addition processing on the reflected wave signals processed by the reception delay unit to generate reflected wave data. The addition processing by the adder emphasizes the reflected components from the direction corresponding to the reception directivity of the reflected wave signals, and an overall beam for ultrasound transmission and reception is formed based on the reception directivity and transmission directivity.
[0019] The signal processing circuit 42 performs, for example, logarithmic amplification, envelope detection processing, etc. on the reflected wave data received from the transmission / reception circuit 41 to generate data (B-mode data) in which the signal intensity for each sample point is expressed as brightness. The B-mode data generated by the signal processing circuit 42 is output to the processing circuit 45.
[0020] Furthermore, the signal processing circuit 42 generates data (Doppler data) that extracts motion information based on the Doppler effect of a moving object at each sample point within the scanning region from, for example, the reflected wave data received from the transmitting / receiving circuit 41. Specifically, the signal processing circuit 42 frequency-analyzes velocity information from the reflected wave data, extracts blood flow, tissue, and contrast agent echo components due to the Doppler effect, and generates data (Doppler data) that extracts moving object information such as average velocity, variance, and power for multiple points. Here, the moving object refers to, for example, blood flow, tissue such as the heart wall, or contrast agent. The motion information (blood flow information) obtained by the signal processing circuit 42 is sent to the processing circuit 45 and displayed in color on the display 2 as an average velocity image, variance image, power image, or a combination of these images.
[0021] The image memory 43 is a memory that stores image data for display generated by the processing circuitry 45. The image memory 43 can also store data generated by the signal processing circuitry 42. The B-mode data and Doppler data stored in the image memory 43 can be called up by the operator after diagnosis, for example, and are converted into an ultrasound image for display via the processing circuitry 45.
[0022] The memory circuitry 44 stores control programs for transmitting and receiving ultrasound, image processing, and display processing, as well as various data such as diagnostic information (e.g., patient ID, doctor's findings, etc.), diagnostic protocols, and various body marks. The memory circuitry 44 also stores the processing results of the transmission / reception circuitry 41, signal processing circuitry 42, and processing circuitry 45. The memory circuitry 44 is also used, as necessary, to store image data stored in the image memory 43. The data stored in the memory circuitry 44 can be transferred to an external device via an interface (not shown).
[0023] The processing circuitry 45 controls the overall processing of the ultrasound diagnostic apparatus 10. Specifically, the processing circuitry 45 controls the processing of the transmission / reception circuitry 41 and the signal processing circuitry 42 based on various setting requests input by the operator via the input interface 3 and various control programs and various data read from the storage circuitry 44. The processing circuitry 45 also controls the display 2 to display ultrasound images for display stored in the image memory 43.
[0024] 1, the processing circuit 45 executes a control function 451, an image processing function 452, a measurement function 453, a calculation function 454, and an evaluation function 455. Here, the control function 451 is an example of a display control unit. The measurement function 453 is an example of a measurement unit. The calculation function 454 is an example of a calculation unit. The evaluation function 455 is an example of an evaluation unit.
[0025] The control function 451 controls the processing of the transmission / reception circuit 41 and the signal processing circuit 42 based on various setting requests input by the operator via the input interface 3 and various control programs and data read from the memory circuit 44. Here, the control function 451 can control the transmission and reception of ultrasound waves for measuring tissue attribute parameters including the elasticity, viscosity, and ultrasonic attenuation of the subject's tissue. The control function 451 also controls the display 2 to display ultrasound images and various display information. For example, the control function 451 causes the display 2 to display index values and reliability indexes based on multiple tissue attribute parameters. The display by the control function 451 will be described in detail later.
[0026] The image processing function 452 generates an ultrasound image from the data generated by the signal processing circuit 42. That is, the image processing function 452 generates an ultrasound image in which the intensity of the reflected wave is represented by brightness from the B-mode data generated by the signal processing circuit 42. The image processing function 452 also generates an ultrasound image representing moving object information (blood flow information and tissue movement information) from the Doppler data generated by the signal processing circuit 42. The ultrasound image based on the Doppler data is velocity image data, variance image data, power image data, or image data combining these.
[0027] Here, the image processing function 452 generally converts (scan converts) a scan line signal sequence of an ultrasound scan into a scan line signal sequence of a video format, such as that of a television, to generate an ultrasound image for display. Specifically, the image processing function 452 generates an ultrasound image for display by performing coordinate conversion according to the ultrasound scanning form of the ultrasound probe 1. In addition to scan conversion, the image processing function 452 also performs various other image processing, such as image processing (smoothing processing) that regenerates an average brightness image using multiple image frames after scan conversion, and image processing (edge enhancement processing) that uses a differential filter within the image. The image processing function 452 also combines text information of various parameters, scales, body marks, etc., with the ultrasound image.
[0028] That is, the B-mode data and Doppler data are ultrasound image data before scan conversion processing, and the data generated by the image processing function 452 is ultrasound image data for display after scan conversion processing. When the signal processing circuit 42 generates three-dimensional data (three-dimensional B-mode data and three-dimensional Doppler data), the image processing function 452 generates volume data by performing coordinate conversion in accordance with the ultrasound scanning form of the ultrasound probe 1. Then, the image processing function 452 performs various rendering processes on the volume data to generate two-dimensional image data for display.
[0029] The measurement function 453 measures a plurality of tissue attribute parameters based on the reflected wave signal received from the subject. Specifically, the measurement function 453 measures tissue attribute parameters including at least two of tissue elasticity, tissue viscosity, and ultrasonic wave attenuation. For example, the measurement function 453 measures a parameter indicating tissue elasticity by calculating the propagation velocity of a shear wave based on the reflected wave signal. Note that the measurement function 453 can also calculate the elastic modulus (Young's modulus, shear modulus) from the propagation velocity of the shear wave.
[0030] Furthermore, the measurement function 453 measures a parameter indicating the viscosity of the tissue based on, for example, the relationship between the frequency of the shear wave and the propagation speed of the shear wave. As an example, the measurement function 453 calculates the slope of the phase velocity distribution as the parameter indicating the viscosity of the tissue. Note that the measurement function 453 can also calculate the viscosity coefficient.
[0031] Furthermore, the measurement function 453 measures a parameter indicating the attenuation of the ultrasonic wave, for example, based on the reflected wave signal. As an example, the measurement function 453 calculates the attenuation amount of the transmitted ultrasonic wave as the parameter indicating the attenuation of the ultrasonic wave.
[0032] Furthermore, the measurement function 453 calculates an index value based on the tissue attribute parameters, using a regression model or machine learning model based on statistical analysis. For example, the measurement function 453 calculates the index value using the results of tissue elasticity, tissue viscosity, and ultrasonic attenuation. The processing performed by the measurement function 453 will be described in detail later.
[0033] The calculation function 454 calculates a reliability index for the index value based on the plurality of tissue attribute parameters based on the reliability of each of the plurality of tissue attribute parameters. Specifically, the calculation function 454 acquires the reliability of each tissue attribute parameter, and calculates a reliability index indicating the reliability of the index value calculated by the measurement function 453 based on the acquired reliability. The processing by the calculation function 454 will be described in detail later.
[0034] The evaluation function 455 evaluates an index value based on a plurality of tissue attribute parameters based on the reliability index. Specifically, the evaluation function 455 evaluates the index value calculated by the measurement function 453 based on the reliability index calculated by the calculation function 454. The processing by the evaluation function 455 will be described in detail later.
[0035] Here, the ultrasound diagnostic apparatus 10 according to the first embodiment enables appropriate analysis of index values. For example, in analysis using tissue attribute parameters, a diagnostic method using index values that utilize multiple tissue attribute parameters has been considered, but it is difficult to determine whether the data corresponding to the region for which index values are analyzed is reliable. As a result, the subjectivity of the operator is involved, and there are cases where the index values cannot be analyzed appropriately.
[0036] Therefore, the ultrasound diagnostic apparatus 10 calculates a reliability index for the index value based on a plurality of tissue attribute parameters based on the reliability of each of the plurality of tissue attribute parameters, thereby enabling appropriate analysis of the index value.
[0037] The processing procedure by the ultrasonic diagnostic apparatus 10 will be described below with reference to Fig. 2, and then each step will be described in detail. Fig. 2 is a flowchart showing the processing procedure of the ultrasonic diagnostic apparatus according to the first embodiment.
[0038] 2, in this embodiment, the control function 411 executes a scan to measure tissue attribute parameters (step S101). For example, the control function 411 executes a scan to perform measurements using SWE (Shear Wave Elastography), SWD (Shear Wave Dispersion), and ATI (Attenuation Imaging). The processing of step S101 is realized, for example, by the processing circuitry 45 calling up a program corresponding to the control function 451 from the storage circuitry 44 and executing it.
[0039] Next, the measurement function 453 measures a plurality of tissue attribute parameters based on the data obtained by the scan (step S102). Furthermore, the measurement function 453 calculates an index value based on the plurality of tissue attribute parameters based on the measurement results (step S103). For example, the measurement function 453 measures tissue elasticity, tissue viscosity, and ultrasonic wave attenuation, and calculates an index value based on these results. The processes of steps S102 and S103 are realized, for example, by the processing circuitry 45 calling up a program corresponding to the measurement function 453 from the storage circuitry 44 and executing it.
[0040] Next, the calculation function 454 acquires the reliability of each tissue attribute parameter (step S104), and calculates a reliability index indicating the reliability of the index value based on the acquired reliability of each tissue attribute parameter (step S105). The processes of steps S104 and S105 are realized, for example, by the processing circuitry 45 calling up a program corresponding to the calculation function 454 from the storage circuitry 44 and executing it.
[0041] Next, the evaluation function 455 evaluates the index value based on the calculated reliability index (step S106). The process of step S106 is realized, for example, by the processing circuitry 45 calling up a program corresponding to the evaluation function 455 from the storage circuitry 44 and executing it.
[0042] Next, the control function 451 controls the display 2 to display the display information (reliability index, index value, etc.) (step S107). The processing of step S107 is realized, for example, by the processing circuitry 45 calling up a program corresponding to the control function 451 from the storage circuitry 44 and executing it.
[0043] Each process executed by the ultrasound diagnostic apparatus 10 will be described in detail below.
[0044] (scan) As described in step S101, the control function 451 executes a scan to measure a plurality of tissue attribute parameters. For example, when performing measurements using SWE and SWD, the control function 451 controls to transmit displacement generating ultrasound waves (push pulses) to generate shear waves in the subject, and to transmit and receive displacement observing ultrasound waves (tracking pulses) to observe the generated shear waves.
[0045] For example, the control function 451 causes the ultrasonic probe 1 to transmit a push pulse to generate a shear wave in biological tissue. Then, the control function 451 causes the ultrasonic probe 1 to transmit a tracking pulse to observe the shear wave generated based on the push pulse. The tracking pulse is transmitted to observe the propagation speed of the shear wave generated by the push pulse at each sample point within the measurement region. Typically, the tracking pulse is transmitted multiple times (e.g., 100 times) for each scanning line within the measurement region. The control function 451 generates reflected wave data (scan data) from the reflected wave signal of the tracking pulse transmitted for each scanning line within the measurement region.
[0046] Furthermore, for example, when performing measurement using ATI, the control function 451 executes a scan under the same conditions as a normal B-mode scan. ATI utilizes the phenomenon in which ultrasound transmitted into a living body is attenuated by absorption, diffusion, etc. as it passes through tissue, and can be measured from scan data obtained in B-mode.
[0047] (Measurement and processing of tissue attribute parameters) As described in step S102, the measurement function 453 measures a plurality of tissue attribute parameters based on the scan data generated under the control of the control function 451. For example, when measuring the elasticity of tissue by SWE, the measurement function 453 acquires time change information of displacement due to shear waves for each position in a region of interest (ROI) corresponding to the scan range from the scan data generated from the reflected wave signal of the tracking pulse, calculates the arrival time of the shear waves for each position in the ROI based on the acquired time change information of displacement, and calculates the velocity of the shear waves based on the acquired arrival time.
[0048] The image processing function 452 can generate the elasticity image (image representing elasticity) shown in Fig. 3A by assigning pixel values according to the shear wave speed calculated above to each position in the region of interest. Note that Fig. 3A is a diagram showing an example of the results of the measurement process according to the first embodiment.
[0049] Furthermore, for example, when measuring the viscosity of tissue using SWD, the measurement function 453 acquires information on the time change of displacement due to shear waves for each position in the region of interest from the scan data generated from the reflected wave signal of the tracking pulse, performs frequency analysis on the acquired information on the time change of displacement, generates a distribution showing the relationship between shear rate and frequency for each position in the region of interest, and calculates the viscosity value based on that relationship.
[0050] The image processing function 452 can generate the viscosity image (image representing viscosity) shown in Fig. 3B by assigning the viscosity value calculated above to each position in the region of interest. Note that Fig. 3B is a diagram showing an example of the result of the measurement process according to the first embodiment.
[0051] Furthermore, for example, when measuring attenuation due to ATI, the measurement function 453 performs processing on the scan data obtained in B mode to offset the signal amplification due to various gains and to offset the effects of the sound field, thereby obtaining processed scan data, and then obtains an attenuation index value (attenuation coefficient) for each position in the region of interest by differentiating the obtained processed scan data along the transmission and reception direction (depth direction) of the ultrasound.
[0052] The image processing function 452 can generate the attenuation image (image showing the attenuation of ultrasonic waves) shown in Fig. 3C by assigning the attenuation index value calculated above to each position in the region of interest. Note that Fig. 3C is a diagram showing an example of the result of the measurement processing according to the first embodiment.
[0053] (Calculation process of index value) As described in step S103, the measurement function 453 calculates an index value based on the measured tissue attribute parameters. For example, the measurement function 453 calculates an index value for evaluating the presence or progression of a disease based on the results of SWE, SWD, and ATI.
[0054] For example, the measurement function 453 uses a regression model or machine learning model based on statistical analysis to calculate a score for evaluating liver disease for each pixel from the SWE results, SWD results, and ATI results. Here, the regression model is, for example, a model calculated by logistic regression, and the machine learning model is, for example, a model obtained by a support vector machine or random forest. These models are pre-constructed and stored in the memory circuitry 44 so that a score indicating the presence or absence and progression of liver disease such as non-alcoholic steatohepatitis (NASH) can be obtained from the SWE results, SWD results, and ATI results. That is, the measurement function 453 uses these models read from the memory circuitry 44 to calculate an index value combining multiple tissue attribute parameters.
[0055] While the above example describes measurement of parameters using SWE, SWD, and ATI, embodiments are not limited thereto, and other parameters may be measured as long as they are parameters that represent tissue characteristics. Furthermore, while the above example describes calculation of an index value that combines SWE, SWD, and ATI, embodiments are not limited thereto, and other index values may be calculated using any combination. For example, an index value may be calculated using a combination of any two of SWE, SWD, and ATI, or a combination of at least one of SWE, SWD, and ATI with another parameter, or a combination of other parameters.
[0056] (Reliability acquisition process) As described in step S104, the calculation function 454 obtains the reliability of each tissue attribute parameter measured by the measurement function 453. For example, the calculation function 454 obtains the reliability of the elasticity and viscosity of the tissue based on at least one of the amplitude of the shear wave, the S / N (signal / noise) ratio, the accuracy of the shear wave propagation, and the standard deviation of the numerical values.
[0057] For example, the calculation function 454 obtains a reliability based on the relationship between the propagation velocity of the shear wave and the amplitude of the shear wave. The propagation velocity of the shear wave is slower in soft tissue and faster in hard tissue. The amplitude of the shear wave is higher in soft tissue and lower in hard tissue. Using these relationships, the calculation function 454 quantifies the degree of consistency between the propagation velocity of the shear wave and the amplitude as a reliability for each position within the region of interest. The calculation function 454 can also obtain the S / N ratio of the scan data as a reliability.
[0058] The calculation function 454 can also acquire the reliability from a propagation map that indicates the accuracy of shear wave propagation. Fig. 4A is a diagram for explaining an example of acquiring the reliability according to the first embodiment. Fig. 4A shows a propagation map. As shown in Fig. 4A, the propagation map is rendered as a linear image (line image) in which lines connect positions where the arrival times of shear waves are approximately the same (for example, positions where the arrival times are approximately the same).
[0059] For example, in an environment where there is no displacement due to the subject's body movement or reflection or refraction of shear waves and where the elasticity and viscosity of biological tissue can be accurately measured, the shear wave propagates almost uniformly from the push pulse transmission position. Therefore, the line indicating the arrival time is almost parallel to the push pulse transmission direction and curves according to the elasticity and viscosity of the biological tissue. In contrast, in an environment where the elasticity and viscosity of biological tissue cannot be accurately measured, the shear wave propagation may be observed to be extremely fast or extremely slow. Therefore, the line indicating the arrival time will be significantly curved. The calculation function 454 quantifies the reliability based on this propagation image and obtains it for each position within the region of interest.
[0060] Furthermore, the calculation function 454 can obtain the reliability of each measured tissue attribute parameter based on the standard deviation of the numerical values. For example, the calculation function 454 obtains the reliability by using a measurement area detection (MAD) function that automatically detects areas where the standard deviation of the numerical values is small and calculates the average value. That is, the calculation function 454 obtains the size of the standard deviation calculated by MAD as the reliability.
[0061] In the above example, the amplitude of the shear wave, the S / N ratio, the accuracy of the shear wave propagation, and the standard deviation of the numerical values are used as the reliability of the elasticity and viscosity of the tissue. However, the embodiment is not limited to this, and any index that can be used as the reliability of the elasticity and viscosity of the tissue may be used.
[0062] The calculation function 454 also acquires the reliability of ultrasonic attenuation based on at least one of the accuracy of linear approximation of the reflected wave signal, the multiplexed signal, and the structure. For example, the calculation function 454 acquires the accuracy of fitting (coefficient of determination) when linearly fitting the amount of change (slope) taken from the signal intensity distribution of the processed scan data as the reliability of ultrasonic attenuation.
[0063] Furthermore, the calculation function 454 can acquire the reliability by utilizing, for example, a function for removing multiple reflections originating from the abdominal wall. FIG. 4B is a diagram for explaining an example of acquiring the reliability according to the first embodiment. As shown in FIG. 4B, in B mode, a region where multiple reflections are caused by the abdominal wall (multiple region) may be included in the shallow part of the region of interest, and the function for removing multiple reflections extracts this multiple region and removes it from the measurement results. Using this function, the calculation function 454 acquires the extracted multiple region as a region with low reliability.
[0064] The calculation function 454 can also acquire the reliability by utilizing a function for removing structures within the region of interest. For example, as shown by the black area in FIG. 4B, if a region of a structure such as a blood vessel (structure region) is included within the region of interest, it becomes difficult to calculate the correct attenuation coefficient. Therefore, the structure removal function extracts this structure region and removes it from the measurement results. The calculation function 454 utilizes this function to acquire the extracted structure region as a region with low reliability.
[0065] In the above example, the accuracy of linear approximation of the reflected wave signal, multiple signals, and structures are used as the reliability of ultrasonic attenuation. However, the embodiment is not limited to this, and any index that can be used as the reliability of ultrasonic attenuation may be used.
[0066] (Reliability index calculation process) As described in step S105, the calculation function 454 calculates a reliability index for the index value based on multiple tissue attribute parameters using the reliability of each tissue attribute parameter. Specifically, the calculation function 454 calculates a reliability index that combines the reliability values obtained for each tissue attribute parameter. For example, the calculation function 454 combines the reliability values obtained for each tissue attribute parameter (SWE, SWD, ATI) for each position within the region of interest to calculate a reliability index expressed as a numerical value, a binary indicator, or a probability. That is, the calculation function 454 calculates a reliability index for each pixel within the region of interest.
[0067] Here, the calculation function 454 can extract a high-reliability region based on the reliability of each tissue attribute parameter. Specifically, the calculation function 454 can calculate a reliability index within a region of the subject's tissue where the reliability of each of the tissue attribute parameters is equal to or greater than a threshold. FIG. 5 is a diagram for explaining an example of extraction of a high-reliability region according to the first embodiment. For example, as shown in FIG. 5, the calculation function 454 overlaps a two-dimensional map (SWE / SWD 2DMAP) showing a high-reliability region in the measurement results by SWE and SWD whose reliability exceeds a threshold with a two-dimensional map (ATI 2DMAP) showing a high-reliability region in the measurement results by ATI whose reliability exceeds a threshold, and extracts the overlapping region as a high-reliability region.
[0068] The calculation function 454 can also extract, as a high-reliability region, a region other than the region where all tissue attribute parameters exceed a threshold. For example, the calculation function 454 can calculate a reliability index within a region of the subject's tissue where the reliability of at least one of the tissue attribute parameters is equal to or greater than a threshold. As an example, the calculation function 454 can extract, as a high-reliability region, the region shown in the middle diagram of FIG. 5.
[0069] (Evaluation process of index values) As described in step S106, the evaluation function 455 evaluates the index value calculated by the measurement function 453 based on the reliability index calculated by the calculation function 454. For example, when the measurement function 453 calculates an index value (score) for diagnosing the presence or absence or the degree of progression of NASH by combining the measurement results of SWE, SWD, and ATI, the evaluation function 455 evaluates the index value based on the reliability index calculated by the calculation function 454.
[0070] For example, the evaluation function 455 evaluates the index value for each position (each pixel) within the region of interest based on a threshold value set for the reliability index calculated by the calculation function 454. That is, the evaluation function 455 evaluates the score calculated for each pixel within the region of interest using the reliability index for the corresponding position. For example, the evaluation function 455 compares the reliability index with a threshold value for each pixel within the high-reliability region (the region shown in the lower diagram of FIG. 5) extracted as an overlapping region in FIG. 5. Then, based on the comparison result, the evaluation function 455 evaluates which index values, among the index values of each pixel within the high-reliability region, have a reliability index that exceeds the threshold value. This allows the evaluation function 455 to evaluate, for example, which index values for diagnosing NASH have a high reliability.
[0071] (Display information display processing) As described in step S107, the control function 451 causes the display 2 to display display information including the index values calculated by the measurement function 453 and the reliability index values calculated by the calculation function 454. For example, the control function 451 causes a two-dimensional color map showing the reliability indexes for a region of interest in the tissue of the subject to be displayed. That is, the control function 451 can display a two-dimensional color map in which a color according to the reliability index is assigned to each position within the scan range.
[0072] Furthermore, the control function 451 can also display a two-dimensional color map showing reliability indices only for high-reliability regions. Fig. 6 is a diagram showing an example of display information according to the first embodiment. For example, as shown in the upper diagram of Fig. 6, the control function 451 can display a two-dimensional color map in which colors corresponding to reliability indices are assigned to pixels in high-reliability regions where the reliability of all tissue characterization parameters exceeds a threshold. In other words, the control function 451 can display high-reliability regions while also displaying differences in reliability within the high-reliability regions.
[0073] In this way, by the control function 451 displaying the two-dimensional color map of the reliability index, the operator can grasp at a glance the areas with high reliability within the region of interest, and can appropriately set the region R1, which is the measurement ROI for analyzing the index values, as shown in the lower diagram of Figure 6. This makes it possible for the ultrasound diagnostic apparatus 10 to appropriately analyze the index values regardless of the operator operating it.
[0074] Here, the measurement function 453 can calculate various analytical values using index values of pixels included in the set measurement ROI. For example, the measurement function 453 calculates at least one of the mean, median, and standard deviation of index values based on multiple tissue attribute parameters in a specified region (e.g., region R1).
[0075] The control function 451 can also display index values based on multiple tissue attribute parameters only in regions of the subject's tissue where the reliability index is equal to or greater than a threshold. FIG. 7 is a diagram showing an example of display information according to the first embodiment. For example, as shown in the upper diagram of FIG. 7, the control function 451 can display a two-dimensional color map in which colors corresponding to index values are assigned to only pixels included in regions where the reliability index exceeds a threshold within a high-reliability region where the reliability of all tissue attribute parameters exceeds a threshold. In other words, the control function 451 can display the state of index values only for regions with even higher reliability within the high-reliability region.
[0076] This allows the operator to grasp at a glance the index values of areas with even higher reliability indices within the high reliability area, and allows the operator to appropriately set the measurement ROI (area R1) as shown in the lower diagram of Figure 7.
[0077] Here, the control function 451 can also display a GUI (Graphical User Interface) for setting a threshold for the index value, as shown in Fig. 7. In such a case, the control function 451 can also perform control so that only index values that exceed the set threshold (or are equal to or less than the set threshold) are displayed.
[0078] As described above, according to the first embodiment, the measurement function 453 measures a plurality of tissue attribute parameters based on reflected wave signals received from the subject. The calculation function 454 calculates a reliability index of an index value based on the plurality of tissue attribute parameters based on the reliability of each of the plurality of tissue attribute parameters. Therefore, the ultrasound diagnostic apparatus 10 according to the first embodiment can evaluate the reliability of an index value based on a plurality of tissue attribute parameters, enabling appropriate analysis of the index value.
[0079] Furthermore, according to the first embodiment, the plurality of tissue attribute parameters include at least two of tissue elasticity, tissue viscosity, and ultrasonic attenuation, thereby enabling the ultrasound diagnostic apparatus 10 according to the first embodiment to appropriately analyze index values related to liver disease.
[0080] Furthermore, according to the first embodiment, the calculation function 454 obtains the reliability of the elasticity and viscosity of the tissue based on at least one of the amplitude of the shear wave, the S / N ratio, the accuracy of the shear wave propagation, and the standard deviation of the numerical values. Therefore, the ultrasound diagnostic apparatus 10 according to the first embodiment can obtain appropriate reliability of the elasticity and viscosity of the tissue.
[0081] Furthermore, according to the first embodiment, the calculation function 454 acquires the reliability of ultrasonic wave attenuation based on at least one of the accuracy of linear approximation of the reflected wave signal, the multiplexed signal, and the structure. Therefore, the ultrasonic diagnostic apparatus 10 according to the first embodiment can acquire an appropriate reliability of ultrasonic wave attenuation.
[0082] Furthermore, according to the first embodiment, the calculation function 454 calculates a reliability index for a region of the subject's tissue where the reliability of each of the tissue attribute parameters is equal to or greater than a threshold. Therefore, the ultrasound diagnostic apparatus 10 according to the first embodiment can obtain a reliability index for the index value for a region where the reliability of each tissue attribute parameter is high.
[0083] Furthermore, according to the first embodiment, the calculation function 454 calculates a reliability index for a region of the subject's tissue where the reliability of at least one of the tissue attribute parameters is equal to or greater than a threshold. Therefore, the ultrasound diagnostic apparatus 10 according to the first embodiment can obtain a reliability index for a region where the reliability of at least one tissue attribute parameter is high.
[0084] Furthermore, according to the first embodiment, the evaluation function 455 evaluates index values based on multiple tissue attribute parameters based on a reliability index. Therefore, the ultrasound diagnostic apparatus 10 according to the first embodiment can perform analysis targeting index values with high reliability indexes, enabling appropriate analysis of index values.
[0085] Furthermore, according to the first embodiment, the control function 451 causes the display 2 to display index values and reliability indices based on multiple tissue attribute parameters. The control function 451 also causes the display 2 to display index values based on multiple tissue attribute parameters only for regions of the subject's tissue where the reliability indices are equal to or greater than a threshold. The control function 451 also displays a two-dimensional color map showing the reliability indices for the region of interest in the subject's tissue. Therefore, the ultrasound diagnostic apparatus 10 according to the first embodiment makes it possible to easily perform appropriate analysis of index values.
[0086] Furthermore, according to the first embodiment, the measurement function 453 calculates an index value based on the tissue attribute parameters based on a regression model or machine learning model based on statistical analysis. Therefore, the ultrasound diagnostic apparatus 10 according to the first embodiment makes it possible to easily obtain an index value based on the tissue attribute parameters.
[0087] Furthermore, according to the first embodiment, the calculation function 454 calculates a reliability index that is expressed as a numerical value, a binary indicator, or a probability. Therefore, the ultrasound diagnostic apparatus 10 according to the first embodiment can provide an easy-to-understand reliability index.
[0088] Furthermore, according to the first embodiment, the measurement function 453 calculates at least one of the mean, median, and standard deviation in a specified region for an index value based on multiple tissue attribute parameters. Therefore, the ultrasound diagnostic apparatus 10 according to the first embodiment can provide an analysis value of the index value.
[0089] According to the first embodiment, the regression model is a model calculated by logistic regression. The machine learning model is a model obtained by a support vector machine or a random forest. Therefore, the ultrasound diagnostic apparatus 10 according to the first embodiment can appropriately calculate the index value.
[0090] (Other embodiments) In the above-described embodiment, an example has been described in which an index value calculated from multiple tissue attribute parameters (SWE, SWD, ATI) is evaluated using a reliability index. However, the embodiment is not limited to this, and an index value based on a single tissue attribute parameter may also be evaluated using a reliability index. For example, an elastic modulus measured by SWE may be evaluated using the above-described reliability index (a reliability index based on the reliability of each of multiple tissue attribute parameters). In such a case, the control function 451 may perform control to display only the elastic modulus at a position in the region of interest where the reliability index exceeds a threshold.
[0091] The term "processor" used in the above description refers to a circuit such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). A processor realizes its function by reading and executing a program stored in a memory. Instead of storing a program in a memory, the processor may be configured so that the program is directly embedded in its circuit. In this case, the processor realizes its function by reading and executing the program embedded in the circuit. Each processor in this embodiment is not limited to being configured as a single circuit, but may also be configured as a single processor by combining multiple independent circuits to realize its function.
[0092] Note that the components of each device illustrated in the above description of the embodiments are conceptual functional units and do not necessarily have to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to that illustrated, and all or part of the devices can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.
[0093] The methods described in the above embodiments can be realized by executing a prepared program on a computer such as a personal computer or a workstation. This program can be distributed via a network such as the Internet. This program can also be recorded on a non-transitory computer-readable recording medium such as a hard disk, a flexible disk (FD), a CD-ROM, an MO, a DVD, a USB memory, or a flash memory such as an SD card memory, and can be executed by being read from the non-transitory recording medium by a computer.
[0094] As described above, according to the embodiment, it is possible to appropriately analyze index values.
[0095] Although several embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]
[0096] 10 Ultrasound diagnostic equipment 451 Control Functions 453 Measurement Function 454 Calculation Function 455 rating function
Claims
1. a measurement unit that measures a plurality of tissue attribute parameters based on reflected wave signals received from the subject; a calculation unit that calculates a reliability index of an index value based on the plurality of tissue attribute parameters based on the reliability of each of the plurality of tissue attribute parameters; An ultrasound diagnostic device comprising:
2. The ultrasound diagnostic apparatus according to claim 1 , wherein the plurality of tissue attribute parameters include at least two of tissue elasticity, tissue viscosity, and ultrasonic wave attenuation.
3. 3. The ultrasound diagnostic device according to claim 2, wherein the calculation unit obtains a confidence level regarding the elasticity and viscosity of the tissue based on at least one of an amplitude of a shear wave, an S / N ratio, an accuracy of propagation of the shear wave, and a standard deviation of a numerical value.
4. The ultrasound diagnostic device according to claim 2 , wherein the calculation unit acquires the reliability of the attenuation of the ultrasound waves based on at least one of accuracy of linear approximation of the reflected wave signal, a multiple signal, and a structure.
5. The ultrasound diagnostic apparatus according to claim 1 , wherein the calculation unit calculates the reliability index within a region of the tissue of the subject where the reliability of each of the plurality of tissue attribute parameters is equal to or greater than a threshold.
6. The ultrasound diagnostic apparatus according to claim 1 , wherein the calculation unit calculates the reliability index within a region of the tissue of the subject where the reliability of at least one of the plurality of tissue attribute parameters is equal to or greater than a threshold.
7. The ultrasonic diagnostic apparatus of claim 1 , further comprising an evaluation unit that evaluates an index value based on the plurality of tissue attribute parameters based on the reliability index.
8. The ultrasound diagnostic apparatus according to claim 1 , further comprising a display control unit that causes an index value and a reliability index based on the plurality of tissue attribute parameters to be displayed on a display unit.
9. The ultrasound diagnostic apparatus according to claim 8 , wherein the display control unit displays index values based on the plurality of tissue attribute parameters only for regions in the tissue of the subject where the reliability index is equal to or greater than a threshold value.
10. The ultrasound diagnostic apparatus according to claim 8 , wherein the display control unit displays a two-dimensional color map indicating the reliability index within a region of interest in the tissue of the subject.
11. The ultrasound diagnostic apparatus of claim 1 , wherein the measurement unit calculates an index value based on the plurality of tissue attribute parameters, based on the plurality of tissue attribute parameters and a regression model or a machine learning model based on statistical analysis.
12. The ultrasound diagnostic apparatus of claim 1 , wherein the calculation unit calculates the reliability index as a numerical value, a binary indicator, or a probability.
13. The ultrasound diagnostic apparatus according to claim 12 , wherein the measurement unit calculates at least one of a mean value, a median value, and a standard deviation in a designated region for index values based on the plurality of tissue attribute parameters.
14. The ultrasound diagnostic apparatus according to claim 11 , wherein the regression model is a model calculated by logistic regression.
15. The ultrasound diagnostic apparatus according to claim 11 , wherein the machine learning model is a model obtained by a support vector machine or a random forest.
16. measuring a plurality of tissue attribute parameters based on the reflected wave signals received from the subject; calculating a reliability index of an index value based on the plurality of tissue attribute parameters based on the reliability of each of the plurality of tissue attribute parameters; A method comprising:
17. measuring a plurality of tissue attribute parameters based on the reflected wave signals received from the subject; calculating a reliability index of an index value based on the plurality of tissue attribute parameters based on the reliability of each of the plurality of tissue attribute parameters; A program that causes a computer to perform each process.
Citation Information
Patent Citations
Ultrasonic diagnostic apparatus and control program thereof
JP2019024682A
Non-invasive apparatus for detecting liver damage
JP2021073017A
System and method for classifying and characterizing tissues using first-order and second-order statistics of quantitative ultrasound parametric maps
US10226227B2
Automatic measurement of lesions on medical images
US9830699B2