Tissue state evaluation method, ultrasonic detection equipment and storage medium

Abstract

The invention provides a tissue state evaluation method, ultrasonic detection equipment and a readable medium. The method comprises the following steps: acquiring a first ultrasonic echo signal of a target tissue; determining a first parameter value of at least one target ultrasonic quantitative parameter according to the first ultrasonic echo signal, wherein the target ultrasonic quantitative parameter is an ultrasonic quantitative parameter related to a tissue state; based on a tissue state prediction model, obtaining a first index value of a target evaluation index according to the first parameter value of the at least one target ultrasonic quantitative parameter; wherein the target evaluation index is an index representing that the target organization state is normal or abnormal; and obtaining a state evaluation result of the target organization according to the first index value of the target evaluation index.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the technical field of medical devices, and more specifically, to a method for evaluating tissue status, an ultrasonic detection device, and a readable medium. Background Art

[0002] With the development of medical technology, ultrasound technology plays an increasingly important role in medical evaluation and treatment.

[0003] Ultrasonic technology is not only applicable to the medical field, but also widely used in the fields of industry, civil engineering, etc. In the medical field, ultrasonic quantitative parameters can be used to detect cells, tissues and organs, providing an important basis for the evaluation and treatment of diseases. Moreover, ultrasonic technology is harmless to the human body, painless, has no special contraindications, and has no radiation damage. This makes ultrasonic technology easier to be accepted by doctors and patients, especially suitable for long-term monitoring and follow-up treatment.

[0004] In addition, ultrasound technology can obtain information about the internal structure, properties, and defects of tissues without damaging them. It can accurately reflect the slight changes in tissue composition and structure, and can monitor tissue changes in real time during treatment, helping doctors to adjust treatment plans in a timely manner and improve treatment effects. Ultrasonic quantitative parameters can provide a variety of information, such as sound speed, frequency, attenuation coefficient, and time interval, which can complement each other and provide comprehensive quantitative analysis of tissues.

[0005] Therefore, it is very valuable to use ultrasound quantitative parameters in clinical practice to assist in accurate quantitative tissue assessment. Summary of the invention

[0006] An object of the embodiments of the present disclosure is to provide a method for evaluating tissue status, an ultrasonic detection device, and a readable medium.

[0007] According to a first aspect of an embodiment of the present disclosure, there is provided a method for evaluating a tissue state, comprising:

[0008] Acquiring a first ultrasonic echo signal of a target tissue;

[0009] determining a first parameter value of at least one target ultrasound quantitative parameter according to the first ultrasound echo signal, wherein the target ultrasound quantitative parameter is an ultrasound quantitative parameter related to a tissue state;

[0010] Based on the tissue state prediction model, a first index value of a target evaluation index is obtained according to a first parameter value of the at least one target ultrasound quantitative parameter; wherein the target evaluation index at least includes an index characterizing whether the target tissue state is normal or abnormal;

[0011] A status assessment result of the target organization is obtained according to the first indicator value of the target assessment indicator.

[0012] Optionally, the method further includes:

[0013] Acquiring a plurality of set ultrasound quantitative parameters;

[0014] According to the plurality of ultrasound quantitative parameters, a plurality of parameter combinations are obtained, each parameter combination including at least one ultrasound quantitative parameter;

[0015] Determining the correlation between each parameter combination and the target evaluation indicator;

[0016] Selecting one or more parameter combinations according to the correlation, wherein the correlation of the selected parameter combination should be at least better than the correlation of a group of parameter combinations that are not selected, or the selected parameter combination has the highest correlation among all parameter combinations;

[0017] The target ultrasound quantitative parameter is determined according to the selected one or more sets of parameter combinations.

[0018] Optionally, the at least one target ultrasonic quantitative parameter includes at least one of tissue thickness, ultrasonic scattering parameter, nonlinear parameter, attenuation parameter, texture parameter, motion parameter, and elastic parameter; wherein the ultrasonic scattering parameter includes at least one of average intensity parameter, scattering peak value, scatterer density, and scatterer distribution characteristics; the nonlinear characteristic parameter includes at least one of normalized nonlinear parameter, ultrasonic nonlinear coefficient, second harmonic amplitude, phase matching, non-zero energy flow, and high-order elastic constant; the motion parameter includes at least one of displacement and strain; and the elastic parameter includes parameters used to characterize the elastic coefficient and / or viscosity coefficient.

[0019] Optionally, acquiring a first ultrasonic echo signal of a target tissue includes:

[0020] A first ultrasonic echo signal of the target tissue under different conditions is acquired.

[0021] Optionally, the different conditions include the target tissue being compressed by different pressures, or actively contracting or relaxing, or at different times.

[0022] Optionally, the characterization method of the normal or abnormal state of the target tissue includes the risk level of at least one of sarcopenia, tissue fattening degree, liver inflammation, portal hypertension, renal failure, pancreatic cancer, fatty pancreas, articular cartilage damage, local muscle damage, liver fibrosis, and liver cirrhosis;

[0023] The target tissue is a tissue associated with at least one of the characterized sarcopenia, degree of tissue fattening, liver inflammation, portal hypertension, renal failure, pancreatic cancer, fatty pancreas, articular cartilage damage, local muscle damage, liver fibrosis, and cirrhosis.

[0024] Optionally, acquiring a first ultrasonic echo signal of a target tissue includes:

[0025] Acquiring a second ultrasonic echo signal of at least one to-be-tested area of ​​the target tissue;

[0026] determining a target area in the area to be measured according to the second ultrasonic echo signal;

[0027] An ultrasonic signal is transmitted to the target area, and an ultrasonic echo signal reflected by the target area is received as the first ultrasonic echo signal.

[0028] Optionally, when the at least one target ultrasound quantitative parameter includes a nonlinear parameter, determining a parameter value of the at least one target ultrasound quantitative parameter according to the ultrasound echo signal includes:

[0029]

[0030] Among them, β represents the nonlinear parameter, ρ 0 represents the density of the target tissue, p 2 (x) represents the amplitude of the second harmonic in the first ultrasonic echo signal, p 0 represents the amplitude of the first ultrasonic echo signal at the target tissue, c 0 represents the speed at which the first ultrasonic echo signal propagates in the target tissue, f represents the frequency of the first ultrasonic echo signal, α 1 represents the attenuation coefficient of the fundamental wave in the first ultrasonic echo signal, α 2 represents the attenuation coefficient of the second harmonic in the first ultrasonic echo signal, and x represents the propagation distance of the first ultrasonic echo signal.

[0031] Optionally, the tissue state prediction model is obtained by the following method:

[0032] Acquire a training sample set, each training sample in the training sample set includes a second parameter value of the at least one target ultrasound quantitative parameter and a second index value of the target evaluation index, wherein the second parameter value is determined according to a third ultrasound echo signal corresponding to the training sample;

[0033] The tissue state prediction model is trained according to the training sample set.

[0034] According to a second aspect of the present disclosure, an ultrasonic detection device is provided, comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the method described in the first aspect of the present disclosure under the control of the computer program.

[0035] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect of the present disclosure is implemented.

[0036] Through the embodiments of the present disclosure, a first parameter value of at least one target ultrasound quantitative parameter is determined based on a first ultrasound echo signal of the target tissue, and a state assessment result of the target tissue is obtained based on the first parameter value of the at least one target ultrasound quantitative parameter. This can provide strong support for the state assessment of the target tissue through the quantitative, objective, non-invasive and other technical advantages of ultrasound technology.

[0037] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0039] Figure 1 is a block diagram of an example of a hardware configuration of an ultrasonic detection device that can be used to implement an embodiment of the present invention;

[0040] Figure 2 is a flow chart of a method for evaluating tissue status according to one embodiment of the present disclosure;

[0041] Figure 3 is a flow chart of a method for evaluating tissue status according to another embodiment of the present disclosure;

[0042] Figure 4 is a flowchart of an example of a method for evaluating tissue status according to an embodiment of the present disclosure;

[0043] Figure 5 is a block diagram of an ultrasonic detection device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0045] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0046] Technologies, methods and equipment known to persons of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods and equipment should be considered part of the specification.

[0047] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0048] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0049] <Hardware Configuration>

[0050] Figure 1 is a block diagram showing a hardware configuration of an ultrasonic detecting apparatus 1000 that can implement an embodiment of the present disclosure.

[0051] like Figure 1 As shown, the ultrasonic detection device 1000 may include a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a probe handle 1700, and the like. Among them, the processor 1100 may be a processor CPU, a microprocessor MCU, and the like. The memory 1200 may include, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, and the like. The interface device 1300 may include, for example, a USB interface, a headphone interface, and the like. The communication device 1400 may, for example, be capable of wired or wireless communication, and may specifically include Wifi communication, Bluetooth communication, 2G / 3G / 4G / 5G communication, and the like. The display device 1500 may, for example, be a liquid crystal display screen, a touch display screen, and the like. The input device 1600 may include, for example, a touch screen, a keyboard, a somatosensory input, and the like. The probe handle 1700 may be used to emit and receive ultrasonic waves.

[0052] Figure 1 The ultrasonic detection device shown is merely illustrative and does not imply any limitation on the present disclosure, its application or use. In the embodiments of the present disclosure, the memory 1200 of the ultrasonic detection device 1000 is used to store instructions, and the instructions are used to control the processor 1100 to operate to perform any one of the methods provided in the embodiments of the present disclosure. It should be understood by those skilled in the art that although Figure 1The ultrasonic detection device 1000 is shown with multiple devices, but the present disclosure may only involve some of the devices, for example, the ultrasonic detection device 1000 only involves the processor 1100, the memory 1200 and the probe handle 1700. The technicians can design instructions according to the scheme disclosed in the present disclosure. How the instructions control the processor to operate is well known in the art, so it will not be described in detail here.

[0053] <Method Example>

[0054] The present disclosure provides a method for evaluating a tissue state, which can be implemented by an ultrasonic detection device, and the ultrasonic detection device can be, for example, the aforementioned ultrasonic detection device 1000 .

[0055] Figure 2 The present invention is a flowchart of a method for evaluating tissue status according to an embodiment of the present disclosure.

[0056] like Figure 2 As shown, the method includes steps S2100 to S2400 as shown below:

[0057] Step S2100: acquiring a first ultrasonic echo signal of a target tissue.

[0058] In this embodiment, the target tissue may be any one of muscle, liver, kidney, pancreas, and blood vessel.

[0059] In one embodiment of the present disclosure, it is possible to transmit only an ultrasonic signal to the target tissue and receive an ultrasonic echo signal reflected by the target tissue, namely, a first ultrasonic echo signal.

[0060] In one embodiment of the present disclosure, acquiring a first ultrasonic echo signal of a target tissue includes: acquiring a first ultrasonic echo signal of the target tissue under different conditions; wherein the different conditions include when the target tissue is compressed by different pressures, or actively contracts or relaxes, or at different times.

[0061] In one embodiment of the present disclosure, obtaining a first ultrasonic echo signal of a target tissue includes steps S2110 to S2130 as shown below:

[0062] Step S2110, acquiring a second ultrasonic echo signal of at least one area to be measured.

[0063] In this embodiment, the ultrasonic detection device may be a parallel ultrasonic detection device, which may transmit and receive ultrasonic signals to at least one area to be detected in parallel through multiple channels to obtain a second ultrasonic echo signal.

[0064] Furthermore, an ultrasonic signal may be transmitted to at least one area to be measured, and a second ultrasonic echo signal reflected by the at least one area to be measured may be received.

[0065] Step S2120: determining a target area in the area to be measured according to the second ultrasonic echo signal.

[0066] In this embodiment, the target area is the area where the target tissue is located in the area to be tested.

[0067] In this embodiment, an ultrasonic image of at least one area to be measured can be generated according to the ultrasonic echo signal reflected by at least one area to be measured. The obtained ultrasonic image is not affected by the distortion caused by the conventional imaging of transmitting and receiving according to the scanning line, the pulse repetition frequency is high, and the time to obtain the target area is extremely short, not exceeding 100ms, which has the advantages of being fast and free of distortion artifacts. The obtained ultrasonic image is the average of the second ultrasonic echo signal obtained by a single transmission or multiple transmissions, and the average of multiple transmissions can improve the signal-to-noise ratio.

[0068] Furthermore, the scope of the target tissue in the area to be tested can be accurately defined as the target area based on the assistance of an image recognition algorithm or a machine learning model.

[0069] In one embodiment of the present disclosure, determining a target area in a test area based on a first ultrasound image may include: performing image preprocessing on the first ultrasound image; extracting feature values ​​of selected features in the first ultrasound image using an image processing algorithm; and classifying areas in the first ultrasound image based on a classification algorithm according to the feature values ​​of the selected features in the first ultrasound image to obtain the target area.

[0070] Specifically, the preprocessing may include denoising, enhancement, smoothing and other processing to improve the quality of the first ultrasound image and facilitate subsequent feature extraction and classification.

[0071] Furthermore, the image processing algorithm may be, for example, any one or more of an edge detection algorithm, a corner point detection algorithm, and a texture analysis algorithm. The selected feature may be, for example, any one or more of a shape, a contour, and a texture.

[0072] Furthermore, the classification algorithm may be, for example, any one or more of a support vector machine, a decision tree, and a neural network.

[0073] Step S2130: transmitting an ultrasonic signal to the target area, and receiving an ultrasonic echo signal reflected by the target area as a first ultrasonic echo signal.

[0074] In one embodiment, the ultrasonic signal may be transmitted only to the target area, and the received ultrasonic echo signal may be used as the first ultrasonic echo signal of the target tissue.

[0075] In another embodiment, an ultrasonic signal may be emitted to at least one area to be measured, and an ultrasonic echo signal reflected by at least one area to be measured is received, and a first ultrasonic echo signal of the target tissue is extracted from the received ultrasonic echo signal according to a sampling frame corresponding to the target area.

[0076] Step S2200: determining a first parameter value of at least one target ultrasound quantitative parameter according to the first ultrasound echo signal, where the target ultrasound quantitative parameter is an ultrasound quantitative parameter related to the tissue state.

[0077] In this embodiment, the characterization method of the normal or abnormal state of the target tissue includes the risk level of at least one of sarcopenia, tissue fattening degree, liver inflammation, portal hypertension, renal failure, pancreatic cancer, fatty pancreas, articular cartilage damage, local muscle damage, liver fibrosis, and cirrhosis.

[0078] Furthermore, the target tissue is a tissue associated with at least one of the characterized sarcopenia, degree of tissue fattening, liver inflammation, portal hypertension, renal failure, pancreatic cancer, fatty pancreas, articular cartilage damage, local muscle damage, liver fibrosis, and cirrhosis.

[0079] In a case where the way to characterize the normal or abnormal state of the target tissue includes the risk level of at least one of sarcopenia, muscle fattening, and local muscle damage, the target tissue is muscle; in a case where the way to characterize the normal or abnormal state of the target tissue includes the risk level of at least one of liver inflammation, liver fibrosis, and liver cirrhosis, the target tissue is liver; in a case where the way to characterize the normal or abnormal state of the target tissue includes the risk level of at least one of pancreatic cancer and fatty pancreas, the target tissue is pancreas; in a case where the way to characterize the normal or abnormal state of the target tissue includes the risk level of renal failure, the target tissue is kidney.

[0080] Further, when the characterization method of the normal or abnormal state of the target tissue includes the risk level of the target disease being sarcopenia, the target tissue may be a forearm muscle, specifically, the superficial digital flexor and / or extensor muscle of the forearm muscle.

[0081] In one embodiment of the present disclosure, at least one target ultrasound quantitative parameter includes at least one of tissue thickness, ultrasound scattering parameter, nonlinear parameter, attenuation parameter, texture parameter, motion parameter, and elastic parameter; the ultrasound scattering parameter includes at least one of a standardized mean intensity parameter, a scattering peak value, a scatterer density, and a scatterer distribution characteristic; the nonlinear characteristic parameter includes at least one of a normalized nonlinear parameter, an ultrasound nonlinear coefficient, a second harmonic amplitude, phase matching, a non-zero energy flow, and a high-order elastic constant; the motion parameter includes at least one of a displacement and a strain; and the elastic parameter includes a parameter used to characterize an elastic coefficient and / or a viscosity coefficient.

[0082] Furthermore, the motion parameters specifically refer to changes in displacement, strain, etc. of the target tissue caused by force (external pressure or active contraction and relaxation).

[0083] Studies have shown that the L3 pyramidal plane skeletal muscle area is the most commonly used site for assessing overall muscle condition, but ultrasound cannot be used to measure the area of ​​all skeletal muscles within the lumbar plane due to limited field of view. Therefore, the forearm muscles, upper arm muscles, thigh muscles, and calf muscle groups are the most commonly used areas for ultrasound assessment of muscle status, but there is currently no recognized optimal measurement site that can reflect overall muscle condition. Considering the moderate to high effectiveness of muscle thickness at each location in diagnosing sarcopenia and the ultrasound imaging effect, the forearm muscles were finally selected as the target muscle tissue for ultrasound assessment because the forearm muscles are more superficial and have high-quality imaging, making them suitable for diagnosing muscle atrophy. Due to the different functions of flexors and extensors, the order of atrophy is also different. Therefore, the superficial flexor digitorum (FDS) and extensor digitorum (ED) of the forearm muscles can be selected to represent forearm flexion and extension, respectively, for assessing low muscle content and low muscle quality. In addition, the volume under muscle contraction is more strongly correlated with the muscle contraction potential.

[0084] In one embodiment of the present disclosure, the superficial digital flexors and extensors of the forearm muscles may be selected as target tissues to assess the state of the muscles.

[0085] In this embodiment, the subject can be placed in a supine position with the palm facing upward, and continuous short-axis scanning is performed on the flexor muscle on the side of the forearm to ensure that the forearm muscle is not compressed, so as to obtain the first ultrasonic echo signal of the superficial digital flexor muscle in the relaxed state of the forearm muscle. The subject can be placed in a supine position with the palm facing upward, and then the subject is instructed to clench their fist with maximum force to obtain the first ultrasonic echo signal of the superficial digital flexor muscle in the contracted state of the forearm muscle. The subject can be placed in a supine position with the palm facing downward to continuously scan the extensor muscle to obtain the first ultrasonic echo signal of the extensor muscle in the relaxed state of the forearm muscle. The subject can be placed in a supine position with the palm facing downward, and then the subject is instructed to lift the finger with maximum force to obtain the first ultrasonic echo signal of the extensor muscle in the contracted state of the forearm muscle.

[0086] In an embodiment where the target ultrasonic quantitative parameter includes tissue thickness, determining a first parameter value of at least one target ultrasonic quantitative parameter based on a first ultrasonic echo signal may include: determining a reception time of the first ultrasonic echo signal corresponding to a boundary of the target tissue based on a parameter value of the target characteristic parameter of the first ultrasonic echo signal and a first threshold value of the target characteristic parameter corresponding to the target tissue; and determining a thickness value of the tissue thickness of the target tissue based on the reception time of the first ultrasonic echo signal corresponding to the boundary of the target tissue.

[0087] The target characteristic parameters include reflection characteristic parameters and / or scattering characteristic parameters. The reflection characteristic parameters include reflection values ​​and / or reflection value distribution parameters. The scattering characteristic parameters include at least one of scattering peak value, scatterer density, and scatterer distribution characteristics.

[0088] In this embodiment, the tissue thickness of the target tissue is an effective indicator for evaluating tissue quality. As age increases, tissue gradually shrinks, resulting in a decrease in the tissue thickness of the target tissue. Therefore, by measuring the tissue thickness of the target tissue, the quality of the target tissue can be intuitively understood. In the state assessment of the target tissue, when the tissue thickness of the target tissue is lower than the corresponding normal range, it may indicate that the state of the target tissue is abnormal.

[0089] Since each tissue has different reflection or transmission characteristics of ultrasound, the strong fascia reflection signals on the upper and lower surfaces of the target tissue can be identified based on the target characteristic parameters of the first ultrasonic echo signal, and the muscle thickness can be calculated based on the reception time difference of the strong fascia reflection signals on the upper and lower surfaces of the muscle.

[0090] In an embodiment where the target tissue is muscle, the tissue thickness of the target tissue may include at least one of: the tissue thickness of the superficial digital flexor muscle in a contracted state of the forearm muscle, the tissue thickness of the extensor muscle in a contracted state of the forearm muscle, the tissue thickness of the superficial digital flexor muscle in a relaxed state of the forearm muscle, and the tissue thickness of the extensor muscle in a relaxed state of the forearm muscle. Ultrasonic propagation is a nonlinear process, and the impact of nonlinear effects cannot be ignored in clinical diagnosis. The fundamental wave image of traditional B-mode ultrasound examination lacks a comprehensive description of biological tissues and cannot reflect the nonlinear changes of ultrasonic waves during propagation in the human body, thereby affecting the accuracy of the diagnostic results. Ultrasonic nonlinear parameters are parameters used to describe the nonlinear effects generated when ultrasonic waves propagate in a medium.

[0091] The nonlinear parameter is a parameter corresponding to the nonlinear effect generated by the ultrasonic signal propagating in the tissue to be tested. In some embodiments, the nonlinear parameter is determined based on the corresponding relationship between the second harmonic and the nonlinear parameter when the ultrasonic signal propagates in the tissue to be tested, and the attenuation coefficient of the ultrasonic signal when propagating in the tissue to be tested.

[0092] The mathematical relationship between the second harmonic and the nonlinear parameters is as follows:

[0093]

[0094] Among them, β represents the nonlinear parameter, ρ 0 represents the density of the target tissue, p 2 (x) represents the amplitude of the second harmonic in the first ultrasonic echo signal, p 0 represents the amplitude of the first ultrasonic echo signal at the target tissue, c 0 represents the speed at which the first ultrasonic echo signal propagates in the target tissue, f represents the frequency of the first ultrasonic echo signal, and x represents the distance the first ultrasonic echo signal propagates. When ultrasonic waves propagate in the tissue to be measured, it is necessary to consider the attenuation of ultrasonic waves in the tissue to be measured, and make corresponding compensation based on the attenuation to improve the accuracy of nonlinear parameter determination. Combining the above mathematical relationship and the attenuation coefficient of the ultrasonic signal when propagating in the tissue to be measured, the nonlinear parameter β is obtained based on the following calculation formula:

[0095]

[0096] Among them, α 1 represents the attenuation coefficient of the fundamental wave in the first ultrasonic echo signal, α 2 represents the attenuation coefficient of the second harmonic in the first ultrasonic echo signal. When x approaches 0 Substitute the value of into the above calculation formula. When x approaches 0 The value of is determined by determining the second harmonic amplitude at different propagation distances and plotting The curve of x, and through linear deduction, it is obtained that when x approaches 0 The value of .

[0097] Ultrasonic scattering parameters can be used to evaluate the scattering characteristics of tissues. They describe the parameters of the scattering phenomenon when ultrasound encounters stray particles or interfaces in the medium. Ultrasonic scattering parameters can characterize the energy distribution of incident ultrasound in all directions after scattering.

[0098] The scattering distribution parameter may include at least one of a K distribution and a Nakagami distribution. In this embodiment, the Nakagami distribution statistical model is used to image the ultrasonic echo signal. The generated Nakagami image is an m parameter mapping diagram of the model, which is a shape parameter used to describe the statistical distribution of the backscatter signal envelope. The change of m from 0 to 1 indicates the change of the signal envelope statistical distribution from the "front Rayleigh distribution" (generally K distribution) to the Rayleigh distribution. If it is greater than 1, it means that it obeys the "back Rayleigh distribution" (generally Rician distribution).

[0099] The probability density function of the ultrasonic backscatter signal envelope R in the Nakagami statistical model can be expressed as:

[0100]

[0101] Where Γ(·) represents the gamma function, U(·) represents the unit step function, r represents a specific horizontal coordinate value of the function, f(r) represents the numerical value of the scatterer distribution characteristic, Ω represents the scale parameter related to the Nakagami distribution, and m represents the Nakagami parameter.

[0102] Furthermore, the scale parameter Ω associated with the Nakagami distribution can be calculated by the following formula:

[0103] Ω=E(R 2 )

[0104] Furthermore, the Nakagami parameter m can be calculated by the following formula:

[0105]

[0106] Among them, E(R 2 ) represents the mean square value of the variable r.

[0107] In one embodiment of the present disclosure, determining a first parameter value of at least one target ultrasound quantitative parameter includes: performing signal reconstruction processing on a first ultrasound echo signal; performing signal analysis processing on the reconstructed first ultrasound echo signal to obtain the first parameter value of the target ultrasound quantitative parameter, wherein the signal analysis includes at least one of time domain analysis, frequency domain analysis, and time-frequency analysis.

[0108] In this embodiment, the first ultrasonic echo signal may be reconstructed using a signal processing technique such as Fourier transform, wavelet transform or sparse representation.

[0109] The signal reconstruction process includes signal denoising, signal enhancement, feature extraction and other processing.

[0110] This embodiment can restore the characteristics of the original signal through the signal reconstruction process, improve the signal quality, and provide a basis for subsequent analysis.

[0111] In this embodiment, the reconstructed first ultrasonic echo signal can be subjected to multi-dimensional signal analysis processing, including at least one of time domain analysis (such as waveform analysis, statistical analysis), frequency domain analysis (such as spectrum analysis, power spectrum analysis) and time-frequency analysis (such as short-time Fourier transform, wavelet transform).

[0112] By performing signal analysis on the reconstructed first ultrasonic echo signal, key feature information of the first ultrasonic echo signal can be extracted, such as frequency, amplitude, phase, energy, etc. The feature extraction process may involve steps such as feature selection and feature dimension reduction.

[0113] In one embodiment of the present disclosure, in an embodiment where the target ultrasound quantitative parameter includes a texture parameter, determining a first parameter value of at least one target ultrasound quantitative parameter according to the first ultrasound echo signal may include: Figure 3 Steps S3100 to S3500 shown:

[0114] Step S3100: acquiring a first ultrasonic image of the area to be tested according to the first ultrasonic echo signal, and acquiring mask data identifying the position of the target tissue in the area to be tested.

[0115] In this embodiment, the ultrasonic detection device can be a parallel ultrasonic detection device, which can transmit and receive ultrasonic signals in parallel through multiple channels. The first ultrasonic image obtained is not affected by the distortion caused by the traditional imaging of transmitting and receiving according to the scanning line, the pulse repetition frequency is high, and the time to obtain the target area is extremely short, not exceeding 100ms, which has the advantages of being fast and free of distortion artifacts. The first ultrasonic image obtained is the average of a single transmission or multiple transmissions, and the average of multiple transmissions can improve the signal-to-noise ratio.

[0116] Furthermore, an ultrasonic signal may be emitted to at least one area to be tested, and an ultrasonic echo signal reflected by at least one area to be tested may be received, and a first ultrasonic image may be generated based on the ultrasonic echo signal reflected by at least one area to be tested, wherein the target tissue is located within at least one area to be tested.

[0117] This embodiment can improve the speed and efficiency of data acquisition by introducing a method of parallel transmission and reception of ultrasonic signals, thereby improving the efficiency of tissue texture analysis. In addition, the parallel ultrasonic detection equipment adopts intelligent frequency allocation and management algorithms, high-precision synchronization and calibration technology, which can ensure the accuracy and stability of data acquisition, provide a solid foundation for signal reconstruction, analysis and model training, and further improve the overall performance of the signal analysis and model training system.

[0118] The first ultrasonic image acquired in this embodiment may be an ultrasonic image including all tissues in the area to be tested.

[0119] In this embodiment, the mask data may be determined based on a pre-acquired second ultrasound image of the region to be measured of a reference human body.

[0120] Furthermore, it may be possible to use image recognition algorithms or machine learning models as an aid to accurately define the scope of the target tissue in the area to be tested as mask data.

[0121] In one embodiment of the present disclosure, the mask data may be acquired in advance by manual outlining, semi-automatic segmentation, or fully automatic segmentation.

[0122] In another embodiment of the present disclosure, obtaining mask data that identifies the position of the target tissue in the area to be tested may include: performing image preprocessing on the second ultrasound image; using an image processing algorithm to extract feature values ​​of selected features in the second ultrasound image; and classifying the area in the second ultrasound image based on a classification algorithm according to the feature values ​​of the selected features in the second ultrasound image to obtain the target area as the mask data.

[0123] Specifically, the preprocessing may include denoising, enhancement, smoothing and other processing to improve the quality of the first ultrasound image and facilitate subsequent feature extraction and classification.

[0124] Furthermore, the image processing algorithm may be, for example, any one or more of an edge detection algorithm, a corner point detection algorithm, and a texture analysis algorithm. The selected feature may be, for example, any one or more of a shape, a contour, and a texture.

[0125] Furthermore, the classification algorithm may be, for example, any one or more of a support vector machine, a decision tree, and a neural network.

[0126] Step S3200: segment the first ultrasound image into multiple image blocks.

[0127] In one embodiment, the first ultrasound image may be segmented into a plurality of image blocks of the same size based on a set size by using an image scaling method, and the size of each image block is the set size.

[0128] Specifically, the set size can be set according to the target tissue, the resolution of the ultrasonic detection equipment and the specific analysis requirements. For example, the set size can be 20 pixels * 20 pixels. In this way, the interference of invalid data can be reduced and the accuracy of the texture analysis results can be improved.

[0129] In another embodiment, the first ultrasound image may be segmented into a set number of image blocks based on a set number by using an image scaling method.

[0130] Specifically, the set number can be set according to the target tissue, the resolution of the ultrasonic detection equipment and the specific analysis requirements. For example, the set number can be 10*20.

[0131] Step S3300, obtaining the parameter value of the texture parameter corresponding to each image block according to the grayscale information of the pixel points in each image block.

[0132] In this embodiment, the texture parameter includes at least one of mean, variance, energy, entropy, contrast, correlation and homogeneity.

[0133] In this embodiment, the parameter value of the texture parameter corresponding to each image block may be calculated using a gray level co-occurrence matrix method.

[0134] In the embodiment where the texture parameter includes a mean value, the parameter value of the texture parameter corresponding to the image block may be determined by the following formula:

[0135]

[0136] Among them, μ represents the mean, N represents the size of the image block, and P ij Represents the grayscale information of the pixel in the i-th row and j-th column of an image block.

[0137] In an embodiment where the texture parameter includes variance, the parameter value of the texture parameter corresponding to the image block may be determined by the following formula:

[0138]

[0139] Among them, σ 2 represents the variance, N represents the size of the image block P ij It represents the grayscale information of the pixel in the i-th row and j-th column in an image block, and μ represents the mean.

[0140] In an embodiment where the texture parameter includes energy, the parameter value of the texture parameter corresponding to the image block may be determined by the following formula:

[0141]

[0142] Among them, Energy represents energy, P ij Represents the grayscale information of the pixel in the i-th row and j-th column in an image block, and N represents the size of the image block.

[0143] In an embodiment where the texture parameter includes entropy, the parameter value of the texture parameter corresponding to the image block may be determined by the following formula:

[0144]

[0145] Among them, Entropy represents entropy, P ij Represents the grayscale information of the pixel in the i-th row and j-th column in an image block, and N represents the size of the image block.

[0146] In an embodiment where the texture parameter includes contrast, the parameter value of the texture parameter corresponding to the image block may be determined by the following formula:

[0147]

[0148] Among them, Contrast represents contrast, P ij Represents the grayscale information of the pixel in the i-th row and j-th column in an image block, and N represents the size of the image block.

[0149] In an embodiment where the texture parameter includes correlation, the parameter value of the texture parameter corresponding to the image block may be determined by the following formula:

[0150]

[0151] Among them, Correlation represents correlation, P ij represents the grayscale information of the pixel in the i-th row and j-th column of an image block, N represents the size of the image block, μ represents the mean, σ 2 Represents variance.

[0152] In an embodiment where the texture parameter includes homogeneity, the parameter value of the texture parameter corresponding to the image block may be determined by the following formula:

[0153]

[0154] Among them, Homogeneity means homogeneity, P ij Represents the grayscale information of the pixel in the i-th row and j-th column in an image block, and N represents the size of the image block.

[0155] These texture parameters can comprehensively describe the texture characteristics of the target tissue in multiple dimensions, such as thickness, depth, uniformity, and complexity.

[0156] When calculating the gray-level co-occurrence matrix, it is also necessary to select appropriate distance and direction parameters according to the characteristics of clinical symptoms to reflect the different characteristics of the texture of the target tissue.

[0157] Step S3400 , performing splicing processing on the multiple image blocks according to parameter values ​​of texture parameters corresponding to the multiple image blocks to obtain a first spliced ​​image.

[0158] After processing each small block, the results are stitched together into an image of the original size for subsequent analysis. This method can reduce computational complexity and improve processing efficiency.

[0159] When stitching images, bilinear interpolation or other interpolation methods can also be used to interpolate multiple image blocks, such as nearest neighbor interpolation, bicubic interpolation, etc., to ensure the smoothness and continuity of the image. This helps to reduce artifacts and distortion caused by image segmentation and stitching.

[0160] The size of the first stitched image is the same as the size of the first ultrasound image.

[0161] In this embodiment, each pixel in the first stitched image has a parameter value corresponding to each texture parameter.

[0162] In the case where the texture parameters include multiple ones of mean, variance, energy, entropy, contrast, correlation and homogeneity, the parameter value of the texture parameter corresponding to each pixel point in the first stitched image can be obtained for each texture parameter separately according to the parameter values ​​of the texture parameter corresponding to multiple image blocks.

[0163] Step S3500, obtaining the parameter value of the texture parameter corresponding to the target tissue according to the mask data and the parameter value of the texture parameter corresponding to the pixel point in the first spliced ​​image.

[0164] In the case where the texture parameters include multiple ones of mean, variance, energy, entropy, contrast, correlation and homogeneity, the parameter value of the target tissue corresponding to the texture parameter can be obtained for each texture parameter separately according to the parameter value of the texture parameter corresponding to each pixel point in the mask data and the first stitched image.

[0165] In one embodiment of the present disclosure, obtaining the parameter value of the texture parameter corresponding to the target tissue according to the mask data and the parameter value of the pixel point in the first stitched image includes the following steps S3510 to S3530:

[0166] Step S3510: extracting a target image region representing a target tissue in the first spliced ​​image according to the mask data.

[0167] In this embodiment, the target image region extracted according to the mask data may be an image region representing the target tissue in the first stitched image.

[0168] Step S3520: determining a first statistical value of a parameter value of a texture parameter corresponding to each pixel point in the target image region.

[0169] In one embodiment of the present disclosure, the first statistical value is at least one of a maximum value, a minimum value, a mean value, and a median value.

[0170] In this embodiment, the first statistical value is used to determine the significant difference of the first ultrasound image.

[0171] Step S3530, obtaining a parameter value of the texture parameter corresponding to the target tissue according to the first statistical value of the texture parameter.

[0172] In this embodiment, for each texture parameter, the first statistical value corresponding to the texture parameter may be used as the parameter value of the target tissue corresponding to the texture parameter.

[0173] In one embodiment of the present disclosure, obtaining the parameter value of the texture parameter corresponding to the target tissue according to the first statistical value of the corresponding texture parameter may also include: determining the second statistical value of the texture parameter corresponding to the pixel point in the target image area; and obtaining the parameter value of the texture parameter corresponding to the target tissue according to the first statistical value only when the second statistical value meets the preset condition.

[0174] In one embodiment of the present disclosure, the second statistical value includes at least one of a variance, a lower quartile, and an upper quartile.

[0175] In this embodiment, the second statistical value corresponding to the texture parameter can be used to assist in determining the stability of the parameter value of the texture parameter corresponding to the target tissue.

[0176] In this embodiment, a corresponding qualified range may be pre-set for each texture parameter, and the qualified ranges corresponding to different texture parameters may be the same or different, which is not limited here.

[0177] When the second statistical values ​​corresponding to all texture parameters are within the corresponding qualified range, it can be determined that the second statistical value meets the preset conditions; when the second statistical value corresponding to any texture parameter exceeds the corresponding qualified range, it can be determined that the second statistical value does not meet the preset conditions.

[0178] When the second statistical value does not meet the preset condition, a prompt message may be outputted to reacquire the first ultrasonic image of the target tissue to evaluate the state of the target tissue based on texture analysis; or a prompt message may be outputted that the state evaluation result of the target tissue cannot be obtained. The prompt message may be sound information and / or text information.

[0179] Through the embodiment of the present disclosure, the first ultrasound image of the area to be tested is divided into multiple image blocks, and the parameter value of the texture parameter corresponding to each image block is obtained according to the grayscale information of each pixel in each image block, and then the multiple image blocks are spliced ​​according to the parameter values ​​of the texture parameters corresponding to the multiple image blocks to obtain a first spliced ​​image, and the parameter value of the texture parameter corresponding to the pixel in the first spliced ​​image and the mask data identifying the position of the target tissue in the area to be tested are obtained. In this way, the accuracy and reliability of the texture analysis results of the target tissue can be improved.

[0180] Step S2300: Based on the tissue state prediction model and according to the first parameter value of at least one target ultrasound quantitative parameter, a first index value of a target evaluation index is obtained.

[0181] Among them, the target evaluation index at least includes an index characterizing whether the state of the target tissue is normal or abnormal.

[0182] In one embodiment of the present disclosure, when the characterization of the normal or abnormal state of the target tissue includes the risk level of sarcopenia, the target evaluation indicator includes at least one of grip strength, low skeletal muscle index, and low average skeletal muscle density.

[0183] Through the embodiments of the present disclosure, a first parameter value of at least one target ultrasound quantitative parameter is determined according to a first ultrasound echo signal of the target tissue, and based on a tissue state prediction model, a first indicator value of a target evaluation index is obtained according to the first parameter value of at least one target ultrasound quantitative parameter; according to the first indicator value of the target evaluation index, a state evaluation result of the target tissue is obtained, which can provide strong support for the evaluation of the tissue state of the target tissue through the technical advantages of ultrasound technology such as quantitative, objective, and non-invasive.

[0184] In one embodiment of the present disclosure, the method may further include: acquiring multiple set ultrasound quantitative parameters; obtaining multiple parameter combinations based on the multiple ultrasound quantitative parameters, each parameter combination including at least one ultrasound quantitative parameter; determining the correlation between each parameter combination and the target evaluation index; selecting one or more groups of parameter combinations based on the correlation, the correlation of the selected parameter combination should be at least better than the correlation of a group of parameter combinations that are not selected, or the selected parameter combination is the one with the highest correlation among all parameter combinations; determining the target ultrasound quantitative parameters based on the selected one or more groups of parameter combinations.

[0185] When the characterization method of normal or abnormal target tissue state includes the risk degree of sarcopenia, the multiple ultrasound quantitative parameters set may include the tissue thickness of the superficial flexor digitorum in the forearm muscle contraction state, the tissue thickness of the extensor digitorum in the forearm muscle contraction state, the tissue thickness of the superficial flexor digitorum in the forearm muscle relaxation state, the tissue thickness of the extensor digitorum in the forearm muscle relaxation state, the normalized nonlinear parameter of the superficial flexor digitorum in the forearm muscle contraction state, the normalized nonlinear parameter of the extensor digitorum in the forearm muscle contraction state, the average strength parameter of the superficial flexor digitorum in the forearm muscle contraction state, the average strength parameter of the extensor digitorum in the forearm muscle contraction state, the normalized nonlinear parameter of the superficial flexor digitorum in the forearm muscle relaxation state, the normalized nonlinear parameter of the extensor digitorum in the forearm muscle relaxation state, the average strength parameter of the superficial flexor digitorum in the forearm muscle relaxation state, and the average strength parameter of the extensor digitorum in the forearm muscle relaxation state.

[0186] In the present embodiment, the continuous variables meeting the normal distribution are described as mean ± standard deviation, and t-test is used to assess the difference between groups.For other continuous variables, median (25th percentile to 75th percentile) is used, and in the case of non-normal distribution continuous variables, Mann-Whitney U test (Mann-Whitney UTest) is applied to compare between groups. Chi-square test or Fisher probability comparison ratio is used. Model is generated using regression coefficient to identify low grip strength, low SMI, low SMD, and area under receiver operating curve (AUROC) is reported. Binary logistic regression analysis determines the independent factors of bone marrow suppression. P value is <0.05 for indicating the statistical significance of bilateral test.

[0187] When evaluating ultrasound quantitative parameters for correlation with grip strength, a hydraulic hand dynamometer can be used as a standard way to clinically evaluate hand grip strength (HGS). When measured in the non-dominant hand, the maximum value of the three times can be selected and recorded as the HGS. As shown in Table 1, the correlation between tissue thickness, normalized nonlinear parameter (MusQBOX.NLP), and normalized mean intensity (MusQBOX.NMI) of the superficial digital flexors and extensors was evaluated under muscle contraction and relaxation. It can be seen that the tissue thickness of the superficial digital flexors has the highest correlation with grip strength (relaxed state: r = 0.836, contracted state: r = 0.825), while the tissue thickness of the extensors has a lower correlation with grip strength (relaxed state: r = 0.689, contracted state: r = 0.724). The correlation between normalized nonlinear parameter or normalized mean intensity and grip strength is weak (see Table 1). Regardless of the muscle contraction state, the tissue thickness of the superficial digital flexors and extensors is highly correlated with grip strength (r = 0.733-0.814). Compared with forearm thickness measured using ultrasound, tissue thickness of the superficial digital flexors alone correlated better with grip strength (r = 0.825-0.836). These studies highlight the importance of muscle thickness as a reliable indicator of muscle strength, particularly in lymphoma patients receiving chemotherapy.

[0188] In Table 1, r is the correlation coefficient; P is the confidence interval of statistical significance, and P < 0.05 is considered statistically significant.

[0189]

[0190]

[0191] Table 1

[0192] When evaluating the ultrasound quantitative parameters associated with low SMI and low SMD, CT was used as the standard clinical method for measuring SMI and SMD. As shown in Tables 2 and 3, a binary logistic regression model for the prediction of low SMI and low SMD was established. In the relaxed state of forearm muscles, MT and MusQBOX.NLP of superficial digital flexors were associated with low SMI (odds ratio (OR) for tissue thickness was 0.470, 95% CI (CI) 0.328-0.672, P < 0.001; OR for MusQBOX.NLP was 2.133, 95% CI 1.490-3.054, P < 0.001), and the correlation between MusQBOX.NLP of superficial digital flexors and MusQBOX.NMI of extensors and low SMD was A132.024, 95% CI 1.474-2.780, P < 0.001; OR was A581.045, 95% CI 1.005-1.086, P = 0.026) (as shown in Table 2). In the forearm muscle contraction state, MT and MusQBOX.NLP of the superficial digital flexors and MusQBOX.NLP of the extensors were associated with low SMI (OR for MT was 0.512, 95% CI 0.367-0.716, P < 0.001; OR for MusQBOX.NLP in the superficial digital flexors was 1.302, 95% CI 1.008-1.680, P = 0.043; OR for MusQBOX.NLP in the superficial digital flexors was 1.302, 95% CI 1.008-1.680, P = 0.043). BOX.NLP was 1.490, 95%CI 1.190-1.866, P=0.001), and MusQBOX.NLP of superficial digital flexors and MT of extensors were associated with low SMD (OR of MusQBOX.NLP 1.466, 95%CI 0.907-1.042, P=0.005; OR of MT was 0.675, 95%CI 0.488-0.935, P=0.018).

[0193]

[0194]

[0195] Table 2

[0196]

[0197] Table 3

[0198] The model was established using EI and muscle thickness. The combination of tissue thickness and EI was predictive of sarcopenia. The results showed that muscle thickness, normalized nonlinear parameter, and normalized mean strength were independent predictors of low SMI and low SMD, presenting higher AUCs (area under the curve) to predict low SMI (AUC: contraction 0.874, relaxation 0.886, P = 0.604) and low SMD (AUC: contraction 0.768, relaxation 0.825, P = 0.030). Moreover, although measuring quantitative ultrasound parameters after muscle contraction did not improve the predictive ability, combining parameters could produce higher AUC values ​​for diagnosing low SMI and low SMD. The selection and combined use of specific parameters emphasize the potential of quantitative ultrasound parameters in accurately assessing the muscle status of patients with lymphoma.

[0199] Regarding the evaluation of independent factors of chemotherapy toxicity, as shown in Table 4, binary logistic regression analysis found that tissue thickness, normalized nonlinear parameter, and normalized mean intensity of superficial digital flexor muscles were important independent risk factors for hematological toxicity. High tissue thickness was an inhibitor of chemotherapy toxicity, and normalized nonlinear parameter and normalized mean intensity were important promoters of chemotherapy toxicity (OR value of tissue thickness was 0.655, 95% CI 0.491-0.894, P = 0.008; OR value of normalized nonlinear parameter was 2.494, 95% CI 1.731-3.593, P < 0.001; OR value of normalized mean intensity was 0.944, 95% CI 0.904-0.986, P = 0.010).

[0200]

[0201] Table 4

[0202] This embodiment collects ultrasonic echo signals of forearm muscles in relaxed and contracted states, and extracts ultrasonic quantitative parameters including tissue thickness, normalized nonlinear parameters, and normalized mean intensity. Correlation analysis shows that among these quantitative ultrasonic quantitative parameters, only tissue thickness is closely related to muscle strength. Ultrasonic scattering parameters and attenuation parameters can be used to predict low SMI and low SMD, and a higher AUC is obtained. In addition, it is also confirmed that quantitative ultrasonic quantitative parameters are independent imaging factors for bone marrow suppression in lymphoma patients after chemotherapy.

[0203] In one embodiment of the present disclosure, when the target evaluation index includes grip strength, the target ultrasonic quantitative parameter includes the tissue thickness of the superficial digital flexor. When the target evaluation index includes a low skeletal muscle index, the target ultrasonic quantitative parameter includes at least one of the thickness of the superficial digital flexor in the forearm muscle contraction state, the normalized nonlinear parameter of the superficial digital flexor in the forearm muscle contraction state, the normalized nonlinear parameter of the extensor in the forearm muscle contraction state, the thickness of the superficial digital flexor in the forearm muscle relaxation state, and the normalized nonlinear parameter of the superficial digital flexor in the forearm muscle relaxation state. When the target evaluation index includes low skeletal muscle average density, the target ultrasonic quantitative parameter includes at least one of the thickness of the extensor in the forearm muscle contraction state, the normalized nonlinear parameter of the superficial digital flexor in the forearm muscle contraction state, the normalized nonlinear parameter of the superficial digital flexor in the forearm muscle relaxation state, and the average strength parameter of the extensor in the forearm muscle relaxation state.

[0204] In one embodiment of the present disclosure, when the target evaluation index includes low average skeletal muscle density, the target ultrasonic quantitative parameter includes at least one of the normalized nonlinear parameter of the superficial digital flexor muscle in the relaxed state of the forearm muscle and the average strength parameter of the extensor muscle in the relaxed state of the forearm muscle.

[0205] In one embodiment of the present disclosure, when the target evaluation index includes chemotherapy toxicity, the target ultrasound quantitative parameter includes at least one of the tissue thickness, normalized nonlinear parameter and mean intensity parameter of the superficial digital flexor muscle.

[0206] In one embodiment of the present disclosure, the method also includes: acquiring a training sample set, each training sample in the training sample set includes a second parameter value of at least one target ultrasound quantitative parameter, and a second index value of a target evaluation index, wherein the second parameter value is determined based on a third ultrasound echo signal of a target tissue corresponding to the training sample, and the second index value is determined based on an actual tissue state of the target tissue corresponding to the training sample; and training a tissue state prediction model based on the training sample set.

[0207] In this embodiment, the method for determining the second parameter value of at least one target ultrasonic quantitative parameter according to the second ultrasonic echo signal can specifically refer to the method for determining the first parameter value of at least one target ultrasonic quantitative parameter according to the first ultrasonic echo signal in the aforementioned embodiment, and will not be repeated here.

[0208] In the case where the target ultrasound quantitative parameter includes a texture parameter, the method of obtaining the parameter value of the texture parameter corresponding to the training sample may include: obtaining a second ultrasound image of the area to be tested and mask data identifying the position of the target tissue in the area to be tested; dividing the second ultrasound image into multiple image blocks; obtaining the parameter value of the texture parameter corresponding to each image block according to the grayscale information of the pixel points in each image block; splicing the multiple image blocks according to the parameter values ​​of the texture parameters corresponding to the multiple image blocks to obtain a second spliced ​​image; extracting the target image area representing the target tissue in the second spliced ​​image according to the mask data; determining the first statistical value of the parameter value of the texture parameter corresponding to the pixel points in the target image area; and obtaining the parameter value of the texture parameter corresponding to the target tissue according to the first statistical value of the corresponding texture parameter. For details, please refer to the aforementioned steps S3100 to S3500.

[0209] Furthermore, the method further includes steps S3600 to S3800 as shown below:

[0210] Step S3600: determining a second statistical value of a parameter value of a texture parameter corresponding to each pixel point in the target image region.

[0211] In one embodiment of the present disclosure, the second statistical value includes at least one of a variance, a lower quartile, and an upper quartile.

[0212] In this embodiment, the second statistical value corresponding to the texture parameter can be used to assist in determining the stability of the parameter value of the texture parameter corresponding to the target tissue.

[0213] Step S3700: determining whether the texture parameter corresponding to the training sample meets a preset condition according to the second statistical value of the texture parameter.

[0214] In this embodiment, a corresponding qualified range may be pre-set for each texture parameter, and the qualified ranges corresponding to different texture parameters may be the same or different, which is not limited here.

[0215] When the second statistical values ​​corresponding to all texture parameters are within the corresponding qualified range, it can be determined that the texture parameters corresponding to the training sample meet the preset conditions; when the second statistical value corresponding to any texture parameter exceeds the corresponding qualified range, it can be determined that the texture parameters corresponding to the training sample do not meet the preset conditions.

[0216] Step S3800: Use the training samples in the training sample set that meet the preset conditions to train the tissue state prediction model.

[0217] Through this embodiment, the training samples used for training the tissue state prediction model in the training sample set are screened according to the second statistical value of the corresponding texture parameter, so as to ensure the validity and accuracy of the tissue state prediction model obtained through training.

[0218] Based on the training sample set, the parameters of the tissue state prediction model, such as the learning rate and regularization coefficient, are optimized to implement iterative training of the tissue state prediction model, which can improve the generalization ability and prediction accuracy of the tissue state prediction model. This process may involve steps such as cross-validation and hyperparameter tuning.

[0219] In this embodiment, by iteratively training the tissue state prediction model, a cut-off value (cut off value) of each target evaluation indicator can also be obtained.

[0220] Step S2400, obtaining a status assessment result of a target organization according to a first indicator value of a target assessment indicator.

[0221] In this embodiment, the state evaluation result of the target tissue may include the first indicator value of the target evaluation indicator and the corresponding cutoff value, may also include the comparison result of the first indicator value of the target evaluation indicator and the corresponding cutoff value, and may also include the normal or abnormal detection result of the target tissue. The normal or abnormal detection result of the target tissue may be determined based on the comparison result of the first indicator value of the target evaluation indicator and the corresponding cutoff value.

[0222] In one embodiment, the results of the tissue status assessment can be output in a clear and intuitive manner, including necessary explanations and descriptions. The output form may include charts, reports, visual interfaces, etc. This embodiment facilitates users to understand and apply the assessment results by providing a user-friendly interface or report. This process may involve steps such as result visualization and result interpretation.

[0223] Through the embodiments of the present disclosure, a first parameter value of at least one target ultrasound quantitative parameter is determined based on a first ultrasound echo signal of the target tissue, and a state assessment result of the target tissue is obtained based on the first parameter value of the at least one target ultrasound quantitative parameter. This can provide strong support for the state assessment of the target tissue through the quantitative, objective, non-invasive and other technical advantages of ultrasound technology.

[0224] Figure 4 The flowchart is an example of a method for evaluating tissue status according to an embodiment of the present disclosure.

[0225] like Figure 4 As shown, the method may include the following steps:

[0226] Step S4001, acquiring a second ultrasonic echo signal of at least one area to be measured.

[0227] Step S4002: determining a target area in the area to be measured according to the second ultrasonic echo signal.

[0228] Step S4003: transmitting an ultrasonic signal to the target area, and receiving an ultrasonic echo signal reflected by the target area as a first ultrasonic echo signal.

[0229] Step S4004: performing signal reconstruction processing on the first ultrasonic echo signal.

[0230] Step S4005: performing signal analysis processing on the reconstructed first ultrasound echo signal to obtain a first parameter value of a target ultrasound quantitative parameter.

[0231] The target ultrasound quantitative parameter is an ultrasound quantitative parameter related to the tissue state, and the signal analysis includes at least one of time domain analysis, frequency domain analysis and time-frequency analysis.

[0232] Step S4006: Based on the tissue state prediction model and according to a first parameter value of at least one target ultrasound quantitative parameter, a first index value of a target evaluation index is obtained.

[0233] Step S4007, obtaining a status assessment result of the target organization according to the first indicator value of the target assessment indicator.

[0234] <Ultrasonic Testing Equipment Example>

[0235] This embodiment provides an ultrasonic detection device, such as Figure 5 As shown, the ultrasonic detection device 5000 may include a processor 5100 and a memory 5200, the memory 5200 is used to store a computer program, and the processor 5100 is used to control the ultrasonic detection device to execute the method of any embodiment of the present disclosure under the control of the computer program.

[0236] <Readable Storage Medium Embodiment>

[0237] This embodiment provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method described in any method embodiment of the present disclosure is executed.

[0238] All steps of the methods of various embodiments of the present invention may be implemented by a computer device.

[0239] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0240] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0241] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0242] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.

[0243] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0244] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0245] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0246] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a part of a module, a program segment or an instruction, and a part of the module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0247] Embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A method for evaluating an organization's status, characterized in that: include: Acquiring a first ultrasonic echo signal of a target tissue; determining a first parameter value of at least one target ultrasound quantitative parameter according to the first ultrasound echo signal, wherein the target ultrasound quantitative parameter is an ultrasound quantitative parameter related to a tissue state; Based on the tissue state prediction model, a first index value of a target evaluation index is obtained according to a first parameter value of the at least one target ultrasound quantitative parameter; wherein the target evaluation index at least includes an index characterizing whether the target tissue state is normal or abnormal; A status assessment result of the target organization is obtained according to the first indicator value of the target assessment indicator.

2. The method according to claim 1, characterized in that The method further comprises: Acquiring a plurality of set ultrasound quantitative parameters; According to the plurality of ultrasound quantitative parameters, a plurality of parameter combinations are obtained, each parameter combination including at least one ultrasound quantitative parameter; Determining the correlation between each parameter combination and the target evaluation indicator; Selecting one or more parameter combinations according to the correlation, wherein the correlation of the selected parameter combination should be at least better than the correlation of a group of parameter combinations that are not selected, or the selected parameter combination has the highest correlation among all parameter combinations; The target ultrasound quantitative parameter is determined according to the selected one or more sets of parameter combinations.

3. The method according to claim 2, characterized in that The at least one target ultrasonic quantitative parameter includes at least one of tissue thickness, ultrasonic scattering parameter, nonlinear parameter, attenuation parameter, texture parameter, motion parameter, and elastic parameter; wherein the ultrasonic scattering parameter includes at least one of average intensity parameter, scattering peak value, scatterer density, and scatterer distribution characteristics; the nonlinear characteristic parameter includes at least one of normalized nonlinear parameter, ultrasonic nonlinear coefficient, second harmonic amplitude, phase matching, non-zero energy flow, and high-order elastic constant; the motion parameter includes at least one of displacement and strain; and the elastic parameter includes parameters used to characterize elastic coefficient and / or viscosity coefficient.

4. The method according to claim 1, characterized in that The step of acquiring a first ultrasonic echo signal of a target tissue comprises: A first ultrasonic echo signal of the target tissue under different conditions is acquired.

5. The method according to claim 4, characterized in that The different conditions include when the target tissue is compressed by different pressures, or actively contracts or relaxes, or at different times.

6. The method according to claim 1, characterized in that The normal or abnormal state of the target tissue is characterized by a risk level of at least one of sarcopenia, tissue fattening, liver inflammation, portal hypertension, renal failure, pancreatic cancer, fatty pancreas, articular cartilage damage, local muscle damage, liver fibrosis, and liver cirrhosis; The target tissue is a tissue associated with at least one of the characterized sarcopenia, degree of tissue fattening, liver inflammation, portal hypertension, renal failure, pancreatic cancer, fatty pancreas, articular cartilage damage, local muscle damage, liver fibrosis, and cirrhosis.

7. The method according to claim 1, characterized in that The step of acquiring a first ultrasonic echo signal of a target tissue comprises: Acquiring a second ultrasonic echo signal of at least one to-be-tested area of ​​the target tissue; determining a target area in the area to be measured according to the second ultrasonic echo signal; An ultrasonic signal is transmitted to the target area, and an ultrasonic echo signal reflected by the target area is received as the first ultrasonic echo signal.

8. The method according to claim 3, characterized in that When the at least one target ultrasound quantitative parameter includes a nonlinear parameter, determining a parameter value of the at least one target ultrasound quantitative parameter according to the ultrasound echo signal includes: Wherein, β represents a nonlinear parameter, ρ0 represents the density of the target tissue, p2(x) represents the amplitude of the second harmonic in the first ultrasonic echo signal, p0 represents the amplitude of the first ultrasonic echo signal at the target tissue, c0 represents the speed at which the first ultrasonic echo signal propagates in the target tissue, f represents the frequency of the first ultrasonic echo signal, α1 represents the attenuation coefficient of the fundamental wave in the first ultrasonic echo signal, α2 represents the attenuation coefficient of the second harmonic in the first ultrasonic echo signal, and x represents the propagation distance of the first ultrasonic echo signal.

9. The method according to claim 1, characterized in that: The tissue state prediction model is obtained by the following method: Acquire a training sample set, each training sample in the training sample set includes a second parameter value of the at least one target ultrasound quantitative parameter and a second index value of the target evaluation index, wherein the second parameter value is determined according to a third ultrasound echo signal corresponding to the training sample; The tissue state prediction model is trained according to the training sample set.

10. An ultrasonic testing device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the method according to any one of claims 1 to 9 under the control of the computer program.

11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 9 when executed by a processor.

Images