Ultrasonic image adaptive optimization method and device and electronic equipment

Abstract

The embodiment of the invention discloses an ultrasonic image adaptive optimization method and device and electronic equipment, and relates to the technical field of ultrasonic images. And self-adaptive adjustment and optimization of imaging parameters can be realized conveniently, so that the acquisition quality of ultrasonic images is improved. The method comprises the following steps: acquiring pressure data, body surface temperature data and displacement data of an ultrasonic probe in a contact state with a human body; according to the pressure data, the body surface temperature data and the displacement data, hardware control parameters of the ultrasonic imaging system are dynamically adjusted based on a preset algorithm model; and according to the adjusted hardware control parameters, acquiring an ultrasonic image of the human tissue.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of ultrasonic imaging, and particularly relates to an ultrasonic imaging adaptive optimization method and device and electronic equipment. BACKGROUND

[0002] With the continuous development of clinical medical diagnosis technology, ultrasonic imaging technology is widely used for visualizing various internal human tissues, providing key information for disease diagnosis. It plays an important role in early screening, diagnosis and treatment monitoring of various diseases. At present, in clinical examination, the adjustment of ultrasonic imaging parameters of ultrasonic imaging equipment usually depends on manual operation of operators. In specific operation, the operator will adjust the ultrasonic equipment hardware control parameters such as transmission power, focusing depth and time gain compensation curve according to experience and referring to the real-time display of ultrasonic image effect on the device screen, so as to optimize the quality of acquired ultrasonic images.

[0003] However, the adjustment of imaging parameters depending on the experience of operators lacks standardization, and the parameter adjustment of different operators for the same case may differ greatly, resulting in unstable imaging quality. In addition, the real-time performance of manual adjustment is poor. During the examination process, the state of human tissues, the contact condition of the probe and the human body and other factors are constantly changing, and manual adjustment often cannot adapt to these dynamic changes in time, which is easy to miss key image information. SUMMARY

[0004] Therefore, the embodiments of the application provide an ultrasonic imaging adaptive optimization method and device and electronic equipment, which facilitate adaptive adjustment and optimization of imaging parameters, thereby improving the acquisition quality of ultrasonic images.

[0005] To achieve the above application purposes, the application adopts the following technical solutions: In a first aspect, the embodiments of the application provide an ultrasonic imaging adaptive optimization method, which comprises: collecting pressure data, body surface temperature data and displacement data under the contact state of an ultrasonic probe and a human body; dynamically adjusting hardware control parameters of an ultrasonic imaging system based on a preset algorithm model according to the pressure data, the body surface temperature data and the displacement data; and collecting and acquiring ultrasonic images of human tissues according to the adjusted hardware control parameters.

[0006] According to one embodiment of the present application, after the ultrasonic image of the human tissue is collected, the method further comprises: inputting the ultrasonic image into a lightweight neural network model; the lightweight neural network model is configured to perform multi-scale feature extraction on the ultrasonic image and output a feature parameter representing the quality of the ultrasonic image; comparing the output feature parameter with a preset image quality feature parameter standard, and iteratively adjusting the compensation coefficient of the hardware control parameter in the preset algorithm model according to the comparison result until the difference between the output feature parameter and the preset image quality feature parameter standard is less than a preset threshold; determining the hardware control parameter corresponding to the current output feature parameter as the optimal hardware control parameter corresponding to the pressure data, body surface temperature data and displacement data, and updating the preset algorithm model; wherein the preset algorithm model comprises a mapping function relationship between the pressure data, body surface temperature data and displacement data and the bottom layer control parameter of the ultrasonic imaging system.

[0007] According to one embodiment of the present application, the hardware control parameter includes transmit power, focus depth and time gain compensation curve; and the hardware control parameter of the ultrasonic imaging system is dynamically adjusted based on the preset algorithm model according to the pressure data, body surface temperature data and displacement data, which comprises: determining the corresponding transmit power according to the mapping function relationship between the pressure data and the transmit power according to the pressure data; and determining the corresponding focus depth according to the mapping function relationship between the body surface temperature data and the focus depth according to the body surface temperature data; and determining the corresponding time gain compensation curve according to the mapping function relationship between the displacement data and the time gain compensation curve according to the displacement data.

[0008] According to one embodiment of the present application, the corresponding transmit power is determined according to the mapping function relationship between the pressure data and the transmit power according to the pressure data, which comprises: when the pressure data is lower than the lower limit threshold of pressure, the target transmit power is calculated based on the first mapping function relationship: ; wherein the is the target transmit power, is the initial transmit power, is the real-time pressure data, is the lower limit threshold of pressure, is the transmit power adjustment coefficient corresponding to the pressure interval; when the pressure data is between the lower limit threshold of pressure and the upper limit threshold of pressure, the target transmit power is calculated according to the formula ; wherein, is the transmit power adjustment coefficient of the interval, and ; when the pressure data is higher than the upper limit threshold of pressure, the target transmit power is locked as a preset maximum safe transmit power, and a pressure overload prompt signal is triggered.​

[0009] According to one embodiment of the present application, the method further comprises: in advance, in a phantom experiment, simulating different contact states of the ultrasonic probe with the human body, collecting a plurality of groups of ultrasonic images under each contact state; manually labeling optimal hardware control parameters for each group of ultrasonic images; fitting mapping functions between pressure and transmit power, temperature and focusing depth, and displacement data and time gain compensation curves by using the least square method, so that the deviation rate of the output values of the fitting functions and the manually labeled optimal parameters is controlled within a desired deviation value; storing the mapping functions obtained by fitting and the corresponding adjustment coefficients to form the preset algorithm model.

[0010] In a second aspect, the embodiments of the present application also provide an ultrasonic image self-adaptive optimization device, comprising: an acquisition program unit configured to collect pressure data, body surface temperature data, and displacement data in a contact state of an ultrasonic probe with a human body; an adjustment program unit configured to dynamically adjust hardware control parameters of an ultrasonic imaging system based on a preset algorithm model according to the pressure data, the body surface temperature data, and the displacement data; and an acquisition program unit configured to collect ultrasonic images of human tissues according to the adjusted hardware control parameters.

[0011] According to one embodiment of the present application, the device further comprises: a feature extraction program unit configured to input the ultrasonic images of human tissues into a lightweight neural network model after the ultrasonic images are collected; the lightweight neural network model is configured to perform multi-scale feature extraction on the ultrasonic images and output feature parameters representing the quality of the ultrasonic images; a comparison program unit configured to compare the output feature parameters with preset image quality feature parameter standards, iteratively adjust compensation coefficients of the hardware control parameters in the preset algorithm model according to the comparison results, until the difference between the output feature parameters and the preset image quality feature parameter standards is less than a preset threshold; and a determination program unit configured to determine the hardware control parameters corresponding to the current output feature parameters as the optimal hardware control parameters corresponding to the pressure data, the body surface temperature data, and the displacement data, and update the preset algorithm model; wherein the preset algorithm model comprises a mapping function relationship between the pressure data, the body surface temperature data, and the displacement data and the bottom-layer control parameters of the ultrasonic imaging system.

[0012] According to one embodiment of the present application, the hardware control parameters include transmit power, focal depth and time gain compensation curve; the adjustment procedure unit is specifically configured to: determine the corresponding transmit power according to the pressure data based on a mapping function relationship between the pressure data and the transmit power; determine the corresponding focal depth according to the body surface temperature data based on a mapping function relationship between the body surface temperature data and the focal depth for dynamic adjustment; and determine the corresponding time gain compensation curve according to the displacement data based on a mapping function relationship between the displacement data and the time gain compensation curve.

[0013] According to one embodiment of the present application, the device further comprises a model construction procedure unit, which is configured to: in a phantom experiment, simulate different contact pressure states of an ultrasonic probe and a human body, collect a plurality of groups of ultrasonic images under each contact pressure state; manually label optimal hardware control parameters for each group of ultrasonic images; adopt a least square method to fit mapping functions between pressure and transmit power, temperature and focal depth, and displacement data and time gain compensation curve, so that the deviation rate of the output values of the fitting functions and the manually labeled optimal parameters is controlled within a desired deviation value; store the fitting obtained mapping functions and corresponding adjustment coefficients to form the preset algorithm model.

[0014] In a third aspect, the embodiments of the present application further provide an electronic device, which comprises: a shell, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is arranged inside a space enclosed by the shell, the processor and the memory are arranged on the circuit board; the power supply circuit is configured to supply power to each circuit or device of the electronic device; the memory is configured to store executable program codes; the processor is configured to run programs corresponding to the executable program codes by reading the executable program codes stored in the memory, and execute the method of any one of the embodiments of the first aspect.

[0015] Compared with the traditional method of directly performing examination by manually adjusting the ultrasonic imaging parameters by an operator before ultrasonic image examination, the ultrasonic image adaptive optimization method, device and electronic device provided by the embodiments of the present application provide a basis for secondary real-time dynamic adjustment of the hardware control parameters of the ultrasonic device by collecting the contact state data of the ultrasonic probe under the contact state with the human body, avoid the problem of mismatch between the parameters and the contact state in the traditional technology, and collect images based on the adjusted hardware control parameters, so that the collected ultrasonic images are adapted to the current contact state in terms of signal intensity, focusing accuracy, brightness balance and the like, which facilitates adaptive adjustment and optimization of the imaging parameters, thereby improving the collection quality of the ultrasonic images. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0017] Figure 1 is a process schematic diagram of an embodiment of the ultrasound image self-adaptive optimization method in the present application.

[0018] Figure 2 is a process schematic diagram of another embodiment of the ultrasound image self-adaptive optimization method in the present application.

[0019] Figure 3 is a structure schematic block diagram of an embodiment of the ultrasound image self-adaptive optimization device in the present application.

[0020] Figure 4 is a structure schematic block diagram of an embodiment of the electronic device in the present application. DETAILED DESCRIPTION

[0021] The embodiments of the present application will be described in detail below with reference to the drawings.

[0022] It should be clear that the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0023] In order to help understand the technical solutions and technical effects provided by the embodiments of the present application, before the description is expanded, a brief introduction to the prior art is as follows: In the process of ultrasonic examination, the doctor holds the ultrasonic probe in contact with the patient's body surface to obtain the image of human tissue. At this time, the contact state of the probe with the human body is in dynamic change: different pressing forces of the doctor will cause the pressure of the probe on the body surface to fluctuate, long-time contact of the probe will cause changes in the local body surface temperature, and the movement of the probe when scanning different parts will produce displacement. These dynamic changes of the contact state parameters with the human body, such as pressure, body surface temperature and displacement, will directly affect the propagation characteristics of ultrasonic waves in human tissue, and then affect the collection quality of the ultrasonic image.

[0024] In a conventional ultrasound examination, the hardware control parameters of an ultrasound imaging system, such as the transmit power, the focal depth, etc., are usually manually set by a doctor and remain fixed, or are manually adjusted based on a single dimension during the examination, which cannot match the dynamically changing contact state in real time. For example, when the probe pressure is too small, the ultrasound signal is attenuated due to insufficient coupling, which may result in insufficient image brightness; when the body surface temperature changes, the ultrasound propagation speed changes, and the fixed focal depth may result in blurred imaging of the target tissue; when the probe displacement speed changes, the fixed time gain compensation curve may not balance the signal strength of the tissue at different depths, resulting in uneven image brightness. The above mismatch between the pre-adjusted parameters based on empirical values and the actual contact state will affect the quality of ultrasound image acquisition.

[0025] Therefore, referring to Figure 1 The embodiments of the present application provide an ultrasound image adaptive optimization method, which comprises: S110, collecting pressure data, body surface temperature data and displacement data under the contact state of an ultrasound probe and a human body; S120, dynamically adjusting the hardware control parameters of an ultrasound imaging system based on a preset algorithm model according to the pressure data, the body surface temperature data and the displacement data; S130, collecting and acquiring the ultrasound image of the human tissue according to the adjusted hardware control parameters.

[0026] The pressure data can be collected in real time by a pressure sensor integrated on the contact surface of the probe, reflecting the coupling tightness of the probe and the body surface; the body surface temperature data can be collected by a temperature sensor on the edge of the probe, representing the temperature characteristics of the local tissue; the displacement data can be collected by an inertial measurement unit built in the probe, including the moving speed and direction, etc. The preset algorithm model pre-establishes the mapping relationship between the pressure data, the body surface temperature data, the displacement data and the hardware control parameters, such as the correlation rule between the pressure data and the transmit power, the adaptive relationship between the temperature data and the focal depth, etc. When the real-time contact data is collected, the preset algorithm model can automatically calculate and adjust the hardware control parameters according to the preset mapping relationship, so that the parameters are adapted to the current contact state, and finally the ultrasound image acquisition is completed based on the adjusted parameters, thereby improving the quality of image acquisition.

[0027] In this embodiment, when the ultrasonic probe is in contact with the human body, the contact state of the probe and the human body is sensed, and the dynamic adjustment of the hardware control parameters is realized through the preset algorithm model, thereby avoiding the problem of mismatching with the contact state caused by the fixed parameters or manual adjustment in the traditional method. The adjusted hardware control parameters can adapt to the ultrasonic wave propagation characteristics under different pressures, temperatures and displacements. Therefore, the image collected based on the adjusted hardware control parameters can be adapted to the current contact state in terms of signal strength, focusing accuracy, brightness balance and the like, so as to facilitate the adaptive adjustment and optimization of the imaging parameters, thereby improving the brightness uniformity and target tissue clarity of the collected ultrasonic image and improving the collection quality of the ultrasonic image. At the same time, the automatic adjustment of the hardware control parameters effectively reduces the frequency of manual intervention by doctors, thereby improving the examination efficiency.

[0028] Due to the differences in tissue characteristics of different patients, such as different fat thicknesses and muscle densities, or different physiological characteristics of different examination sites of the same patient, the initial preset algorithm model may not completely match all scenarios, resulting in that the quality of the collected image is still not optimal in some cases.

[0029] Therefore, referring to Figure 2 In some embodiments, after the ultrasonic image of the human tissue is collected, the method further includes: S140, inputting the ultrasonic image into a lightweight neural network model; the lightweight neural network model is configured to perform multi-scale feature extraction on the ultrasonic image and output feature parameters representing the quality of the ultrasonic image; S150, comparing the output feature parameters with a preset image quality feature parameter standard, and iteratively adjusting the compensation coefficients of the hardware control parameters in the preset algorithm model according to the comparison result until the difference between the output feature parameters and the preset image quality feature parameter standard is less than a preset threshold; S160, determining the hardware control parameters corresponding to the current output feature parameters as the optimal hardware control parameters corresponding to the pressure data, body surface temperature data and displacement data, and updating the preset algorithm model; wherein the preset algorithm model includes a mapping function relationship between the pressure data, body surface temperature data and displacement data and the bottom control parameters of the ultrasonic imaging system.

[0030] In this embodiment, after the ultrasonic image of the human tissue is initially obtained, the hardware control parameters in the preset algorithm model are adjusted in reverse according to the quality of the ultrasonic image, thereby solving the adaptation deviation problem of the initial preset algorithm model and the individual tissue characteristics. After multiple iterations, the optimal parameter corresponding relationship of different contact states and different tissue types can be accumulated, so that the adjustment of the subsequent hardware control parameters is more accurate, and the stability and consistency of the ultrasonic image quality are further improved.

[0031] Specifically, the hardware control parameters include a transmit power, a focal depth, and a time gain compensation curve.

[0032] The hardware control parameters of the ultrasonic imaging system are dynamically adjusted based on a preset algorithm model according to the pressure data, the body surface temperature data, and the displacement data, including: the corresponding transmit power is determined according to the pressure data based on a mapping function relationship between the pressure data and the transmit power; the corresponding focal depth is determined according to the body surface temperature data based on a mapping function relationship between the body surface temperature data and the focal depth for dynamic adjustment; and the corresponding time gain compensation curve is determined according to the displacement data based on a mapping function relationship between the displacement data and the time gain compensation curve.

[0033] Specifically, the pressure data is used to reflect the coupling tightness between the probe and the body surface, the worse the coupling, the smaller the pressure, and the more the ultrasonic wave attenuates, correspondingly, the mapping function needs to reflect the mapping rule that the transmit power increases when the pressure decreases; the body surface temperature affects the ultrasonic wave propagation speed, the temperature and the sound speed are generally positively correlated, the higher the temperature, the faster the sound speed, the focal depth increases when the temperature rises, and the focal depth should be appropriately reduced to ensure that the focal point always falls on the target tissue; the moving speed in the displacement data reflects the scanning dynamics, and the displacement data also needs to be set to enhance the deep signal gain.

[0034] It can be understood that the contact pressure of the ultrasonic probe and the human body has significant differences in the influence degree on the ultrasonic wave propagation in different ranges. When the pressure is at a low level, the coupling state between the probe and the body surface is relatively sensitive, and slight pressure changes may cause significant changes in ultrasonic energy attenuation; when the pressure is at a medium level, the coupling state is relatively stable, and the pressure change has a relatively gentle influence on the attenuation; when the pressure is at a high level, not only the coupling state tends to be saturated, but also the ultrasonic reflection interface may be affected by the deformation of the tissue under pressure, at which time the imaging safety needs to be considered first.

[0035] If the power is adjusted by the same coefficient for all pressure intervals, there will be problems of insufficient compensation in the low interval and excessive compensation in the medium interval. Therefore, the mapping function of the pressure data and the transmit power is segmented and refined in this embodiment. Specifically, when the pressure data is lower than a pressure lower limit threshold, the target transmit power is calculated based on a first mapping function relationship: ; wherein, the target transmit power is , the initial transmit power is , the real-time pressure data is , the pressure lower limit threshold is , and the transmit power adjustment coefficient of the corresponding pressure interval is ; the second mapping function relationship is used when the pressure data is between the pressure lower limit threshold and a pressure upper limit threshold, and the third mapping function relationship is used when the pressure data is higher than the pressure upper limit threshold. When the pressure data is between the lower pressure threshold and the upper pressure threshold, the target transmit power is calculated according to the formula ; wherein, is the transmit power adjustment coefficient of the interval, and When the pressure data is higher than the upper pressure threshold, the target transmit power is locked as the preset maximum safe transmit power, and a pressure overload prompt signal is triggered. The maximum safe transmit power is the upper limit of power that meets the clinical safety standard, and the overload prompt signal can be informed to the doctor through device screen display or probe vibration, so as to avoid tissue damage or image distortion caused by excessive pressure.

[0036] In this embodiment, by setting different mapping functions and adjustment coefficients for different pressure intervals, the adjustment of transmit power can adapt to the coupling characteristics under different pressures, enhance the compensation sensitivity at low pressure, maintain gentle adjustment at medium pressure, and ensure safety at high pressure, thereby solving the problem of compensation imbalance of a single adjustment coefficient.

[0037] The change of body surface temperature also changes the ultrasonic wave propagation speed of human soft tissue. In clinical ultrasonic examination, the preset focus depth of the probe is calculated based on the speed of sound under normal body temperature, so as to ensure that the ultrasonic focus point accurately falls on the target tissue. However, when the body surface temperature deviates from the normal range, the speed of sound will change, resulting in a deviation between the actual focus point position and the depth of the target tissue, and further affecting the image clarity.

[0038] Therefore, in this embodiment, the focus depth can be dynamically adjusted by a segmented mapping function to offset the deviation caused by the change of the speed of sound. In some embodiments, the corresponding focus depth is determined based on the mapping function relationship between the body surface temperature data and the focus depth according to the body surface temperature data, including: when the body surface temperature data is lower than the lower temperature threshold, the target focus depth , wherein is the initial focus depth set for the target tissue under normal temperature, unit: mm, is the depth adjustment coefficient of the temperature interval, unit: mm / ℃, and is positive; which represents the difference when the temperature is lower than the normal range. At this time, the speed of sound decreases due to low temperature, and the actual focus point is shallow. By adding a positive adjustment amount to the baseline focus depth, the preset focus depth is increased, so that the actual focus point is deepened to the target tissue position.

[0039] When the body surface temperature data is between the lower temperature threshold and the upper temperature threshold, the target focus depth remains the initial focus depth and does not need to be adjusted; when the body surface temperature data is higher than the upper temperature threshold, the target focus depth , wherein,​​ is a depth adjustment coefficient for the temperature interval, and At this time, the sound speed increases due to the high temperature, and the actual focus point is deep. By superimposing a negative adjustment amount on the basis of the reference focus depth, the preset focus depth is reduced, and the actual focus point is shallowed to the target tissue position.

[0040] During clinical examination, the doctor needs to adjust the probe movement mode according to the characteristics of the examination site. For example, when examining superficial tissues, the probe moves slowly, the displacement is small, the ultrasonic wave propagation path in the tissue is stable, and the signal attenuation law is predictable; when examining deep tissues, the probe moves faster, the displacement is larger, the ultrasonic wave propagation path changes slightly with the movement of the probe, and the fast movement shortens the effective acquisition time of the echo signal, resulting in intensified signal attenuation of the deep tissue, resulting in dark images and blurred boundaries.

[0041] Therefore, in some embodiments, the displacement data includes the displacement S and the displacement speed V of the probe. The corresponding time gain compensation curve is determined based on the mapping function relationship between the displacement data and the time gain compensation curve according to the displacement data, including: when the probe displacement speed is less than or equal to V 低速 , V 低速 An example value is 5 mm / s. The displacement data and the gain value of the time gain compensation curve are adjusted according to the first compensation rule, specifically: the gain value increases by G1 for every 10 mm increase in depth, and G1=k v1 ×S. Wherein, k v1 is the gain coefficient under low-speed displacement, unit: dB / mm, and its value is calibrated based on the phantom experiment. Specifically, by simulating the coupling state under different displacement amounts, it is ensured that G1 can compensate for the slight coupling deviation caused by the displacement amount, such as the greater the displacement amount, the higher the possibility of uneven distribution of the coupling agent, and k v1 should be appropriately increased to maintain signal stability.

[0042] When the probe displacement speed is between V 低速 and V 高速 , the gain value of the displacement data and the time gain compensation curve does not need to be increased. When the probe displacement speed is in the high-speed displacement interval, the displacement data and the time gain compensation curve are switched to the preset fast scanning mode curve. In this way, because the ultrasonic signal attenuates rapidly under high-speed movement and there is a risk of lag in real-time calculation and adjustment, by presetting the fast scanning mode curve, the signal attenuation can be quickly offset, and the dark area of the image caused by adjustment delay can be avoided.

[0043] ​In some embodiments, the method further comprises: S10, in a phantom experiment, simulating different contact states of an ultrasonic probe with a human body, and collecting a plurality of groups of ultrasonic images under each contact state; specifically, a plurality of experiments can be performed, and a plurality of groups of ultrasonic images are collected under different initial compensation coefficients and different contact state data. The contact state is quantitatively represented by pressure data, body surface temperature data, and displacement data, and the initial compensation coefficient is an initial adjustment reference value of the transmission power, the focusing depth, and the time gain compensation curve.

[0044] S20, manually labeling optimal hardware control parameters for each group of ultrasonic images. For each group of ultrasonic images, a professional ultrasonic physician manually labels the corresponding optimal hardware control parameters in combination with clinical diagnosis requirements, including the transmission power, the focusing depth, and the time gain compensation curve parameter values that enable the image brightness uniformity, the target tissue clarity, and the signal-to-noise ratio to meet the standards.

[0045] S30, using a least squares method to fit a mapping function between the pressure and the transmission power, the temperature and the focusing depth, and the displacement data and the time gain compensation curve, so that the deviation rate between the output value of the fitting function and the manually labeled optimal parameters is controlled within a desired deviation value; during the fitting process, the deviation rate between the output value of the function and the manually labeled optimal parameters is controlled within a preset expected range deviation value through iterative optimization, to ensure that the fitting accuracy of the function meets the clinical imaging requirements.

[0046] S40, storing the mapping function and the corresponding adjustment coefficient obtained by fitting, to form the preset algorithm model, which is used to automatically adjust the hardware control parameters in subsequent ultrasonic image examination.

[0047] Referring to Figure 3 , based on the same technical concept as the foregoing embodiments, the embodiments of the present application also provide an ultrasonic image adaptive optimization device, comprising: an acquisition program unit configured to acquire pressure data, body surface temperature data, and displacement data in a contact state of an ultrasonic probe with a human body; an adjustment program unit configured to dynamically adjust hardware control parameters of an ultrasonic imaging system based on a preset algorithm model according to the pressure data, the body surface temperature data, and the displacement data; and an acquisition program unit configured to acquire ultrasonic images of human tissues according to the adjusted hardware control parameters.

[0048] According to one embodiment of the present application, further comprising: a feature extraction program unit for inputting the ultrasonic image of the human tissue into a lightweight neural network model after the ultrasonic image of the human tissue is collected; the lightweight neural network model is configured to perform multi-scale feature extraction on the ultrasonic image and output a feature parameter representing the quality of the ultrasonic image; a comparison program unit for comparing the output feature parameter with a preset image quality feature parameter standard, and iteratively adjusting a compensation coefficient of the hardware control parameter in the preset algorithm model according to the comparison result until the difference between the output feature parameter and the preset image quality feature parameter standard is less than a preset threshold; a determination program unit for determining the hardware control parameter corresponding to the current output feature parameter as the optimal hardware control parameter corresponding to the pressure data, the body surface temperature data and the displacement data, and updating the preset algorithm model; wherein the preset algorithm model comprises a mapping function relationship between the pressure data, the body surface temperature data and the displacement data and the bottom layer control parameter of the ultrasonic imaging system.

[0049] According to one embodiment of the present application, the hardware control parameter includes transmit power, focus depth and time gain compensation curve; the adjustment program unit is specifically configured to: determine the corresponding transmit power based on the mapping function relationship between the pressure data and the transmit power according to the pressure data; and determine the corresponding focus depth based on the mapping function relationship between the body surface temperature data and the focus depth according to the body surface temperature data to perform dynamic adjustment; and determine the corresponding time gain compensation curve based on the mapping function relationship between the displacement data and the time gain compensation curve according to the displacement data.

[0050] According to one embodiment of the present application, the device further comprises: a model construction program unit for simulating different contact pressure states of the ultrasonic probe and the human body in a phantom experiment in advance, collecting a plurality of groups of ultrasonic images under each contact pressure state; manually labeling the optimal hardware control parameter for each group of ultrasonic images; fitting the mapping function between the pressure and the transmit power, the temperature and the focus depth, and the displacement data and the time gain compensation curve by using the least square method, so that the deviation rate of the fitting function output value and the manually labeled optimal parameter is controlled within the expected deviation value; storing the fitted mapping function and the corresponding adjustment coefficient to form the preset algorithm model.

[0051] Figure 4 The structure schematic diagram of one embodiment of the electronic device of the present application can realize the flow of the method embodiment of the present application, as shown in Figure 4As shown, the electronic device provided by the embodiments of the present application can include a shell 91, a processor 92, a memory 93, a circuit board 94 and a power supply circuit 95, wherein the circuit board 94 is arranged inside the space enclosed by the shell 91, and the processor 92 and the memory 93 are arranged on the circuit board 94; the power supply circuit 95 is configured to supply power to each circuit or device of the electronic device; the memory 93 is configured to store executable program codes; and the processor 92 is configured to run programs corresponding to the executable program codes by reading the executable program codes stored in the memory 93, and execute the method described in any of the foregoing embodiments.

[0052] The specific execution process of the processor 92 on the foregoing steps and the steps further executed by the processor 92 by running the executable program codes can be referred to the description of the foregoing embodiments, which will not be repeated here.

[0053] In summary, compared with the conventional method of directly performing examination by manually adjusting the ultrasonic imaging parameters by the operator before ultrasonic image examination, the ultrasonic image adaptive optimization method, device and electronic device provided by the embodiments of the present application can provide a basis for the secondary real-time dynamic adjustment of the hardware control parameters of the ultrasonic device by collecting the contact state data of the ultrasonic probe under the contact state with the human body, thereby avoiding the problem of mismatch between the parameters and the contact state in the conventional technology. The image is collected based on the adjusted hardware control parameters, which can make the collected ultrasonic image adapt to the current contact state in terms of signal strength, focusing accuracy, brightness balance and the like, so as to facilitate the adaptive adjustment and optimization of the imaging parameters, thereby improving the collection quality of the ultrasonic image.

[0054] It should be noted that in this document, the terms "comprising", "containing" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0055] Each of the embodiments in the specification is described in a related manner, and the same or similar parts between each of the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments.

[0056] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, the program can include the processes of the above-mentioned embodiment methods. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), or the like.

[0057] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An adaptive optimization method for ultrasound images, characterized in that, include: Collect pressure data, body surface temperature data, and displacement data when the ultrasound probe is in contact with the human body; Based on the pressure data, body surface temperature data, and displacement data, the hardware control parameters of the ultrasound imaging system are dynamically adjusted according to a preset algorithm model. Based on the adjusted hardware control parameters, ultrasound images of human tissues are acquired.

2. The method according to claim 1, characterized in that, After acquiring ultrasound images of human tissue, the method further includes: inputting the ultrasound images into a lightweight neural network model; the lightweight neural network model is configured to perform multi-scale feature extraction on the ultrasound images and output feature parameters characterizing the quality of the ultrasound images; comparing the output feature parameters with a preset image quality feature parameter standard, and iteratively adjusting the compensation coefficients of the hardware control parameters in the preset algorithm model according to the comparison results, until the difference between the output feature parameters and the preset image quality feature parameter standard is less than a preset threshold; determining the hardware control parameters corresponding to the currently output feature parameters as the optimal hardware control parameters corresponding to the pressure data, body surface temperature data, and displacement data, and updating the preset algorithm model; wherein, the preset algorithm model includes: mapping function relationships between pressure data, body surface temperature data, and displacement data and the underlying control parameters of the ultrasound imaging system, respectively.

3. The method according to claim 1, characterized in that, The hardware control parameters include transmit power, focus depth, and time gain compensation curve; The step of dynamically adjusting the hardware control parameters of the ultrasound imaging system based on the pressure data, body surface temperature data, and displacement data using a preset algorithm model includes: Based on the pressure data, the corresponding transmission power is determined according to the mapping function relationship between the pressure data and the transmission power; and... Based on the stated body surface temperature data, the corresponding focusing depth is determined and dynamically adjusted according to the mapping function relationship between the body surface temperature data and the focusing depth; and... Based on the displacement data, the corresponding time gain compensation curve is determined according to the mapping function relationship between the displacement data and the time gain compensation curve.

4. The method according to claim 3, characterized in that, The step of determining the corresponding transmission power based on the pressure data and the mapping function relationship between the pressure data and the transmission power includes: When the pressure data is below the lower pressure threshold, based on the first mapping function relationship: The target transmission power is calculated; wherein, the For the target transmission power, This is the initial transmit power. For real-time stress data, This is the lower limit threshold of pressure. This is the transmission power adjustment coefficient for the corresponding pressure range; When the pressure data is between the lower pressure threshold and the upper pressure threshold, according to the formula... Calculate the target's transmission power; where, This is the transmit power adjustment factor for this range, and < ; When the pressure data exceeds the upper pressure threshold, the target transmission power is locked at the preset maximum safe transmission power, and a pressure overload warning signal is triggered.

5. The method according to claim 1, characterized in that, The method also includes: simulating different contact states between the ultrasound probe and the human body in a pre-contact experiment, and acquiring multiple sets of ultrasound images under each contact state. The optimal hardware control parameters are manually labeled for each set of ultrasound images; The least squares method is used to fit the mapping function between pressure and transmission power, temperature and focusing depth, displacement data and time gain compensation curve, so that the deviation rate between the output value of the fitted function and the manually labeled optimal parameters is controlled within the expected deviation value. The fitted mapping function and its corresponding adjustment coefficients are stored to form the preset algorithm model.

6. An adaptive optimization device for ultrasound imaging, characterized in that, include: The data acquisition unit is used to acquire pressure data, body surface temperature data, and displacement data when the ultrasound probe is in contact with the human body. The adjustment program unit is used to dynamically adjust the hardware control parameters of the ultrasound imaging system based on a preset algorithm model according to the pressure data, body surface temperature data, and displacement data. The acquisition program unit is used to acquire ultrasound images of human tissues based on the adjusted hardware control parameters.

7. The apparatus according to claim 6, characterized in that, Also includes: The feature extraction program unit is used to input the ultrasound images of human tissue into a lightweight neural network model after acquiring the ultrasound images; the lightweight neural network model is configured to perform multi-scale feature extraction on the ultrasound images and output feature parameters characterizing the quality of the ultrasound images. The comparison program unit is used to compare the output feature parameters with the preset image quality feature parameter standard, and iteratively adjust the compensation coefficient of the hardware control parameters in the preset algorithm model according to the comparison result until the difference between the output feature parameters and the preset image quality feature parameter standard is less than the preset threshold. A program unit is defined to determine the hardware control parameters corresponding to the currently output feature parameters as the optimal hardware control parameters corresponding to the pressure data, body surface temperature data, and displacement data, and to update the preset algorithm model; wherein, the preset algorithm model includes: the mapping function relationship between the pressure data, body surface temperature data, and displacement data and the underlying control parameters of the ultrasound imaging system, respectively.

8. The apparatus according to claim 6, characterized in that, The hardware control parameters include transmit power, focus depth, and time gain compensation curve; The adjustment procedure unit is specifically used for: Based on the pressure data, the corresponding transmission power is determined according to the mapping function relationship between the pressure data and the transmission power; and... Based on the body surface temperature data, the corresponding focusing depth is determined and dynamically adjusted according to the mapping function relationship between the body surface temperature data and the focusing depth. as well as, Based on the displacement data, the corresponding time gain compensation curve is determined according to the mapping function relationship between the displacement data and the time gain compensation curve.

9. The apparatus according to claim 6, characterized in that, The device also includes: a model building program unit, used to simulate different contact pressure states between the ultrasound probe and the human body in advance in the phantom experiment, and to acquire multiple sets of ultrasound images under each contact pressure state. The optimal hardware control parameters are manually labeled for each set of ultrasound images; The least squares method is used to fit the mapping function between pressure and transmission power, temperature and focusing depth, displacement data and time gain compensation curve, so that the deviation rate between the output value of the fitted function and the manually labeled optimal parameters is controlled within the expected deviation value. The fitted mapping function and its corresponding adjustment coefficients are stored to form the preset algorithm model.

10. An electronic device, characterized in that, The electronic device includes: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside the space enclosed by the housing, and the processor and the memory are disposed on the circuit board; the power supply circuit is used to supply power to various circuits or devices of the electronic device; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, for executing the method of any one of claims 1 to 5.

Images