Medical ultrasonic image intelligent processing method and system

Abstract

The embodiment of the invention relates to an intelligent processing method and system for a medical ultrasonic image, and the method comprises the steps: determining an output alternating voltage waveform of a target through calling the cycle length and the duty ratio of output PWM (Pulse-Width Modulation) data; the output alternating voltage waveform of the target is input into the steady-state function of the MOS tube set, and the induced electric field applied to the piezoelectric material can be determined. The piezoelectric material emits ultrasonic waves, the ultrasonic waves make contact with a target object to generate different waves, and the different waves serve as mechanical waves in the environment and can form superposed echoes with the output mechanical waves. And the output mechanical waves and the received superposed echoes are analyzed. Analysis of echo data may determine abnormal waves. The abnormal wave is a characteristic echo, and an ultrasonic image is formed based on a characteristic echo-to-image function. The steady-state function of the MOS tube set is utilized to analyze the induction electric field deformation in the starting process and the steady-state process of the field effect transistor, so that the ambiguity of the ultrasonic image can be reduced.

Description

Technical Field

[0001] The present application relates to the field of medical device technology, and in particular to a method and system for intelligent processing of medical ultrasound images. Background Art

[0002] Ultrasonic technology can use the high-frequency oscillation of the circuit to apply an alternating voltage to the piezoelectric material, so that the piezoelectric material produces high-frequency mechanical vibrations, thereby achieving the output of ultrasonic waves. Piezoelectric materials are materials that convert electrical energy into mechanical energy. When ultrasonic waves meet the object to be measured, an echo is formed, and the echo receiving circuit receives the echo to generate a digital signal. The processor processes the digital signal to generate an ultrasonic image.

[0003] Since the traditional circuit high-frequency oscillation generating device uses field effect transistor as the oscillation core element, the startup process and steady-state process of the field effect transistor will affect the blurriness of the ultrasound image. Therefore, it is necessary to propose a medical ultrasound image intelligent processing method and system to address the defect that the traditional ultrasound image imaging results are relatively blurry. Summary of the invention

[0004] Based on this, it is necessary to propose a medical ultrasound image intelligent processing method and system to address the defect that the traditional ultrasound image imaging results are relatively fuzzy.

[0005] The present application provides a medical ultrasound image intelligent processing method, comprising:

[0006] Call the cycle length and duty cycle of the output PWM data;

[0007] Based on the steady-state function of the MOS tube set, the wave function of the output ultrasonic wave is determined;

[0008] Receive echo data;

[0009] According to the echo data analysis function, the characteristic echo to be cleaned is obtained;

[0010] Based on the wave function of ultrasonic waves, the fuzzy parameters of the characteristic echo to be cleaned are fitted;

[0011] Obtain characteristic echo;

[0012] An ultrasound image is formed based on a characteristic echo-to-image function.

[0013] The present application also provides a medical ultrasound image intelligent processing system.

[0014] A medical ultrasonic image intelligent processing system, comprising:

[0015] A processor, used to execute the medical ultrasound image intelligent processing method;

[0016] a mechanical wave circuit, electrically connected to the processor;

[0017] A display is electrically connected to the processor.

[0018] The present application relates to a medical ultrasonic image intelligent processing method and system, which determines the output alternating voltage waveform of the target by calling the cycle length and duty cycle of the output PWM data. The output alternating voltage waveform of the target is input into the steady-state function of the MOS tube set, and the induced electric field applied to the piezoelectric material can be determined. The piezoelectric material emits ultrasonic waves, and the ultrasonic waves contact the target object to generate abnormal waves. This abnormal wave, as a mechanical wave in the environment, can form a superimposed echo with the output mechanical wave. The output mechanical wave and the received superimposed echo are analyzed. The analysis of the echo data can determine the abnormal wave. This abnormal wave is a characteristic echo, and an ultrasonic image is formed based on the characteristic echo conversion image function. When ultrasonic waves are transmitted from one substance to another substance with different acoustic impedance, two things happen. Part of the ultrasonic wave continues to enter the second substance, but slightly deviates from the original direction. When ultrasonic waves are transmitted from one substance to another substance with different acoustic impedance, this bending is called refraction.

[0019] In addition, part of the sound wave is reflected back to the probe. The amount of reflection depends on the difference in the acoustic impedance of the two materials. The greater the difference, the stronger the reflection. The reflected wave is very important because only the reflected wave can return to the detector and provide the machine with information to display the image.

[0020] As ultrasound waves travel from one tissue to the next, each tissue has a different acoustic impedance, and some of the waves are reflected back at each intersection. As a result, multiple reflected waves return to the probe, and the machine uses this information to display an image showing the different tissues.

[0021] Compressing the wave into a smaller length means that the high and low pressure oscillations of the wave become more concentrated. When a wave is compressed, it has more oscillations (high / low pressure areas) per second than before (i.e. the frequency increases). The waves reflected by an object moving toward the probe have a higher frequency than the waves that were emitted.

[0022] The Doppler effect also occurs when an object moves away from the transmitting probe. Again, there is a difference between the frequency of the transmitted wave and the frequency of the returning wave. This time, however, the frequency of the returning wave is lower than the frequency of the transmitted wave. The faster the object moves, the greater the frequency difference. The reason for the drop in frequency is the opposite of the explanation given previously. In this case, the object moving away "stretches" the waves. The stretching reduces the number of oscillations per second.

[0023] By using the steady-state function of the MOS tube set to analyze the induced electric field deformation during the startup process and steady-state process of the field effect transistor, the ambiguity of the ultrasound image can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The drawings and descriptions of the exemplary embodiments of this application are used to explain this application and do not constitute an improper limitation on this application.

[0025] Figure 1 A method flow chart of a method for intelligent processing of medical ultrasound images provided in one embodiment of the present application.

[0026] Figure 2 A structural connection diagram of a medical ultrasound image intelligent processing system provided in one embodiment of the present application.

[0027] Reference numerals:

[0028] 100-processor; 200-mechanical wave circuit; 300-display. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0030] The present application provides a method for intelligent processing of medical ultrasound images.

[0031] like Figure 1 As shown, in one embodiment of the present application, a medical ultrasound image intelligent processing method includes:

[0032] S100, calling the cycle length and duty cycle of output PWM data.

[0033] S200, determining a wave function of output ultrasonic waves based on a steady-state function of the MOS tube set.

[0034] S300, receiving echo data.

[0035] S400, obtaining a characteristic echo to be cleaned according to an echo data analysis function.

[0036] S500, fitting fuzzy parameters of the characteristic echo to be cleaned based on the wave function of the ultrasonic wave.

[0037] S600: Acquire a characteristic echo.

[0038] S700, forming an ultrasound image based on a characteristic echo-to-image function.

[0039] The present embodiment relates to an intelligent processing method for medical ultrasonic images, which determines the output alternating voltage waveform of the target by calling the cycle length and duty cycle of the output PWM data. The output alternating voltage waveform of the target is input into the steady-state function of the MOS tube set, and the induced electric field applied to the piezoelectric material can be determined. The piezoelectric material emits ultrasonic waves, and the ultrasonic waves contact the target object to generate abnormal waves. This abnormal wave, as a mechanical wave in the environment, can form a superimposed echo with the output mechanical wave. The output mechanical wave and the received superimposed echo are analyzed. The analysis of the echo data can determine the abnormal wave. This abnormal wave is a characteristic echo, and an ultrasonic image is formed based on the characteristic echo conversion image function. Using the steady-state function of the MOS tube set, the startup process and the induced electric field deformation of the steady-state process of the field effect transistor are analyzed, which can reduce the ambiguity of the ultrasonic image.

[0040] In one embodiment of the present application, S100 includes:

[0041] S111, determining the cycle length of output PWM data.

[0042] S112, based on the cycle length of the output PWM data and the voltage intensity of the output PWM data, determining the accumulated amount of the voltage of the output PWM in the full cycle over time.

[0043] S113, based on the duty cycle of output PWM data.

[0044] S114, storing the output PWM data includes the accumulated amount of the voltage for the output PWM over time.

[0045] S115, defining the output PWM data to include the accumulated amount of the voltage for output PWM over time as the accumulated amount of voltage.

[0046] Specifically, multiplying the PWM signal means increasing the frequency of the PWM signal, but the duty cycle does not change. If the frequency after PWM multiplication is greater than the resolution of the processor I0, the piezoelectric material can default to analog quantity and can be input into the analog quantity I / 0.

[0047] In general, the PWM duty cycle is calculated by converting the accumulated voltage of the output PWM data over time. A program is written in the processor to measure the high level time of the PWM signal during this period, thereby calculating the accumulated voltage corresponding to the duty cycle.

[0048] In one embodiment of the present application:

[0049] S121, determining the cycle length of output PWM data.

[0050] S122, based on the cycle length of the output PWM data and the current intensity of the output PWM data, determining the accumulated amount of the current of the output PWM in the full cycle over time.

[0051] S123, based on the duty cycle of output PWM data.

[0052] S124, storing the output PWM data includes the accumulated amount of the current for the output PWM over time.

[0053] S125, defining the output PWM data to include the accumulated amount of the current for output PWM over time as the accumulated current amount.

[0054] Specifically, the PWM signal can be multiplied by the accumulated amount of current for output PWM data, that is, the frequency of the PWM signal is increased, but the duty cycle does not change. If the frequency after PWM multiplication is greater than the resolution of the processor I0, the piezoelectric material can be used as an analog quantity by default, and thus can be input into the analog quantity I / 0.

[0055] Generally, for milliampere currents, PWM frequency multiplication technology can be used to achieve a frequency greater than the resolution of processor I0 after PWM frequency multiplication, so that the piezoelectric material defaults to the I0 output end as an analog quantity, which can be input into the analog quantity I / 0.

[0056] In one embodiment of the present application, S100 further includes:

[0057] S131, determining a target voltage fluctuation function based on the voltage accumulation amount and the cycle length of the output PWM data.

[0058] S132, determining a target current fluctuation function based on the current accumulation amount and the cycle length of the output PWM data.

[0059] Specifically, a signal is an electrical component of GP8101, which inputs a PWM signal Q with a duty cycle of 0%-100%, and linearly converts it into an analog voltage output of 0-5V or 0-10V. GP8101M inputs a PWM signal with a duty cycle of 0%-100%, and linearly converts it into an analog voltage output of 0-5V or 0-10V. This chip needs to be used together with a high-frequency modulation APC chip (GP9301M, GP9303M, etc.) for capacitor isolation of analog signals or transformer isolation. The input signal range is 0%-100%. Input PWM signal high level: 3.0V-5.5V, output voltage error: <1% (0.5%), output voltage linearity error <0.5% (0.2%), power supply voltage: 10V-15V, power consumption: <2mA, startup time: <2ms, operating temperature: -40℃ to85℃.

[0060] In one embodiment of the present application, S200 includes:

[0061]

[0062] Among them, E p is the induced electric field, V' is the starting voltage, is the deformed magnetic field, r is the basic magnetic field width, that is, the equivalent width of the electrical device, and r' is the distance between the target area and the basic magnetic field.

[0063] The changing induced magnetic field can be measured by a magnetic field sensor.

[0064] It is understandable that when there is a conductive medium, the electric field induced by the time-varying magnetic field of the quasi-static field generates an induced current in the conductive medium. This induced current is the same as the conduction current generated by the excitation source (and its magnitude cannot be ignored) and will generate a magnetic field. The distribution of the electric field around the conductor in the quasi-static system has important engineering significance. For example, the insulation of the power transformer winding depends on the quasi-static field electric field.

[0065] It is assumed that the conductor in the magnetic quasistatic system is a good conductor (approximately a perfect conductor) and the insulating material around it is a linear medium. Since the charge relaxation time in a good conductor is much shorter than the time scale involved in engineering, there is no space charge density in the conductor. In addition, the charge relaxation time in insulating materials (including lossy media) is very long, but for uniform linear media, there is no free charge density in the medium.

[0066] Therefore, an induced current will be generated in a high-frequency electric field, and this induced current will generate a parasitic magnetic field. The electromagnetic environment such as the induced electric field and the parasitic magnetic field will affect the blurriness of the ultrasound image.

[0067] S210, incorporating the target voltage fluctuation function into Formula 1.

[0068] S220, obtaining a fluctuation function of the output voltage.

[0069] S310, defining the waveform of the output mechanical wave to be the same as the waveform of the wave function of the output voltage.

[0070] Specifically, the waveform of the mechanical wave is the same as the waveform of the fluctuation function of the output voltage, and the cycle length and duty cycle of the output PWM data are linked with the fluctuation function of the output voltage, which effectively reduces the blurriness of the image.

[0071] In one embodiment of the present application, S200 further includes:

[0072]

[0073] Among them, F(T) is the echo after superposition, F(t1) is the mechanical wave after contacting the environment, F(t2) is the output mechanical wave, q is the environmental adjustment constant, C1 is the amplitude of the mechanical wave after contacting the environment, ω1 is the inverse of the frequency of the mechanical wave after contacting the environment, C2 is the amplitude of the output mechanical wave, ω2 is the inverse of the frequency of the output mechanical wave, and ζ is the superposition damping.

[0074] Specifically, superimposed damping is related to the attenuation rate of vibration, and the attenuation rate is often expressed as Calculated by the method.

[0075] There is a linear relationship between superposition damping and the attenuation rate of vibration with a constant coefficient. When the fuzzy algorithm is used, this embodiment ignores the constant coefficient, thereby improving the effectiveness of mechanical wave analysis in complex environments.

[0076] In fact, in the working state of large monitoring data volume, due to the superposition between mechanical waves, the superposition damping is small and approaches zero, so the superposition damping can take a non-zero constant. When the superposition damping takes a constant less than 1, the high-frequency mechanical waves in the mechanical waves of the stronger environment can be adjusted.

[0077] When the superposition damping takes a constant greater than 1, the low-frequency mechanical waves in the fundamental mechanical waves of the weaker environment can be adjusted.

[0078] When ultrasound waves pass from one substance to another substance with a different acoustic impedance, two things happen. Part of the ultrasound waves continue into the second substance, but are slightly deflected from their original direction. This bending of ultrasound waves when they pass from one substance to another substance with a different acoustic impedance is called refraction.

[0079] In addition, part of the sound wave is reflected back to the probe. The amount of reflection depends on the difference in the acoustic impedance of the two materials. The greater the difference, the stronger the reflection. The reflected wave is very important because only the reflected wave can return to the detector and provide the machine with information to display the image.

[0080] As ultrasound waves travel from one tissue to the next, each tissue has a different acoustic impedance, and some of the waves are reflected back at each intersection. As a result, multiple reflected waves return to the probe, and the machine uses this information to display an image showing the different tissues.

[0081] Compressing the wave into a smaller length means that the high and low pressure oscillations of the wave become more concentrated. When a wave is compressed, it has more oscillations (high / low pressure areas) per second than before (i.e. the frequency increases). The waves reflected by an object moving toward the probe have a higher frequency than the waves that were emitted.

[0082] The Doppler effect also occurs when an object moves away from the transmitting probe. Again, there is a difference between the frequency of the transmitted wave and the frequency of the returning wave. This time, however, the frequency of the returning wave is lower than the frequency of the transmitted wave. The faster the object moves, the greater the frequency difference. The reason for the drop in frequency is the opposite of the explanation given previously. In this case, the object moving away "stretches" the waves. The stretching reduces the number of oscillations per second.

[0083] In one embodiment of the present application, S700 includes:

[0084] S710, based on the cross-platform computer vision library, generate a cross-platform computer vision library calling function.

[0085] S720, generate a connection function using the type managed by the system.

[0086] S730, incorporating the cross-platform computer vision library calling function and connection function into the feature echo-to-image function.

[0087] Specifically, OpenCV (open source computer vision library) is a cross-platform computer vision library based on BSD open source, which can run on Linux, Windows, Android and Mac OS operating systems. It is lightweight and efficient - it consists of a series of C functions and a small number of C++ classes, and provides interfaces for languages ​​such as Python, Ruby, and MATLAB, and implements many common algorithms in image processing and computer vision. OpenCV is written in C++, and its main interface is also in C++, but it still retains a large number of C language interfaces. In the development of computer vision projects, OpenCV, as a more popular open source library, has a rich library of commonly used image processing functions. It is written in C / C++ and can run on operating systems such as Linux / Windows / Mac, and can quickly implement some image processing and recognition tasks. OpenCV also provides interfaces for Java, python, cuda, etc., and basic algorithm calls for machine learning.

[0088] As a part of the image recognition function, the connection function can connect the operation program of the processor and the storage calling program of the memory.

[0089] The connection function can also connect the processor's computing program and the cloud storage calling program, and the connection function can connect the processor's computing program and the cloud computing program, thereby realizing the processor's high applicability in complex optical wave parsing and analysis environments.

[0090] The present application provides a medical ultrasound image intelligent processing system.

[0091] like Figure 1 As shown, in one embodiment of the present application, a medical ultrasound image intelligent processing system includes:

[0092] The processor 100 is used to execute the medical ultrasound image intelligent processing method.

[0093] The mechanical wave circuit 200 is electrically connected to the processor 100 .

[0094] The display 300 is electrically connected to the processor 100 .

[0095] The present embodiment relates to a medical ultrasonic image intelligent processing system. The processor 100 determines the output alternating voltage waveform of the target by calling the cycle length and duty cycle of the output PWM data. The output alternating voltage waveform of the target is input into the steady-state function of the MOS tube set, and the induced electric field applied to the piezoelectric material of the mechanical wave circuit 200 can be determined. The piezoelectric material emits ultrasonic waves, and the ultrasonic waves contact the target object to generate abnormal waves. This abnormal wave, as a mechanical wave in the environment, can form a superimposed echo with the output mechanical wave. The output mechanical wave and the received superimposed echo are analyzed. The analysis of the echo data can determine the abnormal wave. This abnormal wave is a characteristic echo, and an ultrasonic image is formed based on the characteristic echo conversion image function and displayed on the display 300. By using the steady-state function of the MOS tube set, the induced electric field deformation of the start-up process and the steady-state process of the field effect transistor is analyzed, and the ambiguity of the ultrasonic image can be reduced.

[0096] As can be understood, the medical ultrasonic diagnostic instrument mainly consists of two parts, namely the processor 100 in the main unit of the device and the mechanical wave circuit 200 of the ultrasonic probe. The main unit of the ultrasonic diagnostic instrument mainly processes and displays the signals received from the probe. The ultrasonic probe can transmit and receive ultrasound, perform electroacoustic signal conversion, convert the electrical signal sent by the main unit into a high-frequency oscillating ultrasonic signal, and convert the ultrasonic signal reflected from the tissue and organs into an electrical signal and display it on the display 300 of the main unit.

[0097] The technical features of the above-described embodiments may be arbitrarily combined, and the execution order of the method steps is not limited. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A medical ultrasound image intelligent processing method, characterized in that: include: Call the cycle length and duty cycle of the output PWM data; Based on the steady-state function of the MOS tube set, the wave function of the output ultrasonic wave is determined; Receive echo data; According to the echo data analysis function, the characteristic echo to be cleaned is obtained; Based on the wave function of ultrasonic waves, the fuzzy parameters of the characteristic echo to be cleaned are fitted; Obtain characteristic echo; An ultrasound image is formed based on a characteristic echo-to-image function.

2. The medical ultrasound image intelligent processing method according to claim 1, characterized in that: The calling of the cycle length and duty cycle of the output PWM data includes: Determine the cycle length of the output PWM data; Based on the cycle length of the output PWM data and the voltage intensity of the output PWM data, determine the accumulated amount of the voltage of the output PWM in the full cycle over time; Based on the duty cycle of output PWM data; The output PWM data is stored in the accumulated amount of the voltage of the output PWM over time; The output PWM data is defined as the voltage accumulation amount of the output PWM over time.

3. The medical ultrasound image intelligent processing method according to claim 2, characterized in that: The calling of the cycle length and duty cycle of the output PWM data also includes: Determine the cycle length of the output PWM data; Based on the cycle length of the output PWM data and the current intensity of the output PWM data, determine the accumulated amount of the current of the output PWM in the full cycle over time; Based on the duty cycle of output PWM data; The output PWM data is stored with the accumulated amount of current for the output PWM over time; The output PWM data is defined as the current accumulation amount of the output PWM current over time.

4. The medical ultrasound image intelligent processing method according to claim 3, characterized in that: The calling of the cycle length and duty cycle of the output PWM data also includes: Determine the target voltage fluctuation function based on the voltage accumulation amount and the cycle length of the output PWM data; The target current fluctuation function is determined based on the current accumulation amount and the cycle length of the output PWM data.

5. The medical ultrasonic image intelligent processing method according to claim 4, characterized in that: The step of determining the wave function of the output ultrasonic wave based on the steady-state function of the MOS tube set includes: Formula 1 Among them, E p is the induced electric field, V' is the starting voltage, is the deformed magnetic field, r is the basic magnetic field width, that is, the equivalent width of the electrical device, and r' is the distance between the target area and the basic magnetic field.

6. The medical ultrasound image intelligent processing method according to claim 5, characterized in that: The method of determining the wave function of outputting ultrasonic waves based on the steady-state function of the MOS tube set also includes: Incorporate the target voltage fluctuation function into Formula 1; Obtain the fluctuation function of the output voltage.

7. The medical ultrasonic image intelligent processing method according to claim 6, characterized in that: The receiving echo data comprises: The shape of the mechanical wave that defines the output is the same as the shape of the wave function of the output voltage.

8. The medical ultrasound image intelligent processing method according to claim 7, characterized in that: The receiving echo data further comprises: Among them, F(T) is the echo after superposition, F(t1) is the mechanical wave after contacting the environment, F(t2) is the output mechanical wave, q is the environmental adjustment constant, C1 is the amplitude of the mechanical wave after contacting the environment, ω1 is the inverse of the frequency of the mechanical wave after contacting the environment, C2 is the amplitude of the output mechanical wave, ω2 is the inverse of the frequency of the output mechanical wave, and ζ is the superposition damping.

9. The medical ultrasound image intelligent processing method according to claim 8, characterized in that: The forming of an ultrasound image based on a characteristic echo-to-image function comprises: Based on the cross-platform computer vision library, generate a cross-platform computer vision library call function; Generate connection functions using system-managed types; Incorporate cross-platform computer vision library calling functions and connection functions into the feature echo-to-image function.

10. A medical ultrasonic image intelligent processing system, characterized in that: include: A processor, configured to execute a medical ultrasound image intelligent processing method according to any one of claims 1 to 9; a mechanical wave circuit, electrically connected to the processor; A display is electrically connected to the processor.

Images