Medical defect detection method and system based on magneto-acoustic-electric imaging

Abstract

The invention provides a medical defect detection method and system based on magneto-acoustic-electric imaging, and relates to the technical field of defect detection. The electromagnetic response quantity of each detection area is determined according to the frequency characteristic of an induced magnetic field and the distribution characteristic of an electromagnetic signal; performing signal deconvolution on the magneto-acoustic-electric imaging based on each electromagnetic response quantity and the field intensity distribution characteristics in the electromagnetic excitation to obtain convolution excitation information; determining the coupling elasticity modulus of each detection area according to the coupling characteristic of the coupling sound field and the time domain characteristic of the acoustic signal, and carrying out coupling inversion on the magnetoacoustic electric imaging according to all the coupling elasticity moduli and the excitation intensity of the alternating electric field to obtain an inversion coupling characteristic; and performing partition imaging mapping on the defects in the magnetoacoustic-electric imaging based on the convolution excitation information and the inversion coupling characteristics to obtain imaging defects in the magnetoacoustic-electric imaging, and realizing partition fusion detection of the defects in the magnetoacoustic-electric imaging.

Description

Technical Field

[0001] The present application relates to the technical field of defect detection, and more specifically, to a medical defect detection method and system based on magnetoacoustic electrical imaging. Background Art

[0002] Magnetoacoustic-electric imaging combines the advantages of magnetic fields, sound waves and electrical signals, and has made significant progress in medical defect detection in recent years. Magnetoacoustic-electric imaging can achieve high-resolution and high-contrast internal structure imaging by utilizing the response characteristics of magnetic materials, sound wave conduction and the interaction of electrical signals. It has potential in the early diagnosis of tissue defects, tumors, etc.

[0003] Existing technologies often face problems such as insufficient defect detection accuracy, difficulty in effectively combining different types of signals, and inability to accurately identify tiny or deep defects in complex environments. Partition fusion detection can effectively improve the ability to identify defects under complex working conditions by processing defect information in different areas separately, especially the detection of hidden or deep defects. Fusion of data from different signal sources can make up for the shortcomings of a single detection method, thereby more accurately locating, identifying and classifying different types of defects. Therefore, how to achieve partition fusion detection of defects in magnetoacoustic and electrical imaging to improve the positioning accuracy of defects is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a medical defect detection method and system based on magnetoacoustic electrical imaging, which can realize the partition fusion detection of defects in magnetoacoustic electrical imaging.

[0005] In a first aspect, the present application provides a medical defect detection method based on magnetoacoustic electrical imaging, the defect detection method comprising the following steps:

[0006] Under the alternating electric field of electromagnetic excitation, the coupled acoustic field and the induced magnetic field under the alternating electric field are monitored, and the acoustic signal and electromagnetic signal of the medical target are collected;

[0007] Determine the electromagnetic response of each detection area in the medical target according to the frequency characteristics of the induced magnetic field and the distribution characteristics of the electromagnetic signal, perform signal deconvolution on the magnetoacoustic-electric imaging based on each electromagnetic response and the field intensity distribution characteristics in the electromagnetic excitation, and obtain the convolution excitation information of the induced magnetic field during the magnetoacoustic-electric imaging;

[0008] Determine the coupled elastic modulus of each detection area in the medical target by the coupling characteristics of the coupled acoustic field and the time domain characteristics of the acoustic signal, perform coupled inversion on the magnetoacoustic-electric imaging according to all the coupled elastic moduli and the excitation intensity of the alternating electric field, and obtain the inversion coupling characteristics of the coupled acoustic field during magnetoacoustic-electric imaging;

[0009] Based on the convolution excitation information and the inversion coupling characteristics, the defects in magnetoacoustic-electric imaging are subjected to partition imaging mapping to obtain imaging defects during magnetoacoustic-electric imaging.

[0010] In this embodiment, determining the electromagnetic response amount of each detection area in the medical target according to the frequency characteristics of the induced magnetic field and the distribution characteristics of the electromagnetic signal specifically includes:

[0011] For each detection area in the medical target, extracting the distribution characteristics of the signal intensity in the detection area from the distribution characteristics of the electromagnetic signal;

[0012] Extracting the frequency spectrum characteristics of the signal in the detection area from the frequency characteristics of the induced magnetic field;

[0013] The electromagnetic response amount of the detection area is determined according to the distribution characteristics and the frequency spectrum characteristics, and then the electromagnetic response amount of each detection area in the medical target is obtained.

[0014] In this embodiment, the signal deconvolution of the magnetoacoustic-electric imaging is performed based on each electromagnetic response quantity and the field intensity distribution characteristics in the electromagnetic excitation, and the convolution excitation information of the induced magnetic field during the magnetoacoustic-electric imaging is obtained, which specifically includes:

[0015] The signal convolution model of the induced magnetic field is constructed through the field intensity distribution characteristics in electromagnetic excitation;

[0016] Based on the signal convolution model and the deconvolution algorithm, the electromagnetic signal in the magnetoacoustic-electric imaging is deconvoluted to obtain the excitation signal of the induced magnetic field;

[0017] The convolution excitation information of the induced magnetic field during magnetoacoustic-electric imaging is extracted from the excitation signal according to each electromagnetic response amount.

[0018] In this embodiment, determining the coupling elastic modulus of each detection area in the medical target by coupling characteristics of the coupled sound field and the time domain characteristics of the acoustic signal specifically includes:

[0019] For each detection area in the medical target, the elastic response of the detection area is extracted from the coupling characteristics of the coupled acoustic field;

[0020] Extracting dynamic response characteristics of the detection area from the time domain characteristics of the acoustic signal;

[0021] The coupling elastic modulus of the detection area is determined according to the dynamic response characteristics and the elastic response amount, and then the coupling elastic modulus of each detection area in the medical target is obtained.

[0022] In this embodiment, coupling inversion is performed on magnetoacoustic-electric imaging according to all coupling elastic moduli and the excitation intensity of the alternating electric field, and the inversion coupling characteristics of the coupled acoustic field during magnetoacoustic-electric imaging are obtained, which specifically include:

[0023] Determine the elastic inversion value of the coupled acoustic field according to all coupled elastic moduli;

[0024] Performing coupling verification on the elastic inversion value through the excitation intensity of the alternating electric field to obtain coupling inversion parameters;

[0025] Based on the coupling inversion parameters, the acoustic field of the magnetoacoustic-electric imaging is inverted to obtain the inversion coupling characteristics of the coupled acoustic field during the magnetoacoustic-electric imaging.

[0026] In this embodiment, based on the convolution excitation information and the inversion coupling characteristics, the defects in the magnetoacoustic-electrical imaging are subjected to partition imaging mapping, and the imaging defects obtained during the magnetoacoustic-electrical imaging specifically include:

[0027] Based on an imaging algorithm, the convolution excitation information and the inversion coupling feature are combined to perform fusion imaging to obtain a partition fusion image of the medical target;

[0028] Defects are marked on the partition fusion image, thereby obtaining imaging defects during magnetoacoustic-electrical imaging.

[0029] In this embodiment, defects are marked on the partition fusion image, and then imaging defects during magnetoacoustic electric imaging are obtained by automatically marking defects in the partition fusion image using a convolutional neural network in deep learning, and then all marked defects are used as imaging defects during magnetoacoustic electric imaging.

[0030] In this embodiment, an acoustic sensor array is used to monitor the coupled acoustic field under the alternating electric field.

[0031] In this embodiment, an electromagnetic sensor array is used to monitor the induced magnetic field under the alternating electric field.

[0032] In a second aspect, the present application provides a medical defect detection system based on magnetoacoustic electric imaging, which is used to perform a medical defect detection method based on magnetoacoustic electric imaging, and the defect detection system includes:

[0033] A signal acquisition module is used to collect real-time operation signals of the target vehicle charging pile;

[0034] A fault data extraction module is used to extract the fault operation signal of the target vehicle charging pile from the real-time operation signal, decompose and quantify the fault operation signal, and obtain local fault data and global fault data of the target vehicle charging pile;

[0035] A fault prediction module, used to determine the coupling elastic modulus through the local fault data and the global fault data, perform fault prediction according to the fault description vector and the environmental operating parameters of the target vehicle charging pile, and obtain a fault prediction result of the target vehicle charging pile;

[0036] A fault judgment module is used to determine the imaging defect using the fault prediction result and the fault description vector, and judge the fault state of the target vehicle charging pile according to the fault coefficient.

[0037] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0038] Under the alternating electric field of electromagnetic excitation, the coupled acoustic field and the induced magnetic field under the alternating electric field are monitored, and the acoustic signal and the electromagnetic signal of the medical target are collected; the electromagnetic response of each detection area in the medical target is determined according to the frequency characteristics of the induced magnetic field and the distribution characteristics of the electromagnetic signal, and the signal deconvolution of the magnetoacoustic-electric imaging is performed based on each electromagnetic response and the field strength distribution characteristics in the electromagnetic excitation to obtain the convolution excitation information of the induced magnetic field during magnetoacoustic-electric imaging; the coupled elastic modulus of each detection area in the medical target is determined by the coupling characteristics of the coupled acoustic field and the time domain characteristics of the acoustic signal, and the magnetoacoustic-electric imaging is coupled inverted according to all the coupled elastic moduli and the excitation intensity of the alternating electric field to obtain the inversion coupling characteristics of the coupled acoustic field during magnetoacoustic-electric imaging; the defects in the magnetoacoustic-electric imaging are partitioned and imaged based on the convolution excitation information and the inversion coupling characteristics to obtain the imaging defects during magnetoacoustic-electric imaging.

[0039] It can be seen that in the present application, based on the convolution excitation information and the inversion coupling characteristics, the defects in the magnetoacoustic electric imaging are partitioned and imaged to obtain the imaging defects during magnetoacoustic electric imaging; first, the convolution excitation information is determined to obtain the signal convolution information related to the electromagnetic response of the target area. In magnetoacoustic electric imaging, the convolution excitation information of the induced magnetic field can help reveal the subtle structural changes in the target area, especially those areas related to defects. The convolution excitation information can effectively identify the electromagnetic field intensity distribution characteristics of different areas, which is helpful to distinguish different types of defects, such as cracks, bubbles or other diseased areas, thereby improving the spatial resolution of imaging, so that the magnetoacoustic electric imaging system can accurately distinguish the various detection areas in the target, thereby achieving more accurate defect positioning and feature extraction. In addition, the convolution excitation information provides a basis for subsequent defect detection. A more realistic and detailed electromagnetic response is obtained, the detection capability of the entire imaging system is optimized, and the accuracy of defect zoning and fusion detection is improved; then, the inversion coupling characteristics are determined to obtain the characteristics that describe the interaction relationship between the acoustic field and the electromagnetic field. By considering the influence of the coupling elastic modulus and the alternating electric field excitation intensity in different detection areas, the propagation behavior of the acoustic field in complex media can be accurately simulated, so that the nonlinear characteristics of the coupled acoustic field can be converted into quantifiable inversion characteristics, which helps to detect the complex interaction between the acoustic field and the electromagnetic field, and then accurately identify possible defects. Through the inversion of the coupling characteristics, the imaging system can identify tiny defects or abnormal structures in the target area, especially those areas where electromagnetic signals or acoustic signals cannot be effectively detected alone. This not only improves the detection resolution, but also realizes the accurate classification of different defect types.

[0040] In summary, the technical solution adopted in this application can realize the partition fusion detection of defects in magnetoacoustic and electrical imaging. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0042] Figure 1 is a flow chart of a medical defect detection method based on magnetoacoustic electrical imaging provided by the present application;

[0043] Figure 2 is an exemplary flow chart for determining the coupling elastic modulus provided in the present application;

[0044] Figure 3 is an exemplary flow chart for determining imaging defects according to the present application;

[0045] Figure 4 This is a module structure diagram of a medical defect detection system based on magnetoacoustic electrical imaging provided in this application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] The embodiment of the present application provides a medical defect detection method and system based on magnetoacoustic-electric imaging, the core of which is to monitor the coupled acoustic field and induced magnetic field under the alternating electric field of electromagnetic excitation, and collect the acoustic signal and electromagnetic signal of the medical target under test; determine the electromagnetic response of each detection area in the medical target under test according to the frequency characteristics of the induced magnetic field and the distribution characteristics of the electromagnetic signal, perform signal deconvolution on the magnetoacoustic-electric imaging based on each electromagnetic response and the field strength distribution characteristics in the electromagnetic excitation, and obtain the convolution excitation information of the induced magnetic field during magnetoacoustic-electric imaging; determine the coupled elastic modulus of each detection area in the medical target under test through the coupling characteristics of the coupled acoustic field and the time domain characteristics of the acoustic signal, perform coupled inversion on the magnetoacoustic-electric imaging based on all the coupled elastic moduli and the excitation intensity of the alternating electric field, and obtain the inversion coupling characteristics of the coupled acoustic field during magnetoacoustic-electric imaging; perform partition imaging mapping on the defects in the magnetoacoustic-electric imaging based on the convolution excitation information and the inversion coupling characteristics, and obtain the imaging defects during magnetoacoustic-electric imaging. The above scheme can realize the partition fusion detection of defects in magnetoacoustic-electric imaging.

[0048] Embodiment 1

[0049] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 As shown in FIG. 1 , this figure is an exemplary flow chart of a medical defect detection method based on magnetoacoustic electrical imaging according to this embodiment of the present application, and the defect detection method includes the following steps:

[0050] In step S1, under the alternating electric field of electromagnetic excitation, the coupled acoustic field and the induced magnetic field under the alternating electric field are monitored, and the acoustic signal and the electromagnetic signal of the medical target are collected.

[0051] It should be noted that in the present application, an electromagnetic sensor array is used to monitor the induced magnetic field under an alternating electric field; an acoustic sensor array is used to monitor the coupled acoustic field under an alternating electric field; and the medical targets to be measured may be tissues, organs and diseased areas inside or on the surface of the human body.

[0052] In specific implementation, under the alternating electric field of electromagnetic excitation, a high-frequency alternating electric field is first generated by an electromagnetic excitation device to excite the medical target to be measured. The alternating electric field will cause the propagation of electromagnetic waves in the target area and interact with the material in the target area to produce a coupling effect of an induced magnetic field and an acoustic field. The electromagnetic sensor array and the acoustic sensor array can be arranged to synchronously collect signals of the induced magnetic field and the coupled acoustic field near the target area. After the signal is collected, the collected electromagnetic signal and acoustic signal are synchronously processed using digital signal processing technology. Specifically, the characteristic parameters of the signal are first extracted by frequency analysis and time domain analysis methods. The characteristic parameters include the spectral characteristics of the magnetic field and the time domain characteristics of the acoustic wave. The signal is then deconvolved and filtered to remove noise interference and highlight the response characteristics of the target area. These processing technologies combined with existing signal processing algorithms (for example, fast Fourier transform FFT and time-frequency analysis) can effectively extract the electromagnetic response and acoustic field characteristics of the medical target to be measured, providing reliable basic data for subsequent defect detection and imaging.

[0053] In step S2, the electromagnetic response amount of each detection area in the medical target is determined according to the frequency characteristics of the induced magnetic field and the distribution characteristics of the electromagnetic signal, and the magnetoacoustic-electric imaging signal is deconvoluted based on the various electromagnetic response amounts and the field strength distribution characteristics in the electromagnetic excitation to obtain the convolution excitation information of the induced magnetic field during magnetoacoustic-electric imaging.

[0054] In this embodiment, the electromagnetic response amount of each detection area in the medical target to be measured can be determined according to the frequency characteristics of the induced magnetic field and the distribution characteristics of the electromagnetic signal in the following manner, namely:

[0055] For each detection area in the medical target, extracting the distribution characteristics of the signal intensity in the detection area from the distribution characteristics of the electromagnetic signal;

[0056] Extracting the frequency spectrum characteristics of the signal in the detection area from the frequency characteristics of the induced magnetic field;

[0057] The electromagnetic response amount of the detection area is determined according to the distribution characteristics and the frequency spectrum characteristics, and then the electromagnetic response amount of each detection area in the medical target is obtained.

[0058] It should be noted that, in the present application, the electromagnetic response refers to the reaction intensity of each detection area in the medical target under the action of the induced magnetic field to the electromagnetic signal; the distribution characteristics of the signal intensity refer to the intensity change characteristics of the electromagnetic signal in each area in space; the spectrum characteristics refer to the distribution of the signal in the detection area on different frequency components.

[0059] In specific implementation, first, the area corresponding to the medical target to be measured can be divided into multiple detection areas by using the layout of the electromagnetic sensor array and the acoustic sensor array. For each detection area in the medical target to be measured, a spatial interpolation algorithm (for example, Kriging interpolation) can be used to model the spatial distribution of the signal to obtain the distribution characteristics of the electromagnetic signal, and the signal strength information in the detection area is extracted from the distribution characteristics of the electromagnetic signal. The signal strength information is arranged according to the spatial position as the distribution characteristics of the signal strength in the detection area; then, the frequency characteristics of the induced magnetic field can be extracted by wavelet transform, and the frequency characteristics can be used as the spectrum characteristics of the signal in the detection area; finally, a finite element model based on the least squares method is initialized, the distribution characteristics are used as the boundary conditions and source terms in the finite element model, and the spectrum characteristics are used as the input parameters in the frequency domain of the finite element model. The finite element model is used to simulate the propagation and distribution of the electromagnetic field in the detection area, and the output value of the response simulation result in the finite element model can be used as the electromagnetic response amount of the detection area. The electromagnetic response amount of each detection area in the medical target to be measured can be obtained in the above manner.

[0060] In this embodiment, the signal deconvolution of the magnetoacoustic-electric imaging is performed based on the field intensity distribution characteristics of each electromagnetic response and electromagnetic excitation, and the convolution excitation information of the induced magnetic field during the magnetoacoustic-electric imaging is obtained in the following manner, namely:

[0061] The signal convolution model of the induced magnetic field is constructed through the field intensity distribution characteristics in electromagnetic excitation;

[0062] Based on the signal convolution model and the deconvolution algorithm, the electromagnetic signal in the magnetoacoustic-electric imaging is deconvoluted to obtain the excitation signal of the induced magnetic field;

[0063] The convolution excitation information of the induced magnetic field during magnetoacoustic-electric imaging is extracted from the excitation signal according to each electromagnetic response amount.

[0064] It should be noted that in the present application, convolution excitation information refers to signal convolution information related to the electromagnetic response of the target area; the excitation signal refers to a signal that can stimulate the electromagnetic response of the target area; and the signal convolution model is a mathematical model that describes the interaction between the electromagnetic excitation signal and the electromagnetic response of the target area.

[0065] In the specific implementation, first, under electromagnetic excitation, the response of the induced magnetic field is the convolution result between the excitation source signal and the propagation characteristics of the target area. Therefore, the field intensity distribution characteristics in the electromagnetic excitation can be used as the source data for constructing the convolution model, so as to combine the excitation signal with the propagation characteristics of the target area to construct the signal convolution model of the induced magnetic field; then, a deconvolution algorithm (for example: Wiener deconvolution) is used in the signal convolution model to deconvolve the electromagnetic signal in magnetoacoustic-electric imaging, and the deconvolution result in the signal convolution model can be used as the excitation signal of the induced magnetic field; finally, each electromagnetic response quantity is used as the weight of the signal strength of each detection area in the excitation signal, and the weighted average of the corresponding signal strength of each detection area in the excitation signal is calculated as the convolution excitation information of the induced magnetic field during magnetoacoustic-electric imaging.

[0066] In step S3, the coupling elastic modulus of each detection area in the medical target is determined by the coupling characteristics of the coupled sound field and the time domain characteristics of the acoustic signal, and the magnetoacoustic-electric imaging is coupled inverted according to all the coupling elastic moduli and the excitation intensity of the alternating electric field to obtain the inversion coupling characteristics of the coupled sound field during magnetoacoustic-electric imaging.

[0067] It should be noted that, in the present application, the coupling characteristics of the coupled sound field are the set of elastic response quantities corresponding to each detection area in the medical target to be measured, and the elastic response quantity refers to the response intensity of the target area to the coupled sound field; the time domain characteristics of the acoustic signal are the set of dynamic response characteristics corresponding to each detection area in the medical target to be measured, and the dynamic response characteristics refer to the time domain response characteristics of the detection area under the excitation of the external sound field; in specific implementation, for each detection area in the medical target to be measured, the boundary element method can be used to simulate the sound field of the coupled sound field in each detection area, and the quantized value of the simulation result is used as the elastic response quantity of the detection area, and the time-frequency analysis method (for example: wavelet transform) can be used to extract the time domain characteristics of the signal at the detection area as the dynamic response characteristics of the acoustic signal at the detection area. The elastic response quantity and dynamic response characteristics of each detection area in the medical target to be measured can be obtained by the above method, the set of all elastic response quantities can be used as the coupling characteristics of the coupled sound field, and the set of all dynamic response characteristics can be used as the time domain characteristics of the acoustic signal.

[0068] Preferably, in this embodiment, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart for determining the coupling elastic modulus in an embodiment of the present application. In this embodiment, the coupling elastic modulus of each detection area in the medical target to be measured is determined by the coupling characteristics of the coupled sound field and the time domain characteristics of the acoustic signal, which can be specifically implemented by the following steps:

[0069] First, in step S31, for each detection area in the medical object to be detected, the elastic response of the detection area is extracted from the coupling characteristics of the coupled acoustic field;

[0070] Then, in step S32, the dynamic response characteristics of the detection area are extracted from the time domain characteristics of the acoustic signal;

[0071] Finally, in step S33, the coupling elastic modulus of the detection area is determined according to the dynamic response characteristics and the elastic response amount, and then the coupling elastic modulus of each detection area in the medical target is obtained.

[0072] It should be noted that, in the present application, the coupled elastic modulus is a physical property that describes each detection area in the medical target under the interaction of acoustics and elasticity; in specific implementation, first, the elastic response of the detection area is obtained from the coupling characteristics of the coupled sound field; then, the dynamic response characteristics of the detection area are obtained from the time domain characteristics of the acoustic signal; finally, a finite difference model based on the maximum likelihood estimation method is initialized, the dynamic response characteristics are used as the boundary conditions in the finite difference model, and the elastic response is used as the medium parameter in the finite difference model. The finite difference model is used to perform coupled simulation on the propagation and distribution of the electromagnetic field in the detection area. The output value of the coupled simulation result in the finite difference model can be used as the coupled elastic modulus of the detection area. The coupled elastic modulus of each detection area in the medical target can be obtained in the above manner.

[0073] In this embodiment, coupling inversion is performed on magnetoacoustic-electric imaging according to all coupling elastic moduli and the excitation intensity of the alternating electric field to obtain the inversion coupling characteristics of the coupled acoustic field during magnetoacoustic-electric imaging, which can be specifically achieved by the following steps:

[0074] Determine the elastic inversion value of the coupled acoustic field according to all coupled elastic moduli;

[0075] Performing coupling verification on the elastic inversion value through the excitation intensity of the alternating electric field to obtain coupling inversion parameters;

[0076] Based on the coupling inversion parameters, the acoustic field of the magnetoacoustic-electric imaging is inverted to obtain the inversion coupling characteristics of the coupled acoustic field during the magnetoacoustic-electric imaging.

[0077] It should be noted that the inversion coupling feature is a feature that describes the interaction relationship between the acoustic field and the electromagnetic field. In specific implementation, first, the mean value of all coupled elastic moduli can be used as the elastic inversion value of the coupled acoustic field. Then, the electromagnetic properties of the electric field source (including: the frequency and amplitude of the power supply) and the electric field propagation medium (including: air, tissue or other substances) are obtained from the description document of the magnetoacoustic-electric imaging system. The Maxwell equations are combined with the conductivity and dielectric constant parameters in the electromagnetic properties to calculate the excitation intensity of the alternating electric field. The excitation intensity of the alternating electric field can be used as the verification weight of the coupling verification, so that the product of the excitation intensity and the elastic inversion is used as the coupling inversion parameter. Finally, an inversion model based on the coupling of the electromagnetic field and the acoustic field is initialized, and the coupling inversion parameter is used as the physical quantity in the inversion model. The inversion model is used to perform acoustic field inversion on magnetoacoustic-electric imaging. The result of the acoustic field inversion on magnetoacoustic-electric imaging can be used as the inversion coupling feature of the coupled acoustic field during magnetoacoustic-electric imaging.

[0078] In step S4, the defects in magnetoacoustic-electric imaging are subjected to partition imaging mapping based on the convolution excitation information and the inversion coupling characteristics to obtain imaging defects in magnetoacoustic-electric imaging.

[0079] Preferably, in this embodiment, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart for determining imaging defects in an embodiment of the present application. In this embodiment, based on the convolution excitation information and the inversion coupling characteristics, the defects in the magnetoacoustic-electric imaging are subjected to partition imaging mapping, and the imaging defects in the magnetoacoustic-electric imaging can be obtained by the following steps:

[0080] First, in step S41, fusion imaging is performed based on an imaging algorithm in combination with the convolution excitation information and the inversion coupling feature to obtain a partition fusion image of the medical target;

[0081] Then, in step S42, defects are marked on the partition fusion image, thereby obtaining imaging defects during magnetoacoustic and electrical imaging.

[0082] In the specific implementation, first, an imaging algorithm (for example, iterative reconstruction algorithm) is selected, and the convolution excitation information is used as the signal input of the magnetic field in the imaging algorithm, and the inversion coupling feature is used as the signal input of the sound field in the imaging algorithm. The imaging algorithm is used to fuse the information of the medical target to be measured in the magnetic field and the sound field, and the result of the fusion imaging can be used as a partition fusion map of the medical target to be measured, wherein the purpose of the imaging algorithm is to use this information to fuse multiple signal sources in space to form a comprehensive image; then, defects are marked on the partition fusion map, and then the imaging defects during magnetoacoustic and electrical imaging are obtained by using the convolutional neural network in deep learning to automatically mark the defects in the partition fusion map, and then all marked defects are used as imaging defects during magnetoacoustic and electrical imaging.

[0083] It can be seen that in the present application, based on the convolution excitation information and the inversion coupling characteristics, the defects in the magnetoacoustic electric imaging are partitioned and imaged to obtain the imaging defects during magnetoacoustic electric imaging; first, the convolution excitation information is determined to obtain the signal convolution information related to the electromagnetic response of the target area. In magnetoacoustic electric imaging, the convolution excitation information of the induced magnetic field can help reveal the subtle structural changes in the target area, especially those areas related to defects. The convolution excitation information can effectively identify the electromagnetic field intensity distribution characteristics of different areas, which is helpful to distinguish different types of defects, such as cracks, bubbles or other diseased areas, thereby improving the spatial resolution of imaging, so that the magnetoacoustic electric imaging system can accurately distinguish the various detection areas in the target, thereby achieving more accurate defect positioning and feature extraction. In addition, the convolution excitation information provides a basis for subsequent defect detection. A more realistic and detailed electromagnetic response is obtained, the detection capability of the entire imaging system is optimized, and the accuracy of defect zoning and fusion detection is improved; then, the inversion coupling characteristics are determined to obtain the characteristics that describe the interaction relationship between the acoustic field and the electromagnetic field. By considering the influence of the coupling elastic modulus and the alternating electric field excitation intensity in different detection areas, the propagation behavior of the acoustic field in complex media can be accurately simulated, so that the nonlinear characteristics of the coupled acoustic field can be converted into quantifiable inversion characteristics, which helps to detect the complex interaction between the acoustic field and the electromagnetic field, and then accurately identify possible defects. Through the inversion of the coupling characteristics, the imaging system can identify tiny defects or abnormal structures in the target area, especially those areas where electromagnetic signals or acoustic signals cannot be effectively detected alone. This not only improves the detection resolution, but also realizes the accurate classification of different defect types.

[0084] In summary, the technical solution adopted in this application can realize the partition fusion detection of defects in magnetoacoustic and electrical imaging.

[0085] Embodiment 2

[0086] This application provides a medical defect detection system based on magnetoacoustic electrical imaging, referring to Figure 4 As shown, this figure is a schematic diagram of a defect detection system according to this embodiment of the present application, and the defect detection system includes:

[0087] The signal acquisition module 100 is used to monitor the coupled acoustic field and the induced magnetic field under the alternating electric field of electromagnetic excitation, and to collect the acoustic signal and electromagnetic signal of the medical target under test;

[0088] The magnetic field processing module 200 is used to determine the electromagnetic response of each detection area in the medical target according to the frequency characteristics of the induced magnetic field and the distribution characteristics of the electromagnetic signal, and perform signal deconvolution on the magnetoacoustic-electric imaging based on each electromagnetic response and the field strength distribution characteristics in the electromagnetic excitation to obtain the convolution excitation information of the induced magnetic field during the magnetoacoustic-electric imaging;

[0089] The acoustic field processing module 300 is used to determine the coupled elastic modulus of each detection area in the medical target by coupling the coupling characteristics of the coupled acoustic field and the time domain characteristics of the acoustic signal, and to perform coupled inversion on the magnetoacoustic-electric imaging according to all the coupled elastic moduli and the excitation intensity of the alternating electric field to obtain the inversion coupling characteristics of the coupled acoustic field during magnetoacoustic-electric imaging;

[0090] The defect detection module 400 is used to perform partition imaging mapping on the defects in magnetoacoustic-electric imaging based on the convolution excitation information and the inversion coupling characteristics to obtain imaging defects during magnetoacoustic-electric imaging.

[0091] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, the storage medium including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically-erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0093] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A medical defect detection method based on magnetoacoustic electrical imaging, characterized in that: The defect detection method comprises the following steps: Under the alternating electric field of electromagnetic excitation, the coupled acoustic field and the induced magnetic field under the alternating electric field are monitored, and the acoustic signal and electromagnetic signal of the medical target are collected; Determine the electromagnetic response of each detection area in the medical target according to the frequency characteristics of the induced magnetic field and the distribution characteristics of the electromagnetic signal, perform signal deconvolution on the magnetoacoustic-electric imaging based on each electromagnetic response and the field intensity distribution characteristics in the electromagnetic excitation, and obtain the convolution excitation information of the induced magnetic field during the magnetoacoustic-electric imaging; Determine the coupled elastic modulus of each detection area in the medical target by the coupling characteristics of the coupled acoustic field and the time domain characteristics of the acoustic signal, perform coupled inversion on the magnetoacoustic-electric imaging according to all the coupled elastic moduli and the excitation intensity of the alternating electric field, and obtain the inversion coupling characteristics of the coupled acoustic field during magnetoacoustic-electric imaging; Based on the convolution excitation information and the inversion coupling characteristics, the defects in magnetoacoustic-electric imaging are subjected to partition imaging mapping to obtain imaging defects during magnetoacoustic-electric imaging.

2. A medical defect detection method based on magnetoacoustic electrical imaging as claimed in claim 1, characterized in that: Determining the electromagnetic response of each detection area in the medical target according to the frequency characteristics of the induced magnetic field and the distribution characteristics of the electromagnetic signal specifically includes: For each detection area in the medical target, extracting the distribution characteristics of the signal intensity in the detection area from the distribution characteristics of the electromagnetic signal; Extracting the frequency spectrum characteristics of the signal in the detection area from the frequency characteristics of the induced magnetic field; The electromagnetic response amount of the detection area is determined according to the distribution characteristics and the frequency spectrum characteristics, and then the electromagnetic response amount of each detection area in the medical target is obtained.

3. A medical defect detection method based on magnetoacoustic electrical imaging as claimed in claim 1, characterized in that: Based on the electromagnetic response and the field intensity distribution characteristics in the electromagnetic excitation, the signal of the magnetoacoustic-electric imaging is deconvoluted to obtain the convolution excitation information of the induced magnetic field during the magnetoacoustic-electric imaging, which specifically includes: The signal convolution model of the induced magnetic field is constructed through the field intensity distribution characteristics in electromagnetic excitation; Based on the signal convolution model and the deconvolution algorithm, the electromagnetic signal in the magnetoacoustic-electric imaging is deconvoluted to obtain the excitation signal of the induced magnetic field; The convolution excitation information of the induced magnetic field during magnetoacoustic-electric imaging is extracted from the excitation signal according to each electromagnetic response amount.

4. A medical defect detection method based on magnetoacoustic electrical imaging as claimed in claim 1, characterized in that: Determining the coupling elastic modulus of each detection area in the medical target by coupling characteristics of the coupled sound field and the time domain characteristics of the acoustic signal specifically includes: For each detection area in the medical target, the elastic response of the detection area is extracted from the coupling characteristics of the coupled acoustic field; Extracting dynamic response characteristics of the detection area from the time domain characteristics of the acoustic signal; The coupling elastic modulus of the detection area is determined according to the dynamic response characteristics and the elastic response amount, and then the coupling elastic modulus of each detection area in the medical target is obtained.

5. The medical defect detection method based on magnetoacoustic electrical imaging according to claim 1, characterized in that: According to all the coupled elastic moduli and the excitation intensity of the alternating electric field, the magnetoacoustic-electric imaging is coupled inverted to obtain the inverted coupling characteristics of the coupled acoustic field during magnetoacoustic-electric imaging, which specifically include: Determine the elastic inversion value of the coupled acoustic field according to all coupled elastic moduli; Performing coupling verification on the elastic inversion value through the excitation intensity of the alternating electric field to obtain coupling inversion parameters; Based on the coupling inversion parameters, the acoustic field of the magnetoacoustic-electric imaging is inverted to obtain the inversion coupling characteristics of the coupled acoustic field during the magnetoacoustic-electric imaging.

6. A medical defect detection method based on magnetoacoustic electrical imaging as claimed in claim 1, characterized in that: Based on the convolution excitation information and the inversion coupling characteristics, the defects in the magnetoacoustic-electrical imaging are subjected to partition imaging mapping, and the imaging defects obtained during the magnetoacoustic-electrical imaging specifically include: Based on an imaging algorithm, the convolution excitation information and the inversion coupling feature are combined to perform fusion imaging to obtain a partition fusion image of the medical target; Defects are marked on the partition fusion image, thereby obtaining imaging defects during magnetoacoustic-electrical imaging.

7. A medical defect detection method based on magnetoacoustic electrical imaging as claimed in claim 6, characterized in that: Defects are marked on the partition fusion image, and then imaging defects during magnetoacoustic and electrical imaging are obtained by automatically marking defects in the partition fusion image using a convolutional neural network in deep learning, and then all marked defects are used as imaging defects during magnetoacoustic and electrical imaging.

8. The medical defect detection method based on magnetoacoustic electrical imaging according to claim 1, characterized in that: An acoustic sensor array is used to monitor the coupled acoustic field under an alternating electric field.

9. The medical defect detection method based on magnetoacoustic electrical imaging according to claim 1, characterized in that: An electromagnetic sensor array is used to monitor the induced magnetic field under an alternating electric field.

10. A medical defect detection system based on magnetoacoustic electric imaging, used to execute a medical defect detection method based on magnetoacoustic electric imaging as claimed in any one of claims 1 to 9, characterized in that: The defect detection system comprises: A signal acquisition module is used to monitor the coupled acoustic field and the induced magnetic field under the alternating electric field of electromagnetic excitation, and to collect acoustic signals and electromagnetic signals of the medical target under test; A magnetic field processing module is used to determine the electromagnetic response of each detection area in the medical target according to the frequency characteristics of the induced magnetic field and the distribution characteristics of the electromagnetic signal, and perform signal deconvolution on the magnetoacoustic-electric imaging based on each electromagnetic response and the field strength distribution characteristics in the electromagnetic excitation to obtain the convolution excitation information of the induced magnetic field during the magnetoacoustic-electric imaging; An acoustic field processing module, used to determine the coupled elastic modulus of each detection area in the medical target by means of the coupling characteristics of the coupled acoustic field and the time domain characteristics of the acoustic signal, and to perform coupled inversion on the magnetoacoustic-electric imaging according to all the coupled elastic moduli and the excitation intensity of the alternating electric field, so as to obtain the inversion coupling characteristics of the coupled acoustic field during magnetoacoustic-electric imaging; The defect detection module is used to perform partition imaging mapping on the defects in magnetoacoustic-electric imaging based on the convolution excitation information and the inversion coupling characteristics to obtain imaging defects during magnetoacoustic-electric imaging.

Images