Method for generating brain images based on adaptive time delay phase compensation of microwave data

Abstract

The application provides a brain image generation method based on microwave data adaptive time delay phase compensation, comprising: configuring antenna transceiving parameters, the transceiving parameters comprising a scanning point number, a frequency step, and a starting frequency; collecting microwave data at frequency points based on the transceiving parameters to obtain a matrix-form microwave data set; when the number of collected points of the matrix-form microwave data set is the same as a preset number of collected points, ending the collection and saving the matrix data set; inputting the microwave data of the matrix-form microwave data set into a constructed adaptive phase compensation neural network; performing adaptive time delay phase compensation processing on the microwave data to obtain an output signal; and drawing a regional heat map according to the output signal to generate a microwave brain image. The method improves the accuracy and reliability of imaging.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of microwave imaging technology, and in particular to a brain image generation method based on adaptive time delay phase compensation of microwave data. BACKGROUND

[0002] Stroke is one of the most common cardiovascular diseases, and early detection of first or recurrent stroke and monitoring of stroke development during treatment can enable patients to receive effective treatment in a timely manner. Currently, computed tomography (CT) and magnetic resonance imaging (MRI) are the most commonly used stroke diagnosis tools, although these existing methods can give accurate diagnoses, they are too bulky to be used for on-site detection and patient bedside monitoring. In addition, due to its ionizing radiation, CT is not suitable for frequent checks. Nuclear magnetic resonance imaging is very expensive, time-consuming, and not available in all hospitals, especially in rural areas. Therefore, microwave imaging technology has been introduced as a complementary method to traditional stroke diagnosis techniques, with the advantages of low cost, fast scanning speed, good portability, and no ionizing radiation. This technology is based on detecting the dramatic change in dielectric properties of the affected area of stroke relative to the surrounding healthy tissue. The portability and low cost of this device enable it to be deployed in all hospitals, even at the first point of care, making it easier for patients in need to access these devices.

[0003] In current microwave brain imaging technology, mainly contrast source inversion, time delay inversion and time delay summation techniques are used, which rely on the propagation coefficient of the measured signal on the propagation path between the transmission source, the target area of the brain and the receiver to determine the time delay and the inversion quantity. Since the human brain is composed of multiple different tissues, from the outer skull to the inner brain tissue, the thickness and electromagnetic properties of these tissue layers have a significant impact on the speed of signal propagation, which depends on the frequency of the microwave and the electromagnetic parameters of different tissues at that frequency. In addition, since the signal propagation path is not always perpendicular to the tissue layers, this introduces errors when calculating the average path of the signal, especially when multiple signals are superimposed, this error can affect the final imaging results, which is less significant when there are fewer tissue layers and the electromagnetic parameters of the layers are not significantly different. However, if there is an air layer between the detection device and the patient's scalp, due to the large difference in electromagnetic parameters between air and brain tissue, the signal will produce significant reflection and scattering at the surface of the head, which in turn causes the imaging results to deviate. Therefore, in practical applications, due to the complex distribution of brain tissues, the distance between the antenna and the skull surface varies from person to person, the angle between the transmitted microwave signal and the target to be measured and the skull section is difficult to determine, and the antenna spacing must be fixed a priori, which can cause the microwave imaging results to deviate and become blurred. SUMMARY

[0004] Therefore, the present application provides a brain image generation method based on adaptive time delay phase compensation of microwave data to solve the above problems.

[0005] The application provides a brain image generation method based on microwave data adaptive time delay phase compensation, comprising the following steps: configuring antenna transceiving parameters, wherein the transceiving parameters comprise a scanning point number, a frequency step, and a starting frequency; collecting microwave data at frequency points based on the transceiving parameters to obtain a matrix-form microwave data set; when the number of collected points in the matrix-form microwave data set is the same as a preset number of collected points, ending the collection and saving the matrix-form microwave data set; inputting microwave data of the matrix-form microwave data set into a constructed adaptive phase compensation neural network; performing adaptive time delay phase compensation processing on the microwave data to obtain an output signal; and drawing a regional heat map according to the output signal to generate a microwave brain image.

[0006] In another implementation manner of the application, after the microwave data of the matrix-form microwave data set is input into the constructed adaptive phase compensation neural network, the method further comprises the following steps: transmitting the microwave data from an input layer of the adaptive phase compensation neural network into a hidden layer, and performing nonlinear mapping on the microwave data by using a radial basis function.

[0007] In another implementation manner of the application, the step of performing adaptive time delay phase compensation processing on the microwave data to obtain an output signal comprises the following steps: obtaining a feedforward controller based on Laplace-transformed microwave data in the case that a time delay exists when microwave passes through different tissues and causes a phase error, by using a prior given amplitude constant and phase constant; taking the feedforward controller as a compensation controller, combining the feedforward controller with a feedback controller, and obtaining an output signal.

[0008] In another implementation manner of the application, the Laplace-transformed microwave data is expressed as:

[0009]

[0010] Wherein, α is an amplitude constant, θ is a phase constant, x(s) is a Laplace-transformed microwave signal, and x(t+θ) is a microwave original signal under a θ phase condition.

[0011] x(t) is input microwave data, and is expressed as:

[0012]

[0013] Wherein, is a phase-compensated microwave signal, and N is the number of received microwave signals.

[0014] In another implementation manner of the application, the feedforward controller is expressed as:

[0015]

[0016] wherein x(s+θ) is a microwave signal with phase error θ.

[0017] In another implementation of the present application, the feedback controller is represented as:

[0018]

[0019] wherein τ is time delay; β is phase constant, which can be adjusted according to actual situation, β>1 belongs to advance compensation, β<1 belongs to lag compensation.

[0020] In another implementation of the present application, the output signal is represented as:

[0021]

[0022] wherein, T is the transpose symbol of matrix; is the Laplace transform of microwave data received by each antenna; w i is the weight vector represented by each antenna; s i is each transform vector of data for Laplace transform; W is weight, p is control coefficient, and q is weight update coefficient.

[0023] In another aspect of the present application, a brain image generation system based on adaptive time delay phase compensation of microwave data is provided, comprising: a data acquisition module: configure antenna transceiver parameters, the transceiver parameters including the number of scanning points, frequency step, starting frequency; based on the transceiver parameters, frequency point data is collected to obtain a matrix data set; when the number of sampling points of the matrix form microwave data set is the same as the preset sampling point number, the sampling is ended and the matrix data set is saved; a data processing module: input the microwave data of the matrix form microwave data set into the constructed adaptive phase compensation neural network; the microwave data is subjected to adaptive time delay phase compensation processing to obtain an output signal; an imaging module: according to the output signal, a regional thermal map is drawn to generate a microwave brain image.

[0024] In another aspect of the present application, an electronic device is provided, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the brain image generation method based on adaptive time delay phase compensation of microwave data according to any one of the above.

[0025] In another aspect of the present application, a computer storage medium is provided, characterized in that the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the brain image generation method based on adaptive time delay phase compensation of microwave data according to any one of the above.

[0026] The brain image generation method based on microwave data adaptive time delay phase compensation of the application, through the control signal transceiver format, realizes multi-frequency point multi-antenna sweep frequency receiving, takes the obtained microwave data as input, constructs an adaptive phase compensation neural network, data is transmitted from the input layer to the hidden layer, is nonlinearly mapped by the radial basis function, is compensated according to the time delay, the latter is transmitted to the output layer and output, realizes fast, accurate and effective microwave brain imaging. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical scheme in the embodiments of the application or the prior art, the drawings needed to be used in the embodiment or prior art description will be briefly introduced below, and the advantages and benefits in the scheme will become clear and obvious to those skilled in the art by reading the following detailed description of the embodiment. The drawings are only for the purpose of showing the preferred embodiments, and are not considered as limiting the application.

[0028] Figure 1 The brain image generation method based on microwave data adaptive time delay phase compensation of the application, through the control signal transceiver format, realizes multi-frequency point multi-antenna sweep frequency receiving, takes the obtained microwave data as input, constructs an adaptive phase compensation neural network, data is transmitted from the input layer to the hidden layer, is nonlinearly mapped by the radial basis function, is compensated according to the time delay, the latter is transmitted to the output layer and output, realizes fast, accurate and effective microwave brain imaging.

[0029] Figure 2 The microwave signal transceiver switch module of an embodiment of the application is shown in the figure.

[0030] Figure 3 The microwave signal acquisition overall flowchart of an embodiment of the application is shown in the figure.

[0031] Figure 4 The single frequency point single antenna signal acquisition flowchart of an embodiment of the application is shown in the figure.

[0032] Figure 5 The adaptive time delay phase compensation flowchart of an embodiment of the application is shown in the figure.

[0033] Figure 6 The radial basis neural network based on time delay phase compensation of an embodiment of the application is shown in the figure.

[0034] Figure 7 The imaging result optimization of an embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0035] To enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and thoroughly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art should fall within the protection scope of the present invention.

[0036] Figure 1 This is a schematic flowchart of a brain image generation method based on adaptive time delay phase compensation of microwave data, provided by an embodiment of the present invention. Figure 1 As shown.

[0037] S101. Configure antenna transmit and receive parameters, including the number of scan points, frequency step, and starting frequency.

[0038] For example, it is necessary to acquire microwave frequency sweep data with multiple frequency points and multiple antennas. Therefore, multiple switches are needed in series and parallel to realize single-transmit and multi-receive single-frequency microwave scanning. The MAX2871 RF chip is controlled by a typical embodiment such as an STM32 microcontroller to transmit high-frequency signals of different frequencies in sequence.

[0039] like Figure 2 As shown, taking a 16-antenna microwave signal transmission and reception example, to ensure that antennas 1 to 16 can transmit sequentially in each scan, and that all antennas except the transmitting antenna can receive signals during the transmission process, a BGSX44MU18 RF switch chip is preferred to build the switch module. The 16 antennas are connected to terminals A1-A4 of four switch chips. Terminal B1 of each switch chip is connected to terminals A1-A4 of the TX switch chip, and transmission is selectively selected via B1. Terminal B4 of each switch chip is connected to terminals A1-A4 of the RX switch chip, and reception is selectively selected via B1.

[0040] S102. Based on the transmit and receive parameters, microwave data at the frequency point is collected to obtain a microwave dataset in matrix form.

[0041] For example, such as Figure 3 As shown, after ensuring that microwave signal transmission and reception can be achieved with single transmission and multiple reception, configure the antenna transmission and reception parameters, including the number of scan points, frequency step, and starting frequency, to complete the acquisition of data at a single frequency point. For example, with 16 antennas, complete 16 microwave signal transmissions with 1 transmission and 15 receptions, thus obtaining a 16*15 matrix dataset.

[0042] Specifically, such as Figure 4As shown, firstly, the transmit frequency and power are configured according to the transmission and reception requirements. After waiting for the phase-locked loop to lock, the reference signal is acquired. Subsequently, the input matching S11 and isolation S12 parameters in the signal transmission are acquired sequentially, the Dcache buffer is refreshed, and the RMS amplitude and phase are calculated. The results of this frequency point are saved to the buffer. It is usually necessary to calculate the real and imaginary parts of the microwave signal amplitude, the phase intensity and angle, and the linear phase characteristics. Finally, the signal received by the computer is in an 8*16*15*5 matrix format.

[0043] S103. When the number of acquisition points of the microwave dataset in matrix form is the same as the preset number of acquisition points, the acquisition ends and the matrix dataset is saved.

[0044] For example, the scanning is completed based on the preset number of sampling points. For instance, if 8 frequency points are to be sampled, the sampling points are determined to be sufficient after obtaining an 8*16*15 matrix dataset, and the sampling ends and is saved.

[0045] S104. Input the microwave data of the matrix-form microwave dataset into the constructed adaptive phase compensation neural network.

[0046] For example, after obtaining microwave data for all antennas at all frequencies, the data is input into an adaptive phase compensation neural network.

[0047] S105. Perform adaptive time delay phase compensation processing on the microwave data to generate a microwave brain image.

[0048] S106. Draw a regional heat map based on the output signal to obtain microwave brain imaging results.

[0049] The present invention provides a brain image generation method based on adaptive time delay phase compensation of microwave data. By controlling the signal transmission and reception format, it achieves multi-frequency point and multi-antenna frequency sweep reception. The obtained microwave data is used as input to construct an adaptive phase compensation neural network. The data is passed from the input layer to the hidden layer and nonlinearly mapped through the radial basis function. The preceding term is compensated according to the time delay, and the following term is passed to the output layer for output, thereby achieving fast, accurate and effective microwave brain imaging.

[0050] In another implementation of the present invention, after inputting the microwave data of the matrix-form microwave dataset into the constructed adaptive phase compensation neural network, the method further includes: passing the microwave data from the input layer of the adaptive phase compensation neural network into the hidden layer, and performing nonlinear mapping on it through radial basis functions.

[0051] In another implementation of the present invention, the adaptive time delay phase compensation processing of the microwave data to obtain the output signal includes: obtaining a feedforward controller based on the microwave data after Laplace transform, using a priori given amplitude constant and phase constant, in the case of phase error caused by time delay when microwaves pass through different tissues; using the feedforward controller as a compensation controller, and combining the feedforward controller and the feedback controller to obtain the output signal.

[0052] For example, such as Figure 6 As shown, taking a 16-antenna microwave detection device and 10 standard brain data as an example, each target to be tested will generate the aforementioned 8*16*15*5 data. When compared with the 10 standard brain data, it will generate 10*8*16*15*5 data containing amplitude difference and phase difference, which can be divided into 8*10 inputs, namely x(1)~x(80), and each input neuron contains 16*15*5 data.

[0053] like Figure 5 As shown, each neuron is input into the hidden layer according to the time delay phase compensation rule, and the output signal can be obtained according to the compensated hidden layer weights.

[0054] In another implementation of the present invention, the microwave data after the Laplace transform is represented as follows:

[0055]

[0056] Where α is the amplitude constant; θ is the phase constant; x(s) is the microwave signal after Laplace transform; and x(t+θ) is the original microwave signal under phase θ.

[0057] x(t) is the input microwave data, expressed as:

[0058]

[0059] in, The signal is the phase-compensated microwave signal; N is the number of received microwave signals.

[0060] In another implementation of the present invention, the feedforward controller is represented as:

[0061]

[0062] Where x(s+θ) is a microwave signal with a phase error θ.

[0063] In another implementation of the present invention, the feedback controller is represented as:

[0064]

[0065] Where τ is the time delay; β is the phase constant, which can be adjusted according to the actual situation. When β>1, it belongs to advance compensation; when β<1, it belongs to lag compensation.

[0066] In another implementation of the present invention, the output signal is represented as:

[0067]

[0068] in, T This is the transpose symbol for a matrix; The Laplace transform of the microwave data received by each antenna; w i s represents the weight vector for each antenna; i The transformation vectors for performing the Laplace transform on the data; W is the weight, p is the control coefficient, and q is the weight update coefficient.

[0069] In another implementation of the present invention, such as Figure 7 As shown, simulations can be performed using Feko electromagnetic simulation software. Simulations are conducted using FMCW waves ranging from 2-5.5 GHz (with an electric field strength threshold of 5 V / m, sweeping the frequency at 0.5 GHz intervals) to obtain microwave scattering signals. The processed scattering signals are then input as shown in the figure. Figure 6 The imaging results can be obtained by plotting a heat map of the region using the output signal of the neural network shown. It can be seen that the microwave imaging results obtained using this method are clearer than those obtained without this method.

[0070] It should be understood that during the research process, standard brain data of normal people were obtained using microwave imaging devices to construct a standard brain model for microwave brain imaging. Subsequently, data from patients with cerebral hemorrhage and cerebral infarction were obtained and compared with the standard brain model. Based on the time delay of the received signal, an adaptive phase compensation neural network was used to re-superimpose and enhance the phase of the data after the time delay, ultimately forming a brain image obtained by microwave scanning.

[0071] For microwave brain imaging, each analysis in clinical applications involves new data not found in the database and without prior MRI knowledge. This invention, by constructing a standard brain model and performing phase compensation, can generalize to unseen data, resulting in more accurate imaging results. The adaptive phase compensation neural network exhibits strong resistance to small-scale head movements and electromagnetic noise interference during data acquisition, improving robustness. Building upon the traditional microwave inverse scattering algorithm's signal phase processing, feedback compensation is performed based on the measured phase of the target object using the standard brain model, thereby improving imaging accuracy.

[0072] Another aspect of the present invention provides a brain image generation system based on microwave data adaptive time delay phase compensation, comprising:

[0073] Data acquisition module: Configure antenna transmit and receive parameters, including the number of scan points, frequency step, and starting frequency; collect frequency point data based on the transmit and receive parameters to obtain a matrix dataset; when the number of collection points in the matrix microwave dataset is the same as the preset number of collection points, end the acquisition and save the matrix dataset.

[0074] Data processing module: Inputs the microwave data of the matrix-form microwave dataset into the constructed adaptive phase compensation neural network; performs adaptive time delay phase compensation processing on the microwave data to obtain the output signal.

[0075] Imaging module: Draws a regional thermal map based on the output signal to obtain microwave brain imaging results.

[0076] The present invention relates to a brain image generation system based on adaptive time delay phase compensation of microwave data. By controlling the signal transmission and reception format, it achieves multi-frequency point and multi-antenna frequency sweep reception. The obtained microwave data is used as input to construct an adaptive phase compensation neural network. The data is passed from the input layer to the hidden layer and nonlinearly mapped through the radial basis function. The preceding term is compensated according to the time delay, and the following term is passed to the output layer for output, thereby achieving fast, accurate and effective microwave brain imaging.

[0077] In another aspect of the present invention, the electronic device includes: a processor, a memory, and a communication bus and a communication interface.

[0078] in:

[0079] The processor, memory, and communication interface communicate with each other via a communication bus.

[0080] A communication interface is used to communicate with other electronic devices or servers.

[0081] The processor is used to execute programs, specifically, to perform any of the steps of the brain image generation method based on microwave data adaptive time delay phase compensation in the above embodiments.

[0082] Specifically, the program may include program code, which includes computer operation instructions.

[0083] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0084] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0085] Specifically, the program can be used to cause the processor to execute the steps of any of the brain image generation methods based on microwave data adaptive time-delay phase compensation described in the embodiments. The specific implementation of each step in the program can be found in the corresponding descriptions of the steps and units executed in any of the brain image generation methods based on microwave data adaptive time-delay phase compensation described above, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments.

[0086] An exemplary embodiment of this application also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods of various embodiments of this application.

[0087] The methods described above according to embodiments of the present invention can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code originally stored on a remote recording medium or a non-transitory machine-readable medium and subsequently stored on a local recording medium, downloaded via a network. Thus, the methods described herein can be processed by software stored on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components (e.g., RAM, ROM, flash memory, etc.) capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods described herein. Furthermore, when a general-purpose computer accesses code used to implement the methods shown herein, the execution of the code transforms the general-purpose computer into a dedicated computer for executing the methods shown herein.

[0088] Specific embodiments of the present invention have now been described. Other embodiments are within the scope of the appended claims. In some cases, the actions described in the claims can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result.

[0089] It should be noted that all directional indications (such as up, down, left, right, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship between the components in a certain order (as shown in the figure). If the specific order changes, the directional indication will also change accordingly.

[0090] In the description of this invention, the terms "first" and "second" are used only for convenience in describing different components or names, and should not be construed as indicating or implying a sequential relationship, relative importance, or implicitly specifying the number of technical features indicated. Thus, a feature defined with "first" and "second" may explicitly or implicitly include at least one of that feature.

[0091] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0092] It should be noted that although specific embodiments of the present invention have been described in detail with reference to the accompanying drawings, this should not be construed as limiting the scope of protection of the present invention. Various modifications and variations that can be made by those skilled in the art without inventive effort within the scope described in the claims still fall within the scope of protection of the present invention.

[0093] The examples of the embodiments of the present invention are intended to concisely illustrate the technical features of the embodiments of the present invention, so that those skilled in the art can intuitively understand the technical features of the embodiments of the present invention, and are not intended to be an improper limitation of the embodiments of the present invention.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating brain images based on adaptive time delay phase compensation of microwave data, characterized in that, include: Configure antenna transmit and receive parameters, including the number of scan points, frequency step, and starting frequency; Microwave data at the frequency point is collected based on the aforementioned transmit and receive parameters to obtain a microwave dataset in matrix form; When the number of acquisition points in the matrix-form microwave dataset is the same as the preset number of acquisition points, the acquisition ends and the matrix-form microwave dataset is saved. The microwave data of the matrix-form microwave dataset is input into the constructed adaptive phase compensation neural network; The microwave data is subjected to adaptive time delay phase compensation processing to obtain an output signal, including: By using a priori given amplitude and phase constants, a feedforward controller is obtained based on microwave data after Laplace transform, under the condition that microwaves have time delays when passing through different tissues, resulting in phase errors. The microwave data after the Laplace transform is represented as follows: Where α is the amplitude constant; θ is the phase constant; x(s) is the microwave signal after Laplace transform; and x(t+θ) is the original microwave signal under phase θ. x(t) is the input microwave data, expressed as: in, The signal is the phase-compensated microwave signal; N is the number of received microwave signals. The feedforward controller is represented as follows: Where x(s+θ) is a microwave signal with a phase error θ; The feedforward controller is used as a compensation controller, and the output signal is obtained by combining the feedforward controller and the feedback controller. The feedback controller is represented as: Where τ is the time delay; β is the phase constant, which can be adjusted according to the actual situation. When β>1, it belongs to advance compensation; when β<1, it belongs to lag compensation. The output signal is represented as: in, T This is the transpose symbol for a matrix; The Laplace transform of the microwave data received by each antenna; w i s represents the weight vector for each antenna; i The transformation vectors for performing the Laplace transform on the data; W is the weight, p is the control coefficient, and q is the weight update coefficient; A regional heat map is drawn based on the output signal to generate a microwave brain image.

2. The method according to claim 1, characterized in that, After inputting the microwave data of the matrix-form microwave dataset into the constructed adaptive phase compensation neural network, the process further includes: The microwave data is fed from the input layer of the adaptive phase compensation neural network into the hidden layer and then nonlinearly mapped using radial basis functions.

3. A brain image generation system based on microwave data adaptive time delay phase compensation, characterized in that, include: Data acquisition module: Configures antenna transmit and receive parameters, including the number of scan points, frequency step, and starting frequency; Microwave data at the frequency point is collected based on the transmit and receive parameters to obtain a microwave dataset in matrix form; when the number of collection points in the microwave dataset in matrix form is the same as the preset number of collection points, the collection ends and the microwave dataset in matrix form is saved; Data processing module: Inputs the microwave data of the matrix-form microwave dataset into the constructed adaptive phase compensation neural network; The microwave data is subjected to adaptive time delay phase compensation processing to obtain an output signal, including: By using a priori given amplitude and phase constants, a feedforward controller is obtained based on microwave data after Laplace transform, under the condition that microwaves have time delays when passing through different tissues, resulting in phase errors. The microwave data after the Laplace transform is represented as follows: Where α is the amplitude constant; θ is the phase constant; x(s) is the microwave signal after Laplace transform; and x(t+θ) is the original microwave signal under phase θ. x(t) is the input microwave data, expressed as: in, The signal is the phase-compensated microwave signal; N is the number of received microwave signals. The feedforward controller is represented as follows: Where x(s+θ) is a microwave signal with a phase error θ; The feedforward controller is used as a compensation controller, and the output signal is obtained by combining the feedforward controller and the feedback controller. The feedback controller is represented as: Where τ is the time delay; β is the phase constant, which can be adjusted according to the actual situation. When β>1, it belongs to advance compensation; when β<1, it belongs to lag compensation. The output signal is represented as: in, T This is the transpose symbol for a matrix; The Laplace transform of the microwave data received by each antenna; w i s represents the weight vector for each antenna; i The transformation vectors for performing the Laplace transform on the data; W is the weight, p is the control coefficient, and q is the weight update coefficient; Imaging module: Draws a regional heat map based on the output signal and generates a microwave brain image.

4. An electronic device, characterized in that, include: The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a brain image generation method based on microwave data adaptive time delay phase compensation as described in any one of claims 1 to 2.

5. A computer storage medium, characterized in that, The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of a brain image generation method based on microwave data adaptive time delay phase compensation as described in any one of claims 1 to 2.

Images