Assessment device, method, apparatus, and medium for tissue properties and water content of a human body

Abstract

The application is suitable for the technical field of human health monitoring, and provides an evaluation device for tissue properties and water content of human body, which comprises: a signal excitation unit for controlling an electromagnetic excitation system to generate an excitation signal and supplying the excitation signal into a human body tissue to be measured through orthogonal excitation electrodes in the electromagnetic excitation system; a signal acquisition unit for controlling an electromagnetic information acquisition system to acquire an electric field signal generated by the tissue to be measured under the action of the excitation signal; a signal processing unit for processing the electric field signal to obtain target electric field data; a data inversion unit for inverting a human tissue electrical property model based on the target electric field data to obtain tissue information of the tissue to be measured; and a property evaluation unit for inputting the tissue information into a human property evaluation wide learning network to obtain evaluation results of tissue properties and water content of the tissue to be measured, thereby improving the evaluation speed and evaluation accuracy of the tissue properties and water content of the human body.

Description

Technical Field

[0001] This invention belongs to the field of human health monitoring technology, and in particular relates to a device, method, equipment and medium for evaluating the tissue characteristics and water content of the human body. Background Technology

[0002] Monitoring or examining the water content of human tissues is an important approach to evaluating human tissues and overall health. Human tissue testing can be broadly categorized into: tissue water content testing, hydrocephalus testing, and pulmonary edema testing. Currently, domestic and international human tissue testing equipment utilizes methods such as audio, laser, and electromagnetic approaches. However, since most human tissue water content testing is qualitative, it is difficult to apply clinically, especially for diagnosing organ diseases. CT and MRI scans have significant limitations in terms of safety, efficiency, cost, and environmental requirements. Therefore, in recent years, electrical impedance tomography (EIT) and magnetoelectric impedance tomography (MET) methods have begun to be applied to human tissue testing.

[0003] Bioimpedance impedance (BII) is a detection technology that extracts biomedical information related to human physiological and pathological conditions by utilizing the electrical properties and changes of biological tissues and organs. It involves sending a small alternating current or voltage to the subject through an electrode system placed on the body surface to detect the corresponding impedance and its changes. Depending on the application, it can obtain relevant physiological and pathological information, finding applications in areas such as changes in body fat, pulmonary edema, hemodynamics, and diagnosis of cancer cell sites, all related to changes in body composition and physiological conditions. Internationally, bioimpedance measurement technology has a higher level of basic research, with next-generation bioimpedance technology, particularly electrical impedance tomography (EIT), attracting increasing numbers of researchers. In China, however, bioimpedance technology is primarily focused on applied research and consumer electronics. Bioimpedance technologies, represented by various admittance flow maps and body fat analyzers, are widely used in clinical and health monitoring. Their radiation-free, low-cost, and non-invasive characteristics are increasingly driving market demand for high-efficiency bioimpedance measurement equipment. However, traditional bioimpedance measurement systems still have many shortcomings and issues requiring improvement. For example, measurement systems relying on gel electrodes are unsuitable for wearable real-time detection due to the electrode area and gel size, resulting in a poor user experience. The application of small-sized dry electrodes introduces extremely high contact impedance, leading to signal distortion. Additionally, the input signal-related noise of the readout circuit can severely reduce the system's measurement accuracy when the bioimpedance signal is large. Finally, the use of complementary current sources in traditional designs suffers from current mismatch, resulting in low output impedance and limited voltage margin. Consequently, existing detection devices suffer from narrow operating frequency ranges, large size, and high cost. There is room for improvement in both measurement methods and system design.

[0004] To this day, electrochemical impedance spectroscopy (EIT) technology has not been widely applied in clinical practice, its fundamental drawback being low resolution. Firstly, solving EIT is a typical inverse problem, exhibiting severe ill-conditioned nature, making it difficult to obtain stable, high-precision solutions. Secondly, the sensitivity of the peripheral voltage distribution to impedance perturbations is highly spatially dependent, showing poor sensitivity to changes in internal impedance. Furthermore, EIT only utilizes peripheral voltage data, resulting in limited information; increasing the number of electrodes to increase data volume exacerbates the ill-conditioned nature. On the other hand, non-contact electrical impedance tomography (EIT), specifically biomedical magnetic induction tomography (MIT), while similar to EIT in reconstructing the conductivity distribution within the measured region, differs in that it applies magnetic field excitation instead of electric field excitation. Due to its non-contact nature, MIT offers unique advantages over EIT. Currently, MIT is widely used in industrial fields such as metal composition detection and liquid metal impurity detection. Given the unique advantages of magnetic field excitation, MIT also holds broad application prospects in the biomedical field. Summary of the Invention

[0005] The purpose of this invention is to provide a device, method, equipment, and medium for evaluating the tissue characteristics and water content of the human body, aiming to solve the problems of slow speed and low accuracy in evaluating the tissue characteristics and water content of the human body due to the prior art.

[0006] On one hand, the present invention provides an apparatus for evaluating the tissue characteristics and water content of the human body, the apparatus comprising:

[0007] The signal excitation unit is used to control the electromagnetic excitation system to generate an excitation signal, and to supply the excitation signal to the human body tissue to be tested by controlling the orthogonal excitation electrodes in the electromagnetic excitation system.

[0008] The signal acquisition unit is used to control the electromagnetic information acquisition system to acquire the electric field signal generated by the tissue under test under the action of the excitation signal;

[0009] The signal processing unit is used to process the electric field signal according to a preset data processing strategy to obtain target electric field data.

[0010] The data inversion unit is used to invert the preset human tissue electrical model based on the target electric field data to obtain the tissue information of the tissue to be tested.

[0011] The trait evaluation unit is used to input the tissue information into a pre-trained human trait evaluation width learning network to obtain the evaluation results of the tissue traits and water content of the tissue to be tested.

[0012] Preferably, the device further includes:

[0013] A stable magnetic field excitation unit is used to control the stable magnetic field excitation system to generate a stable magnetic field in the region of the tissue to be tested.

[0014] Preferably, the electromagnetic excitation system is a time-frequency dual-domain excitation system, the excitation signal includes a frequency-domain excitation signal and a time-domain excitation signal, and the signal excitation unit includes:

[0015] The signal excitation subunit is used to control the electromagnetic excitation system to generate frequency-domain excitation signals and time-domain excitation signals without an stable magnetic field when the stable magnetic field does not exist in the region of the tissue to be tested, and to control the electromagnetic excitation system to generate frequency-domain excitation signals and time-domain excitation signals with a stable magnetic field when the stable magnetic field exists in the region of the tissue to be tested. The frequency-domain excitation signal is generated by low-frequency and high-frequency excitation of the electromagnetic excitation system, and the time-domain excitation signal is generated by low-frequency excitation of the electromagnetic excitation system.

[0016] Preferably, the electric field signal includes a frequency-domain electric field signal and a time-domain electric field signal, and the signal processing unit includes:

[0017] A frequency domain signal processing unit is used to process the frequency domain electric field signal according to a preset frequency domain signal processing strategy to obtain a frequency domain electric field curve.

[0018] The time-domain signal processing unit is used to process the time-domain electric field information according to a preset time-domain signal processing strategy to obtain the time-domain electric field curve.

[0019] The differential anomaly calculation unit is used to calculate the frequency domain electric field differential anomaly and the time domain electric field differential anomaly of the tissue under test before and after the application of the stable magnetic field, respectively, based on the frequency domain electric field curve and the time domain electric field curve.

[0020] An electric field data generation unit is used to obtain an electric field distribution based on the frequency domain electric field curve and the time domain electric field curve, obtain an electric field anomaly distribution based on the frequency domain electric field differential anomaly and the time domain electric field differential anomaly, and generate the target electric field data based on the electric field distribution and the electric field anomaly distribution.

[0021] Preferably, the device further includes:

[0022] The data forward modeling unit is used to perform forward modeling simulation on the pre-collected electric field data of human tissue samples to obtain the sample tissue information of the human tissue.

[0023] Preferably, the human tissue electrical model includes a geometric model, a resistivity model, and a polarizability model, and the data inversion unit includes:

[0024] The data inversion subunit is used to iteratively invert the resistivity model and the polarizability model based on the sample tissue information and the target electric field data, using a time-frequency joint, step-by-step constrained sequential inversion strategy, until the fitting error of the resistivity model is within a preset resistivity variation range and the fitting error of the polarizability model is within a preset polarizability variation range, thereby obtaining the tissue information including resistivity distribution, polarizability distribution, electric field distribution, and electric field anomaly distribution. The geometric parameters of the geometric model remain constant during the inversion process, and the resistivity variation range... and the range of polarizability variation The results are provided by testing human tissue samples. and These are the minimum and maximum values ​​in the resistivity model of human tissue samples, respectively. and These are the minimum and maximum values ​​in the polarizability model of human tissue samples, respectively.

[0025] Preferably, the device further includes:

[0026] The network training unit is used to train the human trait assessment width learning network based on the sample tissue information, so that the human trait assessment width learning network can assess the tissue characteristics and water content of the human tissue.

[0027] On the other hand, the present invention provides a method for evaluating the tissue properties and water content of the human body, the method comprising the following steps:

[0028] The electromagnetic excitation system is controlled to generate an excitation signal, and the excitation signal is supplied to the test tissue of the human body by controlling the orthogonal excitation electrodes in the electromagnetic excitation system.

[0029] The electromagnetic information acquisition system is controlled to acquire the electric field signal generated by the tissue under test under the action of the excitation signal;

[0030] The electric field signal is processed according to a preset data processing strategy to obtain the target electric field data;

[0031] Based on the target electric field data, the preset human tissue electrical model is inverted to obtain the tissue information of the tissue to be tested;

[0032] The tissue information is input into a pre-trained human trait assessment width learning network to obtain the assessment results of the tissue trait and water content of the tissue to be tested.

[0033] On the other hand, the present invention also provides a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the functions described in the above-described human tissue characteristics and water content assessment device.

[0034] On the other hand, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the functions described in the above-described human tissue morphology and water content assessment device.

[0035] The device for evaluating the tissue properties and water content of the human body provided by this invention includes a signal excitation unit, a signal acquisition unit, a signal processing unit, a data inversion unit, and a property evaluation unit. The signal excitation unit controls an electromagnetic excitation system to generate an excitation signal and supplies the excitation signal to the tissue to be tested by controlling the orthogonal excitation electrodes in the electromagnetic excitation system. The signal acquisition unit controls an electromagnetic information acquisition system to acquire the electric field signal generated by the tissue to be tested under the action of the excitation signal. The signal processing unit processes the electric field signal according to a preset data processing strategy to obtain target electric field data. The data inversion unit inverts the electrical model of human tissue based on the target electric field data to obtain the tissue information of the tissue to be tested. The property evaluation unit inputs the tissue information into a pre-trained human property evaluation width learning network to obtain the evaluation results of the tissue properties and water content of the tissue to be tested, thereby improving the speed and accuracy of evaluating the tissue properties and water content of the human body, while reducing the cost of human health monitoring and the radiation damage during the monitoring process. Attached Figure Description

[0036] Figure 1(a) is a schematic diagram of the structure of the human tissue characteristics and water content evaluation device provided in Embodiment 1 of the present invention;

[0037] Figure 1(b) is a schematic diagram of the acquisition principle of frequency domain electric field signal in the human tissue property and water content evaluation device provided in Embodiment 1 of the present invention.

[0038] Figure 1(c) is a schematic diagram of the acquisition principle of time-domain electric field signal in the human tissue property and water content evaluation device provided in Embodiment 1 of the present invention.

[0039] Figure 2(a) is a schematic diagram of the structure of the human tissue characteristics and water content evaluation device provided in Embodiment 2 of the present invention;

[0040] Figure 2(b) is a schematic diagram of the stable magnetic field excitation system in the human tissue property and water content evaluation device provided in Embodiment 2 of the present invention;

[0041] Figure 2(c) is a waveform diagram of the frequency domain excitation signal in the human tissue characteristics and water content evaluation device provided in Embodiment 2 of the present invention;

[0042] Figure 2(d) is a waveform diagram of the time-domain excitation signal in the human tissue characteristics and water content evaluation device provided in Embodiment 2 of the present invention;

[0043] Figure 2(e) is a schematic diagram of the arrangement of the electromagnetic excitation system, electromagnetic information acquisition system and stable magnetic field excitation system on the tissue to be tested in the human tissue property and water content evaluation device provided in Embodiment 2 of the present invention.

[0044] Figure 3 This is a flowchart illustrating the implementation of the method for evaluating the tissue properties and water content of the human body provided in Embodiment 3 of the present invention.

[0045] Figure 4 This is a schematic diagram of the structure of the computing device provided in Embodiment 4 of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0047] The specific implementation of the present invention will be described in detail below with reference to specific embodiments:

[0048] Example 1:

[0049] Figure 1(a) shows the structure of the human tissue morphology and water content evaluation device provided in Embodiment 1 of the present invention. For ease of explanation, only the parts relevant to the embodiment of the present invention are shown. As shown in Figure 1(a), the evaluation device includes a signal excitation unit 1.1, a signal acquisition unit 1.2, a signal processing unit 1.3, a data inversion unit 1.4, and a morphology evaluation unit 1.5, wherein:

[0050] The signal excitation unit 1.1 is used to control the electromagnetic excitation system to generate an excitation signal and to supply the excitation signal to the tissue to be tested in the human body by controlling the orthogonal excitation electrodes in the electromagnetic excitation system.

[0051] This invention is applicable to computing devices, such as personal computers and servers. In this embodiment, the signal excitation unit 1.1 controls the electromagnetic excitation system to generate an excitation signal with a preset excitation waveform. This excitation signal is supplied to the test tissue through orthogonal excitation electrodes coupled to the skin of the test tissue. The orthogonal excitation electrodes include north-south excitation electrodes and east-west excitation electrodes. The north-south excitation electrodes are used to supply north-south excitation signals to the test tissue, and the east-west excitation electrodes are used to supply east-west excitation signals to the test tissue.

[0052] In one feasible embodiment, the north-south excitation electrode and the east-west excitation electrode are connected, and the north-south excitation signal and the east-west excitation signal are cyclically supplied to the tissue to be tested.

[0053] In another feasible embodiment, the electromagnetic excitation system is a time-frequency dual-domain excitation system integrating the frequency domain and the time domain. Its excitation waveform is a square wave. All excitations (including low frequency and high frequency) constitute the frequency domain excitation, which is generally composed of 5-9 square waves. At this time, the generated excitation signal is called the frequency domain excitation signal. 1-2 low frequency (long period square wave) excitations in all excitations are used as time domain excitations, and the generated excitation signal is called the time domain excitation signal. That is, the excitation signal includes the frequency domain excitation signal and the time domain excitation signal.

[0054] In another feasible embodiment, since the excitation signal is divided into north-south excitation signal and east-west excitation signal, for ease of description and distinction, the frequency domain excitation signal supplied by the north-south excitation electrode of the time-frequency dual-domain excitation system is called the north-south frequency domain excitation signal, the frequency domain excitation signal supplied by the east-west excitation electrode of the time-frequency dual-domain excitation system is called the east-west frequency domain excitation signal, the time domain excitation signal supplied by the north-south excitation electrode of the time-frequency dual-domain excitation system is called the north-south time domain excitation signal, and the time domain excitation signal supplied by the east-west excitation electrode of the time-frequency dual-domain excitation system is called the east-west time domain excitation signal. That is, the frequency domain excitation signal includes the north-south frequency domain excitation signal and the east-west frequency domain excitation signal, and the time domain excitation signal includes the north-south time domain excitation signal and the east-west time domain excitation signal.

[0055] In another feasible embodiment, a control signal to trigger the electromagnetic excitation system is sent via GPS, so as to control the electromagnetic excitation system through the control signal.

[0056] The signal acquisition unit 1.2 is used to control the electromagnetic information acquisition system to acquire the electric field signal generated by the tissue under test under the action of the excitation signal.

[0057] In this embodiment of the invention, the electromagnetic information acquisition system is a non-polarized electrode system, and the electrodes are silver chloride nanoelectrodes. The non-polarized electrode system is placed on the skin of the tissue to be tested, and a coupling agent is used to ensure good coupling between the system and the skin. The electromagnetic information acquisition system corresponds to the electromagnetic excitation system. While the signal excitation unit 1.1 controls the electromagnetic excitation system to generate an excitation signal, the signal acquisition unit 1.2 controls the electromagnetic information acquisition system to acquire the electric field signal, which includes electric field and magnetic field components, generated by the tissue to be tested under the action of the excitation signal.

[0058] In one feasible embodiment, the electromagnetic information acquisition system is an integrated frequency domain and time domain receiving system. Corresponding to the excitation signal, the electric field signal includes a frequency domain electric field signal and a time domain electric field signal. The electromagnetic information acquisition system includes a preamplifier, a low-pass filter, a main amplifier, a high-pass filter, a detector circuit, a reading circuit, and a regulated power supply to acquire the frequency domain electric field signal generated when the frequency domain excitation signal generated by the electromagnetic excitation system acts on the tissue under test. Figure 1(b) shows the principle of acquiring the frequency domain electric field signal. The electromagnetic information acquisition system also includes a self-current compensation module, a preamplifier and filter module, a main amplifier, an inverter, an integrator, an automatic self-current compensation module, and a main control module to acquire the time domain electric field signal generated when the time domain excitation signal generated by the electromagnetic excitation system acts on the tissue under test. Figure 1(c) shows the principle of acquiring the time domain electric field signal.

[0059] The signal processing unit 1.3 is used to process the electric field signal according to the preset data processing strategy to obtain the target electric field data. The data inversion unit 1.4 is used to invert the preset human tissue electrical model based on the target electric field data to obtain the tissue information of the tissue to be tested. The trait evaluation unit 1.5 is used to input the tissue information into the pre-trained human trait evaluation width learning network to obtain the evaluation results of the tissue trait and water content of the tissue to be tested.

[0060] In this embodiment of the invention, the specific description of the functions of the signal processing unit 1.3, the data inversion unit 1.4, and the trait evaluation unit 1.5 is detailed in Embodiment 2 below, and will not be repeated here.

[0061] The human tissue morphology and water content assessment device of this invention includes a signal excitation unit, a signal acquisition unit, a signal processing unit, a data inversion unit, and a morphology assessment unit. The signal excitation unit controls an electromagnetic excitation system to generate an excitation signal and supplies the excitation signal to the human tissue to be tested by controlling the orthogonal excitation electrodes in the electromagnetic excitation system. The signal acquisition unit controls an electromagnetic information acquisition system to acquire the electric field signal generated by the tissue to be tested under the action of the excitation signal. The signal processing unit processes the electric field signal according to a preset data processing strategy to obtain target electric field data. The data inversion unit inverts the human tissue electrical model based on the target electric field data to obtain the tissue information of the tissue to be tested. The morphology assessment unit inputs the tissue information into a pre-trained human morphology assessment width learning network to obtain the assessment results of the tissue morphology and water content of the tissue to be tested, thereby improving the speed and accuracy of human tissue morphology and water content assessment, while reducing the cost of human health monitoring and radiation damage during the monitoring process.

[0062] In this embodiment of the invention, each unit of the human body tissue characteristics and water content evaluation device can be implemented by corresponding hardware or software units. Each unit can be an independent hardware or software unit, or it can be integrated into a hardware or software unit, which is not intended to limit the invention.

[0063] Example 2:

[0064] Figure 2(a) shows the structure of the human tissue morphology and water content evaluation device provided in Embodiment 2 of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown. As shown in Figure 2(a), the evaluation device includes a stable magnetic field excitation unit 2.1, a signal excitation unit 2.2, a signal acquisition unit 2.3, a signal processing unit 2.4, a data inversion unit 2.5, and a morphology evaluation unit 2.6. The functions of each unit are detailed below:

[0065] The stable magnetic field excitation unit 2.1 is used to control the stable magnetic field excitation system to generate a stable magnetic field in the region of the tissue to be tested.

[0066] In this embodiment of the invention, the power supply current of the stable magnetic field excitation system is direct current. The poles of the stable magnetic field excitation system are arranged around the tissue to be tested. When the stable magnetic field excitation system is powered on, it will generate a stable magnetic field environment (hereinafter referred to as stable magnetic field) in the area of ​​the tissue to be tested. Figure 2(b) shows a schematic diagram of the structure of the stable magnetic field excitation system.

[0067] The signal excitation unit 2.2 is used to control the electromagnetic excitation system to generate an excitation signal, and to supply the excitation signal to the test tissue of the human body by controlling the orthogonal excitation electrodes in the electromagnetic excitation system.

[0068] In this embodiment of the invention, some functions of the signal excitation unit 2.2 are detailed in the functional description of the signal excitation unit 1.1 in Embodiment 1, and will not be repeated here.

[0069] In one feasible embodiment, the signal excitation unit 2.2 includes a signal excitation subunit 2.2.1, which is used to control the electromagnetic excitation system to generate excitation signals when there is no stable magnetic field in the region of the tissue to be tested and when there is a stable magnetic field in the region of the tissue to be tested.

[0070] In this embodiment of the invention, while controlling the electromagnetic excitation system to generate an excitation signal, the stable magnetic field excitation system is initially de-energized, meaning there is no stable magnetic field in the area of ​​the tissue to be tested. Then, the stable magnetic field excitation system is energized to generate a stable magnetic field in the area of ​​the tissue to be tested. At this point, the excitation signal generated by the electromagnetic excitation system is divided into the excitation signal generated without a stable magnetic field and the excitation signal generated with a stable magnetic field. Furthermore, the excitation signal includes frequency domain excitation signals and time domain excitation signals. Therefore, the excitation signal generated without a stable magnetic field includes both frequency domain and time domain excitation signals, and the excitation signal generated with a stable magnetic field includes both frequency domain and time domain excitation signals. For ease of description and distinction, the term "unstable magnetic field" is used. The excitation signal generated under a constant magnetic field is called the first excitation signal, and the excitation signal generated under a stable magnetic field is called the second excitation signal. The first excitation signal includes a first frequency domain excitation signal and a first time domain excitation signal. The second excitation signal includes a second frequency domain excitation signal and a second time domain excitation signal. The frequency domain excitation signal includes north-south frequency domain excitation signal and east-west frequency domain excitation signal, and the time domain excitation signal includes north-south time domain excitation signal and east-west time domain excitation signal. Therefore, the first excitation signal includes the first north-south frequency domain excitation signal, the first east-west frequency domain excitation signal, the first north-south time domain excitation signal, and the first east-west time domain excitation signal. The second excitation signal includes the second north-south frequency domain excitation signal, the second east-west frequency domain excitation signal, the second north-south time domain excitation signal, and the second east-west time domain excitation signal.

[0071] In another feasible embodiment, the excitation waveforms of the first frequency domain excitation signal and the second frequency domain excitation signal are positive and negative square waves with different periods, respectively, as shown in (a) and (b) of Figure 2(c), and the excitation waveforms of the first time domain excitation signal and the second time domain excitation signal are shown in (a) and (b) of Figure 2(d), respectively.

[0072] The signal acquisition unit 2.3 is used to control the electromagnetic information acquisition system to acquire the electric field signal generated by the tissue under test under the action of the excitation signal.

[0073] In this embodiment of the invention, some functions of the signal acquisition unit 2.3 are detailed in the functional description of the signal acquisition unit 1.2 in Embodiment 1, and will not be repeated here.

[0074] In one feasible embodiment, the electric field signal acquired by the electromagnetic information acquisition system corresponds to the excitation signal generated by the electromagnetic excitation system. Due to two data acquisition processes—north-south excitation and east-west excitation—and the acquisition of data under a stable magnetic field applied to the tissue under test, the electric field signal acquired by the electromagnetic information acquisition system includes both electric field signals acquired under conditions of no stable magnetic field and electric field signals acquired under conditions of a stable magnetic field. For ease of description and distinction, the electric field signal acquired under conditions of no stable magnetic field is referred to as the first electric field signal, and the electric field signal acquired under conditions of a stable magnetic field is referred to as the second electric field signal. Corresponding to the first excitation signal and the second excitation signal, the first electric field signal includes… The electric field signals consist of a first north-south frequency domain electric field signal, a first east-west frequency domain electric field signal, a first north-south time domain electric field signal, and a first east-west time domain electric field signal. The second electric field signal includes the second north-south frequency domain electric field signal, the second east-west frequency domain electric field signal, the second north-south time domain electric field signal, and the second east-west time domain electric field signal. In other words, four sets of frequency domain electric field signals (the first north-south frequency domain electric field signal, the first east-west frequency domain electric field signal, the second north-south frequency domain electric field signal, and the second east-west frequency domain electric field signal) and four sets of time domain electric field signals (the first north-south time domain electric field signal, the first east-west time domain electric field signal, the second north-south time domain electric field signal, and the second east-west time domain electric field signal) are obtained.

[0075] The signal processing unit 2.4 is used to process the electric field signal according to the preset data processing strategy to obtain the target electric field data.

[0076] In this embodiment of the invention, the signal processing unit 2.4 processes the four sets of frequency domain electric field signals and the four sets of time domain electric field signals according to a preset data processing strategy to obtain the target electric field data.

[0077] In a feasible embodiment, the signal processing unit 2.4 includes a frequency domain signal processing unit 2.4.1, a time domain signal processing unit 2.4.2, a differential anomaly calculation unit 2.4.3, and an electric field data generation unit 2.4.4, wherein:

[0078] The frequency domain signal processing unit 2.4.1 is used to process the frequency domain electric field signal according to the preset frequency domain signal processing strategy to obtain the frequency domain electric field curve.

[0079] In this embodiment of the invention, the frequency domain signal processing unit 2.4.1 first performs a Fourier transform on the original frequency domain electric field signal to obtain the spectrum of all frequency domain electric field signals. Then, it superimposes the spectra of all frequencies and performs noise filtering to obtain the frequency domain electric field curve of the tissue under test. The four sets of frequency domain electric field signals can then produce four corresponding frequency domain electric field curves characterizing the amplitude and phase, namely: the first north-south frequency domain electric field curve, the first east-west frequency domain electric field curve, the second north-south frequency domain electric field curve, and the second east-west frequency domain electric field curve.

[0080] The time-domain signal processing unit 2.4.2 is used to process the time-domain electric field information according to the preset time-domain signal processing strategy to obtain the time-domain electric field curve.

[0081] In this embodiment of the invention, the time-domain signal processing unit 2.4.2 first superimposes the original time-domain electric field signals to obtain a time-domain attenuation curve. Then, it first performs deconvolution on the time-domain attenuation curve to eliminate the influence of the excitation signal, and then performs denoising and filtering to obtain the time-domain electric field curve of the tissue under test. The four sets of time-domain electric field signals can then produce four corresponding time-domain electric field curves characterizing the amplitude, namely: the first north-south time-domain electric field curve, the first east-west time-domain electric field curve, the second north-south time-domain electric field curve, and the second east-west time-domain electric field curve.

[0082] The differential anomaly calculation unit 2.4.3 is used to calculate the frequency domain electric field differential anomaly and the time domain electric field differential anomaly before and after applying a stable magnetic field to the tissue under test, based on the frequency domain electric field curve and the time domain electric field curve, respectively.

[0083] In this embodiment of the invention, the differential anomaly calculation unit 2.4.3 calculates the north-south frequency domain electric field differential anomaly representing amplitude and phase under conditions of no stable magnetic field applied to the tissue under test and before and after the application of a stable magnetic field, based on the first north-south frequency domain electric field curve and the second north-south frequency domain electric field curve. Similarly, it calculates the east-west frequency domain electric field differential anomaly representing amplitude and phase based on the first east-west frequency domain electric field curve and the second east-west frequency domain electric field curve. It also calculates the north-south time domain electric field differential anomaly representing amplitude based on the first north-south time domain electric field curve and the second north-south time domain electric field curve. Furthermore, it calculates the east-west time domain electric field differential anomaly representing amplitude based on the first east-west time domain electric field curve and the second east-west time domain electric field curve. In other words, the frequency domain electric field differential anomaly includes the north-south frequency domain electric field differential anomaly and the east-west frequency domain electric field differential anomaly, and the time domain electric field differential anomaly includes the northwest time domain electric field differential anomaly and the east-west time domain electric field differential anomaly.

[0084] The electric field data generation unit 2.4.4 is used to obtain the electric field distribution based on the frequency domain electric field curve and the time domain electric field curve, obtain the electric field anomaly distribution based on the frequency domain electric field difference anomaly and the time domain electric field difference anomaly, and generate the target electric field data based on the electric field distribution and the electric field anomaly distribution.

[0085] In this embodiment of the invention, the electric field data generation unit 2.4.4 obtains the electric field distribution e based on four sets of frequency domain electric field curves and four sets of time domain electric field curves, and obtains the electric field anomaly distribution m based on the frequency domain electric field difference anomaly and the time domain electric field difference anomaly.

[0086] The data inversion unit 2.5 is used to invert the preset human tissue electrical model based on the target electric field data to obtain the tissue information of the tissue to be tested.

[0087] In this embodiment of the invention, the tissue information of the tissue under test includes the resistivity distribution r, polarizability distribution p, electric field distribution e, and the abnormal electric field distribution m after magnetic stabilization loading. The human tissue electrical model M includes a geometric model M. G Resistivity model M R and polarizability model M η That is, M = M G +M R +M η Among them, geometric model M G M is composed of known parameters given by a human body model, including the skin, muscles, fat, bones, blood vessels, and epidermis of a normal human body. R It is an initial model constructed from the known resistivity of tissues such as skin, muscle, fat, bone, and blood vessels, M. η It is an initial model constructed from the known polarizabilities of tissues such as skin, muscle, fat, bone, and blood vessels, namely M. G ={m G i |1<i<N},M R ={m R i |1<i<N+1},M η ={m η i |1<i<N+1}, Let i be the geometric model of the i-th tissue in the human body. Let be the resistivity of the i-th tissue in the human body. Let N be the polarizability of the i-th tissue in the human body, and N be the total number of tissues in the human body.

[0088] The trait assessment unit 2.6 is used to input tissue information into a pre-trained human trait assessment width learning network to obtain the assessment results of the tissue traits and water content of the tissue to be tested.

[0089] In this embodiment of the invention, the trait evaluation unit 2.6 inputs tissue information including e, r, p, and m into the trained human trait evaluation width learning network to obtain the electrical structure corresponding to erpm, analyzes the electrical structure, and obtains the evaluation results of the tissue traits and water content of the tissue to be tested.

[0090] As an example, Figure 2(e) shows the arrangement of the electromagnetic excitation system, the electromagnetic information acquisition system, and the stable magnetic field excitation system on the tissue under test.

[0091] In one feasible embodiment, the human tissue morphology and water content evaluation device of the present invention further includes a data forward modeling unit, which is used to perform forward modeling simulation on the pre-collected sample electric field data of human tissue to obtain sample tissue information of human tissue.

[0092] In another feasible embodiment, the human tissue morphology and water content evaluation device of the present invention further includes a network training unit, which is used to train the human morphology evaluation width learning network according to the sample tissue information, so that the human morphology evaluation width learning network can evaluate the tissue morphology and water content of human tissue.

[0093] In another feasible embodiment, the data inversion unit 2.5 of this embodiment includes a data inversion subunit 2.5.1. The data inversion subunit 2.5.1 is used to iteratively invert the resistivity model and the polarizability model based on the sample organization information and the target electric field data, using a time-frequency joint, step-by-step constrained sequential inversion strategy, until the fitting error of the resistivity model is within a preset resistivity variation range and the fitting error of the polarizability model is within a preset polarizability variation range.

[0094] In this embodiment of the invention, the resistivity variation range of the resistivity model of human tissue is... Polarizability variation range of the polarizability model The results are given by testing human tissue samples, among which, and These are the minimum and maximum values ​​in the resistivity model, respectively. and These are the minimum and maximum values ​​in the polarizability model, respectively. The geometric parameters of the geometric model remain unchanged during the inversion process; that is, the geometric model parameters do not participate in the inversion. Only resistivity and polarizability are inverted. When using a time-frequency joint, step-by-step constrained sequential inversion strategy to iteratively invert the resistivity and polarizability models, the iterative inversion is specifically achieved through the following steps:

[0095] ① Resistivity inversion is performed using the least squares inversion algorithm;

[0096] In this embodiment of the invention, the polarization effect of human tissue (or the dielectric effect at high frequencies) is not considered initially, so the inversion equation is M = M G +M R And M G It does not participate in the inversion, only for the resistivity model M R Inversion is performed, and from one-dimensional inversion, it can be calculated that the model's geometric parameters do not participate in the inversion. The number of inversion unknowns is reduced from 2n+1 to n+1. The reduction is even greater in two-dimensional inversion. The search range of the resistivity model is narrowed from more than three orders to within one order, which speeds up the convergence and inversion speed. In particular, it enables the inversion to converge towards a reasonable range of electrical changes, and finally obtains a resistivity model that conforms to the electrical laws of human tissue. The resistivity model results reflect the electrical characteristics of the basic human tissue model.

[0097] ② The least squares inversion algorithm is used to perform polarizability inversion;

[0098] In this embodiment of the invention, after the resistivity model is determined by inversion, the polarization effect of human tissue is inverted. To represent the polarizability, an equivalent Cole-Cole complex resistivity model is introduced. To characterize the electrical properties of human tissues, the resistivity of the Cole-Cole model is first fixed to the resistivity obtained in step ①, and remains unchanged during the polarizability inversion process. Then, the polarizability in the Cole-Cole model is inverted. Other parameters such as τ and c can also be fixed and inverted one by one. The polarizability inversion model result is the residual electromagnetic anomaly in addition to the basic electrical characteristics. Here, ρ0 is the zero-frequency resistivity, m is the polarizability, τ is the time constant, c is the frequency correlation coefficient, ω is the angular frequency, and i is the imaginary part of the complex number.

[0099] ③ Analyze and evaluate the inversion results. If the inversion results do not meet the resistivity variation range and / or polarizability variation range, return to step ① and continue the inversion until the fitting error of the resistivity model is within the resistivity variation range and the fitting error of the polarizability is within the polarizability variation range.

[0100] The inversion accuracy is improved by performing iterative inversion through the above steps ①-③.

[0101] In another feasible embodiment, the resistivity distribution r and polarizability distribution p of the tissue under test are obtained based on the resistivity and polarizability obtained by iterative inversion, and then combined with the target electric field data, the tissue information of the tissue under test is obtained.

[0102] In this embodiment of the invention, each unit of the human body tissue characteristics and water content evaluation device can be implemented by corresponding hardware or software units. Each unit can be an independent hardware or software unit, or it can be integrated into a hardware or software unit, which is not intended to limit the invention.

[0103] Example 3:

[0104] Figure 3 The implementation flow of the method for evaluating the tissue properties and water content of the human body provided in Embodiment 3 of the present invention is shown. For ease of explanation, only the parts related to the embodiments of the present invention are shown, and are described in detail below:

[0105] In step S301, the electromagnetic excitation system is controlled to generate an excitation signal, and the excitation signal is supplied to the tissue to be tested in the human body by controlling the orthogonal excitation electrodes in the electromagnetic excitation system.

[0106] This invention is applicable to computing devices, such as personal computers and servers. In this invention, an electromagnetic excitation system is controlled to generate an excitation signal with a preset excitation waveform. This excitation signal is supplied to the test tissue through orthogonal excitation electrodes coupled to the skin of the test tissue. The orthogonal excitation electrodes include north-south excitation electrodes and east-west excitation electrodes. The north-south excitation electrodes are used to supply north-south excitation signals to the test tissue, and the east-west excitation electrodes are used to supply east-west excitation signals to the test tissue.

[0107] In one feasible embodiment, the north-south excitation electrode and the east-west excitation electrode are connected, and the north-south excitation signal and the east-west excitation signal are cyclically supplied to the tissue to be tested.

[0108] In another feasible embodiment, the electromagnetic excitation system is a time-frequency dual-domain excitation system integrating the frequency domain and the time domain. Its excitation waveform is a square wave. All excitations (including low frequency and high frequency) constitute the frequency domain excitation, which is generally composed of 5-9 square waves. At this time, the generated excitation signal is called the frequency domain excitation signal. 1-2 low frequency (long period square wave) excitations in all excitations are used as time domain excitations, and the generated excitation signal is called the time domain excitation signal. That is, the excitation signal includes the frequency domain excitation signal and the time domain excitation signal.

[0109] In another feasible embodiment, since the excitation signal is divided into north-south excitation signal and east-west excitation signal, for ease of description and distinction, the frequency domain excitation signal supplied by the north-south excitation electrode of the time-frequency dual-domain excitation system is called the north-south frequency domain excitation signal, the frequency domain excitation signal supplied by the east-west excitation electrode of the time-frequency dual-domain excitation system is called the east-west frequency domain excitation signal, the time domain excitation signal supplied by the north-south excitation electrode of the time-frequency dual-domain excitation system is called the north-south time domain excitation signal, and the time domain excitation signal supplied by the east-west excitation electrode of the time-frequency dual-domain excitation system is called the east-west time domain excitation signal. That is, the frequency domain excitation signal includes the north-south frequency domain excitation signal and the east-west frequency domain excitation signal, and the time domain excitation signal includes the north-south time domain excitation signal and the east-west time domain excitation signal.

[0110] In another feasible embodiment, a stable magnetic field excitation system is controlled to generate a stable magnetic field in the region of the tissue to be tested, wherein the power supply current of the stable magnetic field excitation system is direct current.

[0111] In another feasible embodiment, when controlling the electromagnetic excitation system to generate an excitation signal, the electromagnetic excitation system is controlled to generate an excitation signal when there is no stable magnetic field in the region of the tissue to be tested and when there is a stable magnetic field in the region of the tissue to be tested.

[0112] In this embodiment of the invention, a stable magnetic field excitation system is positioned around the tissue to be tested. While controlling the electromagnetic excitation system to generate an excitation signal, the stable magnetic field excitation system is initially de-energized, meaning there is no stable magnetic field in the area of ​​the tissue to be tested. Then, the stable magnetic field excitation system is energized to generate a stable magnetic field in the area of ​​the tissue to be tested. At this point, the excitation signal generated by the electromagnetic excitation system is divided into an excitation signal generated without a stable magnetic field and an excitation signal generated with a stable magnetic field. For ease of description and distinction, the excitation signal generated without a stable magnetic field is referred to as the first excitation signal, and the excitation signal generated with a stable magnetic field is referred to as the second excitation signal. Furthermore, the excitation... The signal includes a frequency domain excitation signal and a time domain excitation signal. The first excitation signal includes a first frequency domain excitation signal and a first time domain excitation signal. The second excitation signal includes a second frequency domain excitation signal and a second time domain excitation signal. The frequency domain excitation signal includes north-south frequency domain excitation signals and east-west frequency domain excitation signals. The time domain excitation signal includes north-south time domain excitation signals and east-west time domain excitation signals. Therefore, the first excitation signal includes a first north-south frequency domain excitation signal, a first east-west frequency domain excitation signal, a first north-south time domain excitation signal, and a first east-west time domain excitation signal. The second excitation signal includes a second north-south frequency domain excitation signal, a second east-west frequency domain excitation signal, a second north-south time domain excitation signal, and a second east-west time domain excitation signal.

[0113] In another feasible embodiment, a control signal to trigger the electromagnetic excitation system is sent via GPS, so as to control the electromagnetic excitation system through the control signal.

[0114] In step S302, the electromagnetic information acquisition system is controlled to acquire the electric field signal generated by the tissue under test under the action of the excitation signal.

[0115] In this embodiment of the invention, the electromagnetic information acquisition system is a non-polarized electrode system, and the electrode is a silver chloride nanoelectrode. The non-polarized electrode system is placed on the skin of the tissue to be tested, and a coupling agent is used to make it well coupled with the skin. The electromagnetic information acquisition system corresponds to the electromagnetic excitation system. While controlling the electromagnetic excitation system to generate an excitation signal, the electromagnetic information acquisition system is controlled to acquire the electric field signal, which contains electric field components and magnetic field components, generated by the tissue to be tested under the action of the excitation signal.

[0116] In one feasible embodiment, the electromagnetic information acquisition system is an integrated frequency domain and time domain receiving system. Corresponding to the excitation signal, the electric field signal includes a frequency domain electric field signal and a time domain electric field signal. The electromagnetic information acquisition system includes a preamplifier, a low-pass filter, a main amplifier, a high-pass filter, a detector circuit, a reading circuit, and a regulated power supply to acquire the frequency domain electric field signal generated when the frequency domain excitation signal generated by the electromagnetic excitation system acts on the tissue under test. The electromagnetic information acquisition system also includes a self-current compensation module, a preamplifier and filter module, a main amplifier, an inverter, an integrator, an automatic self-current compensation module, and a main control module to acquire the time domain electric field signal generated when the time domain excitation signal generated by the electromagnetic excitation system acts on the tissue under test.

[0117] In another feasible embodiment, the electric field signal acquired by the electromagnetic information acquisition system corresponds to the excitation signal generated by the electromagnetic excitation system. Due to two data acquisition processes—north-south excitation and east-west excitation—and the acquisition of data under a stable magnetic field applied to the tissue under test, the electric field signal acquired by the electromagnetic information acquisition system includes both the electric field signal acquired under conditions of no stable magnetic field and the electric field signal acquired under conditions of a stable magnetic field. For ease of description and distinction, the electric field signal acquired under conditions of no stable magnetic field is referred to as the first electric field signal, and the electric field signal acquired under conditions of a stable magnetic field is referred to as the second electric field signal. Corresponding to the first excitation signal and the second excitation signal, the first electric field signal includes… The electric field signals consist of a first north-south frequency domain electric field signal, a first east-west frequency domain electric field signal, a first north-south time domain electric field signal, and a first east-west time domain electric field signal. The second electric field signal includes the second north-south frequency domain electric field signal, the second east-west frequency domain electric field signal, the second north-south time domain electric field signal, and the second east-west time domain electric field signal. In other words, four sets of frequency domain electric field signals (the first north-south frequency domain electric field signal, the first east-west frequency domain electric field signal, the second north-south frequency domain electric field signal, and the second east-west frequency domain electric field signal) and four sets of time domain electric field signals (the first north-south time domain electric field signal, the first east-west time domain electric field signal, the second north-south time domain electric field signal, and the second east-west time domain electric field signal) are obtained.

[0118] In step S303, the electric field signal is processed according to a preset data processing strategy to obtain the target electric field data.

[0119] In this embodiment of the invention, four sets of frequency-domain electric field signals and four sets of time-domain electric field signals are processed according to a preset data processing strategy to obtain target electric field data.

[0120] In another feasible embodiment, the processing of the electric field signal is achieved through the following steps:

[0121] (1) The frequency domain electric field signal is processed according to the preset frequency domain signal processing strategy to obtain the frequency domain electric field curve;

[0122] In this embodiment of the invention, the original frequency domain electric field signal is first subjected to Fourier transform to obtain the spectrum of all frequency domain electric field signals. Then, the spectra of all frequencies are superimposed and then denoised and filtered to obtain the frequency domain electric field curve of the tissue under test. The four sets of frequency domain electric field signals can then be used to obtain four corresponding frequency domain electric field curves characterizing the amplitude and phase, namely: the first north-south frequency domain electric field curve, the first east-west frequency domain electric field curve, the second north-south frequency domain electric field curve, and the second east-west frequency domain electric field curve.

[0123] (2) The time-domain electric field information is processed according to the preset time-domain signal processing strategy to obtain the time-domain electric field curve;

[0124] In this embodiment of the invention, the original time-domain electric field signals are first superimposed to obtain a time-domain attenuation curve. Then, the time-domain attenuation curve is deconvolved to eliminate the influence of the excitation signal. After denoising and filtering, the time-domain electric field curve of the tissue under test can be obtained. The four sets of time-domain electric field signals can then produce four corresponding time-domain electric field curves characterizing the amplitude, namely: the first north-south time-domain electric field curve, the first east-west time-domain electric field curve, the second north-south time-domain electric field curve, and the second east-west time-domain electric field curve.

[0125] (3) Based on the frequency domain electric field curve and the time domain electric field curve, calculate the frequency domain electric field difference anomaly and the time domain electric field difference anomaly before and after applying a stable magnetic field to the tissue under test.

[0126] In this embodiment of the invention, based on the first north-south frequency domain electric field curve and the second north-south frequency domain electric field curve, frequency domain electric field differential anomalies characterizing amplitude and phase in the north-south direction are calculated before and after applying a stable magnetic field to the tissue under test. Similarly, based on the first east-west frequency domain electric field curve and the second east-west frequency domain electric field curve, east-west frequency domain electric field differential anomalies characterizing amplitude and phase are calculated. Based on the first north-south time domain electric field curve and the second north-south time domain electric field curve, north-south time domain electric field differential anomalies characterizing amplitude are calculated. Based on the first east-west time domain electric field curve and the second east-west time domain electric field curve, east-west time domain electric field differential anomalies characterizing amplitude are calculated. That is, frequency domain electric field differential anomalies include north-south frequency domain electric field differential anomalies and east-west frequency domain electric field differential anomalies, and time domain electric field differential anomalies include northwest time domain electric field differential anomalies and east-west time domain electric field differential anomalies.

[0127] (4) Based on the frequency domain electric field curve and the time domain electric field curve, the electric field distribution is obtained. Based on the frequency domain electric field difference anomaly and the time domain electric field difference anomaly, the electric field anomaly distribution is obtained. Based on the electric field distribution and the electric field anomaly distribution, the target electric field data is generated.

[0128] In this embodiment of the invention, the electric field distribution e is obtained based on four sets of frequency domain electric field curves and four sets of time domain electric field curves, and the electric field anomaly distribution m is obtained based on the frequency domain electric field difference anomaly and the time domain electric field difference anomaly.

[0129] In step S304, based on the target electric field data, the preset human tissue electrical model is inverted to obtain the tissue information of the tissue to be tested.

[0130] In this embodiment of the invention, the tissue information of the tissue under test includes the resistivity distribution r, polarizability distribution p, electric field distribution e, and the abnormal electric field distribution m after magnetic stabilization loading. The human tissue electrical model M includes a geometric model M. G Resistivity model M R and polarizability model M η That is, M = M G +M R +M η Among them, geometric model M G M is composed of known parameters given by a human body model, including the skin, muscles, fat, bones, blood vessels, and epidermis of a normal human body. R It is an initial model constructed from the known resistivity of tissues such as skin, muscle, fat, bone, and blood vessels, M. η It is an initial model constructed from the known polarizabilities of tissues such as skin, muscle, fat, bone, and blood vessels, namely M. G ={m G i |1<i<N},M R ={m R i |1<i<N+1},M η ={m η i |1<i<N+1}, Let i be the geometric model of the i-th tissue in the human body. Let be the resistivity of the i-th tissue in the human body. Let N be the polarizability of the i-th tissue in the human body, and N be the total number of tissues in the human body.

[0131] In one feasible embodiment, before inverting the preset human tissue electrical model, forward modeling is performed on the pre-collected sample electric field data of human tissue to obtain sample tissue information of human tissue. The sample tissue information includes the resistivity distribution r, polarizability distribution p, electric field distribution e, and electric field anomaly distribution m after magnetic stabilization loading of the sample tissue.

[0132] In another feasible embodiment, when inverting a preset human tissue electrical model, based on sample tissue information and target electric field data, a time-frequency joint, step-by-step constrained sequential inversion strategy is used to iteratively invert the resistivity model and the polarizability model until the fitting error of the resistivity model is within a preset resistivity variation range and the fitting error of the polarizability model is within a preset polarizability variation range, thereby improving the inversion accuracy.

[0133] In this embodiment of the invention, the resistivity variation range of the resistivity model of human tissue is... Polarizability variation range of the polarizability model The results are given by testing human tissue samples, among which, and These are the minimum and maximum values ​​in the resistivity model, respectively. and These are the minimum and maximum values ​​in the polarizability model, respectively. The geometric parameters of the geometric model remain unchanged during the inversion process; that is, the geometric model parameters do not participate in the inversion. Only resistivity and polarizability are inverted. When using a time-frequency joint, step-by-step constrained sequential inversion strategy to iteratively invert the resistivity and polarizability models, the iterative inversion is specifically achieved through the following steps:

[0134] ① Resistivity inversion is performed using the least squares inversion algorithm;

[0135] In this embodiment of the invention, the polarization effect of human tissue (or the dielectric effect at high frequencies) is not considered initially, so the inversion equation is M = M G +M R And M G It does not participate in the inversion, only for the resistivity model M R Inversion is performed, and from one-dimensional inversion, it can be calculated that the model's geometric parameters do not participate in the inversion. The number of inversion unknowns is reduced from 2n+1 to n+1. The reduction is even greater in two-dimensional inversion. The search range of the resistivity model is narrowed from more than three orders to within one order, which speeds up the convergence and inversion speed. In particular, it enables the inversion to converge towards a reasonable range of electrical changes, and finally obtains a resistivity model that conforms to the electrical laws of human tissue. The resistivity model results reflect the electrical characteristics of the basic human tissue model.

[0136] ② The least squares inversion algorithm is used to perform polarizability inversion;

[0137] In this embodiment of the invention, after the resistivity model is determined by inversion, the polarization effect of human tissue is inverted. To represent the polarizability, an equivalent Cole-Cole complex resistivity model is introduced. To characterize the electrical properties of human tissues, the resistivity of the Cole-Cole model is first fixed to the resistivity obtained in step ①, and remains unchanged during the polarizability inversion process. Then, the polarizability in the Cole-Cole model is inverted. Other parameters such as τ and c can also be fixed and inverted one by one. The polarizability inversion model result is the residual electromagnetic anomaly in addition to the basic electrical characteristics. Here, ρ0 is the zero-frequency resistivity, m is the polarizability, τ is the time constant, c is the frequency correlation coefficient, ω is the angular frequency, and i is the imaginary part of the complex number.

[0138] ③ Analyze and evaluate the inversion results. If the inversion results do not meet the resistivity variation range and / or polarizability variation range, return to step ① and continue the inversion until the fitting error of the resistivity model is within the resistivity variation range and the fitting error of the polarizability is within the polarizability variation range.

[0139] In one feasible embodiment, the resistivity distribution r and polarizability distribution p of the tissue under test are obtained based on the resistivity and polarizability obtained by iterative inversion, and then combined with the target electric field data, the tissue information of the tissue under test is obtained.

[0140] In step S305, the tissue information is input into a pre-trained human trait assessment width learning network to obtain the assessment results of the tissue trait and water content of the tissue to be tested.

[0141] In this embodiment of the invention, tissue information including e, r, p, and m is input into a trained human trait assessment width learning network to obtain the electrical structure corresponding to erpm. The electrical structure is analyzed to obtain the assessment results of the tissue trait and water content of the tissue to be tested.

[0142] In one feasible embodiment, the human trait assessment width learning network is trained based on sample tissue information before the tissue information is input into the pre-trained human trait assessment width learning network, so that the human trait assessment width learning network can assess the tissue characteristics and water content of human tissues.

[0143] In this embodiment of the invention, an electromagnetic excitation system is controlled to generate an excitation signal, and the excitation signal is supplied to the test tissue of the human body by controlling the orthogonal excitation electrodes in the electromagnetic excitation system. An electromagnetic information acquisition system is controlled to collect the electric field signal generated by the test tissue under the action of the excitation signal. The electric field signal is processed according to a preset data processing strategy to obtain target electric field data. Based on the target electric field data, the electrical property model of human tissue is inverted to obtain the tissue information of the test tissue. The tissue information is input into a pre-trained human trait assessment width learning network to obtain the assessment results of the tissue trait and water content of the test tissue. This improves the speed and accuracy of assessing the tissue trait and water content of the human body, while reducing the cost of human health monitoring and the radiation damage during the monitoring process.

[0144] Example 4:

[0145] Figure 4 The structure of the computing device provided in Embodiment 4 of the present invention is shown. For ease of explanation, only the parts related to the embodiments of the present invention are shown.

[0146] The computing device 4 of this embodiment includes a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, it implements the functions of each unit in the above-described embodiment of the human body tissue characteristics and water content evaluation device, such as the functions of units 1.1 to 1.5 shown in FIG. 1. Alternatively, when the processor 40 executes the computer program 42, it implements the steps in the above-described embodiment of the human body tissue characteristics and water content evaluation method, for example... Figure 3 Steps S301 to S305 are shown.

[0147] The human tissue morphology and water content assessment device of this invention includes a signal excitation unit, a signal acquisition unit, a signal processing unit, a data inversion unit, and a morphology assessment unit. The signal excitation unit controls an electromagnetic excitation system to generate an excitation signal and supplies the excitation signal to the human tissue to be tested by controlling the orthogonal excitation electrodes in the electromagnetic excitation system. The signal acquisition unit controls an electromagnetic information acquisition system to acquire the electric field signal generated by the tissue to be tested under the action of the excitation signal. The signal processing unit processes the electric field signal according to a preset data processing strategy to obtain target electric field data. The data inversion unit inverts the human tissue electrical model based on the target electric field data to obtain the tissue information of the tissue to be tested. The morphology assessment unit inputs the tissue information into a human morphology assessment width learning network to obtain the assessment results of the tissue morphology and water content of the tissue to be tested, thereby improving the speed and accuracy of human tissue morphology and water content assessment, while reducing the cost of human health monitoring and radiation damage during the monitoring process.

[0148] The computing device in this embodiment of the invention can be a personal computer or a server. The steps implemented by the processor 40 in the computing device 4 when executing the computer program 42 to implement the method for evaluating the tissue characteristics and water content of the human body can be referred to the description of the foregoing method embodiments, and will not be repeated here.

[0149] Example 5:

[0150] In this embodiment of the invention, a computer-readable storage medium is provided, which stores a computer program. When executed by a processor, the computer program implements the functions of each unit in the above-described apparatus embodiment for evaluating the tissue characteristics and water content of the human body, such as the functions of units 1.1 to 1.5 shown in FIG. 1. Alternatively, when executed by a processor, the computer program implements the steps in the above-described method embodiment for evaluating the tissue characteristics and water content of the human body, for example... Figure 3 Steps S301 to S305 are shown.

[0151] The human tissue morphology and water content assessment device of this invention includes a signal excitation unit, a signal acquisition unit, a signal processing unit, a data inversion unit, and a morphology assessment unit. The signal excitation unit controls an electromagnetic excitation system to generate an excitation signal and supplies the excitation signal to the human tissue to be tested by controlling the orthogonal excitation electrodes in the electromagnetic excitation system. The signal acquisition unit controls an electromagnetic information acquisition system to acquire the electric field signal generated by the tissue to be tested under the action of the excitation signal. The signal processing unit processes the electric field signal according to a preset data processing strategy to obtain target electric field data. The data inversion unit inverts the human tissue electrical model based on the target electric field data to obtain the tissue information of the tissue to be tested. The morphology assessment unit inputs the tissue information into a human morphology assessment width learning network to obtain the assessment results of the tissue morphology and water content of the tissue to be tested, thereby improving the speed and accuracy of human tissue morphology and water content assessment, while reducing the cost of human health monitoring and radiation damage during the monitoring process.

[0152] The computer-readable storage medium in embodiments of the present invention may include any entity or device capable of carrying computer program code, a recording medium, such as ROM / RAM, disk, optical disk, flash memory, etc.

[0153] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A device for evaluating the tissue characteristics and water content of the human body, characterized in that, The device includes: The signal excitation unit is used to control the electromagnetic excitation system to generate an excitation signal, and to supply the excitation signal to the human body tissue to be tested by controlling the orthogonal excitation electrodes in the electromagnetic excitation system. The signal acquisition unit is used to control the electromagnetic information acquisition system to acquire the electric field signal generated by the tissue under test under the action of the excitation signal; The signal processing unit is used to process the electric field signal according to a preset data processing strategy to obtain target electric field data. The data inversion unit is used to invert the preset human tissue electrical model based on the target electric field data to obtain the tissue information of the tissue to be tested. The trait evaluation unit is used to input the tissue information into a pre-trained human trait evaluation width learning network to obtain the evaluation results of the tissue traits and water content of the tissue to be tested. The electromagnetic excitation system is a time-frequency dual-domain excitation system, and the excitation signal includes a frequency-domain excitation signal and a time-domain excitation signal. The signal excitation unit includes: The signal excitation subunit is used to control the electromagnetic excitation system to generate frequency domain excitation signals and time domain excitation signals without an stable magnetic field when there is no stable magnetic field in the region of the tissue to be tested, and to control the electromagnetic excitation system to generate frequency domain excitation signals and time domain excitation signals with a stable magnetic field when there is a stable magnetic field in the region of the tissue to be tested, wherein the frequency domain excitation signal is generated by low-frequency and high-frequency excitation of the electromagnetic excitation system, and the time domain excitation signal is generated by low-frequency excitation of the electromagnetic excitation system; The electric field signal includes a frequency domain electric field signal and a time domain electric field signal, and the signal processing unit includes: A frequency domain signal processing unit is used to process the frequency domain electric field signal according to a preset frequency domain signal processing strategy to obtain a frequency domain electric field curve. The time-domain signal processing unit is used to process the time-domain electric field information according to a preset time-domain signal processing strategy to obtain the time-domain electric field curve. The differential anomaly calculation unit is used to calculate the frequency domain electric field differential anomaly and the time domain electric field differential anomaly of the tissue under test before and after the application of the stable magnetic field, respectively, based on the frequency domain electric field curve and the time domain electric field curve. An electric field data generation unit is used to obtain an electric field distribution based on the frequency domain electric field curve and the time domain electric field curve, obtain an electric field anomaly distribution based on the frequency domain electric field differential anomaly and the time domain electric field differential anomaly, and generate the target electric field data based on the electric field distribution and the electric field anomaly distribution.

2. The apparatus as claimed in claim 1, characterized in that, The device further includes: A stable magnetic field excitation unit is used to control the stable magnetic field excitation system to generate the stable magnetic field in the region of the tissue to be tested.

3. The apparatus as described in claim 2, characterized in that, The device further includes: The data forward modeling unit is used to perform forward modeling simulation on the pre-collected electric field data of human tissue samples to obtain the sample tissue information of the human tissue.

4. The apparatus as described in claim 3, characterized in that, The electrical model of human tissue includes a geometric model, a resistivity model, and a polarizability model; the data inversion unit includes: The data inversion subunit is used to iteratively invert the resistivity model and the polarizability model based on the sample tissue information and the target electric field data, using a time-frequency joint, step-by-step constrained sequential inversion strategy, until the fitting error of the resistivity model is within a preset resistivity variation range and the fitting error of the polarizability model is within a preset polarizability variation range, thereby obtaining the tissue information including resistivity distribution, polarizability distribution, electric field distribution, and electric field anomaly distribution. The geometric parameters of the geometric model remain constant during the inversion process, and the resistivity variation range... and the range of polarizability variation The results are provided by testing human tissue samples. and These are the minimum and maximum values ​​in the resistivity model of human tissue samples, respectively. and These are the minimum and maximum values ​​in the polarizability model of human tissue samples, respectively.

5. The apparatus as described in claim 3, characterized in that, The device further includes: The network training unit is used to train the human trait assessment width learning network based on the sample tissue information, so that the human trait assessment width learning network can assess the tissue characteristics and water content of the human tissue.

6. A method for evaluating the tissue characteristics and water content of the human body, characterized in that, The evaluation method, when applied to the apparatus as described in any one of claims 1 to 5, includes the following steps: The electromagnetic excitation system is controlled to generate an excitation signal, and the excitation signal is supplied to the test tissue of the human body by controlling the orthogonal excitation electrodes in the electromagnetic excitation system. The electromagnetic information acquisition system is controlled to acquire the electric field signal generated by the tissue under test under the action of the excitation signal; The electric field signal is processed according to a preset data processing strategy to obtain the target electric field data; Based on the target electric field data, the preset human tissue electrical model is inverted to obtain the tissue information of the tissue to be tested; The tissue information is input into a pre-trained human trait assessment width learning network to obtain the assessment results of the tissue trait and water content of the tissue to be tested.

7. A computing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it performs the functions of the apparatus as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it performs the functions of the apparatus as described in any one of claims 1 to 5.

Images