Prostate surrounding tissue signal analysis method, apparatus and device, and storage medium
Through multi-channel bioelectric signal acquisition and machine learning model analysis, the electrical stimulation parameters are dynamically adjusted, which solves the problem that traditional electrical stimulation systems cannot match the patient's physiological status in real time, and achieves a more efficient and comfortable treatment effect.
Patent Information
- Application Number
- CN202411510121.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-27
- Publication Date
- 2025-03-25
AI Technical Summary
Traditional electrical stimulation systems have large errors in collecting and analyzing the electromyography and nerve pulse signals in the tissues around the prostate, resulting in the inability to match the patient's physiological status in real time, increasing discomfort and side effects.
Multi-channel bioelectric signals are collected by combining surface electrodes and implanted electrodes, and real-time detection and analysis are performed using pre-trained machine learning models to dynamically adjust electrical stimulation parameters to match the patient's physiological state.
By accurately collecting and real-time analysis of tissue signals around the prostate, accurate adjustment of electrical stimulation parameters can be achieved, discomfort and side effects can be reduced, and treatment effect and comfort can be improved.
Smart Images
Figure CN119679434A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of signal processing technology, and in particular to a method, device, equipment and storage medium for analyzing signals of prostate peripheral tissue. Background Art
[0002] Prostate diseases, such as prostatitis and prostatic hyperplasia, are common health problems in middle-aged and elderly men. Traditional treatments include medication and physical therapy. However, medications are prone to side effects, and it is difficult to adjust treatment parameters in a personalized manner with physical therapy. In recent years, electrical stimulation therapy and biosignal monitoring technology have gradually become an effective auxiliary treatment method, in which real-time monitoring and optimization of the treatment process based on bioelectric signals (such as electromyographic signals and neural response signals) can improve the treatment effect and patient comfort.
[0003] However, because the electromyographic (EMG) and nerve pulse signals of the tissues surrounding the prostate are weak and are interfered by multiple factors, traditional electrical stimulation systems have large errors when collecting and analyzing signals, resulting in the inability of electrical stimulation schemes for the prostate to match the patient's physiological state in real time, increasing discomfort and side effects. Summary of the invention
[0004] The embodiments of the present application provide a method, device, equipment and storage medium for analyzing signals of tissues around the prostate, which are intended to accurately acquire signals of tissues around the prostate through multi-channel acquisition, and to use machine learning algorithms to achieve real-time detection and analysis of signals of tissues around the prostate, and to dynamically adjust electrical stimulation parameters based on the analysis results, so as to achieve real-time and accurate adjustment of electrical stimulation parameters for the prostate.
[0005] In a first aspect, an embodiment of the present application provides a method for analyzing prostate peripheral tissue signals, comprising:
[0006] The combination of surface electrodes and implanted electrodes is used to collect multi-channel bioelectric signals of the tissue surrounding the prostate;
[0007] Input the multi-channel bioelectric signals into the pre-trained machine learning model for analysis to determine the status information of the tissue around the prostate;
[0008] Based on the status information of the tissue surrounding the prostate, the electrical stimulation parameters of the prostate are dynamically adjusted.
[0009] In one embodiment, the multi-channel bioelectric signal includes: electromyographic signals of the pelvic floor muscles, nerve pulse signals, and heart rate variability signals.
[0010] In one embodiment, the multi-channel bioelectrical signals are input into a pre-trained machine learning model for analysis to determine the state information of the tissue surrounding the prostate, including:
[0011] The electromyographic signals of the pelvic floor muscles are input into a pre-trained machine learning model for analysis to determine whether the pelvic floor muscles are in a fatigue state;
[0012] The nerve pulse signal is input into the pre-trained machine learning model for analysis to determine the change state of nerve conduction velocity;
[0013] The heart rate variability signal is input into a pre-trained machine learning model for analysis to determine the changing state of sympathetic nerve activity intensity.
[0014] In one embodiment, dynamically adjusting the electrical stimulation parameters of the prostate based on the state information of the tissue surrounding the prostate includes:
[0015] If the pelvic floor muscles are judged to be in muscle fatigue, reduce the frequency of electrical stimulation or perform intermittent stimulation;
[0016] If the nerve conduction velocity is determined to be reduced, the intensity of electrical stimulation is increased;
[0017] If it is determined that the intensity of sympathetic nerve activity is increased, the intensity of electrical stimulation is reduced.
[0018] In one embodiment, the pre-trained machine learning model includes a support vector machine network. Before the multi-channel bioelectric signal is input into the pre-trained machine learning model for analysis to determine the state information of the tissue surrounding the prostate, the following steps are further included:
[0019] Collecting bioelectric signals and corresponding status labels of a preset number of prostate patients, the status labels including normal, muscle fatigue or nerve conduction damage;
[0020] Analyze bioelectric signals in time domain, frequency domain and time-frequency domain to extract target features;
[0021] The target features are input into the pre-established support vector machine network for training to obtain a pre-machine learning model.
[0022] In one embodiment, the target features include the root mean square value and average frequency of the electromyographic signal, the conduction velocity and amplitude variation characteristics of the nerve pulse signal, the spectrum power of the heart rate variability signal, and the sympathetic and parasympathetic nerve characteristics.
[0023] In one embodiment, the bioelectric signal is analyzed in the time domain, frequency domain, and time-frequency domain to extract target features, including:
[0024] Perform time domain feature extraction on the electromyographic signal of the pelvic floor muscles to obtain the root mean square value, and perform time domain feature extraction on the nerve pulse signal to obtain the conduction velocity and amplitude change characteristics of the nerve pulse signal;
[0025] Perform frequency domain feature extraction on the electromyographic signal of the pelvic floor muscles to obtain the average frequency, and perform frequency domain analysis on the heart rate variable conductivity signal to obtain the spectrum power of the heart rate variable conductivity signal;
[0026] The heart rate variability signal is analyzed in time and frequency domains to obtain the sympathetic and parasympathetic nerve characteristics.
[0027] In a second aspect, an embodiment of the present application provides a prostate peripheral tissue signal analysis device, comprising:
[0028] An acquisition module, used for acquiring multi-channel bioelectric signals of tissues surrounding the prostate by combining surface electrodes and implanted electrodes;
[0029] An analysis module is used to input multi-channel bioelectric signals into a pre-trained machine learning model for analysis to determine the status information of the tissue surrounding the prostate;
[0030] The regulating module is used to dynamically adjust the electrical stimulation parameters of the prostate based on the status information of the tissue surrounding the prostate.
[0031] In a third aspect, an embodiment of the present application provides an electronic device, including:
[0032] Memory and processing modules;
[0033] The memory is used to store computer programs;
[0034] The processing module is used to execute the computer program and implement the steps of the prostate peripheral tissue signal analysis method of the first aspect as described above when executing the computer program.
[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program;
[0036] When the computer program is executed by one or more processing modules, the one or more processing modules execute the steps of the prostate surrounding tissue signal analysis method of the first aspect as described above.
[0037] The embodiment of the present application provides a method, device, equipment and storage medium for analyzing signals of tissues around the prostate, wherein the method for analyzing signals of tissues around the prostate includes: using a combination of surface electrodes and implanted electrodes to collect multi-channel bioelectric signals of tissues around the prostate; inputting the multi-channel bioelectric signals into a pre-trained machine learning model for analysis to determine the state information of tissues around the prostate; and dynamically adjusting the electrical stimulation parameters of the prostate based on the state information of tissues around the prostate. Accurately obtain signals of tissues around the prostate through multi-channel acquisition, and use machine learning algorithms to achieve real-time detection and analysis of signals of tissues around the prostate, and dynamically adjust the electrical stimulation parameters based on the analysis results, so as to achieve real-time and accurate adjustment of electrical stimulation parameters for the prostate. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.
[0039] Figure 1 A schematic diagram of a flow chart of a method for analyzing prostate peripheral tissue signals provided in an embodiment of the present application;
[0040] Figure 2 A schematic diagram of the structure of a prostate peripheral tissue signal analysis device provided in an embodiment of the present application;
[0041] Figure 3 A schematic block diagram of a prostate peri-tissue signal analysis device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0043] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.
[0044] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0045] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0046] The technical solution provided by this application will be described in detail below with reference to the accompanying drawings.
[0047] See also Figure 1 , Figure 1 A flow chart of a method for analyzing signals of tissues surrounding the prostate provided in an embodiment of the present application. The method for analyzing signals of tissues surrounding the prostate is implemented by an electronic therapy device, and the electronic therapy device includes a plurality of surface electrodes for collecting bioelectric signals on the skin surface and a plurality of implanted electrodes for implanting the skin to collect bioelectric signals inside the skin. The electronic therapy device also includes but is not limited to a data processing module, a memory, etc. Specifically, as Figure 1 As shown, the prostate peripheral tissue signal analysis method provided in the embodiment of the present application includes the following steps S101 to S103. The details are as follows:
[0048] S101: Use a combination of surface electrodes and implanted electrodes to collect multi-channel bioelectric signals from tissues surrounding the prostate.
[0049] Surface electrodes are placed in the target user's pubococcygeus and levator ani muscles, and microelectrodes are implanted in the pudendal nerve area to ensure the accuracy of multi-channel signal acquisition. Multi-channel bioelectric signals include: electromyographic signals of the pelvic floor muscles, nerve pulse signals, and heart rate variability signals.
[0050] S102: Input the multi-channel bioelectric signal into the pre-trained machine learning model for analysis to determine the status information of the tissue surrounding the prostate.
[0051] Inputting multi-channel bioelectric signals into a pre-trained machine learning model for analysis to determine the status information of tissues around the prostate, including: inputting the electromyographic signals of the pelvic floor muscles into a pre-trained machine learning model for analysis to determine whether the pelvic floor muscles are in a fatigue state; inputting the nerve pulse signals into a pre-trained machine learning model for analysis to determine the change state of nerve conduction velocity; inputting the heart rate variability signals into a pre-trained machine learning model for analysis to determine the change state of sympathetic nerve activity intensity.
[0052] Specifically, the pre-trained machine learning model includes a support vector machine network. Before the multi-channel bioelectric signals are input into the pre-trained machine learning model for analysis to determine the status information of the tissue around the prostate, it also includes: collecting the bioelectric signals and corresponding status labels of a preset number of prostate patients, wherein the status labels include normal, muscle fatigue or damaged nerve conduction; performing time domain, frequency domain and time-frequency domain analysis on the bioelectric signals to extract target features; and inputting the target features into a pre-established support vector machine network for training and verification to obtain a pre-machine learning model.
[0053] For example, it is assumed that the collected multi-channel bioelectric signal is:
[0054] X={x1(t), x2(t), ..., x n (t)}, t∈[0,T]
[0055] Among them, x i (t) is the signal of the i-th channel, n indicates the number of channels, and T is the acquisition time.
[0056] The status labels are represented as:
[0057] Y={y1,y2,...,y m}
[0058] Among them, y i ∈{0,1,2}, 0 represents normal, 1 represents muscle fatigue, and 2 represents impaired nerve conduction.
[0059] Each data pair (X i ,y i ) represents the signal of the i-th patient and its corresponding state label.
[0060] Specifically, the target features include the root mean square value of the electromyographic signal, the average frequency, the conduction velocity and amplitude change characteristics of the nerve pulse signal, the spectral power of the heart rate variable conductivity signal, and the sympathetic and parasympathetic nerve characteristics.
[0061] The bioelectric signal is analyzed in the time domain, frequency domain and time-frequency domain to extract the target features, including: extracting the time domain features of the electromyographic signal of the pelvic floor muscles to obtain the root mean square value, extracting the time domain features of the nerve pulse signal to obtain the conduction velocity and amplitude change characteristics of the nerve pulse signal; extracting the frequency domain features of the electromyographic signal of the pelvic floor muscles to obtain the average frequency, and performing frequency domain analysis on the heart rate variable conductivity signal to obtain the spectral power of the heart rate variable conductivity signal; performing time-frequency domain analysis on the heart rate variable conductivity signal to obtain the sympathetic and parasympathetic nerve characteristics.
[0062] Specifically, the RMS value reflects the average energy of the electromyographic signal of the pelvic floor muscles and is used to measure the strength of muscle contraction. The higher the RMS value, the greater the strength of muscle contraction.
[0063] The conduction velocity of nerve impulse signals refers to the speed at which nerve signals travel along nerve fibers and is used to reflect the health of nerve conduction function. A decrease in conduction velocity may indicate impaired nerve conduction function.
[0064] The amplitude change of nerve pulse signals reflects the strength of nerve signals and is mainly used to detect the excitability of nerve pulses. A significant decrease in amplitude may indicate a nerve conduction disorder or muscle disorder. By detecting the amplitude change, the treatment effect can be judged and the electrical stimulation parameters can be adjusted in real time.
[0065] Spectral power reflects the energy distribution of heart rate variability signals in different frequency bands and is often used to assess the state of the autonomic nervous system.
[0066] The average frequency reflects the frequency center of gravity of the electromyographic signal of the pelvic floor muscles. When the muscles are fatigued, the average frequency of the muscles will decrease.
[0067] Sympathetic and parasympathetic nerve characteristics can reflect the dynamic changes of heart rate variability signals and the real-time neural response during electrical stimulation.
[0068] The pre-built support vector machine network can be expressed as: Constraints: y i (W.F i +b)≥1-ε i , ε i ≥0; where F i is the characteristic vector of the bioelectric signal of the i-th patient, y i is its corresponding label, m is the number of samples collected, W is the weight vector, b is the bias term, C is the regularization parameter, which controls the degree of penalty of the network, and ε i is a slack variable that allows for some misclassification.
[0069] After obtaining the trained support vector machine network, determine the state of the new input signal features:
[0070]
[0071] Among them, F new is the new input signal feature vector, Indicates the classification result.
[0072] S103: Dynamically adjust electrical stimulation parameters of the prostate based on status information of tissues surrounding the prostate.
[0073] Based on the status information of the tissues surrounding the prostate, the electrical stimulation parameters of the prostate are dynamically adjusted, including: if the pelvic floor muscles are determined to be in muscle fatigue, the electrical stimulation frequency is reduced or intermittent stimulation is performed; if the nerve conduction velocity is determined to be reduced, the electrical stimulation intensity is increased; if the sympathetic nerve activity intensity is determined to be enhanced, the electrical stimulation intensity is reduced.
[0074] The fatigue state of the pelvic floor muscles can be determined by the amplitude change of the electromyographic signal of the pelvic floor muscles. When muscle fatigue is detected, the frequency of electrical stimulation is reduced and / or adjusted to an intermittent waveform. When a decrease in nerve conduction velocity is detected, the intensity of stimulation is increased to promote nerve conduction recovery. When the heart rate variability signal is detected to show an increase in the intensity of sympathetic nerve activity, it indicates that the sympathetic nerves are excited, and the intensity of stimulation is reduced to avoid discomfort.
[0075] Through the above analysis, it can be known that the method for analyzing the signal of the tissue around the prostate provided in the embodiment of the present application includes: using a combination of surface electrodes and implanted electrodes to collect multi-channel bioelectric signals of the tissue around the prostate; inputting the multi-channel bioelectric signals into a pre-trained machine learning model for analysis to determine the state information of the tissue around the prostate; and dynamically adjusting the electrical stimulation parameters of the prostate based on the state information of the tissue around the prostate. The signals of the tissue around the prostate are accurately acquired through multi-channel acquisition, and the machine learning algorithm is used to realize the real-time detection and analysis of the signals of the tissue around the prostate, and the electrical stimulation parameters are dynamically adjusted based on the analysis results, so as to realize the real-time and accurate adjustment of the electrical stimulation parameters for the prostate.
[0076] See also Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of the prostate peripheral tissue signal analysis device provided in the embodiment of the present application. Figure 2 It can be seen that the prostate peripheral tissue signal analysis device 20 provided in the embodiment of the present application includes:
[0077] The acquisition module 201 is used to acquire multi-channel bioelectric signals of the tissue surrounding the prostate by combining surface electrodes and implanted electrodes;
[0078] An analysis module 202 is used to input the multi-channel bioelectric signals into a pre-trained machine learning model for analysis to determine the status information of the tissue surrounding the prostate;
[0079] The adjustment module 203 is used to dynamically adjust the electrical stimulation parameters of the prostate based on the status information of the tissue surrounding the prostate.
[0080] In one embodiment, the multi-channel bioelectric signal includes: electromyographic signals of the pelvic floor muscles, nerve pulse signals, and heart rate variability signals.
[0081] In one embodiment, the analysis module 202 includes:
[0082] A first analysis unit is used to input the electromyographic signal of the pelvic floor muscle group into a pre-trained machine learning model for analysis to determine whether the pelvic floor muscle is in a fatigue state;
[0083] The second analysis unit is used to input the nerve pulse signal into the pre-trained machine learning model for analysis to determine the change state of the nerve conduction velocity;
[0084] The third analysis unit is used to input the heart rate variability signal into a pre-trained machine learning model for analysis to determine the change state of the sympathetic nerve activity intensity.
[0085] In one embodiment, the adjustment module 203 includes:
[0086] A first reduction unit is used to reduce the frequency of electrical stimulation or perform intermittent stimulation if it is determined that the pelvic floor muscles are in muscle fatigue;
[0087] An increasing unit, used to increase the intensity of electrical stimulation if it is determined that the nerve conduction velocity is reduced;
[0088] The second reducing unit is used to reduce the intensity of electrical stimulation if it is determined that the intensity of sympathetic nerve activity is increased.
[0089] In one embodiment, the device 20 further includes:
[0090] A state acquisition module, used to collect bioelectric signals and corresponding state labels of a preset number of prostate patients, the state labels including normal, muscle fatigue or nerve conduction damage;
[0091] An extraction module is used to analyze the bioelectric signal in the time domain, frequency domain, and time-frequency domain to extract target features;
[0092] The training module is used to input the target features into the pre-established support vector machine network for training to obtain a pre-machine learning model.
[0093] In one embodiment, the target features include the root mean square value and average frequency of the electromyographic signal, the conduction velocity and amplitude variation characteristics of the nerve pulse signal, the spectrum power of the heart rate variability signal, and the sympathetic and parasympathetic nerve characteristics.
[0094] In one embodiment, the extraction module includes:
[0095] The first obtaining unit is used to extract the time domain features of the electromyographic signals of the pelvic floor muscles to obtain the root mean square value, and to extract the time domain features of the nerve pulse signals to obtain the conduction velocity and amplitude change characteristics of the nerve pulse signals;
[0096] The second obtaining unit is used to extract the frequency domain features of the electromyographic signal of the pelvic floor muscle group to obtain the average frequency, and to perform frequency domain analysis on the heart rate variable conductivity signal to obtain the spectrum power of the heart rate variable conductivity signal;
[0097] The third obtaining unit is used to perform time-frequency domain analysis on the heart rate variable conductivity signal to obtain sympathetic and parasympathetic nerve characteristics.
[0098] It should be noted that the specific implementation process of the above modules or units can refer to the specific implementation process of each step in the previous method embodiment, which will not be repeated here.
[0099] See also Figure 3 As shown, Figure 3 A schematic block diagram of a prostate peri-tissue signal analysis device provided in an embodiment of the present application.
[0100] Exemplarily, the prostate peri-tissue signal analysis device 30 includes a processing module 301 and a memory 302 .
[0101] Exemplarily, the processing module 301 and the memory 302 are connected via a bus 303 , and the bus 303 is, for example, an I2C (Inter-integrated Circuit) bus.
[0102] Specifically, the processing module 301 may be a micro-controller unit (MCU), a central processing unit (CPU) or a digital signal processing module (DSP).
[0103] Specifically, the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.
[0104] The processing module 301 is used to run the computer program stored in the memory 302 and implement the steps of the above-mentioned prostate peripheral tissue signal analysis method when executing the computer program.
[0105] Exemplarily, the processing module 301 is used to run the computer program stored in the memory 302, and implement the following steps when executing the computer program:
[0106] The combination of surface electrodes and implanted electrodes is used to collect multi-channel bioelectric signals of the tissue surrounding the prostate;
[0107] Input the multi-channel bioelectric signals into the pre-trained machine learning model for analysis to determine the status information of the tissue around the prostate;
[0108] Based on the status information of the tissue surrounding the prostate, the electrical stimulation parameters of the prostate are dynamically adjusted.
[0109] In one embodiment, the multi-channel bioelectric signal includes: electromyographic signals of the pelvic floor muscles, nerve pulse signals, and heart rate variability signals.
[0110] In one embodiment, the multi-channel bioelectrical signals are input into a pre-trained machine learning model for analysis to determine the state information of the tissue surrounding the prostate, including:
[0111] The electromyographic signals of the pelvic floor muscles are input into a pre-trained machine learning model for analysis to determine whether the pelvic floor muscles are in a fatigue state;
[0112] The nerve pulse signal is input into the pre-trained machine learning model for analysis to determine the change state of nerve conduction velocity;
[0113] The heart rate variability signal is input into a pre-trained machine learning model for analysis to determine the changing state of sympathetic nerve activity intensity.
[0114] In one embodiment, dynamically adjusting the electrical stimulation parameters of the prostate based on the state information of the tissue surrounding the prostate includes:
[0115] If the pelvic floor muscles are judged to be in muscle fatigue, reduce the frequency of electrical stimulation or perform intermittent stimulation;
[0116] If the nerve conduction velocity is determined to be reduced, the intensity of electrical stimulation is increased;
[0117] If it is determined that the intensity of sympathetic nerve activity is increased, the intensity of electrical stimulation is reduced.
[0118] In one embodiment, the pre-trained machine learning model includes a support vector machine network. Before the multi-channel bioelectric signal is input into the pre-trained machine learning model for analysis to determine the state information of the tissue surrounding the prostate, the following steps are further included:
[0119] Collecting bioelectric signals and corresponding status labels of a preset number of prostate patients, the status labels including normal, muscle fatigue or nerve conduction damage;
[0120] Analyze bioelectric signals in time domain, frequency domain and time-frequency domain to extract target features;
[0121] The target features are input into the pre-established support vector machine network for training to obtain a pre-machine learning model.
[0122] In one embodiment, the target features include the root mean square value and average frequency of the electromyographic signal, the conduction velocity and amplitude variation characteristics of the nerve pulse signal, the spectrum power of the heart rate variability signal, and the sympathetic and parasympathetic nerve characteristics.
[0123] In one embodiment, the bioelectric signal is analyzed in the time domain, frequency domain, and time-frequency domain to extract target features, including:
[0124] Perform time domain feature extraction on the electromyographic signal of the pelvic floor muscles to obtain the root mean square value, and perform time domain feature extraction on the nerve pulse signal to obtain the conduction velocity and amplitude change characteristics of the nerve pulse signal;
[0125] Perform frequency domain feature extraction on the electromyographic signal of the pelvic floor muscles to obtain the average frequency, and perform frequency domain analysis on the heart rate variable conductivity signal to obtain the spectrum power of the heart rate variable conductivity signal;
[0126] The heart rate variability signal is analyzed in time and frequency domains to obtain the sympathetic and parasympathetic nerve characteristics.
[0127] The specific principles and implementation methods of the prostate peri-tissue signal analysis device provided in the embodiment of the present application are similar to those of the prostate peri-tissue signal analysis method in the aforementioned embodiment, and will not be repeated here.
[0128] The embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by the processing module, the processing module implements the following steps:
[0129] The combination of surface electrodes and implanted electrodes is used to collect multi-channel bioelectric signals of the tissue surrounding the prostate;
[0130] Input the multi-channel bioelectric signals into the pre-trained machine learning model for analysis to determine the status information of the tissue around the prostate;
[0131] Based on the status information of the tissue surrounding the prostate, the electrical stimulation parameters of the prostate are dynamically adjusted.
[0132] The computer-readable storage medium may be an internal storage unit of the prostate surrounding tissue signal analysis device in the aforementioned embodiment, such as a hard disk or memory of the prostate surrounding tissue signal analysis device. The computer-readable storage medium may also be an external storage device of the prostate surrounding tissue signal analysis device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the prostate surrounding tissue signal analysis device.
[0133] It should be understood that the terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
[0134] It will also be understood that the term "and / or" used in this application and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
[0135] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A method for analyzing signals of prostate surrounding tissues, characterized in that: include: The combination of surface electrodes and implanted electrodes is used to collect multi-channel bioelectric signals of the tissue surrounding the prostate; Inputting the multi-channel bioelectric signal into a pre-trained machine learning model for analysis to determine the status information of the tissue surrounding the prostate; Based on the status information of the tissue surrounding the prostate, the electrical stimulation parameters of the prostate are dynamically adjusted.
2. The method for analyzing prostate peripheral tissue signals according to claim 1, characterized in that: The multi-channel bioelectric signals include: electromyographic signals of the pelvic floor muscles, nerve pulse signals and heart rate variability signals.
3. The method for analyzing prostate peripheral tissue signals according to claim 2, characterized in that: The multi-channel bioelectric signal is input into a pre-trained machine learning model for analysis to determine the state information of the tissue surrounding the prostate, including: Inputting the electromyographic signal of the pelvic floor muscle group into a pre-trained machine learning model for analysis to determine whether the pelvic floor muscle is in a fatigue state; Inputting the nerve pulse signal into a pre-trained machine learning model for analysis to determine the change state of nerve conduction velocity; The heart rate variability signal is input into a pre-trained machine learning model for analysis to determine the change state of the sympathetic nerve activity intensity.
4. The method for analyzing prostate peripheral tissue signals according to claim 3, characterized in that: The method of dynamically adjusting the electrical stimulation parameters of the prostate based on the state information of the tissue surrounding the prostate comprises: If it is determined that the pelvic floor muscles are in muscle fatigue, the electrical stimulation frequency is reduced or intermittent stimulation is performed; If it is determined that the nerve conduction velocity is reduced, increasing the intensity of the electrical stimulation; If it is determined that the intensity of the sympathetic nerve activity is increased, the intensity of the electrical stimulation is reduced.
5. The method for analyzing prostate peripheral tissue signals according to claim 1, characterized in that: The pre-trained machine learning model includes a support vector machine network. Before the multi-channel bioelectric signal is input into the pre-trained machine learning model for analysis to determine the state information of the tissue surrounding the prostate, the method further includes: Collecting bioelectric signals and corresponding status labels of a preset number of prostate patients, wherein the status labels include normal, muscle fatigue or impaired nerve conduction; Performing time domain, frequency domain and time-frequency domain analysis on the bioelectric signal to extract target features; The target features are input into a pre-established support vector machine network for training to obtain the pre-machine learning model.
6. The method for analyzing prostate peripheral tissue signals according to claim 5, characterized in that: The target features include the root mean square value and average frequency of the electromyographic signal, the conduction velocity and amplitude variation characteristics of the nerve pulse signal, the spectrum power of the heart rate variable conductivity signal, and the sympathetic and parasympathetic nerve characteristics.
7. The method for analyzing prostate peripheral tissue signals according to claim 6, characterized in that: The step of performing time domain, frequency domain and time-frequency domain analysis on the bioelectric signal to extract target features includes: Performing time domain feature extraction on the electromyographic signal of the pelvic floor muscle group to obtain the root mean square value, and performing time domain feature extraction on the nerve pulse signal to obtain the conduction velocity and amplitude change characteristics of the nerve pulse signal; Performing frequency domain feature extraction on the electromyographic signal of the pelvic floor muscle group to obtain the average frequency, and performing frequency domain analysis on the heart rate variable conductivity signal to obtain the spectrum power of the heart rate variable conductivity signal; The heart rate variability signal is analyzed in time and frequency domains to obtain the sympathetic and parasympathetic nerve characteristics.
8. A prostate peripheral tissue signal analysis device, characterized in that: include: An acquisition module, used for acquiring multi-channel bioelectric signals of tissues surrounding the prostate by combining surface electrodes and implanted electrodes; An analysis module, used for inputting the multi-channel bioelectric signal into a pre-trained machine learning model for analysis to determine the status information of the tissue surrounding the prostate; The regulating module is used to dynamically regulate the electrical stimulation parameters of the prostate based on the status information of the tissue surrounding the prostate.
9. An electronic device, characterized in that: include: Memory and processing modules; The memory is used to store computer programs; The processing module is used to execute the computer program and implement the steps of the prostate peripheral tissue signal analysis method as described in claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores a computer program; When the computer program is executed by one or more processing modules, the one or more processing modules execute the steps of the prostate peripheral tissue signal analysis method as described in any one of claims 1 to 7.