A minimally invasive surgery nerve monitoring system

Abstract

The present invention relates to the field of artificial intelligence, and in particular to a minimally invasive surgery neural monitoring system, which comprises an acquisition module, an analysis module, a processing module and an adjustment module; the acquisition module monitors the electroencephalogram (EEG) signals and related neuroanatomical and physiological parameters in minimally invasive surgery in real time; the analysis module calculates the neural path length and waveform time interval, constructs a three-dimensional neural model, and identifies abnormal EEG signals; the processing module integrates historical data to assess surgical risks; the early warning module outputs a safety warning based on the comparison between the risk level and a preset threshold; the system effectively monitors the neural status in minimally invasive surgery and improves surgical safety.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a minimally invasive surgery nerve monitoring system. Background Art

[0002] With the development of minimally invasive surgery technology, nerve monitoring systems have also begun to be used in minimally invasive surgery. These systems can monitor indicators such as nerve function and blood flow in real time, helping doctors better control surgical risks and protect nerve function.

[0003] Patent document with publication number CN105744887A discloses a system and method for neurophysiological assessment during surgical procedures. The health and status of lower motor nerve pathways are established in tissues having neural structures that can cause nerve damage to patients when contacted or violated. A computer-implemented method monitors the health of lower motor nerve pathways before and during spinal surgery. The method includes transmitting a first percutaneous transabdominal stimulation signal to a spinal nerve root above a surgical target site; and determining a neuromuscular response data set based on the transmission of the stimulation signal to a muscle located below the surgical target site.

[0004] This shows that the following problem exists: In the prior art, insufficient preoperative assessment of the patient's overall health condition, surgical risks and possible complications leads to low surgical risk and safety. Summary of the invention

[0005] To this end, the present invention provides a minimally invasive surgery nerve monitoring system to overcome the problem in the prior art that insufficient preoperative assessment of the patient's overall health condition, surgical risks and possible complications leads to low surgical risk and safety.

[0006] To achieve the above object, the present invention provides a minimally invasive surgery nerve monitoring system, comprising:

[0007] The acquisition module is used to collect EEG signals of minimally invasive surgery in real time, and is also used to collect nerve fiber length, myelin thickness, nerve conduction velocity, fiber bundle path, synapse number and distance between brain regions;

[0008] an analysis module connected to the acquisition module, for calculating the nerve path length according to the distance between the brain regions, the number of synapses and the fiber bundle path, calculating the waveform time interval according to the nerve path length, the bone sheath thickness and the nerve conduction velocity, constructing a three-dimensional neural model according to the number of synapses, the nerve fiber length, the nerve conduction velocity and the bone sheath thickness, and identifying the abnormal phase signal of the electroencephalogram signal according to the three-dimensional neural model and the waveform time interval;

[0009] a processing module connected to the analysis module, for acquiring historical data of minimally invasive surgery, and evaluating the risk level of minimally invasive surgery according to the abnormal stage signal and the historical data;

[0010] The early warning module is connected to the processing module and is used to obtain a comparison result based on the comparison between the risk level and a preset safety risk level, and output a safety warning message when the comparison result exceeds the safety risk level.

[0011] Furthermore, the analysis module includes:

[0012] A nerve length calculation unit, used for obtaining the nerve path length according to the sum of the distances between the brain regions, the length of each fiber bundle path and the sum of the number of synapses;

[0013] The waveform interval calculation unit is connected to the nerve length calculation unit, and is used to obtain the waveform time interval according to the quotient of the nerve path length and the nerve conduction velocity plus the quotient of the bone sheath thickness and the nerve conduction velocity.

[0014] Furthermore, the analysis module also includes:

[0015] A parameter input unit, used to use the number of synapses, the length of the nerve fiber, the nerve conduction velocity and the thickness of the bone sheath as input parameters of the model;

[0016] A neural model construction unit, connected to the parameter input unit, for constructing a three-dimensional neural model according to the input parameters;

[0017] a signal simulation unit connected to the neural model building unit, for simulating the propagation process of the neural impulse according to the three-dimensional neural model and the waveform time interval to calculate the standard phase signal;

[0018] The abnormality identification unit is connected to the signal simulation unit and is used to compare the standard phase signal with the electroencephalogram signal to identify the abnormal phase signal.

[0019] Furthermore, the neural model building unit includes:

[0020] A geometric modeling subunit, used to create a geometric structure of neurons and neural networks according to input parameters of the model to obtain a geometric model;

[0021] An electrophysiological simulation subunit, connected to the geometric modeling subunit, for simulating the physiological characteristics of the neuron to obtain an electrophysiological model;

[0022] The signal transmission modeling subunit is connected to the geometric modeling subunit and the electrophysiological simulation subunit respectively, and is used to establish a model of the transmission of the electroencephalogram signal in the neural network according to the geometric model and the electrophysiological model to obtain a signal transmission model.

[0023] Furthermore, the signal simulation unit comprises:

[0024] A numerical simulation subunit, which is used to simulate the propagation process of neural activity in the neural network using numerical methods to obtain the propagation results;

[0025] a signal synthesis subunit, connected to the numerical simulation subunit, for synthesizing the corresponding electroencephalogram signal according to the propagation result to obtain a synthesized signal;

[0026] The standard phase signal calculation subunit is connected to the signal synthesis subunit and is used to calculate the standard phase signal according to the time series of the synthesis signal.

[0027] Furthermore, the abnormality identification unit includes:

[0028] A signal alignment subunit, for aligning the time axis of the standard phase signal and the electroencephalogram signal;

[0029] a difference calculation subunit, connected to the signal alignment subunit, for comparing the waveforms of the aligned standard phase signal and the electroencephalogram signal, and calculating the difference between the standard phase signal and the electroencephalogram signal in the time window to obtain a calculation result;

[0030] a threshold determination subunit, connected to the difference calculation subunit, for setting a difference threshold according to the calculation result;

[0031] The abnormality detection subunit is connected to the threshold determination subunit and is used to compare the calculation result with the difference threshold to identify the abnormal phase signal.

[0032] Furthermore, the processing module includes:

[0033] a feature extraction unit connected to the data collection unit, for extracting the patient's age, patient's gender, patient's preoperative disease status, operation time and blood loss from the historical data to obtain a first feature result;

[0034] A model training unit, connected to the feature extraction unit, for training a risk assessment model according to the first feature result and the historical data to obtain a trained risk assessment model;

[0035] A model verification unit, connected to the model training unit, for verifying the trained model using a test set to obtain a verification result;

[0036] The risk assessment unit is connected to the model training unit and the model verification unit respectively, and is used to use the trained model and the verification result in combination with the abnormal stage signal and the historical data to assess the risk level of minimally invasive surgery to obtain an assessment result.

[0037] Furthermore, the risk assessment unit includes:

[0038] A data integration subunit, for integrating the training model, the verification model, the abnormal phase signal and the historical data into a data set;

[0039] a feature selection subunit, connected to the data integration subunit, for selecting features of the data set using a recursive feature elimination method to obtain a second feature result;

[0040] a model fusion subunit, connected to the feature selection subunit, for taking the second feature result as an input parameter and fusing the training model and the verification model using a weighted average method to obtain a target model;

[0041] The risk calculation subunit is connected to the model fusion subunit and is used to calculate the risk level of minimally invasive surgery according to the target model.

[0042] Furthermore, the adjustment module includes:

[0043] Risk threshold management unit, used to manage preset security risk levels;

[0044] A real-time monitoring comparison unit, connected to the risk threshold management unit, for real-time monitoring the risk level calculated by the risk assessment unit and performing a real-time comparison with the security risk level to obtain a comparison result;

[0045] The risk warning output unit is connected to the real-time monitoring comparison unit and is used to output safety warning information according to the comparison result.

[0046] Furthermore, the risk warning unit includes:

[0047] An audio warning subunit, for issuing an audio warning when the risk level exceeds a preset safety risk level;

[0048] The visual warning subunit is used to issue a visual warning when the risk level exceeds a preset safety risk level.

[0049] Compared with the prior art, the beneficial effect of the present invention is that the acquisition module can timely detect surgical conditions that may affect nerve function by real-time monitoring of EEG activity, so as to take measures to avoid nerve damage. The analysis module helps to predict the transmission time of nerve signals by calculating the length of nerve paths and the time interval of waveforms, thereby reducing surgical complications caused by delayed nerve conduction. The construction of a three-dimensional neural model provides doctors with detailed neural structure information, which helps to optimize surgical paths and plans and reduce damage to surrounding healthy tissues. Through model and computational analysis, abnormalities in EEG signals can be detected in time. The processing module can more accurately assess the risks of surgery and help doctors make better decisions by analyzing abnormal stage signals and historical data. When the risk level monitored by the early warning module exceeds the preset safety risk level, the system can automatically output a safety warning message to remind doctors to take measures to avoid nerve damage.

[0050] In particular, the nerve length calculation unit can obtain a more accurate nerve path length by calculating the distance between brain regions, the fiber bundle path length and the number of synapses, which helps to better understand the physical basis of nerve signal transmission and provide reliable quantitative data for neuroscience research. The waveform interval calculation unit takes into account the effect of bone sheath on nerve conduction velocity, making the calculation results closer to the actual situation. This helps to further study the conduction process of nerve impulses on nerve fibers and provide a theoretical basis for the research and treatment of neurological diseases.

[0051] In particular, the neural model construction unit can accurately construct a three-dimensional neural model through the parameter input of the parameter input unit to improve the accuracy of the simulation. The simulated signal unit can more accurately identify abnormal signals that do not conform to these patterns by simulating the propagation process of neural impulses, thereby improving the accuracy of diagnosis. The abnormality recognition unit can detect signal abnormalities in the early stage, which is helpful for early diagnosis and intervention of diseases.

[0052] In particular, the geometric modeling subunit can accurately create the geometric structure of neurons and neural networks based on the input parameters, ensuring that the model can truly reflect the physical layout of the nervous system. The electrophysiological simulation subunit can simulate the physiological characteristics of neurons, so that the model can more accurately reflect the electrical activity of neurons. The signal transmission modeling subunit can monitor and simulate the transmission process of EEG signals in neural networks in real time, helping researchers understand how signals propagate and interact in complex neural networks.

[0053] In particular, the numerical simulation subunit can accurately simulate the dynamic response of neurons by using numerical methods. The EEG signal synthesized by the synthetic signal subunit reflects the electrophysiological characteristics of neuronal activity and is close to the actual recorded EEG signal. The standard phase signal calculation unit can accurately identify the delay and synchronization changes of nerve impulse propagation by calculating the standard phase signal, which is crucial for detecting abnormal activities in the EEG.

[0054] In particular, the signal alignment subunit can ensure that the standard phase signal and the electroencephalogram signal are compared at the same time point by aligning the time axis of the signal alignment subunit, thereby accurately calculating the difference between the signals. The difference calculation subunit can calculate the difference between the standard phase signal and the electroencephalogram signal within a specific time window by comparing the waveforms of the aligned standard phase signal and the electroencephalogram signal. This helps to identify abnormal patterns in electroencephalogram signals. The threshold determination subunit uses the difference threshold set according to the calculation result as a judgment criterion to identify which differences are significant, thereby determining which signals belong to the abnormal phase. The abnormal detection subunit can identify abnormal phase signals by comparing the calculation result with the difference threshold, which helps to promptly detect brain function abnormalities that may occur during surgery.

[0055] In particular, the feature extraction unit can reduce the dimension of data by extracting key clinical features from historical data, improve the efficiency of data processing, and provide more information support for risk assessment. The simulation training unit can effectively predict surgical risks by establishing an accurate risk assessment model. The model verification unit ensures the performance of the risk assessment model on unknown data by verifying the training model with a test set, thereby improving the reliability and practicality of the model. The risk assessment unit provides accurate, real-time, and reliable risk assessment by combining the training model, verification model, abnormal stage signals, and historical data.

[0056] In particular, the data integration subunit can ensure the integrity and consistency of the data by integrating data from different sources into a unified dataset. The feature selection subunit can effectively reduce the feature dimension, avoid overfitting, and improve the interpretability of the model using the recursive feature elimination method. The model fusion subunit can improve the stability and robustness of risk assessment by fusing the predictions of multiple models through the weighted average method. The risk calculation subunit calculates the degree of risk based on the fused target model, which can provide a comprehensive risk assessment result to help medical professionals make more informed decisions.

[0057] In particular, the risk threshold management unit is responsible for managing the preset safety risk level. By setting reasonable thresholds, the sensitivity and accuracy of the early warning system can be ensured. The real-time monitoring comparison unit can continuously monitor the risk level calculated by the risk assessment unit, which enables the organization to dynamically adjust the risk threshold to adapt to the changing security environment. The risk warning output unit can significantly improve the safety of minimally invasive surgery by outputting safety warnings.

[0058] In particular, by providing both audible and visual warnings, the efficiency and reliability of warning information delivery can be improved. Different personnel may be more inclined to pay attention to one warning method, and multimodal warnings can ensure that all personnel receive warning information in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of the structure of a minimally invasive surgery nerve monitoring system provided by an embodiment of the present invention;

[0060] Figure 2 A schematic diagram of the structure of an analysis module in a minimally invasive surgery nerve monitoring system provided by an embodiment of the present invention;

[0061] Figure 3 A schematic diagram of the structure of a processing module in a minimally invasive surgery nerve monitoring system provided by an embodiment of the present invention;

[0062] Figure 4 A schematic diagram of the structure of an early warning module in a minimally invasive surgery nerve monitoring system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0064] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0065] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0066] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0067] See also Figure 1 As shown, the minimally invasive surgery nerve monitoring system provided by the embodiment of the present invention includes:

[0068] The acquisition module 10 is used to collect the electroencephalogram signals of minimally invasive surgery in real time, and is also used to collect the nerve fiber length, myelin thickness, nerve conduction velocity, fiber bundle path, synapse number and distance between brain regions;

[0069] an analysis module 20, connected to the acquisition module 10, for calculating the nerve path length according to the distance between the brain regions, the number of synapses and the fiber bundle path, calculating the waveform time interval according to the nerve path length, the bone sheath thickness and the nerve conduction velocity, constructing a three-dimensional neural model according to the number of synapses, the nerve fiber length, the nerve conduction velocity and the bone sheath thickness, and identifying the abnormal phase signal of the electroencephalogram signal according to the three-dimensional neural model and the waveform time interval;

[0070] A processing module 30, connected to the analysis module 20, for obtaining historical data of minimally invasive surgery, and evaluating the risk level of minimally invasive surgery according to the abnormal stage signal and the historical data;

[0071] The early warning module 40 is connected to the processing module 30, and is used to obtain a comparison result based on the comparison between the risk level and a preset safety risk level, and output a safety warning message when the comparison result exceeds the safety risk level.

[0072] Specifically, the acquisition module is equipped with multiple EEG electrodes for capturing the electrical activity of the scalp or internal electrodes in real time. The length of nerve fibers, myelin thickness, and distance between brain regions are determined by magnetic resonance imaging (MRI), and measured by electrophysiological tests (such as nerve conduction velocity tests). This usually involves placing electrodes on the surface of the skin and measuring the time between stimulation and response to calculate the nerve conduction velocity. The number of synapses is measured by fMRI (functional magnetic resonance imaging), and the fiber bundle path is determined by diffusion tensor imaging (DTI). The analysis module uses mathematical models and calculation methods to calculate the length of the nerve path, and calculates the time required for the signal to be transmitted between different brain regions based on the nerve conduction velocity and the length of the nerve path. Integrate nerve fiber length, myelin thickness, nerve conduction velocity, and fiber bundle path data to create a three-dimensional model that reflects the actual neural structure. Combine the real-time collected EEG signals with the three-dimensional neural model to analyze the delays and changes in signal transmission and identify possible abnormal signals. The processing module collects and organizes past minimally invasive surgery data, including EEG signals during surgery, surgical results, and possible complications. Combined with abnormal stage signals and historical data, statistical methods and machine learning algorithms are used to evaluate the risk level of the current operation. The adjustment module compares the risk assessment results with the preset safety risk level to determine whether there is a potential risk. When the risk exceeds the preset threshold, a safety warning message is automatically output to remind the doctor to take corresponding measures. An interface is provided to allow the doctor to adjust the surgical plan or take other preventive measures based on the information provided by the system.

[0073] Specifically, the acquisition module can timely detect surgical situations that may affect nerve function by real-time monitoring of EEG activity, so as to take measures to avoid nerve damage. The analysis module helps to predict the transmission time of nerve signals by calculating the length of nerve paths and the time interval of waveforms, thereby reducing surgical complications caused by delayed nerve conduction. The construction of a three-dimensional neural model provides doctors with detailed neural structure information, which helps to optimize surgical paths and plans and reduce damage to surrounding healthy tissues. Through model and computational analysis, abnormalities in EEG signals can be detected in a timely manner. The processing module can more accurately assess the risks of surgery and help doctors make better decisions by analyzing abnormal stage signals and historical data. When the risk level monitored by the early warning module exceeds the preset safety risk level, the system can automatically output a safety warning message to remind doctors to take measures to avoid nerve damage.

[0074] Specifically, if Figure 2 As shown, the analysis module 20 includes:

[0075] A nerve length calculation unit 21, used to obtain the nerve path length according to the sum of the distances between the brain regions, the length of each fiber bundle path and the sum of the number of synapses;

[0076] The waveform interval calculation unit 22 is connected to the nerve length calculation unit 21, and is used to obtain the waveform time interval according to the quotient of the nerve path length and the nerve conduction velocity plus the quotient of the bone sheath thickness and the nerve conduction velocity.

[0077] Specifically, the calculation formula of the nerve length is:

[0078]

[0079] Where L is the total neural path length, d i is the distance between the ith brain regions, p j is the path length of the jth fiber bundle, n is the total number of brain regions, m is the total number of fiber bundles, k is a coefficient related to the number of synapses N, which is used to adjust the total length to reflect the influence of synapses on signal propagation, and N is the number of synapses.

[0080] In neuroscience, synapses are the connection points between neurons that transmit signals, and their efficiency and function can be affected by many factors, such as the distance of the synaptic cleft, the responsiveness of the postsynaptic membrane, and the release and reuptake of neurotransmitters. The purpose of introducing the k factor is to take into account the effect of these additional factors on the speed of signal propagation when calculating the neural path length. Different synapses may have different transmission efficiencies, and some may be slower or more unstable than others. The k factor can be used to adjust the total length to more accurately estimate the delay of the signal propagating throughout the neural network. In practical applications, the value of k may need to be determined by experimental data. For example, if it is known that some synapses are slower than others, the transmission time of different types of synapses can be measured experimentally and this data can be used to set the value of k. In general, the k factor is an adjustment factor used to make the calculated neural path length better reflect the delay of actual signal propagation, thereby providing more accurate models and understanding in the study of neuroscience and neurophysiology.

[0081] The calculation formula of the waveform time interval is:

[0082]

[0083] Among them, Δt is the waveform time interval, t is the thickness of the myelin sheath, and v is the conduction velocity of the nerve impulse on the nerve fiber.

[0084] Specifically, the nerve length calculation unit can obtain a more accurate nerve path length by calculating the distance between brain regions, the fiber bundle path length and the number of synapses, which helps to better understand the physical basis of nerve signal transmission and provide reliable quantitative data for neuroscience research. The waveform interval calculation unit takes into account the effect of bone sheath on nerve conduction velocity, making the calculation results closer to the actual situation. This helps to further study the conduction process of nerve impulses on nerve fibers and provide a theoretical basis for the research and treatment of neurological diseases.

[0085] Specifically, the analysis module also includes:

[0086] A parameter input unit, used to use the number of synapses, the length of the nerve fiber, the nerve conduction velocity and the thickness of the bone sheath as input parameters of the model;

[0087] A neural model construction unit, connected to the parameter input unit, for constructing a three-dimensional neural model according to the input parameters;

[0088] a signal simulation unit connected to the neural model building unit, for simulating the propagation process of the neural impulse according to the three-dimensional neural model and the waveform time interval to calculate the standard phase signal;

[0089] The abnormality identification unit is connected to the signal simulation unit and is used to compare the standard phase signal with the electroencephalogram signal to identify the abnormal phase signal.

[0090] Specifically, the parameter input unit receives parameters such as the number of synapses, the length of nerve fibers, the nerve conduction velocity, and the thickness of myelin through the parameter input unit. These parameters are regarded as input data for constructing a three-dimensional neural model. The neural model construction unit receives input parameters from the parameter input unit. A three-dimensional neural model is constructed using these input parameters, which can simulate the structure and function of nerve fibers. According to the constructed three-dimensional neural model and the calculated waveform time interval, the propagation process of nerve impulses in the neural network is simulated. The simulation includes potential changes, the release of neurotransmitters, the generation of postsynaptic potentials, etc. Numerical simulation methods, such as finite element analysis (FEA) or finite difference method (FDM), are used to calculate the dynamic process of nerve impulse propagation. The signal generated by the simulated nerve impulse propagation process is compared with the actual EEG signal. A pattern recognition algorithm, such as a support vector machine (SVM), is used to identify abnormal phase signals. Whether the signal is abnormal is determined by setting a threshold or using classification performance indicators (such as accuracy, recall, and F1 score) in machine learning.

[0091] Specifically, the neural model construction unit can accurately construct a three-dimensional neural model through the parameter input of the parameter input unit to improve the accuracy of the simulation. The simulation signal unit can more accurately identify abnormal signals that do not conform to these patterns by simulating the propagation process of the neural impulse to obtain the standard phase signal, thereby improving the accuracy of the diagnosis. The abnormality recognition unit can detect signal abnormalities in the early stage, which is helpful for the early diagnosis and intervention of the disease.

[0092] Specifically, the neural model building unit includes:

[0093] A geometric modeling subunit, used to create a geometric structure of neurons and neural networks according to input parameters of the model to obtain a geometric model;

[0094] An electrophysiological simulation subunit, connected to the geometric modeling subunit, for simulating the physiological characteristics of the neuron to obtain an electrophysiological model;

[0095] The signal transmission modeling subunit is connected to the geometric modeling subunit and the electrophysiological simulation subunit respectively, and is used to establish a model of the transmission of the electroencephalogram signal in the neural network according to the geometric model and the electrophysiological model to obtain a signal transmission model.

[0096] Specifically, input parameters (such as the number of synapses, nerve fiber length, etc.) are used to determine the size and shape of neurons. The geometric structure of the neural network is constructed based on the input parameters, including the layout and connection methods of neurons. A geometric model is created that can visualize the structure of the neural network. The electrophysiological simulation subunit uses electrophysiological theories and formulas to simulate the physiological characteristics of neurons, such as membrane potential, generation and propagation of action potentials, etc. The simulation results are compared with experimental data, and the model parameters are adjusted to improve the accuracy of the model. The results of the electrophysiological model are output, such as the change of membrane potential over time, etc. The signal transmission modeling subunit establishes a mathematical model of the transmission of EEG signals in the neural network based on the geometric model and electrophysiological model. The calculation algorithms of the signal transmission model, such as difference equations, differential equations, etc., are implemented. The stability, convergence and accuracy of the signal transmission model are analyzed.

[0097] In this embodiment, it is assumed that the parameter input is as follows:

[0098] Number of synapses: 1000 (number of connections between neurons);

[0099] Nerve fiber length: 1 mm (the length of each neuron axon);

[0100] Nerve conduction velocity: 120 m / s (speed of signal propagation in axons);

[0101] Bone sheath thickness: 0.1mm (the thickness of the bone sheath outside the nerve fiber).

[0102] According to the number of synapses and the length of nerve fibers, a network with 1000 nodes can be constructed, each node represents a neuron. The axon length of the neuron is 1mm, which will be a dimension in the model. Using the membrane potential model of the neuron, the membrane potential changes of the neuron in the resting state and the excitation state can be simulated. Assuming that the threshold potential of the neuron is -55mV, when the membrane potential reaches this value, the neuron will generate an action potential. The width of the action potential is 2ms and the peak potential is +30mV. Based on the geometric model and the electrophysiological model, a differential equation can be established to simulate the propagation of signals in the neural network.

[0103] For example, for a simple integrate-and-fire model, the equations for the signal transfer model might be as follows:

[0104]

[0105] V is the membrane potential, V rest is the resting potential, I syn is the input current from the synapse, and τ is the membrane time constant. Using this equation, we can simulate the propagation of signals in a neural network and observe how the membrane potential changes over time.

[0106] Specifically, the geometric modeling subunit can accurately create the geometric structure of neurons and neural networks based on the input parameters, ensuring that the model can truly reflect the physical layout of the nervous system. The electrophysiological simulation subunit can simulate the physiological characteristics of neurons, so that the model can more accurately reflect the electrical activity of neurons. The signal transmission modeling subunit can monitor and simulate the transmission process of EEG signals in neural networks in real time, helping researchers understand how signals propagate and interact in complex neural networks.

[0107] Specifically, the signal simulation unit includes:

[0108] A numerical simulation subunit, which is used to simulate the propagation process of neural activity in the neural network using numerical methods to obtain the propagation results;

[0109] a signal synthesis subunit, connected to the numerical simulation subunit, for synthesizing the corresponding electroencephalogram signal according to the propagation result to obtain a synthesized signal;

[0110] The standard phase signal calculation subunit is connected to the signal synthesis subunit and is used to calculate the standard phase signal according to the time series of the synthesis signal.

[0111] Specifically, a suitable numerical method (such as finite difference method, finite element analysis, etc.) is selected to simulate the propagation process of neural activity in the neural network. The initial conditions and boundary conditions of the simulation are set according to the parameters of the neural model (such as the number of synapses, nerve fiber length, nerve conduction velocity, and bone sheath thickness, etc.) and the waveform time interval. The propagation of nerve impulses in the neural network is calculated using the numerical simulation method, and the potential changes and propagation time are recorded. The signal synthesis unit synthesizes the corresponding electroencephalogram signal according to the propagation results output by the numerical simulation subunit. The synthesized signal should reflect the propagation of nerve impulses in different areas and at different time points. An integral function or a differential function is used to simulate the potential changes of neurons and synthesize continuous electroencephalogram signals. The standard phase signal calculation subunit calculates the standard phase signal according to the time series of the synthesized signal. The standard phase signal is a reflection of the propagation delay of nerve impulses on different synapses and nerve fibers. The calculation subunit uses a time analysis algorithm to identify the specific phase of the signal and calculates the value of the standard phase signal.

[0112] In this example, we assume a simple neural network consisting of two neurons, where the first neuron is connected to the second neuron through a synapse. We will use a one-dimensional neuron model, where the membrane potential of the neuron changes over time, described by the following equation:

[0113]

[0114] Where V(t) is the membrane potential of the neuron at time t, V m is the resting potential of the neuron, τ is the time constant of the neuron, and I input (t) is the input current, which in this example simulates the synaptic input.

[0115] First set the model parameters: V m =-50mV, τ = 2ms, synaptic input I input (t)(t) is a unit step function, indicating that the synapse releases neurotransmitter at t = 0.

[0116] Use Euler's method for numerical integration to simulate the change of the membrane potential of the neuron over time. For example, you can choose a time step Δt = 0.1ms and simulate a period of time t from 0 to 10ms.

[0117] After the simulation is completed, the neuron membrane potential data is synthesized into a signal. In this example, the simulated data can be directly used to synthesize the signal.

[0118] Based on the time series of the synthetic signal, a standard phase signal is calculated. In this example, the standard phase signal may refer to the time delay of the propagation of neuronal excitation.

[0119] Specifically, the numerical simulation subunit can accurately simulate the dynamic response of neurons by using numerical methods. The EEG signal synthesized by the synthetic signal subunit reflects the electrophysiological characteristics of neuronal activity and is close to the actual recorded EEG signal. The standard phase signal calculation unit can accurately identify the delay and synchronization changes of nerve impulse propagation by calculating the standard phase signal, which is crucial for detecting abnormal activities in the EEG.

[0120] Specifically, the abnormality identification unit includes:

[0121] A signal alignment subunit, for aligning the time axis of the standard phase signal and the electroencephalogram signal;

[0122] a difference calculation subunit, connected to the signal alignment subunit, for comparing the waveforms of the aligned standard phase signal and the electroencephalogram signal, and calculating the difference between the standard phase signal and the electroencephalogram signal in the time window to obtain a calculation result;

[0123] a threshold determination subunit, connected to the difference calculation subunit, for setting a difference threshold according to the calculation result;

[0124] The abnormality detection subunit is connected to the threshold determination subunit and is used to compare the calculation result with the difference threshold to identify the abnormal phase signal.

[0125] Specifically, the signal alignment subunit collects time series data of the standard phase signal and the actual phase signal. Signal processing techniques (such as cross-correlation analysis) are used to find the best time alignment point of the two signal sequences. According to the alignment point found, the time axis of the actual phase signal is adjusted to align it with the standard phase signal. The difference calculation subunit compares the waveforms of the aligned standard phase signal and the actual phase signal. The difference between the two signals within the time window is calculated, including amplitude difference, latency difference, etc. These differences are quantified, for example, by calculating the absolute value or relative value of the difference. The threshold determination subunit determines the basic threshold based on the statistical properties of the signal (such as mean, standard deviation). Statistical tests (such as t-test, chi-square test) are used to determine the significance threshold of the difference. An empirical threshold is set based on expert knowledge and historical data. The anomaly detection subunit compares the output of the difference calculation subunit with the threshold set by the threshold determination subunit. If the calculated difference exceeds the threshold, the signal is marked as abnormal.

[0126] Specifically, the signal alignment subunit can ensure that the standard phase signal and the EEG signal are compared at the same time point by aligning the time axis, thereby accurately calculating the difference between the signals. The difference calculation subunit can calculate the difference between the standard phase signal and the EEG signal within a specific time window by comparing the waveforms of the aligned standard phase signal and the EEG signal. This helps to identify abnormal patterns in EEG signals. The threshold determination subunit uses the difference threshold set according to the calculation result as a judgment criterion to identify which differences are significant, thereby determining which signals belong to the abnormal phase. The abnormal detection subunit can identify abnormal phase signals by comparing the calculation result with the difference threshold, which helps to promptly detect brain function abnormalities that may occur during surgery.

[0127] Specifically, if Figure 3 As shown, the processing module 30 includes:

[0128] A feature extraction unit 31, connected to the data collection unit, is used to extract the patient's age, patient's gender, patient's preoperative disease status, operation time and bleeding amount from the historical data to obtain a first feature result;

[0129] A model training unit 32, connected to the feature extraction unit 31, for training a risk assessment model according to the first feature result and the historical data to obtain a training model;

[0130] A model verification unit 33, connected to the model training unit 32, for verifying the training model using a test set to obtain a verification model;

[0131] The risk assessment unit 34 is connected to the model training unit 32 and the model verification unit 33 respectively, and is used to use the training model and the verification model in combination with the abnormal stage signal and the historical data to assess the risk level of minimally invasive surgery to obtain an assessment result.

[0132] Specifically, the patient's age information is extracted from the historical data, and the age is converted into a continuous variable or a categorical variable. The patient's gender information is extracted from the historical data and converted into a binary categorical variable (such as 0 for female and 1 for male). The patient's preoperative disease status is extracted from the historical data, and coding may be used (such as 0 for no disease and 1 for disease). The duration of the operation is extracted from the historical data, and the time may be converted into minutes or hours. The amount of bleeding during the operation is extracted from the historical data, and the amount of bleeding may be converted into milliliters or units. The model training unit selects a suitable machine learning model according to the problem characteristics and data type, such as logistic regression, decision tree, random forest or deep learning model. The selected model is trained using the first feature result provided by the feature extraction unit and the historical data. This process may include adjusting model parameters, such as learning rate, batch size, number of layers, etc. Cross-validation techniques are applied to evaluate the generalization ability of the model, such as K-fold cross-validation. One or more test sets are separated from the historical data for evaluating the performance of the model. The trained model is validated using the test set, and evaluation indicators such as the accuracy, recall rate, and F1 score of the model are calculated. The model parameters are adjusted or different model architectures are selected according to the validation model to improve the model performance. The risk assessment unit uses the trained risk assessment model and validation results to predict the risk level of minimally invasive surgery. The abnormal stage signal is combined with historical data and model prediction results to identify and assess risk events. Based on the model output and abnormal stage signal, the surgical risk is quantitatively assessed, such as using a risk score or risk level.

[0133] Specifically, the feature extraction unit can reduce the dimension of data by extracting key clinical features from historical data, improve the efficiency of data processing, and provide more information support for risk assessment. The simulation training unit can effectively predict surgical risks by establishing an accurate risk assessment model. The model verification unit verifies the training model using a test set to ensure the performance of the risk assessment model on unknown data, thereby improving the reliability and practicality of the model. The risk assessment unit provides accurate, real-time, and reliable risk assessment by combining training models, verification models, abnormal stage signals, and historical data.

[0134] Specifically, the risk assessment unit includes:

[0135] A data integration subunit, for integrating the training model, the verification model, the abnormal phase signal and the historical data into a data set;

[0136] a feature selection subunit, connected to the data integration subunit, for selecting features of the data set using a recursive feature elimination method to obtain a second feature result;

[0137] a model fusion subunit, connected to the feature selection subunit, for taking the second feature result as an input parameter and fusing the training model and the verification model using a weighted average method to obtain a target model;

[0138] The risk calculation subunit is connected to the model fusion subunit and is used to calculate the risk level of minimally invasive surgery according to the target model.

[0139] Specifically, the data integration subunit collects and organizes training models, validation models, abnormal phase signals and historical data. Ensure that all data use the same format and standardization method for subsequent processing. If the data comes from different sources, data cleaning and preprocessing are required to eliminate differences. The feature selection subunit uses the recursive feature elimination (RFE) method to select features of the data set. Train an initial model on the training data set and calculate the feature importance. Sort the features in descending order of importance and gradually remove features with lower importance. Repeat this process until the predetermined number of features is reached or the performance of the model is no longer improved. The predetermined number is set by a technician in this field according to actual conditions. Obtain the second feature result. The model fusion subunit uses the second feature result output by the feature selection subunit as an input parameter. Use the weighted average method to fuse the training model and the validation model. Assign a weight to each model, which is usually determined based on the cross-validation performance of the model. Calculate the weighted average of the predictions of each model to obtain the final prediction result. The risk calculation subunit uses the fused model to calculate the risk level of minimally invasive surgery. The risk level can be determined based on the predicted probability or score of the model.

[0140] Specifically, the data integration subunit can ensure the integrity and consistency of the data by integrating data from different sources into a unified dataset. The feature selection subunit can effectively reduce the feature dimension, avoid overfitting, and improve the interpretability of the model using the recursive feature elimination method. The model fusion subunit can improve the stability and robustness of risk assessment by fusing the predictions of multiple models through the weighted average method. The risk calculation subunit calculates the degree of risk based on the fused target model, which can provide a comprehensive risk assessment result to help medical professionals make more informed decisions.

[0141] Specifically, if Figure 4 As shown, the early warning module 40 includes:

[0142] A risk threshold management unit 41, used to manage a preset security risk level;

[0143] A real-time monitoring comparison unit 42, connected to the risk threshold management unit 41, is used to compare the risk level calculated by the real-time monitoring risk assessment unit with the security risk level in real time to obtain a comparison result;

[0144] The risk warning output unit 43 is connected to the real-time monitoring comparison unit 42 and is used to output safety warning information according to the comparison result.

[0145] Specifically, the risk threshold management unit sets the risk threshold according to the type of surgery, patient condition and clinical experience. The set risk threshold is stored in the system for real-time monitoring of comparison unit access. During the operation, the risk threshold is adjusted as needed. Multiple levels of risk thresholds are set to adapt to different surgical stages and risk situations. Real-time monitoring comparison unit: Receive the risk level data calculated by the risk assessment unit in real time. Compare and analyze the real-time risk level with the preset safety risk threshold. Generate comparison results, including whether the risk level exceeds the safety threshold. Dynamically monitor changes in risk level to ensure timely response. Risk warning output unit triggers a warning condition when the comparison result shows that the risk level exceeds the safety threshold. Generate specific warning information based on the risk level and the degree of exceeding the threshold.

[0146] Specifically, the risk threshold management unit is responsible for managing the preset safety risk level. By setting reasonable thresholds, the sensitivity and accuracy of the early warning system can be ensured. The real-time monitoring comparison unit can continuously monitor the risk level calculated by the risk assessment unit, which enables the organization to dynamically adjust the risk threshold to adapt to the changing security environment. The risk warning output unit can significantly improve the safety of minimally invasive surgery by outputting safety warnings.

[0147] Specifically, the risk warning unit includes:

[0148] An audio warning subunit, for issuing an audio warning when the risk level exceeds a preset safety risk level;

[0149] The visual warning subunit is used to issue a visual warning when the risk level exceeds a preset safety risk level.

[0150] Specifically, when the risk level calculated by the risk assessment unit exceeds the preset safety risk level, the sound warning subunit will be activated. The sound warning subunit will emit a sound signal of a certain frequency and intensity to ensure that it can be heard by the operating room staff in a noisy surgical environment. It can be configured to stop or adjust other non-emergency sounds while issuing a sound warning to ensure the clarity and recognition of the warning sound. A delay function can also be included to automatically stop the warning sound after the risk level is reduced to reduce unnecessary interference. When the risk level calculated by the risk assessment unit exceeds the preset safety risk level, the visual warning subunit will be activated. The visual warning subunit will display an obvious warning signal on the display screen in the operating room, such as a red flashing warning light or a text prompt. The visual warning subunit can also be installed with LED lights or other light-emitting devices in key parts of the operating room, such as near the operating table or within the doctor's line of sight, to provide intuitive visual warnings.

[0151] Specifically, by providing both audible and visual warnings, the efficiency and reliability of warning information delivery can be improved. Different personnel may be more inclined to pay attention to one warning method, and multimodal warnings can ensure that all personnel can receive warning information in a timely manner.

[0152] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0153] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A minimally invasive surgery nerve monitoring system, characterized in that: include: The acquisition module is used to collect EEG signals of minimally invasive surgery in real time, and is also used to collect nerve fiber length, myelin thickness, nerve conduction velocity, fiber bundle path, synapse number and distance between brain regions; an analysis module connected to the acquisition module, for calculating the nerve path length according to the distance between the brain regions, the number of synapses and the fiber bundle path, calculating the waveform time interval according to the nerve path length, the myelin sheath thickness and the nerve conduction velocity, constructing a three-dimensional neural model according to the number of synapses, the nerve fiber length, the nerve conduction velocity and the myelin sheath thickness, and identifying the abnormal phase signal of the electroencephalogram signal according to the three-dimensional neural model and the waveform time interval; a processing module connected to the analysis module, for acquiring historical data of minimally invasive surgery, and evaluating the risk level of minimally invasive surgery according to the abnormal stage signal and the historical data; an early warning module, connected to the processing module, for obtaining a comparison result based on the comparison between the risk level and a preset safety risk level, and outputting a safety warning message when the comparison result exceeds the safety risk level; The analysis module comprises: A nerve length calculation unit, used for obtaining the nerve path length according to the sum of the distances between the brain regions, the length of each fiber bundle path and the sum of the number of synapses; a waveform interval calculation unit connected to the nerve length calculation unit, for obtaining the waveform time interval according to the quotient of the nerve path length and the nerve conduction velocity plus the quotient of the myelin sheath thickness and the nerve conduction velocity; The analysis module also includes: A parameter input unit, used to use the number of synapses, the length of the nerve fiber, the nerve conduction velocity and the myelin sheath thickness as input parameters of the model; A neural model construction unit, connected to the parameter input unit, for constructing a three-dimensional neural model according to the input parameters; a signal simulation unit connected to the neural model construction unit, for simulating the propagation process of the neural impulse according to the three-dimensional neural model and the waveform time interval to calculate the standard phase signal; an abnormality identification unit connected to the signal simulation unit, for comparing the standard phase signal with the electroencephalogram signal to identify the abnormal phase signal; The neural model building unit comprises: A geometric modeling subunit, used to create a geometric structure of neurons and neural networks according to input parameters of the model to obtain a geometric model; An electrophysiological simulation subunit, connected to the geometric modeling subunit, for simulating the physiological characteristics of the neuron to obtain an electrophysiological model; a signal transmission modeling subunit, connected to the geometric modeling subunit and the electrophysiological simulation subunit respectively, for establishing a model of the transmission of the electroencephalogram signal in the neural network according to the geometric model and the electrophysiological model to obtain a signal transmission model; The signal simulation unit comprises: A numerical simulation subunit, which is used to simulate the propagation process of neural activity in the neural network using numerical methods to obtain the propagation results; a signal synthesis subunit, connected to the numerical simulation subunit, for synthesizing the corresponding electroencephalogram signal according to the propagation result to obtain a synthesized signal; The standard phase signal calculation subunit is connected to the signal synthesis subunit and is used to calculate the standard phase signal according to the time series of the synthesis signal.

2. The minimally invasive surgery nerve monitoring system according to claim 1, characterized in that: The abnormality identification unit comprises: A signal alignment subunit, for aligning the time axis of the standard phase signal and the electroencephalogram signal; a difference calculation subunit, connected to the signal alignment subunit, for comparing the waveforms of the aligned standard phase signal and the electroencephalogram signal, and calculating the difference between the standard phase signal and the electroencephalogram signal in the time window to obtain a calculation result; a threshold determination subunit, connected to the difference calculation subunit, for setting a difference threshold according to the calculation result; The abnormality detection subunit is connected to the threshold determination subunit and is used to compare the calculation result with the difference threshold to identify the abnormal phase signal.

3. The minimally invasive surgery nerve monitoring system according to claim 2, characterized in that: The processing module comprises: a feature extraction unit connected to the data collection unit, for extracting the patient's age, patient's gender, patient's preoperative disease status, operation time and blood loss from the historical data to obtain a first feature result; A model training unit, connected to the feature extraction unit, for training a risk assessment model according to the first feature result and the historical data to obtain a trained risk assessment model; A model verification unit, connected to the model training unit, for verifying the trained model using a test set to obtain a verification result; The risk assessment unit is connected to the model training unit and the model verification unit respectively, and is used to use the trained model and the verification result in combination with the abnormal stage signal and the historical data to assess the risk level of minimally invasive surgery to obtain an assessment result.

4. The minimally invasive surgery nerve monitoring system according to claim 3, characterized in that: The risk assessment unit comprises: A data integration subunit, for integrating the training model, the verification model, the abnormal phase signal and the historical data into a data set; a feature selection subunit, connected to the data integration subunit, for selecting features of the data set using a recursive feature elimination method to obtain a second feature result; a model fusion subunit, connected to the feature selection subunit, for taking the second feature result as an input parameter and fusing the training model and the verification model using a weighted average method to obtain a target model; The risk calculation subunit is connected to the model fusion subunit and is used to calculate the risk level of minimally invasive surgery according to the target model.

5. The minimally invasive surgery nerve monitoring system according to claim 4, characterized in that: The early warning module comprises: Risk threshold management unit, used to manage preset security risk levels; A real-time monitoring comparison unit, connected to the risk threshold management unit, for real-time monitoring the risk level calculated by the risk assessment unit and performing a real-time comparison with the security risk level to obtain a comparison result; The risk warning output unit is connected to the real-time monitoring comparison unit and is used to output safety warning information according to the comparison result.

6. The minimally invasive surgery nerve monitoring system according to claim 5, characterized in that: The risk warning output unit comprises: An audio warning subunit, for issuing an audio warning when the risk level exceeds a preset safety risk level; The visual warning subunit is used to issue a visual warning when the risk level exceeds a preset safety risk level.

Images