CN116602687A - Bioelectric signal conduction device for spinal cord injury repair verification - Google Patents
Bioelectric signal conduction device for spinal cord injury repair verification Download PDFInfo
- Publication number
- CN116602687A CN116602687A CN202310839858.6A CN202310839858A CN116602687A CN 116602687 A CN116602687 A CN 116602687A CN 202310839858 A CN202310839858 A CN 202310839858A CN 116602687 A CN116602687 A CN 116602687A
- Authority
- CN
- China
- Prior art keywords
- spinal cord
- signal
- verification
- bioelectric
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000012795 verification Methods 0.000 title claims abstract description 63
- 208000020431 spinal cord injury Diseases 0.000 title claims abstract description 48
- 230000008439 repair process Effects 0.000 title claims abstract description 40
- 210000000278 spinal cord Anatomy 0.000 claims abstract description 88
- 230000000763 evoking effect Effects 0.000 claims abstract description 47
- 238000004458 analytical method Methods 0.000 claims abstract description 19
- 230000008054 signal transmission Effects 0.000 claims abstract description 13
- 230000008859 change Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 41
- 238000007405 data analysis Methods 0.000 claims description 30
- 230000006698 induction Effects 0.000 claims description 26
- 230000007246 mechanism Effects 0.000 claims description 26
- 230000007831 electrophysiology Effects 0.000 claims description 22
- 238000002001 electrophysiology Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 7
- 230000000638 stimulation Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 210000003205 muscle Anatomy 0.000 claims description 5
- 230000003321 amplification Effects 0.000 claims description 3
- 210000003710 cerebral cortex Anatomy 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 230000007830 nerve conduction Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 14
- 238000013135 deep learning Methods 0.000 abstract description 6
- 238000011282 treatment Methods 0.000 abstract description 6
- 238000011160 research Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 abstract description 2
- 230000006378 damage Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000004064 dysfunction Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 239000013585 weight reducing agent Substances 0.000 description 2
- 206010010214 Compression fracture Diseases 0.000 description 1
- 208000014094 Dystonic disease Diseases 0.000 description 1
- 206010018852 Haematoma Diseases 0.000 description 1
- 208000032843 Hemorrhage Diseases 0.000 description 1
- 206010027468 Metastases to spine Diseases 0.000 description 1
- 206010033799 Paralysis Diseases 0.000 description 1
- 206010040026 Sensory disturbance Diseases 0.000 description 1
- 206010041549 Spinal cord compression Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000036982 action potential Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000012620 biological material Substances 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 208000010118 dystonia Diseases 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007659 motor function Effects 0.000 description 1
- 210000000944 nerve tissue Anatomy 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000008 neuroelectric effect Effects 0.000 description 1
- 230000007121 neuropathological change Effects 0.000 description 1
- 230000008506 pathogenesis Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000011514 reflex Effects 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000037152 sensory function Effects 0.000 description 1
- 210000005070 sphincter Anatomy 0.000 description 1
- 210000000130 stem cell Anatomy 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/388—Nerve conduction study, e.g. detecting action potential of peripheral nerves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
- A61B5/395—Details of stimulation, e.g. nerve stimulation to elicit EMG response
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/486—Bio-feedback
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7246—Details of waveform analysis using correlation, e.g. template matching or determination of similarity
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Theoretical Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Neurosurgery (AREA)
- Neurology (AREA)
- Fuzzy Systems (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a bioelectric signal conduction device for spinal cord injury repair verification, which is characterized in that a bioelectric signal analysis system is constructed, and the spinal cord electrophysiological module, the spinal cord evoked potential module and the signal transmission and reception of the spinal cord exercise evoked potential module are combined to analyze the change of the conduction function and verify the spinal cord injury repair in a full range; simultaneously, a reference and optimized repairing scheme is provided for the repairing of the spinal cord injury by combining with deep learning analysis treatment; the bioelectric signal conduction device for spinal cord injury repair verification is combined with a deep learning scheme to analyze and process bioelectric signal conduction signals, and a normal bioelectric signal conduction verification model is established by combining normal parameters and is compared with the bioelectric signal conduction verification model generated by verification; the method can effectively analyze and record the signal information, and simultaneously input the signal information into a database for storage, so that a basis is provided for subsequent scientific research.
Description
Technical Field
The invention relates to the technical field of spinal cord injury repair, in particular to a bioelectric signal conduction device for spinal cord injury repair verification.
Background
Spinal cord injury (spinal cord) refers to the corresponding changes in various motor, sensory and sphincter dysfunctions, dystonia, pathological reflex, etc. that occur in the corresponding segment of the injury due to external direct or indirect factors. Spinal cord injuries can be classified as primary spinal cord injuries and secondary spinal cord injuries. The former refers to the damage caused by external force directly or indirectly acting on the spinal cord. The latter refers to further damage to spinal cord caused by spinal cord compression by external forces, hematoma from hemorrhage of small blood vessels in the spinal canal, compression fracture, broken disc tissue, and the like.
The repair of spinal cord injuries is still under investigation and no method has emerged to completely cure spinal cord injuries. Currently, researchers are trying to find new methods and techniques to treat spinal cord injury; some experimental treatments include the use of stem cells or biological materials to repair damaged nerve tissue; use of neuroplasticity-related drugs to enhance the attachment of neurons around the damaged area; and stimulating neuronal reconnection and growth in the damaged area using neural electrical stimulation or the like.
For the study of spinal cord injury repair, bioelectric signals are those generated inside a living body, including action potentials of neurons, electrocardiogram of heart, electrical activity of muscles, and the like. These bioelectric signals have an important role in maintaining vital activities of the human body. In spinal cord injury, bioelectric signals play an important role in both neuropathological changes and rehabilitation.
After spinal cord injury, local bioelectric signal transmission is abnormal or interrupted due to dysfunction and connection breakdown of damaged neurons. For example, a patient with spinal cord injury may develop symptoms such as paralysis of limbs, sensory disturbance, etc., which are associated with abnormal transmission of bioelectric signals between muscles and nerves.
At the same time, bioelectric signals may also be used to facilitate spinal cord injury treatment and recovery. For example, the regeneration and reconstruction of neurons in the damaged area can be promoted to some extent by using external nerve electrical stimulation techniques. In addition, there have been studies showing that the motor and sensory functions of spinal cord injured patients can be improved by the combination of robot-assisted rehabilitation training and neuroelectric stimulation.
Therefore, the bioelectric signals play an important role in pathogenesis and treatment research of spinal cord injury, and in the process of spinal cord injury repair research, the bioelectric signals are used for verifying the repair condition, so that the verification of a repair scheme can be realized, and the bioelectric signals are a feasible scheme; however, in the prior art, a reasonable and suitable scheme is lacking, for example, a standardized and reliable evaluation index cannot be obtained through single bioelectric signal verification, and more reliable repair evaluation can be obtained through collection of multi-azimuth signals, analysis of samples and signal parameters, combination of small sample training, and design depending on a neural network model and other schemes, which is also a technical problem to be solved in the art.
Disclosure of Invention
The invention aims to provide a bioelectric signal conduction device for spinal cord injury repair verification, which is used for verifying spinal cord injury repair in a full range by combining signal transmission and reception of a spinal cord electrophysiological module, a spinal cord evoked potential module and a spinal cord exercise evoked potential module through constructing a bioelectric signal analysis system, and providing a reference and optimized repair scheme for spinal cord injury repair by combining deep learning analysis and treatment.
In order to achieve the technical purpose and the technical effect, the invention is realized by the following technical scheme:
a bioelectric signal conduction device for spinal cord injury repair verification, comprising: the system comprises a signal acquisition unit, a signal induction unit, a signal preprocessing unit and a data analysis processing module, wherein the signal acquisition unit comprises a signal acquisition module for spinal cord electrophysiology, spinal cord induction potential and spinal cord exercise induction potential, the signal induction unit comprises a signal induction module for spinal cord induction potential and spinal cord exercise induction potential, and a plurality of signal acquisition modules and signal induction modules are in one-to-one correspondence to transmit data to the signal preprocessing unit to improve the signal quality and input to the data analysis processing module for analysis processing;
the data analysis processing module is used for obtaining an initial model by carrying out feature extraction and classification on signals and inputting convolutional neural network training, and the initial model modeling sequentially establishes a model according to the acquisition of spinal electrophysiology, spinal evoked potential and spinal exercise evoked potential; meanwhile, introducing an attention mechanism to analyze the difference information characteristics and the common information characteristics in each model, and generating a bioelectric signal conduction verification model based on a Gaussian distribution characteristic generation module;
meanwhile, the data analysis processing module establishes a normal bioelectric signal conduction verification model according to normal parameters, and compares the normal bioelectric signal conduction verification model with a bioelectric signal conduction verification model generated by verification.
Further, the signal acquisition module acquires corresponding data according to time-frequency domain respectively, combines time domain analysis with frequency domain analysis, and acquires a change rule of signals in time and frequency;
the system comprises a spinal cord electrophysiology signal acquisition module, a data analysis processing module and a data acquisition module, wherein the spinal cord electrophysiology signal acquisition module adopts an intermittent acquisition mode, and bioelectric signals are respectively acquired at two ends of a spinal cord to be verified and input into the data analysis processing module after acquisition;
the signal acquisition module acquires the corresponding intermittent sending evoked signals of the signal evoked module received in the region to be verified, and uploads the signals to the data analysis processing module.
Further, the spinal cord electrophysiology is characterized in that bioelectricity signals are recorded through an electrode, wherein the bioelectricity signals comprise activities of spinal cord neurons and spinal cord pulse transmission speed, and a spinal cord electrophysiology model is constructed through time-frequency domain changes;
the method comprises the steps that a spinal cord electrophysiological model is used for extracting and classifying characteristics of acquired signals, if signals acquired at two ends of a spinal cord to be verified are consistent, the attention mechanism weight of the signals is reduced or cancelled, namely, difference information characteristics and common information characteristics are analyzed, and the difference information is used for generating a bioelectric signal conduction verification model through a characteristic generation module based on Gaussian distribution;
wherein: difference information features:
assume that there are two sets of data sets A and B, each containing N samples; the difference information characteristic calculating method comprises the following steps:
Δ(A,B)=|μ(A)-μ(B)|/(σ(A)+σ(B))
wherein Δ (A, B) represents the difference information eigenvalue between A and B, μ (A) and μ (B) represent the mean of the data sets A and B, respectively, and σ (A) and σ (B) represent the standard deviation of the data sets A and B, respectively.
Common information features:
in both sets of data sets a and B, the common information feature calculation method is as follows:
Φ(A,B)=|A∩B|/|A|
where Φ (a, B) represents a common information characteristic value between a and B, |a n b| represents the number of intersection elements of data sets a and B, |a| represents the number of elements of data set a;
wherein the attention mechanism is processing for common information feature weight reduction or cancellation.
Further, the spinal cord evoked potential, by recording the change in the potential of spinal cord nerve conduction after administration of the stimulus; corresponding intermittent sending of the evoked signals through the signal evoked modules, and corresponding signals are recorded on the signal acquisition modules of the spinal cord evoked potentials;
wherein: forming a training sample through intermittent induced signals and detection, analyzing difference information characteristics and common information characteristics by adopting an attention mechanism, and comparing signal changes with a normal bioelectric signal conduction verification model;
firstly, constructing a basic convolutional neural network model by an attention mechanism, and introducing the attention mechanism for analyzing difference characteristics;
calculating the attention weight of each input part through an attention mechanism to determine the importance of the attention weight in the model;
the attention weight can be calculated according to the degree of difference between different parts of the input, and a self-attention mechanism or a multi-head attention mechanism is used;
by training the model:
training the model using a training dataset, including a base model and an attention mechanism;
performing supervised learning by using tag information, and optimizing model parameters to accurately predict tags;
calculating the attention weight of each input part based on the trained model and the attention mechanism when predicting the new unseen sample;
and analyzing the difference characteristics according to the attention weight and predicting.
Further, the spinal cord motor evoked potential is through the recording of potential changes in muscle activity following stimulation of the cerebral cortex.
Furthermore, the signal preprocessing unit performs noise reduction and filtering processing on the signal through equal-ratio amplification on the signal, so that the signal quality is improved.
Further, the data analysis processing module further comprises a display module, an interaction module and a storage module, and the processing result is input and displayed through the data analysis processing module.
Furthermore, the signal acquisition modules of spinal cord electrophysiology, spinal cord evoked potential and spinal cord exercise evoked potential all adopt an air bag electrode structure, and the position and the integral structure of the electrode are changed through an air bag, so that data acquisition and analysis under different situations are realized.
Another object of the present invention is to provide a bioelectric signal conduction verification system for spinal cord injury repair verification, wherein the bioelectric signal conduction verification system is configured to verify the bioelectric signal conduction of spinal cord injury repair verification by inputting a spinal cord electrophysiological model, a spinal cord evoked potential model and a spinal cord movement evoked potential model, which are constructed by a data analysis processing module, into a convolutional neural network and comparing the normal bioelectric signal model.
The beneficial effects of the invention are as follows:
the bioelectric signal transmission device for spinal cord injury repair verification is characterized in that a bioelectric signal analysis system is constructed, and the spinal cord electrophysiological module, the spinal cord evoked potential module and the signal transmission and reception of the spinal cord exercise evoked potential module are combined, so that the spinal cord injury repair is verified in a full range by analyzing the change of the transmission function; simultaneously, a reference and optimized repairing scheme is provided for the repairing of the spinal cord injury by combining with deep learning analysis treatment;
the bioelectric signal conduction device for spinal cord injury repair verification is characterized in that signals are extracted and classified, the signals are input into a convolutional neural network for training to obtain an initial model, and the initial model modeling sequentially builds a model according to the acquisition of spinal cord electrophysiology, spinal cord evoked potential and spinal cord exercise evoked potential; meanwhile, introducing an attention mechanism to analyze the difference information characteristics and the common information characteristics in each model, and generating a bioelectric signal conduction verification model based on a Gaussian distribution characteristic generation module;
the bioelectric signal conduction device for spinal cord injury repair verification is combined with a deep learning scheme to analyze and process bioelectric signal conduction signals, and a normal bioelectric signal conduction verification model is established by combining normal parameters and is compared with the bioelectric signal conduction verification model generated by verification; the method can effectively analyze and record the signal information, and simultaneously input the signal information into a database for storage, so that a basis is provided for subsequent scientific research.
Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.
Drawings
FIG. 1 is a block diagram of a bioelectric signal transmission device for spinal cord injury repair verification according to an embodiment of the present invention;
Detailed Description
In order to more clearly describe the technical scheme of the embodiment of the present invention, the embodiment of the present invention will be described in detail below with reference to the accompanying drawings.
The invention is illustrated below with reference to specific examples:
as shown in fig. 1:
example 1
A bioelectric signal conduction device for spinal cord injury repair verification, comprising: the system comprises a signal acquisition unit, a signal induction unit, a signal preprocessing unit and a data analysis processing module, wherein the signal acquisition unit comprises a signal acquisition module for spinal cord electrophysiology, spinal cord induction potential and spinal cord exercise induction potential, the signal induction unit comprises a signal induction module for spinal cord induction potential and spinal cord exercise induction potential, and a plurality of signal acquisition modules and signal induction modules are in one-to-one correspondence to transmit data to the signal preprocessing unit to improve the signal quality and input to the data analysis processing module for analysis processing;
the data analysis processing module is used for obtaining an initial model by carrying out feature extraction and classification on signals and inputting convolutional neural network training, and the initial model modeling sequentially establishes a model according to the acquisition of spinal electrophysiology, spinal evoked potential and spinal exercise evoked potential; meanwhile, introducing an attention mechanism to analyze the difference information characteristics and the common information characteristics in each model, and generating a bioelectric signal conduction verification model based on a Gaussian distribution characteristic generation module;
meanwhile, the data analysis processing module establishes a normal bioelectric signal conduction verification model according to normal parameters, and compares the normal bioelectric signal conduction verification model with a bioelectric signal conduction verification model generated by verification.
Example 2
In this embodiment, the signal acquisition module acquires corresponding data according to time-frequency domain respectively, and combines time domain analysis with frequency domain analysis to obtain a change rule of signals in time and frequency;
the system comprises a spinal cord electrophysiology signal acquisition module, a data analysis processing module and a data acquisition module, wherein the spinal cord electrophysiology signal acquisition module adopts an intermittent acquisition mode, and bioelectric signals are respectively acquired at two ends of a spinal cord to be verified and input into the data analysis processing module after acquisition;
the signal acquisition module acquires the corresponding intermittent sending evoked signals of the signal evoked module received in the region to be verified, and uploads the signals to the data analysis processing module.
Example 3
In this embodiment, the spinal cord electrophysiology records bioelectricity signals through designing electrodes, wherein the bioelectricity signals include activities of spinal cord neurons and spinal cord pulse transmission speeds, and a spinal cord electrophysiology model is constructed through time-frequency domain changes;
the spinal cord electrophysiological model is characterized in that the collected signals are extracted and classified, if the signals collected at two ends of the spinal cord to be verified are consistent, the attention mechanism weight of the signals is reduced or cancelled, namely, the difference information features and the common information features are analyzed, and the difference information is generated into a bioelectric signal conduction verification model through a feature generation module based on Gaussian distribution.
Wherein: difference information features:
assume that there are two sets of data sets A and B, each containing N samples; the difference information characteristic calculating method comprises the following steps:
Δ(A,B)=|μ(A)-μ(B)|/(σ(A)+σ(B))
wherein Δ (A, B) represents the difference information eigenvalue between A and B, μ (A) and μ (B) represent the mean of the data sets A and B, respectively, and σ (A) and σ (B) represent the standard deviation of the data sets A and B, respectively.
Common information features:
in both sets of data sets a and B, the common information feature calculation method is as follows:
Φ(A,B)=|A∩B|/|A|
where Φ (a, B) represents a common information characteristic value between a and B, |a n b| represents the number of intersection elements of data sets a and B, |a| represents the number of elements of data set a;
wherein the attention mechanism is processing for common information feature weight reduction or cancellation.
Example 4
In this example, the spinal cord evoked potential is recorded by potential changes in spinal cord nerve conduction following administration of a stimulus; corresponding intermittent sending of the evoked signals through the signal evoked modules records corresponding signals on the signal acquisition module of the spinal cord evoked potential, wherein: through intermittent induction signals and detection, a training sample is formed, the difference information characteristics and the common information characteristics are analyzed by adopting a concentration mechanism, and the signal change is compared with a normal bioelectric signal conduction verification model.
The spinal cord motor evoked potentials are measured by recording the changes in potential of muscle activity following stimulation of the cerebral cortex.
Firstly, constructing a basic convolutional neural network model by an attention mechanism, and introducing the attention mechanism for analyzing difference characteristics;
calculating the attention weight of each input part through an attention mechanism to determine the importance of the attention weight in the model;
the attention weight can be calculated according to the degree of difference between different parts of the input, and a self-attention mechanism or a multi-head attention mechanism is used;
by training the model:
training the model using a training dataset, including a base model and an attention mechanism;
performing supervised learning by using tag information, and optimizing model parameters to accurately predict tags;
calculating the attention weight of each input part based on the trained model and the attention mechanism when predicting the new unseen sample;
and analyzing the difference characteristics according to the attention weight and predicting.
Example 5
In this embodiment, the signal preprocessing unit performs noise reduction and filtering processing on the signal by performing equal-ratio amplification on the signal, so as to improve signal quality.
In this embodiment, the data analysis processing module further includes a display module, an interaction module, and a storage module, and the processing result is input and displayed through the data analysis processing module.
In this embodiment, the signal acquisition modules of spinal cord electrophysiology, spinal cord evoked potential and spinal cord exercise evoked potential all adopt an airbag electrode structure, and the position and the overall structure of the electrode are changed by the airbag, so that data acquisition and analysis under different situations are realized.
Example 6
The bioelectric signal conduction verification system for spinal cord injury repair verification is characterized in that a spinal cord electrophysiological model, a spinal cord evoked potential model and a spinal cord movement evoked potential model constructed by a data analysis and processing module are input into a convolutional neural network, and the bioelectric signal conduction of spinal cord injury repair verification is verified by comparing with a normal bioelectric signal model.
The bioelectric signal conduction device for spinal cord injury repair verification is combined with a deep learning scheme to analyze and process bioelectric signal conduction signals, and a normal bioelectric signal conduction verification model is established by combining normal parameters and is compared with the bioelectric signal conduction verification model generated by verification; the method can effectively analyze and record the signal information, and simultaneously input the signal information into a database for storage, so that a basis is provided for subsequent scientific research.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not exhaustive or to limit the invention to the precise form disclosed. Many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (9)
1. A bioelectric signal conduction device for spinal cord injury repair verification is characterized in that: comprising the following steps: the system comprises a signal acquisition unit, a signal induction unit, a signal preprocessing unit and a data analysis processing module, wherein the signal acquisition unit comprises a signal acquisition module for spinal cord electrophysiology, spinal cord induction potential and spinal cord exercise induction potential, the signal induction unit comprises a signal induction module for spinal cord induction potential and spinal cord exercise induction potential, and a plurality of signal acquisition modules and signal induction modules are in one-to-one correspondence to transmit data to the signal preprocessing unit to improve the signal quality and input to the data analysis processing module for analysis processing;
the data analysis processing module is used for obtaining an initial model by carrying out feature extraction and classification on signals and inputting convolutional neural network training, and the initial model modeling sequentially establishes a model according to the acquisition of spinal electrophysiology, spinal evoked potential and spinal exercise evoked potential; meanwhile, introducing an attention mechanism to analyze the difference information characteristics and the common information characteristics in each model, and generating a bioelectric signal conduction verification model based on a Gaussian distribution characteristic generation module;
meanwhile, the data analysis processing module establishes a normal bioelectric signal conduction verification model according to normal parameters, and compares the normal bioelectric signal conduction verification model with a bioelectric signal conduction verification model generated by verification.
2. The bioelectric signal transmission device for spinal cord injury repair verification of claim 1, wherein: the signal acquisition module acquires corresponding data according to time-frequency domains respectively, combines time domain analysis with frequency domain analysis, and acquires a change rule of signals in time and frequency;
the system comprises a spinal cord electrophysiology signal acquisition module, a data analysis processing module and a data acquisition module, wherein the spinal cord electrophysiology signal acquisition module adopts an intermittent acquisition mode, and bioelectric signals are respectively acquired at two ends of a spinal cord to be verified and input into the data analysis processing module after acquisition;
the signal acquisition module acquires the corresponding intermittent sending evoked signals of the signal evoked module received in the region to be verified, and uploads the signals to the data analysis processing module.
3. The bioelectric signal transmission device for spinal cord injury repair verification of claim 2, wherein: the spinal cord electrophysiology is characterized in that bioelectricity signals are recorded through a designed electrode, wherein the bioelectricity signals comprise activities of spinal cord neurons and spinal cord pulse transmission speed, and a spinal cord electrophysiology model is constructed through time-frequency domain changes;
the spinal cord electrophysiological model is characterized in that the collected signals are extracted and classified, if the signals collected at two ends of the spinal cord to be verified are consistent, the attention mechanism weight of the signals is reduced or cancelled, namely, the difference information features and the common information features are analyzed, and the difference information is generated into a bioelectric signal conduction verification model through a feature generation module based on Gaussian distribution.
4. The bioelectric signal transmission device for spinal cord injury repair verification of claim 2, wherein: the spinal cord evoked potential, by giving a stimulus, records the change in the potential of spinal cord nerve conduction; corresponding intermittent sending of the evoked signals through the signal evoked modules records corresponding signals on the signal acquisition module of the spinal cord evoked potential, wherein: through intermittent induction signals and detection, a training sample is formed, the difference information characteristics and the common information characteristics are analyzed by adopting a concentration mechanism, and the signal change is compared with a normal bioelectric signal conduction verification model.
5. The bioelectric signal transmission device for spinal cord injury repair verification of claim 1, wherein: the spinal cord motor evoked potentials are measured by recording the changes in potential of muscle activity following stimulation of the cerebral cortex.
6. The bioelectric signal transmission device for spinal cord injury repair verification of claim 1, wherein: the signal preprocessing unit performs noise reduction and filtering processing on the signal through equal-ratio amplification of the signal, so that the signal quality is improved.
7. The bioelectric signal transmission device for spinal cord injury repair verification of claim 1, wherein: the data analysis processing module also comprises a display module, an interaction module and a storage module, and the processing result is input and displayed through the data analysis processing module.
8. The bioelectric signal transmission device for spinal cord injury repair verification of claim 1, wherein: the signal acquisition modules of spinal cord electrophysiology, spinal cord evoked potential and spinal cord exercise evoked potential all adopt an air bag electrode structure, and the position and the whole structure of the electrode are changed through an air bag, so that data acquisition and analysis under different situations are realized.
9. The bioelectric signal conduction verification system for spinal cord injury repair verification is characterized in that: the spinal cord electrophysiological model, the spinal cord evoked potential model and the spinal cord movement evoked potential model constructed by the data analysis and processing module are input into a convolutional neural network, and the bioelectric signal conduction verified by spinal cord injury repair is verified by comparing with a normal bioelectric signal model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310839858.6A CN116602687A (en) | 2023-07-10 | 2023-07-10 | Bioelectric signal conduction device for spinal cord injury repair verification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310839858.6A CN116602687A (en) | 2023-07-10 | 2023-07-10 | Bioelectric signal conduction device for spinal cord injury repair verification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116602687A true CN116602687A (en) | 2023-08-18 |
Family
ID=87674968
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310839858.6A Withdrawn CN116602687A (en) | 2023-07-10 | 2023-07-10 | Bioelectric signal conduction device for spinal cord injury repair verification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116602687A (en) |
-
2023
- 2023-07-10 CN CN202310839858.6A patent/CN116602687A/en not_active Withdrawn
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110876626B (en) | Depression detection system based on optimal lead selection of multi-lead electroencephalogram | |
US20200367800A1 (en) | Method for identifying driving fatigue based on cnn-lstm deep learning model | |
Oweiss | Statistical signal processing for neuroscience and neurotechnology | |
Chen et al. | Adaptive real-time identification of motor unit discharges from non-stationary high-density surface electromyographic signals | |
Paranjape et al. | The electroencephalogram as a biometric | |
CN101677775B (en) | System and method for pain detection and computation of a pain quantification index | |
Poulos, M. Rangoussi, N. Alexandris, A. Evangelou | On the use of EEG features towards person identification via neural networks | |
Zhang et al. | Machine learning for supporting diagnosis of amyotrophic lateral sclerosis using surface electromyogram | |
Singh et al. | A review of EMG techniques for detection of gait disorders | |
Djamal et al. | Identification of post-stroke EEG signal using wavelet and convolutional neural networks | |
CA2779010A1 (en) | Brain activity as a marker of disease | |
WO2014029764A1 (en) | Method for detection of an abnormal sleep pattern in a person | |
Bugeja et al. | A novel method of EEG data acquisition, feature extraction and feature space creation for early detection of epileptic seizures | |
Djamal et al. | Significant variables extraction of post-stroke EEG signal using wavelet and SOM kohonen | |
Benazzouz et al. | EMG Feature selection for diagnosis of neuromuscular disorders | |
Zhang et al. | DWT-Net: Seizure detection system with structured EEG montage and multiple feature extractor in convolution neural network | |
Jose et al. | Robust classification of intramuscular EMG signals to aid the diagnosis of neuromuscular disorders | |
CN114611563B (en) | Method for identifying neurogenic damage of pin-pole electromyogram across parts | |
CN116602687A (en) | Bioelectric signal conduction device for spinal cord injury repair verification | |
Bibina et al. | Time-frequency methods for diagnosing alzheimer's disease using eeg: A technical review | |
Müller-Gerking et al. | Detecting non-linearities in neuro-electrical signals: a study of synchronous local field potentials | |
Bhuvaneswari et al. | Classification of electromyography signal using wavelet decomposition method | |
CN110192877A (en) | Based on the lie detecting method for more leading the EEG signals degree of bias | |
Belgacem et al. | ECG based human identification using random forests | |
Hussein | Scalp and intracranial EEG quantitative analysis: robust detection and prediction of epileptic seizures |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230818 |