CN115429294B - MEP waveform automatic identification method, system and equipment - Google Patents

Abstract

The invention discloses a MEP waveform automatic identification method, system and equipment, wherein the method comprises the following steps: s1: acquiring a MEP waveform diagram to be identified; s2: performing noise elimination processing on the MEP waveform diagram to be identified; s3: generating a comparison window, equally dividing the comparison window into a front window and a rear window, moving the front window and the rear window along a time axis, and calculating and comparing a voltage average value in the front window and a voltage average value in the rear window in the moving process; s4: judging whether the MEP waveform diagram to be identified after noise elimination is a standard MEP waveform diagram or not according to the comparison result of the voltage average value in the front window and the voltage average value in the rear window; s5: and extracting and displaying the peak-to-peak value and the latency time length of the MEP waveform diagram to be identified after noise elimination. The invention realizes the automatic identification and parameter extraction of the MEP waveform diagram, improves the processing and identification efficiency of the MEP waveform diagram, and avoids errors possibly caused by manual identification.

Description

A MEP waveform automatic recognition method, system and device

Technical Field

The present invention relates to the field of waveform recognition, and in particular to a method, system and device for automatically recognizing a MEP waveform.

Background Art

Motor evoked potential (MEP) is a non-invasive detection method. It is a compound potential of muscle movement recorded in the contralateral target muscle by stimulating the motor cortex. It examines the overall synchronization and integrity of the transmission and conduction pathway of motor nerves from the cortex to the muscle. In spinal cord diseases or injuries, the performance of MEP is determined by the degree of spinal cord damage: the more severe the demyelination of white matter fibers and the more the number of anterior horn motor cells damaged, the more significant the delay of MEP latency and the decrease of amplitude. Therefore, by observing the changes in the latency and amplitude of MEP, the degree of damage to the spinal cord motor function and the prognosis can be judged.

At present, when using motor evoked potentials for diagnosis, manual processing and identification of MEP waveforms generated by TMS stimulation are basically adopted. Since the person being diagnosed needs to be stimulated continuously during the examination, multiple MEP waveforms will be generated. Manual processing is inefficient and prone to human errors, which reduces the accuracy of diagnosis.

Summary of the invention

In order to overcome the above-mentioned deficiencies in the prior art, the present invention provides a method, system and device for automatically identifying a MEP waveform, so as to solve at least one of the above-mentioned technical problems.

According to one aspect of the present specification, a method for automatically identifying a MEP waveform is provided, comprising the following steps:

S1: Obtain a waveform of a MEP to be identified, wherein the horizontal axis of the waveform of the MEP to be identified is the time axis, and the vertical axis is the voltage value;

S2: performing noise elimination processing on the MEP waveform to be identified;

S3: Generate a comparison window, set the length of the comparison window to L, and divide the comparison window into a front window and a rear window; the comparison window moves along the time axis of the MEP waveform to be identified after noise is eliminated, and the length of each movement is L/2. During the movement, the voltage mean in the front window and the voltage mean in the rear window are calculated and compared to obtain a comparison result of the voltage mean in the front window and the voltage mean in the rear window;

S4: judging whether the noise-eliminated MEP waveform to be identified is a standard MEP waveform according to the comparison result of the voltage mean in the front window and the voltage mean in the rear window, and the judging process is as follows:

S401: Determine whether the noise-eliminated MEP waveform to be identified has a first falling period, a rising period, and a second falling period arranged in chronological order; if so, identify the period before the first falling period as a latent period and proceed to the next step;

S402: Obtaining the peak-to-peak value and the latency time length of the MEP waveform to be identified after the noise is eliminated, and determining whether the peak-to-peak value of the MEP waveform to be identified after the noise is eliminated is greater than or equal to a first threshold and whether the latency time length is within a set range. If so, the MEP waveform to be identified after the noise is eliminated is a standard MEP waveform.

S5: extract and display the peak-to-peak value and latency time length of the MEP waveform to be identified after noise elimination.

In the above technical scheme, the noise of the acquired MEP waveform to be identified is eliminated, and it is further determined whether the MEP waveform to be identified after the noise elimination is a standard MEP waveform. If so, the latency time length and peak-to-peak value of the MEP waveform are extracted and displayed, thereby realizing automatic recognition and parameter extraction of the MEP waveform, improving the processing and recognition efficiency of the MEP waveform, and avoiding errors that may be caused by manual recognition.

Furthermore, the noise elimination process includes eliminating high-frequency and low-amplitude noise by low-pass filtering.

Using the common low-pass filtering method to eliminate the noise in the MEP waveform to be identified can not only improve work efficiency, but also ensure the noise elimination effect, thereby improving the accuracy of the identification results.

Furthermore, the noise elimination process also includes eliminating spike noise, and the process of eliminating spike noise includes the following steps:

Divide the waveform of the MEP to be identified into a plurality of sub-waveforms according to the first time length _L1 ;

Calculate the voltage mean of each sub-waveform segment, and start from the second sub-waveform segment, calculate the difference between the voltage mean of each sub-waveform segment and the voltage mean of two adjacent sub-waveform segments;

If the difference between the voltage mean of the sub-waveform graph and the voltage mean of the two sub-waveform graphs of the phasor is greater than the second threshold, the voltage mean of the sub-waveform graph is replaced by the average of the voltage mean of the two adjacent sub-waveform graphs.

There are usually occasional spikes in the MEP waveform. Spikes refer to points where the voltage value of one or two points in the MEP waveform is significantly higher than the voltage value of other points around it. In order to eliminate the interference of spikes on the recognition results, they need to be eliminated. Since the voltage value of the spike is significantly higher than the voltage value of its adjacent points, it is only necessary to compare the average voltages of all adjacent sub-waveforms. When the difference between the average voltage of a sub-waveform and the average voltage of the two adjacent sub-waveforms is too large, it means that there is a spike in the sub-waveform, and then the voltage value of the sub-waveform is replaced with the average voltage value of the adjacent sub-waveforms, thereby achieving the purpose of eliminating spike noise.

Further, the determination process of the first falling period, the rising period and the second falling period in S4 is as follows:

If the voltage mean in the rear window is greater than the voltage mean in the front window, and the difference between the voltage mean in the rear window and the voltage mean in the front window is greater than the third threshold, then the MEP waveform to be identified after noise elimination has a rising period;

If the voltage mean in the rear window is less than the voltage mean in the front window, and the difference between the voltage mean in the rear window and the voltage mean in the front window is greater than the third threshold, then the waveform of the MEP to be identified after noise elimination has a falling period;

If the MEP waveform to be identified after noise elimination has two falling periods and one rising period, and the two falling periods are located at both ends of the rising period, then the falling period before the rising period is the first falling period, and the falling period after the rising period is the second falling period.

In the rising period, the voltage mean of the rear window is greater than the voltage mean of the front window, and because it is in the rising period, the difference between the voltage mean of the rear window and the voltage mean of the front window is large. Based on this principle, it can be judged whether there is a rising period in the MEP waveform; in the falling period, the voltage mean of the rear window is less than the voltage mean of the front window, and because it is in the falling period, the difference between the voltage mean of the rear window and the voltage mean of the front window is large. Based on this principle, it can be identified whether there is a falling period in the MEP waveform, and how many falling periods there are. A standard MEP waveform has two falling periods, and the two falling periods should be located on both sides of the rising period respectively. Therefore, when it is necessary to determine whether the MEP waveform to be identified after noise elimination is a standard MEP waveform, it is necessary to first determine the number and distribution of its rising and falling periods.

Furthermore, the process of obtaining the peak-to-peak value of the MEP waveform to be identified after eliminating noise is as follows:

Obtain the voltage peak value during the rising period: determine whether the difference between the voltage mean in the front window and the voltage mean in the rear window is less than or equal to the third threshold value, if so, proceed to the next step; determine whether the voltage mean in the front window and the voltage mean in the rear window are both greater than the third threshold value, if so, the peak value during the rising period is within the window, and the maximum voltage value in the window at this time is taken as the voltage peak value during the rising period;

Obtain the minimum voltage value of the first decline period: determine whether the difference between the voltage mean in the front window and the voltage mean in the rear window is less than or equal to the third threshold value, if so, proceed to the next step; determine whether the voltage mean in the front window and the voltage mean in the rear window are both less than the inverse of the third threshold value, if so, the minimum voltage value of the first decline period is within the window, and the minimum voltage value in the window at this time is taken as the minimum voltage value of the first decline period;

The difference between the voltage peak value in the rising period and the lowest voltage value in the first falling period is calculated, and the difference is the peak-to-peak value.

In order to more accurately determine whether a MEP waveform is a standard MEP waveform, it is also necessary to determine whether the latency time length and peak-to-peak value (i.e., the difference between the peak and trough potential in the MEP waveform) of the MEP waveform are within the numerical range of the corresponding indicators of the standard MEP waveform. In the case of a waveform corresponding to the known latency, the time length of the latency can be obtained. The voltage peak of the rising period is the highest point of the rising period. Under the appropriate comparison window length, the voltage values at both ends of the point corresponding to the voltage peak of the rising period are large, but the difference between the voltage values at both ends is not large. Based on this principle, the comparison window corresponding to the time point of the voltage peak of the rising period can be found, and then the maximum voltage in the comparison window is found, which is the voltage peak of the rising period.

For a standard MEP waveform, the point corresponding to the lowest voltage is usually located at the connection between the first decline period and the rise period. The voltage values at both ends of this point are low, and the difference between the voltage values at both ends is small. Based on this judgment condition, the comparison window corresponding to the point where the lowest point of the first decline period is located can be found, and then the point with the lowest voltage value can be found in this comparison window. This point is the lowest voltage value of the first decline period, and the difference between the voltage peak value of the rise period and the lowest voltage value of the first decline period is the peak-to-peak value.

Furthermore, the comparison window has at least one length, and if the MEP waveform to be identified after noise elimination is determined to be a standard MEP waveform under any length, then the MEP waveform to be identified after noise elimination is a standard MEP waveform.

Different MEP waveforms have different waveform trends and durations of rising and falling periods. Therefore, setting multiple comparison window lengths can avoid the possibility of misjudgment when the length of the time comparison window is inappropriate. When the MEP waveform to be identified meets the judgment criteria of the standard MEP waveform at a certain comparison window length, the MEP waveform can be judged as a standard MEP waveform.

According to another aspect of the present invention, there is provided a system for automatically identifying a MEP waveform, the system comprising:

A waveform acquisition module is used to acquire the waveform of the MEP to be identified;

A noise elimination module, used to eliminate noise in the waveform of the MEP to be identified;

An MEP waveform diagram judgment module is used to judge whether the MEP waveform diagram is a standard MEP waveform diagram;

A data extraction module is used to extract the latency time length and peak-to-peak value of the MEP waveform;

The data display module is used to display the latency time length and peak-to-peak value of the MEP waveform.

In the above technical solution, the MEP waveform to be identified is obtained by the waveform acquisition module, and the noise in the MEP waveform to be identified is eliminated by the noise elimination module. The MEP waveform judgment module determines whether the MEP waveform after noise elimination is a standard MEP waveform. Finally, the data extraction module and the data display module are used to extract and display the latency time length and peak-to-peak value of the MEP waveform.

According to another aspect of the present invention, a computer device is provided, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method for automatic MEP waveform identification are implemented.

Compared with the prior art, the present invention has the following beneficial effects:

(1) The present invention provides a method for automatically identifying a MEP waveform. By eliminating noise from the acquired MEP waveform, it is further determined whether the MEP waveform after noise elimination is a standard MEP waveform. If so, the latency time length and peak-to-peak value of the MEP waveform are extracted and displayed, thereby realizing automatic identification and parameter extraction of the MEP waveform, improving the processing and identification efficiency of the MEP waveform, and avoiding errors that may be caused by manual identification.

(2) The present invention provides an automatic MEP waveform recognition system, which obtains the MEP waveform to be recognized through a waveform acquisition module, and eliminates the noise in the MEP waveform to be recognized through a noise elimination module. The MEP waveform judgment module determines whether the MEP waveform after noise elimination is a standard MEP waveform. Finally, the data extraction module and the data display module are used to extract and display the latency time length and peak-to-peak value of the MEP waveform. The system can automatically recognize the MEP waveform, improve the efficiency of MEP waveform recognition, and reduce the error of manual recognition.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a flow chart of a method for automatically identifying a MEP waveform according to an embodiment of the present invention;

FIG2 is a standard MEP waveform diagram according to an embodiment of the present invention;

FIG3 is a schematic diagram of a comparison window according to an embodiment of the present invention;

FIG4 is a schematic diagram of a sub-waveform diagram according to an embodiment of the present invention;

FIG5 is a schematic diagram of the structure of an automatic MEP waveform recognition system according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of the structure of a computer device according to an embodiment of the present invention.

DETAILED DESCRIPTION

The following will clearly and completely describe the technical solutions of various embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

Example 1

As shown in FIG1 , this embodiment provides a method for automatically identifying a MEP waveform, comprising the following steps:

S1: Obtain a waveform of a MEP to be identified, wherein the horizontal axis of the waveform of the MEP to be identified is the time axis, and the vertical axis is the voltage value;

S2: performing noise elimination processing on the MEP waveform to be identified;

The noise elimination process includes eliminating high-frequency and low-amplitude noise by low-pass filtering;

The noise elimination process also includes eliminating spike noise, and the process of eliminating spike noise includes the following steps:

The MEP waveform to be identified is divided into several sub-waveforms according to the first time length _L1 ; the MEP waveform in this embodiment is a continuous waveform curve formed by fitting 500 data points. In this embodiment, the first time length _L1 is the time length between two adjacent data points. Therefore, the two ends of each sub-waveform obtained by division are actually the length between two adjacent data points, and the data points at the two ends of adjacent sub-waveforms do not overlap.

Calculate the voltage mean of each sub-waveform segment, and start from the second sub-waveform segment, calculate the difference between the voltage mean of each sub-waveform segment and the voltage mean of two adjacent sub-waveform segments;

If the difference between the voltage mean of the sub-waveform diagram and the voltage mean of the two sub-waveform diagrams of the phasor is greater than the third threshold (80μV in this embodiment), the voltage mean of the sub-waveform diagram is replaced by the average of the voltage means of the two adjacent sub-waveform diagrams.

S3: Generate a comparison window, set the length of the comparison window to L, and divide the comparison window into a front window and a rear window; the comparison window moves along the time axis of the MEP waveform to be identified after noise is eliminated, and the length of each movement is L/2. During the movement, the voltage mean in the front window and the voltage mean in the rear window are calculated and compared to obtain a comparison result of the voltage mean in the front window and the voltage mean in the rear window;

S4: judging whether the noise-eliminated MEP waveform to be identified is a standard MEP waveform according to the comparison result of the voltage mean in the front window and the voltage mean in the rear window, and the judging process is as follows:

S401: Determine whether the noise-eliminated MEP waveform to be identified has a first falling period, a rising period, and a second falling period arranged in chronological order; if so, identify the period before the first falling period as a latent period and proceed to the next step;

S402: Obtain the peak-to-peak value and latency time length of the MEP waveform to be identified after the noise is eliminated, and determine whether the peak-to-peak value of the MEP waveform to be identified after the noise is eliminated is greater than or equal to a first threshold (50 μV in this embodiment) and whether the latency time length is within a set range (15-20 μs in this embodiment). If so, the MEP waveform to be identified after the noise is eliminated is a standard MEP waveform;

The judgment process of the first falling period, the rising period and the second falling period is as follows:

If the voltage mean in the rear window is greater than the voltage mean in the front window, and the difference between the voltage mean in the rear window and the voltage mean in the front window is greater than a third threshold (20 μV in this embodiment), then the MEP waveform has a rising period;

If the voltage mean in the rear window is less than the voltage mean in the front window, and the difference between the voltage mean in the rear window and the voltage mean in the front window is greater than a third threshold, then the MEP waveform has a falling period;

If there are two falling periods in the MEP waveform, and the two falling periods are located at the two ends of the rising period, then the falling period before the rising period is the first falling period, and the falling period after the rising period is the second falling period.

In this embodiment, three comparison window lengths are set respectively (10 data point distances, 15 data point distances and 30 data point distances respectively), and the three comparison window lengths are used to determine whether the MEP waveform to be identified after noise elimination is a standard MEP waveform. If at least one of the three determination results is that the MEP waveform to be identified after noise elimination is a standard MEP waveform, then it can be determined that the MEP waveform to be identified is the standard MEP waveform.

S5: Extract and display the peak value and latency time length of the MEP waveform.

Example 2

As shown in FIG5 , this embodiment provides a MEP waveform automatic recognition system, including:

A waveform acquisition module is used to acquire the waveform of the MEP to be identified;

A noise elimination module, used to eliminate noise in the waveform of the MEP to be identified;

An MEP waveform diagram judgment module is used to judge whether the MEP waveform diagram is a standard MEP waveform diagram;

A data extraction module is used to extract the latency time length and peak-to-peak value of the MEP waveform;

The data display module is used to display the latency time length and peak-to-peak value of the MEP waveform.

The noise cancellation module is also used for:

Eliminate high-frequency, low-amplitude noise through low-pass filtering;

Divide the waveform of the MEP to be identified into a plurality of sub-waveforms according to the first time length _L1 ;

Calculate the voltage mean of each sub-waveform segment, and start from the second sub-waveform segment, calculate the difference between the voltage mean of each sub-waveform segment and the voltage mean of two adjacent sub-waveform segments;

If the difference between the voltage mean of the sub-waveform graph and the voltage mean of the two sub-waveform graphs of the phasor is greater than the second threshold, the voltage mean of the sub-waveform graph is replaced by the average of the voltage mean of the two adjacent sub-waveform graphs.

The MEP waveform judgment module is also used for:

Generate a comparison window, set the length of the comparison window to L, and divide the comparison window into a front window and a rear window; move the comparison window along the time axis of the MEP waveform to be identified after noise elimination, and each movement length is L/2. During the movement, calculate and compare the voltage mean in the front window and the voltage mean in the rear window to obtain a comparison result of the voltage mean in the front window and the voltage mean in the rear window; judge whether the MEP waveform to be identified after noise elimination is a standard MEP waveform according to the comparison result of the voltage mean in the front window and the voltage mean in the rear window, and the judgment process is as follows:

Determine whether the noise-eliminated MEP waveform to be identified has a first falling period, a rising period, and a second falling period arranged in chronological order; if so, identify the period before the first falling period as a latent period and proceed to the next step;

Obtain the peak-to-peak value and latency time length of the MEP waveform to be identified after noise elimination, and determine whether the peak-to-peak value of the MEP waveform to be identified after noise elimination is greater than or equal to a first threshold and whether the latency time length is within a set range. If so, the MEP waveform to be identified after noise elimination is a standard MEP waveform.

If the voltage mean in the rear window is greater than the voltage mean in the front window, and the difference between the voltage mean in the rear window and the voltage mean in the front window is greater than the third threshold, then the MEP waveform to be identified after noise elimination has a rising period;

If the voltage mean in the rear window is less than the voltage mean in the front window, and the difference between the voltage mean in the rear window and the voltage mean in the front window is greater than the third threshold, then the waveform of the MEP to be identified after noise elimination has a falling period;

If the MEP waveform to be identified after noise elimination has two falling periods and one rising period, and the two falling periods are located at both ends of the rising period, then the falling period before the rising period is the first falling period, and the falling period after the rising period is the second falling period.

Obtain the voltage peak value during the rising period: determine whether the difference between the voltage mean in the front window and the voltage mean in the rear window is less than or equal to the third threshold value, if so, proceed to the next step; determine whether the voltage mean in the front window and the voltage mean in the rear window are both greater than the third threshold value, if so, the peak value during the rising period is within the window, and the maximum voltage value in the window at this time is taken as the voltage peak value during the rising period;

Obtain the minimum voltage value of the first decline period: determine whether the difference between the voltage mean in the front window and the voltage mean in the rear window is less than or equal to the third threshold value, if so, proceed to the next step; determine whether the voltage mean in the front window and the voltage mean in the rear window are both less than the inverse of the third threshold value, if so, the minimum voltage value of the first decline period is within the window, and the minimum voltage value in the window at this time is taken as the minimum voltage value of the first decline period;

The difference between the voltage peak value in the rising period and the lowest voltage value in the first falling period is calculated, and the difference is the peak-to-peak value.

Example 3

As shown in FIG. 6 , this embodiment provides a computer device, which may be an industrial computer, a server or a computer terminal.

The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the step of automatically identifying the MEP waveform diagram is implemented.

The computer device includes a processor, a memory and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any method for automatically identifying a MEP waveform.

The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any method for automatically identifying the MEP waveform.

The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will appreciate that the structure shown in FIG6 is only a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

S1: Obtain a waveform of a MEP to be identified, wherein the horizontal axis of the waveform of the MEP to be identified is the time axis, and the vertical axis is the voltage value;

S2: performing noise elimination processing on the MEP waveform to be identified;

S3: Generate a comparison window, set the length of the comparison window to L, and divide the comparison window into a front window and a rear window; the comparison window moves along the time axis of the MEP waveform to be identified after noise is eliminated, and the length of each movement is L/2. During the movement, the voltage mean in the front window and the voltage mean in the rear window are calculated and compared to obtain a comparison result of the voltage mean in the front window and the voltage mean in the rear window;

S4: judging whether the noise-eliminated MEP waveform to be identified is a standard MEP waveform according to the comparison result of the voltage mean in the front window and the voltage mean in the rear window, and the judging process is as follows:

Determine whether the noise-eliminated MEP waveform to be identified has a first falling period, a rising period, and a second falling period arranged in chronological order; if so, identify the period before the first falling period as a latent period and proceed to the next step;

Obtaining the peak-to-peak value and the latency time length of the MEP waveform to be identified after the noise is eliminated, and determining whether the peak-to-peak value of the MEP waveform to be identified after the noise is eliminated is greater than or equal to a first threshold value and whether the latency time length is within a set range. If so, the MEP waveform to be identified after the noise is eliminated is a standard MEP waveform;

S5: extract and display the peak-to-peak value and latency time length of the MEP waveform to be identified after noise elimination.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims (6)

1. An automatic identification method of exercise evoked potential waveforms is characterized in that,

The method comprises the following steps:

s1: acquiring a motion evoked potential oscillogram to be identified;

s2: performing noise elimination processing on the motion evoked potential oscillogram to be identified;

S3: setting a comparison window, setting the length of the comparison window as L, and equally dividing the comparison window into a front window and a rear window; the comparison window moves along a time axis of the motion evoked potential oscillogram to be identified after noise is eliminated, the moving length is L/2 each time, and the voltage average value in the front window and the voltage average value in the rear window are calculated and compared in the moving process to obtain a voltage average value comparison result in the front window and the voltage average value in the rear window;

S4: judging whether the motion evoked potential waveform diagram to be identified after noise elimination is a standard motion evoked potential waveform diagram or not according to the comparison result of the voltage average value in the front window and the voltage average value in the rear window, wherein the judging process is as follows:

s401: judging whether the motion evoked potential oscillogram to be identified after noise elimination has a first falling period, a rising period and a second falling period which are arranged in time sequence; if so, the period before the first falling period is regarded as the incubation period and the next step is carried out;

The judging process of the first falling period, the rising period and the second falling period is as follows:

If the voltage average value in the rear window is larger than the voltage average value in the front window, and the difference value between the voltage average value in the rear window and the voltage average value in the front window is larger than a third threshold value, the motion evoked potential waveform diagram to be identified after noise elimination has a rising period;

If the voltage average value in the rear window is smaller than the voltage average value in the front window, and the difference value between the voltage average value in the rear window and the voltage average value in the front window is larger than a third threshold value, the motion evoked potential waveform diagram to be identified after noise elimination has a falling period;

If the motion evoked potential oscillogram to be identified after noise elimination has two falling periods and one rising period, and the two falling periods are respectively positioned at two ends of the rising period, the first falling period is the first falling period, and the second falling period is the second falling period;

the process of obtaining the peak-to-peak value of the motion evoked potential oscillogram to be identified after eliminating noise is as follows:

Acquiring a voltage peak value in a rising period: judging whether the difference value between the voltage average value in the front window and the voltage average value in the rear window is smaller than or equal to a third threshold value, if so, performing the next step; judging whether the voltage average value in the front window and the voltage average value in the rear window are both larger than a third threshold value, if so, locating the peak value in the rising period in the window, and taking the maximum voltage value in the window at the moment as the voltage peak value in the rising period;

acquiring the lowest voltage value of the first falling period: judging whether the difference value between the voltage average value in the front window and the voltage average value in the rear window is smaller than or equal to a third threshold value, if so, performing the next step; judging whether the voltage average value in the front window and the voltage average value in the rear window are smaller than the opposite number of the third threshold value, if so, locating the lowest voltage value in the first falling period in the window, and taking the smallest voltage value in the window at the moment as the lowest voltage value in the first falling period;

Calculating the difference between the voltage peak value in the rising period and the lowest voltage value in the first falling period, wherein the difference is the peak-to-peak value;

S402: acquiring the peak value and the latency time length of the motion evoked potential waveform diagram to be identified after noise elimination, judging whether the peak value of the motion evoked potential waveform diagram to be identified after noise elimination is more than or equal to a first threshold value and whether the latency time length is within a set range, if so, the motion evoked potential waveform diagram to be identified after noise elimination is a standard motion evoked potential waveform diagram;

S5: and extracting and displaying the peak-to-peak value and the latency time length of the motion evoked potential oscillogram to be identified after noise elimination.

2. The method for automatically identifying a motion-induced potential waveform according to claim 1, wherein,

The noise cancellation process includes canceling high frequency low amplitude noise by low pass filtering.

3. The method for automatically identifying a motion-induced potential waveform according to claim 1, wherein,

The noise cancellation process further includes canceling the spike noise, the canceling the spike noise including the steps of:

Dividing a to-be-identified exercise evoked potential oscillogram into a plurality of sub-oscillograms according to a first time length L1;

Calculating the voltage average value of each section of sub-waveform diagram, starting from the second section of sub-waveform diagram, and calculating the difference value between the voltage average value of each section of sub-waveform diagram and the voltage average value of two adjacent sections of sub-waveform diagrams;

If the difference between the voltage average value of the sub-waveform diagram and the voltage average value of the two sections of the phasors is larger than the second threshold value, the average value of the voltage average values of the two adjacent sub-waveform diagrams is used for replacing the voltage average value of the section of the sub-waveform diagram.

4. The method for automatically identifying a motion-induced potential waveform according to claim 1, wherein,

And if the length of the comparison window is at least one, and the motion evoked potential waveform diagram to be identified after noise elimination is judged to be the standard motion evoked potential waveform under any length, the motion evoked potential waveform diagram to be identified after noise elimination is the standard motion evoked potential waveform diagram.

5. An automatic identification system for exercise-induced potential waveforms, which is realized by adopting the automatic identification method for exercise-induced potential waveforms according to any one of claims 1-4,

The system comprises:

the waveform diagram acquisition module is used for acquiring a to-be-identified exercise evoked potential waveform diagram;

A noise cancellation module for canceling noise in the motion-evoked potential waveforms;

The exercise evoked potential waveform diagram judging module is used for judging whether the exercise evoked potential waveform diagram is a standard exercise evoked potential waveform diagram or not;

The data extraction module is used for extracting the latency time length and the peak-to-peak value of the exercise evoked potential oscillogram;

And the data display module is used for displaying the latency time length and the peak-to-peak value of the exercise evoked potential oscillogram.

6. A computer device, characterized in that,

The computer device comprising a processor, a memory, and a computer program stored on the memory and executed by the processor, wherein the computer program when executed by the processor performs the steps of the method for automatically identifying a motion evoked potential waveform as in any of claims 1 to 4.