Intelligent detection method and system for cranial nerves based on ophthalmic nerves

Abstract

The present invention relates to the field of non-invasive detection technology, and is a method and system for intelligent detection of cranial nerves by using an ophthalmic nerve, comprising: performing a pre-calibration operation on a pressure sensor based on an ultrasonic imager, transporting the pressure sensor and a detector to a detection area, obtaining an initial signal from the pressure sensor, performing a decomposition operation on the initial signal to obtain a plurality of decomposed signals, calculating a relationship value between the extracted decomposed signal and the initial signal, obtaining a local calibration signal based on the relationship value, obtaining a pressure value based on a plurality of local calibration signals, and after confirming that the pressure value is within a preset pressure interval, obtaining a first detection report based on the nerve sheath diameter, and completing intelligent detection of cranial nerves based on the ophthalmic nerve according to the first detection report. The present invention can realize the detection of the optic nerve sheath diameter by controlling the detector of the ultrasonic imager using a pressure sensor, and can realize non-invasive detection of cranial nerves by combining the detection of physiological signals when the eye is stimulated.

Description

Technical Field

[0001] The present invention relates to the field of non-invasive detection technology, and in particular to a method, system, electronic device and computer-readable storage medium for intelligent detection of brain nerves using ophthalmic nerves. Background Art

[0002] Intracranial pressure is closely related to the patient's cranial nerves. When the intracranial pressure is too high, it will have adverse effects on the patient's cranial nerves. At the same time, when the cranial nerves are damaged, the patient's optic nerves will also have problems. Therefore, it is very important to monitor intracranial pressure and detect optic nerves.

[0003] In the prior art, there are methods for checking intracranial pressure such as arachnoid cavity pressure measurement and intraventricular pressure measurement. Among them, arachnoid cavity pressure measurement requires the patient to fully expose the intervertebral space and puncture the brain. The cerebrospinal fluid flows out through the puncture needle, and the intracranial pressure is detected by measuring the pressure difference in the pressure measuring tube. Technologies such as intraventricular pressure measurement require puncture of the patient's body. At the same time, in the process of detecting the optic nerve, the prior art also uses methods such as electrooculogram and visual evoked potential to detect whether the optic nerve is normal.

[0004] Although the above technology can detect the intracranial pressure of patients, puncture is required during the detection process, which has adverse effects on the patient's body, and only detecting the intracranial pressure can only roughly determine whether the patient's cranial nerves are normal. Summary of the invention

[0005] The present invention provides an intelligent detection method for cranial nerves by using optic nerves and a computer-readable storage medium. The main purpose of the method is to use a pressure sensor to control the detector of an ultrasonic imager to detect the diameter of the optic nerve sheath, and to combine the detection of physiological signals when the eyes are stimulated to achieve non-invasive detection of cranial nerves.

[0006] To achieve the above object, the present invention provides an intelligent detection method of cranial nerves using ophthalmic nerves, comprising:

[0007] Acquire an ultrasonic imager, wherein the ultrasonic imager comprises: a pressure sensor, a detector, a guide rail positioning unit and an imaging processing unit, wherein the pressure sensor is arranged on the detector, the guide rail positioning unit comprises a guide rail and a positioning processing unit, the detector is slidably arranged on the guide rail, the pressure detected by the pressure sensor is the pressure applied by the detector, and whether the pressure applied by the detector in the detection area is reasonable is detected by the pressure sensor;

[0008] Performing a pre-calibration operation on the pressure sensor based on an ultrasonic imager, after confirming that the pressure sensor has completed calibration, transporting the pressure sensor and the detector to a pre-constructed detection area based on a guide rail and a positioning processing unit, wherein the detection area is an orbital area of ​​a patient provided with a dressing;

[0009] A detection time sequence of the pressure sensor is obtained based on a preset pressure detection frequency, wherein the time sequence includes a plurality of unit detection times, the unit detection times are sequentially extracted from the detection time sequence, and the following operations are performed on the extracted unit detection times:

[0010] An initial signal is acquired based on the extracted unit detection time, a decomposition operation is performed on the initial signal to obtain a plurality of decomposed signals, decomposed signals are sequentially extracted from the plurality of decomposed signals, and the following operations are performed on the extracted decomposed signals:

[0011] Calculating the relationship value between the extracted decomposition signal and the initial signal using a pre-constructed relationship value formula, obtaining a local noise reduction signal based on the relationship value, and performing a correction operation on the local noise reduction signal to obtain a local calibration signal;

[0012] Wherein, obtaining the local noise reduction signal based on the relationship value includes:

[0013] Comparing the relationship value with a preset relationship threshold;

[0014] If the relationship value is less than the relationship threshold, a symmetric decomposition operation is performed on the extracted decomposition signal to obtain a local noise reduction signal;

[0015] Otherwise, confirming that the decomposed signal corresponding to the relationship value is a local noise reduction signal;

[0016] Acquire the pressure value corresponding to the extracted unit detection time based on multiple local calibration signals, and after confirming that the pressure value is within a preset pressure range, acquire unit image data using a detector and an imaging processing unit;

[0017] Aggregating multiple unit image data to obtain an image data set, and constructing an optic nerve sheath image using an imaging processing unit and the image data set;

[0018] Obtaining the optic nerve sheath diameter based on the optic nerve sheath image, and obtaining a first detection report based on a preset healthy diameter interval and the optic nerve sheath diameter;

[0019] Constructing a second electrooculogram detection unit, wherein the second electrooculogram detection unit includes: a stimulation unit, a signal amplification unit and an information processing unit;

[0020] Obtaining a second detection report using a second electrooculographic detection unit;

[0021] A cranial nerve detection report is obtained according to the first detection report and the second detection report, and intelligent detection of the cranial nerves based on the ocular nerves is completed based on the cranial nerve detection report.

[0022] Optionally, performing a pre-calibration operation on the pressure sensor based on an ultrasonic imager includes:

[0023] The pressure sensor is introduced into a pre-built standard load measurement chamber, and a plurality of preset load sets are obtained based on the standard load measurement chamber, wherein each of the plurality of preset load sets includes a plurality of preset loads, and the magnitude of each of the plurality of preset loads is different;

[0024] Preset load sets are sequentially extracted from the plurality of preset load sets, and the following operations are performed on the extracted preset load sets:

[0025] Preset loads are extracted from the preset load set in sequence, and the following operations are performed on the extracted preset loads:

[0026] Receiving a pressure measurement signal based on the pressure sensor, obtaining a pressure measurement value corresponding to the pressure sensor based on the pressure measurement signal, comparing the pressure measurement value with the size of a preset load, and if the pressure measurement value is equal to the preset load, confirming that the pressure sensor is normal, otherwise, confirming that the pressure sensor is calibrated using a pre-built adjustment module, and returning to the step of receiving a pressure measurement signal based on the pressure sensor;

[0027] Summarizing the pressure measurement values ​​corresponding to each preset load in the plurality of preset loads to obtain a pressure measurement value set, constructing a calibration curve based on the pressure measurement value set and the extracted preset load set, and determining a unit compensation coefficient corresponding to the extracted preset load set based on the calibration curve;

[0028] The unit compensation coefficient corresponding to each preset load set in the plurality of preset load sets is aggregated to obtain a unit compensation coefficient set, and a compensation coefficient is obtained based on the unit compensation coefficient set, wherein the compensation coefficient is an average value of all unit compensation coefficients in the unit compensation coefficient set.

[0029] Optionally, constructing a calibration curve based on the pressure measurement value set and the extracted preset load set, and determining a unit compensation coefficient corresponding to the extracted preset load set based on the calibration curve, includes:

[0030] Constructing a plane rectangular coordinate system, wherein the horizontal axis of the plane rectangular coordinate system is the preset load and the vertical axis is the pressure measurement value;

[0031] A calibration curve is obtained by fitting the pressure measurement value set, the extracted preset load set and the plane rectangular coordinate system, a linear fitting operation is performed on the calibration curve using a pre-constructed least squares method to obtain a pressure working straight line, and a unit compensation coefficient is obtained based on the pressure working straight line.

[0032] Optionally, after confirming that the pressure sensor has completed calibration, the method further comprises:

[0033] A pressure numerical expression of the pressure sensor is determined based on the compensation coefficient, wherein the pressure numerical expression is:

[0034]

[0035] in, Indicates the pressure value output by the pressure sensor. represents the pressure sensitivity coefficient of the pressure sensor, and , Indicates the wavelength change of the pressure sensor, represents the change in cavity length of the resonant cavity of the pressure sensor, represents the compensation coefficient, represents the Young's modulus of the pressure sensitive diaphragm, Indicates the thickness of the pressure sensitive diaphragm, represents the effective radius of the pressure sensitive diaphragm, represents the Poisson's ratio of the pressure sensitive diaphragm;

[0036] The calibration of the pressure sensor is confirmed to be completed based on the pressure numerical expression.

[0037] Optionally, performing a decomposition operation on the initial signal to obtain a plurality of decomposed signals includes:

[0038] Based on the extracted initial signal, an extreme value point sequence in the extracted initial signal is obtained, wherein the extreme value point sequence includes a plurality of maximum value points and a plurality of minimum value points, extreme value points are sequentially extracted from the extreme value point sequence, and the following operations are performed on the extracted extreme value points:

[0039] Based on the extracted extreme point, an adjacent extreme point is obtained, wherein the adjacent extreme point is the next extreme point adjacent to the extracted extreme point in the extreme point sequence, and an adjacent local mean is calculated according to the extracted extreme point and the adjacent extreme point, wherein the calculation formula of the adjacent local mean is:

[0040]

[0041] in, is the adjacent local mean, represents the time corresponding to the adjacent extreme point, represents the time corresponding to the extracted extreme point, represents the median value corresponding to the adjacent local means, represents the initial signal, represents the time variable in the initial signal;

[0042] Aggregating multiple adjacent local means to obtain an adjacent local mean sequence, and obtaining a weighted mean sequence based on the adjacent local mean sequence and a pre-constructed weighted mean method, wherein the time corresponding to the weighted mean in the weighted mean sequence corresponds one-to-one to the time corresponding to the extreme point in the extreme point sequence;

[0043] A mean curve is constructed based on a weighted mean sequence, and an iterative operation is performed on an initial signal using the mean curve to obtain a plurality of decomposed signals, wherein the decomposed signal of each of the plurality of decomposed signals is a basic mode function.

[0044] Optionally, aggregating multiple adjacent local means to obtain an adjacent local mean sequence, and obtaining a weighted mean sequence based on the adjacent local mean sequence and a pre-constructed weighted mean method, includes:

[0045] Adjacent local means are sequentially extracted from the adjacent local mean sequence, and the following operations are performed on the extracted adjacent local means:

[0046] The weighted mean of the time corresponding to the extreme point is calculated using the pre-constructed weighted mean formula and the extracted adjacent local means, wherein the weighted mean formula is:

[0047]

[0048] in, represents the weighted mean of the moments corresponding to the extracted extreme points, represents the previous moment adjacent to the moment corresponding to the extracted extreme point, represents the extracted adjacent local mean, represents the previous adjacent local mean adjacent to the extracted adjacent local mean;

[0049] Aggregate multiple weighted means to obtain a sequence of weighted means.

[0050] Optionally, after confirming that the pressure value is within a preset pressure range, the method further comprises:

[0051] Get the minimum pressure value and the maximum pressure value based on the pressure range;

[0052] Compare the pressure value with the minimum pressure value;

[0053] If the pressure value is less than the minimum pressure value, the positioning processing unit is used to obtain a boost correction path, the detector is transported to a pre-constructed correction area based on the boost correction path and the guide rail, and the step of obtaining a detection time sequence of the pressure sensor based on a preset pressure detection frequency is returned;

[0054] If the pressure value is greater than or equal to the minimum pressure value, comparing the pressure value with the maximum pressure value;

[0055] If the pressure value is greater than the maximum pressure value, the positioning processing unit is used to obtain a decompression correction path, the detector is transported to the correction area based on the decompression correction path and the guide rail, and the step of obtaining the detection time sequence of the pressure sensor based on the preset pressure detection frequency is returned;

[0056] If the pressure value is less than or equal to the maximum pressure value, it is confirmed that the pressure value is within the pressure range.

[0057] Optionally, the obtaining of the first detection report based on a preset healthy diameter interval and an optic nerve sheath diameter includes:

[0058] comparing the optic nerve sheath diameter with a healthy diameter interval;

[0059] If the optic nerve sheath diameter is outside the healthy diameter range, it is confirmed that the patient's intracranial pressure is abnormal, and a brain abnormality reminder is generated based on the imaging processing unit;

[0060] If the optic nerve sheath diameter is within the healthy diameter range, it is confirmed that the patient's intracranial pressure is normal, and a normal brain reminder is generated based on the imaging processing unit;

[0061] Get a test report based on abnormal brain alerts or normal brain alerts.

[0062] Optionally, obtaining a second detection report by using a second electrooculographic detection unit includes:

[0063] After confirming that the patient has completed the pretreatment, the number of electrooculogram detections is obtained based on the stimulation unit, wherein the number of electrooculogram detections is greater than or equal to 1, a plurality of detection times are obtained based on the number of electrooculogram detections, the detection times are sequentially extracted from the plurality of detection times, and the following operations are performed on the extracted detection times:

[0064] Starting the second electrooculogram detection unit based on the extracted detection time, after confirming that the second electrooculogram detection unit is started, acquiring the electrode coordinates and the ground electrode coordinates based on the stimulation unit, after confirming that the patient is located in the preset electrooculogram detection area based on the information processing unit, the electrode coordinates and the ground electrode coordinates, acquiring the interference impedance between the electrode and the patient based on the electrode coordinates and the ground electrode coordinates, after confirming that the interference impedance is within a preset negligible impedance interval, generating a stimulation signal using the stimulation unit, wherein the negligible impedance interval is greater than or equal to 0 ohms and less than or equal to 10 ohms;

[0065] Using an amplification unit to receive a physiological signal corresponding to the stimulation signal, and amplifying the physiological signal to obtain an amplified signal, sending the amplified signal to an information processing unit, and using the information processing unit and the amplified signal to obtain a unit diagnosis curve graph;

[0066] A plurality of unit diagnostic curve graphs are aggregated to obtain a diagnostic atlas, and a second test report is obtained based on the diagnostic atlas.

[0067] Optionally, the step of generating a stimulation signal using a stimulation unit comprises:

[0068] Constructing a plurality of stimulation signals using a stimulation unit, wherein the plurality of stimulation signals are respectively: a graphic visual signal, a flash signal, a light on / off signal, a nystagmus image signal, and a visual acuity detection signal;

[0069] A detection item corresponding to the electrooculographic detection is acquired based on the information processing unit, and a stimulation signal corresponding to the detection item is extracted from a plurality of stimulation signals based on the detection item.

[0070] To achieve the above object, the present invention also provides an intelligent detection system for realizing cranial nerves by using ophthalmic nerves, comprising:

[0071] A sensor pre-adjustment module is used to obtain an ultrasonic imager, wherein the ultrasonic imager includes: a pressure sensor, a detector, a guide rail positioning unit and an imaging processing unit, wherein the pressure sensor is arranged on the detector, the guide rail positioning unit includes a guide rail and a positioning processing unit, the detector is slidably arranged on the guide rail, the pressure detected by the pressure sensor is the pressure applied by the detector, and the pressure sensor is used to detect whether the pressure applied by the detector in the detection area is reasonable;

[0072] Performing a pre-calibration operation on the pressure sensor based on an ultrasonic imager, after confirming that the pressure sensor has completed calibration, transporting the pressure sensor and the detector to a pre-constructed detection area based on a guide rail and a positioning processing unit, wherein the detection area is an orbital area of ​​a patient provided with a dressing;

[0073] The signal decomposition module is used to obtain a detection time sequence of the pressure sensor based on a preset pressure detection frequency, wherein the time sequence includes a plurality of unit detection times, and the unit detection times are sequentially extracted from the detection time sequence, and the following operations are performed on the extracted unit detection times:

[0074] Acquire an initial signal based on the extracted unit detection time, and perform a decomposition operation on the initial signal to obtain a plurality of decomposed signals;

[0075] The signal processing module is used to extract decomposed signals from the multiple decomposed signals in sequence, and perform the following operations on the extracted decomposed signals:

[0076] Calculating the relationship value between the extracted decomposition signal and the initial signal using a pre-constructed relationship value formula, obtaining a local noise reduction signal based on the relationship value, and performing a correction operation on the local noise reduction signal to obtain a local calibration signal;

[0077] Wherein, obtaining the local noise reduction signal based on the relationship value includes:

[0078] Comparing the relationship value with a preset relationship threshold;

[0079] If the relationship value is less than the relationship threshold, a symmetric decomposition operation is performed on the extracted decomposition signal to obtain a local noise reduction signal;

[0080] Otherwise, confirming that the decomposed signal corresponding to the relationship value is a local noise reduction signal;

[0081] Acquire the pressure value corresponding to the extracted unit detection time based on multiple local calibration signals, and after confirming that the pressure value is within a preset pressure range, acquire unit image data using a detector and an imaging processing unit;

[0082] A report generation module, for summarizing multiple unit image data to obtain an image data set, and constructing an optic nerve sheath image using the imaging processing unit and the image data set;

[0083] Obtaining the optic nerve sheath diameter based on the optic nerve sheath image, and obtaining a first detection report based on a preset healthy diameter interval and the optic nerve sheath diameter;

[0084] Constructing a second electrooculogram detection unit, wherein the second electrooculogram detection unit includes: a stimulation unit, a signal amplification unit and an information processing unit;

[0085] Obtaining a second detection report using a second electrooculographic detection unit;

[0086] A cranial nerve detection report is obtained according to the first detection report and the second detection report, and intelligent detection of the cranial nerves based on the ocular nerves is completed based on the cranial nerve detection report.

[0087] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0088] a memory storing at least one instruction; and

[0089] The processor executes the instructions stored in the memory to implement the above-mentioned intelligent detection method of the eye nerve and the cranial nerve.

[0090] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned intelligent detection method of eye nerves and cranial nerves.

[0091] The present invention is to solve the problem described in the background technology. The present invention obtains an ultrasonic imager, wherein the ultrasonic imager includes: a pressure sensor, a detector, a guide rail positioning unit and an imaging processing unit, wherein the pressure sensor is arranged on the detector, the guide rail positioning unit includes a guide rail and a positioning processing unit, the detector is slidably arranged on the guide rail, and the ultrasonic imager performs a pre-calibration operation on the pressure sensor. After confirming that the pressure sensor has completed the calibration, the pressure sensor and the detector are transported to a pre-constructed detection area based on the guide rail and the positioning processing unit, wherein the detection area is the patient's eye socket area with a dressing. In the embodiment of the present invention, the pressure detected by the pressure sensor is the pressure applied by the detector, and the pressure sensor is used to detect whether the pressure applied by the detector in the detection area is reasonable. At the same time, the embodiment of the present invention controls the position of the detector through the guide rail and the positioning processing unit, and uses the pressure sensor to control the distance between the detector and the patient's eyelid. The pre-calibration operation on the pressure sensor improves the accuracy of the detection. A detection time series of a pressure sensor is obtained based on a preset pressure detection frequency, wherein the time series includes a plurality of unit detection times, the unit detection times are extracted from the detection time series in sequence, and the following operations are performed on the extracted unit detection times: an initial signal is obtained based on the extracted unit detection time, a decomposition operation is performed on the initial signal to obtain a plurality of decomposed signals, decomposed signals are extracted from the plurality of decomposed signals in sequence, and the following operations are performed on the extracted decomposed signals: a relationship value between the extracted decomposed signal and the initial signal is calculated using a pre-constructed relationship value formula, a local noise reduction signal is obtained based on the relationship value, a correction operation is performed on the local noise reduction signal to obtain a local calibration signal. The embodiment of the present invention performs noise reduction on the initial signal within each unit detection time of the pressure sensor to process the strong noise generated by the pressure sensor due to various normal physiological phenomena such as the patient's breathing and heartbeat, thereby improving the accuracy of detection. A pressure value corresponding to the extracted unit detection time is obtained based on multiple local calibration signals. After confirming that the pressure value is within a preset pressure range, unit image data is obtained using a detector and an imaging processing unit, and multiple unit image data are aggregated to obtain an image data set. An optic nerve sheath image is constructed using the imaging processing unit and the image data set. The optic nerve sheath diameter is obtained based on the optic nerve sheath image. A first detection report is obtained based on a preset healthy diameter range and the optic nerve sheath diameter, and a second electrooculogram detection unit is constructed, wherein the second electrooculogram detection unit includes: a stimulation unit, a signal amplification unit, and an information processing unit. A second detection report is obtained using the second electrooculogram detection unit, and a cranial nerve detection report is obtained based on the first detection report and the second detection report. Based on the cranial nerve detection report, intelligent detection of cranial nerves based on ocular nerves is completed.In an embodiment of the present invention, an optic nerve sheath image is constructed using multiple unit image data, and the purpose is to use an ultrasonic imager to detect the diameter of the optic nerve sheath to determine whether the patient's intracranial pressure is abnormal, thereby realizing non-invasive detection of intracranial pressure. At the same time, the embodiment of the present invention also uses physiological signals around the eyes to assist in the detection of brain nerves, obtain a second detection report, and comprehensively implement accurate detection of the patient's brain nerves based on the second detection report and the first detection report. Therefore, the present invention can use a pressure sensor to control the detector of the ultrasonic imager to detect the diameter of the optic nerve sheath, and combine it with the detection of physiological signals when the eyes are stimulated to jointly realize non-invasive detection of brain nerves. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] Figure 1 A schematic diagram of a flow chart of a method for realizing intelligent detection of cranial nerves by using ophthalmic nerves according to an embodiment of the present invention;

[0093] Figure 2 A functional module diagram of an intelligent detection system for brain nerves using ophthalmic nerves provided by an embodiment of the present invention;

[0094] Figure 3 A schematic diagram of the structure of an electronic device for implementing the intelligent detection method of the ophthalmic nerve and the cranial nerve provided in one embodiment of the present invention.

[0095] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0096] 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.

[0097] The embodiment of the present application provides an intelligent detection method for brain nerves by using the ophthalmic nerve. The execution subject of the intelligent detection method for brain nerves by using the ophthalmic nerve includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the intelligent detection method for brain nerves by using the ophthalmic nerve can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0098] Reference Figure 1 FIG. 1 is a flow chart of a method for realizing intelligent detection of cranial nerves by using ophthalmic nerves according to an embodiment of the present invention. In this embodiment, the method for realizing intelligent detection of cranial nerves by using ophthalmic nerves includes:

[0099] S1. Obtain an ultrasonic imager, wherein the ultrasonic imager includes: a pressure sensor, a detector, a guide rail positioning unit and an imaging processing unit, wherein the pressure sensor is arranged on the detector, the guide rail positioning unit includes a guide rail and a positioning processing unit, the detector is slidably arranged on the guide rail, and a pre-calibration operation is performed on the pressure sensor based on the ultrasonic imager.

[0100] It is understandable that an ultrasound imager is an instrument that generates images of the brain by scanning the brain with ultrasound. Since the propagation characteristics of sound waves in different tissues of the human body are different, the propagation characteristics of ultrasound can be used to construct images of the inside of the patient's brain.

[0101] It should be noted that existing technologies show that when the intracranial pressure of a patient increases, the diameter of the optic nerve sheath also expands in imaging. When the diameter of the optic nerve sheath is greater than the critical value, it can be considered that the patient's intracranial pressure is abnormal. Using ultrasound imaging technology to detect the diameter of the optic nerve sheath can achieve non-invasive detection of intracranial pressure, that is, to detect cranial nerves through the optic nerve.

[0102] Specifically, the detector includes an ultrasonic probe, an ultrasonic generator and an ultrasonic receiver. The ultrasonic probe is a device for sending ultrasonic waves into the human body, the ultrasonic generator is a device for generating ultrasonic waves, and the ultrasonic receiver is a device for receiving ultrasonic waves. The guide rail positioning unit is a unit for intelligently moving the detector and the pressure sensor, and the imaging processing unit is a unit for generating a display image based on the detected data set. The guide rail is a track for providing movement conditions for the detector detection, and the positioning processing unit is a unit for controlling the movement and positioning of the pressure sensor and the detector.

[0103] It is understandable that in the embodiment of the present invention, the pressure detected by the pressure sensor is the pressure applied by the detector. The pressure sensor is used to detect whether the pressure applied by the detector in the detection area is reasonable. This is because when using an ultrasonic imager, the detector needs to be placed on the eyelid of the patient with the dressing. If the pressure applied by the detector is too large at this time, it will not only affect the detection result, but also cause discomfort to the patient. If the pressure of the detector in the detection area is too small, it means that the detector is not directly in contact with the eyelid of the patient with the dressing. At this time, using an ultrasonic imager for detection will result in inaccurate measurements. Therefore, when using an intelligent ultrasonic imager to detect the image of the optic nerve sheath, it is necessary to limit the pressure. The detector can slide on the guide rail, and how the detector slides on the guide rail to achieve detection is controlled by the positioning processing unit.

[0104] Further, the performing a pre-calibration operation on the pressure sensor based on an ultrasonic imager includes:

[0105] The pressure sensor is introduced into a pre-built standard load measurement chamber, and a plurality of preset load sets are obtained based on the standard load measurement chamber, wherein each of the plurality of preset load sets includes a plurality of preset loads, and the magnitude of each of the plurality of preset loads is different;

[0106] Preset load sets are sequentially extracted from the plurality of preset load sets, and the following operations are performed on the extracted preset load sets:

[0107] Preset loads are extracted from the preset load set in sequence, and the following operations are performed on the extracted preset loads:

[0108] Receiving a pressure measurement signal based on the pressure sensor, obtaining a pressure measurement value corresponding to the pressure sensor based on the pressure measurement signal, comparing the pressure measurement value with the size of a preset load, and if the pressure measurement value is equal to the preset load, confirming that the pressure sensor is normal, otherwise, confirming that the pressure sensor is calibrated using a pre-built adjustment module, and returning to the step of receiving a pressure measurement signal based on the pressure sensor;

[0109] Summarizing the pressure measurement values ​​corresponding to each preset load in the plurality of preset loads to obtain a pressure measurement value set, constructing a calibration curve based on the pressure measurement value set and the extracted preset load set, and determining a unit compensation coefficient corresponding to the extracted preset load set based on the calibration curve;

[0110] The unit compensation coefficient corresponding to each preset load set in the plurality of preset load sets is aggregated to obtain a unit compensation coefficient set, and a compensation coefficient is obtained based on the unit compensation coefficient set, wherein the compensation coefficient is an average value of all unit compensation coefficients in the unit compensation coefficient set.

[0111] It is understandable that the standard load measurement chamber is an environment for calibrating the pressure sensor. Since the pressure detected by the pressure sensor in the embodiment of the present invention is very small, too large an error will cause detection errors, so the pressure sensor needs to be calibrated. The preset load set is a set of multiple preset loads, and the preset load is the load set by the standard load measurement chamber. The pressure measurement signal is the signal measured by the pressure sensor, and the adjustment module is a module that controls the output value inside the pressure sensor.

[0112] It should be noted that the calibration curve is a curve constructed by the pressure measurement value set and the preset load set, and the unit compensation coefficient is a compensation coefficient obtained from the calibration curve corresponding to the extracted preset load set. The compensation coefficient is a coefficient used to improve the error of the pressure sensor output value.

[0113] It is understandable that the present invention implements the use of multiple preset load sets to construct a unit compensation coefficient set, uses the unit coefficient compensation set to obtain compensation coefficients, and performs multiple measurements to reduce errors, thereby improving the detection accuracy of the calibrated pressure sensor.

[0114] Specifically, the step of constructing a calibration curve based on the pressure measurement value set and the extracted preset load set, and determining a unit compensation coefficient corresponding to the extracted preset load set based on the calibration curve includes:

[0115] Constructing a plane rectangular coordinate system, wherein the horizontal axis of the plane rectangular coordinate system is the preset load and the vertical axis is the pressure measurement value;

[0116] A calibration curve is obtained by fitting the pressure measurement value set, the extracted preset load set and the plane rectangular coordinate system, a linear fitting operation is performed on the calibration curve using a pre-constructed least squares method to obtain a pressure working straight line, and a unit compensation coefficient is obtained based on the pressure working straight line.

[0117] It is understandable that in the embodiment of the present invention, the preset load and the pressure measurement value corresponding to the preset load are taken as a coordinate, and the coordinates corresponding to each preset load in the extracted preset load set are input into the plane rectangular coordinate system, and then a calibration curve is fitted so that the calibration curve can represent the relationship between the preset load and the pressure measurement value. The least squares method is a prior art, and its purpose is to fit all existing data into a straight line that can represent all data. The technology of fitting a curve using multiple points is a prior art and will not be repeated here.

[0118] S2. After confirming that the pressure sensor has completed calibration, the pressure sensor and the detector are transported to a pre-constructed detection area based on a guide rail and a positioning processing unit, wherein the detection area is an orbital area of ​​the patient with a dressing.

[0119] It should be noted that the embodiment of the present invention controls the position of the detector through the guide rail and the positioning processing unit, and uses the pressure sensor to control the distance between the detector and the patient's eyelid. Performing a pre-calibration operation on the pressure sensor improves the accuracy of the detection.

[0120] Further, after confirming that the pressure sensor has completed calibration, the process includes:

[0121] A pressure numerical expression of the pressure sensor is determined based on the compensation coefficient, wherein the pressure numerical expression is:

[0122]

[0123] in, Indicates the pressure value output by the pressure sensor. represents the pressure sensitivity coefficient of the pressure sensor, and , Indicates the wavelength change of the pressure sensor, represents the change in cavity length of the resonant cavity of the pressure sensor, represents the compensation coefficient, represents the Young's modulus of the pressure sensitive diaphragm, Indicates the thickness of the pressure sensitive diaphragm, represents the effective radius of the pressure sensitive diaphragm, represents the Poisson's ratio of the pressure sensitive diaphragm;

[0124] The calibration of the pressure sensor is confirmed to be completed based on the pressure numerical expression.

[0125] It is understandable that the pressure numerical expression is a calculation formula for calculating the pressure numerical value. The pressure numerical value is the actual output value of the pressure sensor. Optionally, the pressure sensor in the embodiment of the present invention is an optical fiber sensor. The principle of the optical fiber sensor is based on the principle of elastic deformation of the thin film. The pressure sensitive diaphragm is deformed under the action of external pressure, which causes the change in the interference spectrum. By measuring the interference spectrum, the pressure change on the pressure sensitive diaphragm can be measured. The pressure sensitivity coefficient is a numerical value used to describe the sensitivity of the pressure sensitive diaphragm to pressure changes. The wavelength change is the numerical value of the wavelength change in the pressure sensor, and the cavity length change is the change in the length of the resonant cavity in the pressure sensor. The effective radius is the part of the diaphragm radius that can produce effective deformation and thus affect the performance of the sensor when the pressure sensitive diaphragm senses external pressure.

[0126] S3. Acquire a detection time series of the pressure sensor based on a preset pressure detection frequency, wherein the time series includes a plurality of unit detection times, extract the unit detection times in sequence from the detection time series, and perform the following operations on the extracted unit detection times: acquire an initial signal based on the extracted unit detection time, perform a decomposition operation on the initial signal, and obtain a plurality of decomposed signals.

[0127] It can be understood that the pressure detection frequency is the frequency of the pressure sensor detection, the detection time series is the sequence composed of the time periods detected by the pressure sensor, the unit detection time is the time period of the unit time length obtained by the pressure sensor, and the sum of multiple unit detection times is the entire time length of scanning the patient detection area using the ultrasonic imager. The initial signal is the signal directly obtained when the pressure sensor detects the detection area.

[0128] It should be noted that the embodiment of the present invention is intended to use an ultrasonic imaging instrument to detect the detection area of ​​the patient. During the detection process, it is necessary to use a probe to closely contact the detection area coated with a dressing and use ultrasonic imaging. However, when using a pressure sensor to control the position of the probe, due to various normal physiological phenomena such as the patient's breathing and heartbeat, strong noise will be generated in the pressure sensor's detection pressure, resulting in the pressure sensor being unable to directly obtain accurate detection results. Therefore, it is necessary to reduce the noise of the signal detected by the pressure sensor.

[0129] Furthermore, performing a decomposition operation on the initial signal to obtain a plurality of decomposed signals includes:

[0130] Based on the extracted initial signal, an extreme value point sequence in the extracted initial signal is obtained, wherein the extreme value point sequence includes a plurality of maximum value points and a plurality of minimum value points, extreme value points are sequentially extracted from the extreme value point sequence, and the following operations are performed on the extracted extreme value points:

[0131] Based on the extracted extreme point, an adjacent extreme point is obtained, wherein the adjacent extreme point is the next extreme point adjacent to the extracted extreme point in the extreme point sequence, and an adjacent local mean is calculated according to the extracted extreme point and the adjacent extreme point, wherein the calculation formula of the adjacent local mean is:

[0132]

[0133] in, is the adjacent local mean, represents the time corresponding to the adjacent extreme point, represents the time corresponding to the extracted extreme point, represents the median value corresponding to the adjacent local means, represents the initial signal, represents the time variable in the initial signal;

[0134] Aggregating multiple adjacent local means to obtain an adjacent local mean sequence, and obtaining a weighted mean sequence based on the adjacent local mean sequence and a pre-constructed weighted mean method, wherein the time corresponding to the weighted mean in the weighted mean sequence corresponds one-to-one to the time corresponding to the extreme point in the extreme point sequence;

[0135] A mean curve is constructed based on a weighted mean sequence, and an iterative operation is performed on an initial signal using the mean curve to obtain a plurality of decomposed signals, wherein the decomposed signal of each of the plurality of decomposed signals is a basic mode function.

[0136] It can be understood that the extreme point sequence is a sequence of extreme points sorted in time series, the adjacent local means are data values ​​that can represent the data between two adjacent extreme points, and the adjacent local mean sequence is a sequence composed of all adjacent local means sorted in time order. In the embodiment of the present invention, the time corresponding to the adjacent local means is different from the time corresponding to the extracted extreme point. For example, assuming that the extracted time is And the time corresponding to the adjacent extreme points is , then the time corresponding to the adjacent local means is and The median value between .

[0137] It should be noted that the mean curve is a curve obtained by using a weighted mean sequence, and using the mean curve to perform an iterative operation on the initial signal is a basic operation in local wave decomposition, which is a prior art and will not be described in detail here. The decomposed signal is a signal component used to more concisely describe the original signal, and the basic mode function is a signal component of the decomposed signal, and the basic mode function needs to satisfy: in the entire data set, the number of extreme points and the number of zero crossings must be equal or differ by at most one, and at any time, the average value of the upper envelope defined by the local maximum and the lower envelope defined by the local minimum is zero, that is, the upper and lower envelopes are symmetrical about the time axis.

[0138] Specifically, the step of aggregating multiple adjacent local means to obtain an adjacent local mean sequence, and obtaining a weighted mean sequence based on the adjacent local mean sequence and a pre-constructed weighted mean method includes:

[0139] Adjacent local means are sequentially extracted from the adjacent local mean sequence, and the following operations are performed on the extracted adjacent local means:

[0140] The weighted mean of the time corresponding to the extreme point is calculated using the pre-constructed weighted mean formula and the extracted adjacent local means, wherein the weighted mean formula is:

[0141]

[0142] in, represents the weighted mean of the moments corresponding to the extracted extreme points, represents the previous moment adjacent to the moment corresponding to the extracted extreme point, represents the extracted adjacent local mean, represents the previous adjacent local mean adjacent to the extracted adjacent local mean;

[0143] Aggregate multiple weighted means to obtain a sequence of weighted means.

[0144] It can be understood that the weighted mean formula is a formula for calculating the weighted mean, the weighted mean is a numerical value used to describe the local mean at the moment corresponding to the extreme point, and the weighted mean sequence is a sequence of multiple weighted means in chronological order.

[0145] It should be noted that the time series corresponding to each weighted mean in the weighted mean sequence is the same as the time series corresponding to the extreme point. For example, assuming that the extracted adjacent local means are ,and The adjacent local means are , and in There is and only , is the time corresponding to the extreme point sequence, so the time corresponding to the weighted mean is also , instead of The median between The median value between .

[0146] It is understandable that, in the embodiment of the present invention, the above method can optimize the value of the time corresponding to the extreme point, thereby improving the accuracy of signal analysis and providing a basis for subsequent signal decomposition.

[0147] S4. Extract decomposed signals from the multiple decomposed signals in sequence, and perform the following operations on the extracted decomposed signals: use a pre-constructed relationship value formula to calculate the relationship value between the extracted decomposed signal and the initial signal, obtain a local noise reduction signal based on the relationship value, perform a correction operation on the local noise reduction signal, and obtain a local calibration signal.

[0148] Specifically, the acquiring the local noise reduction signal based on the relationship value includes:

[0149] Comparing the relationship value with a preset relationship threshold;

[0150] If the relationship value is less than the relationship threshold, a symmetric decomposition operation is performed on the extracted decomposition signal to obtain a local noise reduction signal;

[0151] Otherwise, it is confirmed that the decomposed signal corresponding to the relationship value is a local noise reduction signal.

[0152] Specifically, the relationship value formula is a relationship formula used to describe the degree of association between the decomposed signal and the initial signal. Optionally, the embodiment of the present invention uses the Pearson formula as the relationship value formula. This formula is a prior art, so it will not be repeated here. The relationship value is a numerical value used to describe the degree of association between the decomposed signal and the initial signal. The relationship threshold is a threshold at which the degree of association between the decomposed signal and the initial signal is considered to be high enough. When the relationship value is less than the relationship threshold, it is considered that the decomposed signal corresponding to the relationship value includes more noise, and the decomposed signal corresponding to the relationship value needs to be denoised again. The local noise reduction signal is the decomposed signal after noise reduction obtained according to the relationship value. Symmetric decomposition is a technology in the prior art that can reduce the noise of the signal. This technology is a prior art and will not be repeated here.

[0153] It should be noted that after the initial signal is decomposed into multiple decomposed signals, the multiple decomposed signals will cause the final pressure sensing signal to be offset due to background DC and amplitude-phase imbalance. This offset includes scaling, movement, rotation, etc. The correction operation in the embodiment of the present invention is to perform inverse transformation processing on these phenomena. Since there are many methods for implementing the correction operation in the prior art, the embodiment of the present invention will not be repeated here.

[0154] S5. Acquire the pressure value corresponding to the extracted unit detection time based on multiple local calibration signals, and after confirming that the pressure value is within a preset pressure range, acquire unit image data using a detector and an imaging processing unit.

[0155] Specifically, after confirming that the pressure value is within a preset pressure range, the process includes:

[0156] Get the minimum pressure value and the maximum pressure value based on the pressure range;

[0157] Compare the pressure value with the minimum pressure value;

[0158] If the pressure value is less than the minimum pressure value, the positioning processing unit is used to obtain a boost correction path, the detector is transported to a pre-constructed correction area based on the boost correction path and the guide rail, and the step of obtaining a detection time sequence of the pressure sensor based on a preset pressure detection frequency is returned;

[0159] If the pressure value is greater than or equal to the minimum pressure value, comparing the pressure value with the maximum pressure value;

[0160] If the pressure value is greater than the maximum pressure value, the positioning processing unit is used to obtain a decompression correction path, the detector is transported to the correction area based on the decompression correction path and the guide rail, and the step of obtaining the detection time sequence of the pressure sensor based on the preset pressure detection frequency is returned;

[0161] If the pressure value is less than or equal to the maximum pressure value, it is confirmed that the pressure value is within the pressure range.

[0162] It is understandable that the pressure interval is a preset interval in which the detector can correctly detect the pressure at the patient's eyelid. The minimum pressure value is the minimum pressure value in the pressure interval, and the maximum pressure value is the maximum pressure value in the pressure interval. When the pressure value is inside the pressure interval, it is considered that the position of the detector can complete the ultrasonic detection more accurately. When the pressure value is outside the pressure interval, it is necessary to use the positioning processing unit to move the detector so that the pressure between the detector and the detection area is finally within the pressure interval. Therefore, the correction area is the area that needs to be detected by the detector after correction by the basic positioning processing unit. The correction area is also the orbital area of ​​the patient with the dressing. The decompression correction path is the path that the detector needs to move when reducing the pressure between the detector and the detection area. The path that the detector needs to move is realized by the guide rail. Similarly, the pressurization correction path is the path that the detector needs to move when increasing the pressure between the detector and the detection area.

[0163] S6. Aggregate multiple unit image data to obtain an image data set, and construct an optic nerve sheath image using the imaging processing unit and the image data set.

[0164] It can be understood that the embodiment of the present invention aims to use an ultrasonic imager to detect the diameter of the optic nerve sheath to determine whether the patient's intracranial pressure is abnormal. The unit image data is the image data generated corresponding to the extracted unit detection time. The imaging processing unit generates the patient's optic nerve sheath image by reconstructing the image data set, thereby obtaining the optic nerve sheath diameter through the optic nerve sheath image.

[0165] S7. Obtain the optic nerve sheath diameter based on the optic nerve sheath image, and obtain a first detection report based on a preset healthy diameter range and the optic nerve sheath diameter.

[0166] Specifically, the obtaining of the first detection report based on the preset healthy diameter interval and the optic nerve sheath diameter includes:

[0167] comparing the optic nerve sheath diameter with a healthy diameter interval;

[0168] If the optic nerve sheath diameter is outside the healthy diameter range, it is confirmed that the patient's intracranial pressure is abnormal, and a brain abnormality reminder is generated based on the imaging processing unit;

[0169] If the optic nerve sheath diameter is within the healthy diameter range, it is confirmed that the patient's intracranial pressure is normal, and a normal brain reminder is generated based on the imaging processing unit;

[0170] Obtain the first test report based on abnormal brain reminder or normal brain reminder.

[0171] It is understandable that the optic nerve sheath image is an image of the optic nerve sheath part of the patient obtained by using an ultrasonic imager, and the optic nerve sheath diameter is the diameter of the optic nerve sheath on the optic nerve sheath image. The first test report is a report for reporting the test results of the optic nerve sheath and intracranial pressure. The healthy diameter interval is the interval corresponding to the healthy diameter of the optic nerve sheath. When the diameter of the optic nerve sheath is within the healthy interval, it means that the patient's intracranial pressure is normal. When the diameter of the optic nerve sheath is outside the healthy interval, it means that the patient's intracranial pressure is abnormal, and the intracranial pressure is non-invasively detected by the ultrasonic imager. When the intracranial pressure is abnormal, it will have an adverse effect on the cranial nerves.

[0172] S8. Construct a second electrooculogram detection unit, wherein the second electrooculogram detection unit includes: a stimulation unit, a signal amplification unit and an information processing unit. The second electrooculogram detection unit is used to obtain a second detection report, and a cranial nerve detection report is obtained according to the first detection report and the second detection report. Based on the cranial nerve detection report, intelligent detection of cranial nerves based on ocular nerves is completed.

[0173] It is understandable that the second electrooculogram detection unit is a unit that detects the patient's eye response through an external stimulation signal, and thus indirectly detects the patient's brain nerves. In the embodiment of the present invention, the intracranial pressure has been detected by detecting the diameter of the optic nerve sheath, but judging whether the patient's brain nerves are abnormal by only this method has a large error. For example, the influence relationship between the optic nerve sheath diameter and the intracranial pressure is different at different ages. Therefore, on the basis of detecting the patient's intracranial pressure, the second electrooculogram detection unit is used to perform further detection on the patient, which can more accurately realize non-invasive detection of the patient's brain nerves.

[0174] It is understandable that the stimulation unit is a unit for releasing a stimulation signal for stimulating the patient's ocular nerve. The signal amplification unit is a unit for amplifying the physiological signal generated by the patient in response to the stimulation signal. This is because the changes in the physiological state of the eye and its physiological signals are weak, and using the signal amplification unit to amplify the physiological signal is conducive to more accurately capturing the patient's physiological signal, thereby improving the accuracy of the detection. The information processing unit is a unit that processes the physiological signal and generates corresponding test results. The second test report is the test result obtained after the patient is tested using the second electrooculographic detection unit. The cranial nerve test report is a test result report of the patient's cranial nerves given after combining the first test report and the second test report.

[0175] Further, after confirming that the patient has completed the pretreatment, the number of electrooculogram detections is obtained based on the stimulation unit, wherein the number of electrooculogram detections is greater than or equal to 1, a plurality of detection times are obtained based on the number of electrooculogram detections, the detection times are sequentially extracted from the plurality of detection times, and the following operations are performed on the extracted detection times:

[0176] Starting the second electrooculogram detection unit based on the extracted detection time, after confirming that the second electrooculogram detection unit is started, acquiring the electrode coordinates and the ground electrode coordinates based on the stimulation unit, after confirming that the patient is located in the preset electrooculogram detection area based on the information processing unit, the electrode coordinates and the ground electrode coordinates, acquiring the interference impedance between the electrode and the patient based on the electrode coordinates and the ground electrode coordinates, after confirming that the interference impedance is within a preset negligible impedance interval, generating a stimulation signal using the stimulation unit, wherein the negligible impedance interval is greater than or equal to 0 ohms and less than or equal to 10 ohms;

[0177] Using an amplification unit to receive a physiological signal corresponding to the stimulation signal, and amplifying the physiological signal to obtain an amplified signal, sending the amplified signal to an information processing unit, and using the information processing unit and the amplified signal to obtain a unit diagnosis curve graph;

[0178] A plurality of unit diagnostic curve graphs are aggregated to obtain a diagnostic atlas, and a second test report is obtained based on the diagnostic atlas.

[0179] It is understandable that before executing the second electrooculographic detection unit on the patient, in order to make the detection result more accurate, it is optionally necessary to apply a dressing on the patient's eyes and dilate the patient's pupils again, so that when the patient's eye condition is detected, the detection result will not be affected by the patient's normal physiological reactions such as blinking and avoiding. After completing the pretreatment, the medical staff will issue a confirmation instruction to confirm that the patient has completed the pretreatment according to the confirmation instruction.

[0180] It should be noted that the number of electrooculographic detections is the number of times the patient is detected. In the process of detecting the patient's eye state, multiple detections are required to avoid detection errors. This is a common technical means in daily life. In the detection process, multiple detections are required for each of the different detection items. In the embodiment of the present invention, no unique limitation is made to the detection items, but in the embodiment of the present invention, each different type of stimulation signal corresponds to a unique detection item.

[0181] Specifically, the detection time is the preset time for using the second electrooculogram detection unit to detect the test item on the patient. The electrode coordinates and the ground electrode coordinates are the coordinates of the electrode and the ground electrode used to receive the patient's physiological signals. Since the electrode and the ground electrode need to be in contact with the patient's skin, the relative position of the patient and the instrument corresponding to the second electrooculogram detection unit can be obtained through the electrode coordinates, the ground electrode coordinates and the pre-constructed coordinate system, so it can be determined whether the patient is in a position where he can be detected normally. The electrooculogram detection area is the corresponding position when the patient can be detected normally. The interference impedance is the impedance detected by the electrode and the ground electrode. In the embodiment of the present invention, the interference impedance is limited. This is because if an excessively large impedance is detected, it will not only interfere with the detection results, but also cause harm to the patient. The negligible impedance interval is an interference impedance interval in which the interference impedance neither causes harm to the patient nor interferes with the detection results.

[0182] Furthermore, the physiological signal is a bioelectric signal generated by the patient's reaction after receiving the stimulation signal. For example, when the stimulation unit generates a flash signal, the stimulation unit will emit a flash to the patient, and the patient will have a series of physiological reactions to the flash after seeing the flash. The bioelectric signal generated by the series of physiological reactions is the physiological signal.

[0183] It is understandable that the amplified signal is a signal obtained by amplifying the physiological signal. Optionally, the amplification unit includes a basic waveform amplifier. This technology is existing technology and will not be described in detail here.

[0184] It should be noted that the unit diagnostic curve is a curve chart that converts physiological signals within the detection time into images. The unit diagnostic curve chart can express the characteristics of the patient's physiological signals after receiving the stimulation signal. By analyzing the unit diagnostic curve chart, the patient's ocular nerve state can be analyzed. Furthermore, the patient's brain nerve state can be indirectly detected through the ocular nerve state.

[0185] Furthermore, a plurality of stimulation signals are constructed by using the stimulation unit, wherein the plurality of stimulation signals are respectively: a graphic visual signal, a flash signal, a light on / off signal, a nystagmus image signal, and a visual acuity detection signal;

[0186] A detection item corresponding to the electrooculographic detection is acquired based on the information processing unit, and a stimulation signal corresponding to the detection item is extracted from a plurality of stimulation signals based on the detection item.

[0187] It is understandable that for different test items, the corresponding stimulation signals are different, and thus the physiological signals generated by the patient are different, and further, the unit diagnostic curve graphs are different. The embodiment of the present invention does not limit the type of each stimulation signal, so there are many possibilities for the diagnostic atlas. Exemplarily, in the embodiment of the present invention, in three tests, each stimulation signal given to the patient is a flash signal, then the diagnostic atlas is a set corresponding to the three unit diagnostic curve graphs. Since the combination results are various, they are not given one by one here.

[0188] It should be noted that the graphic visual signal is a signal that controls the corresponding detection device to display an image. The graphic visual signal is used to detect the patient's ability to recognize images. The flash signal is a signal that controls the corresponding detection device to emit a flash, which is used to detect the patient's reaction to light changes. The light removal signal is a device that controls the corresponding detection device to change from continuous light to continuous darkness. The light removal signal is used to detect whether the retinal light perception function is normal. The nystagmus image signal is a signal that controls the corresponding detection device to display an image following eye movement. The nystagmus image signal is a signal used to detect whether the patient's eye movement is normal. The visual acuity detection signal is a signal that controls the corresponding device to display an image corresponding to the visual acuity detection.

[0189] The present invention is to solve the problem described in the background technology. The present invention obtains an ultrasonic imager, wherein the ultrasonic imager includes: a pressure sensor, a detector, a guide rail positioning unit and an imaging processing unit, wherein the pressure sensor is arranged on the detector, the guide rail positioning unit includes a guide rail and a positioning processing unit, the detector is slidably arranged on the guide rail, and the ultrasonic imager performs a pre-calibration operation on the pressure sensor. After confirming that the pressure sensor has completed the calibration, the pressure sensor and the detector are transported to a pre-constructed detection area based on the guide rail and the positioning processing unit, wherein the detection area is the patient's eye socket area with a dressing. In the embodiment of the present invention, the pressure detected by the pressure sensor is the pressure applied by the detector, and the pressure sensor is used to detect whether the pressure applied by the detector in the detection area is reasonable. At the same time, the embodiment of the present invention controls the position of the detector through the guide rail and the positioning processing unit, and uses the pressure sensor to control the distance between the detector and the patient's eyelid. The pre-calibration operation on the pressure sensor improves the accuracy of the detection. A detection time series of a pressure sensor is obtained based on a preset pressure detection frequency, wherein the time series includes a plurality of unit detection times, the unit detection times are extracted from the detection time series in sequence, and the following operations are performed on the extracted unit detection times: an initial signal is obtained based on the extracted unit detection time, a decomposition operation is performed on the initial signal to obtain a plurality of decomposed signals, decomposed signals are extracted from the plurality of decomposed signals in sequence, and the following operations are performed on the extracted decomposed signals: a relationship value between the extracted decomposed signal and the initial signal is calculated using a pre-constructed relationship value formula, a local noise reduction signal is obtained based on the relationship value, a correction operation is performed on the local noise reduction signal to obtain a local calibration signal. The embodiment of the present invention performs noise reduction on the initial signal within each unit detection time of the pressure sensor to process the strong noise generated by the pressure sensor due to various normal physiological phenomena such as the patient's breathing and heartbeat, thereby improving the accuracy of detection. A pressure value corresponding to the extracted unit detection time is obtained based on multiple local calibration signals. After confirming that the pressure value is within a preset pressure range, unit image data is obtained using a detector and an imaging processing unit, and multiple unit image data are aggregated to obtain an image data set. An optic nerve sheath image is constructed using the imaging processing unit and the image data set. The optic nerve sheath diameter is obtained based on the optic nerve sheath image. A first detection report is obtained based on a preset healthy diameter range and the optic nerve sheath diameter, and a second electrooculogram detection unit is constructed, wherein the second electrooculogram detection unit includes: a stimulation unit, a signal amplification unit, and an information processing unit. A second detection report is obtained using the second electrooculogram detection unit, and a cranial nerve detection report is obtained based on the first detection report and the second detection report. Based on the cranial nerve detection report, intelligent detection of cranial nerves based on ocular nerves is completed.In an embodiment of the present invention, an optic nerve sheath image is constructed using multiple unit image data, and the purpose is to use an ultrasonic imager to detect the diameter of the optic nerve sheath to determine whether the patient's intracranial pressure is abnormal, thereby realizing non-invasive detection of intracranial pressure. At the same time, the embodiment of the present invention also uses physiological signals around the eyes to assist in the detection of brain nerves, obtain a second detection report, and comprehensively implement accurate detection of the patient's brain nerves based on the second detection report and the first detection report. Therefore, the present invention can use a pressure sensor to control the detector of the ultrasonic imager to detect the diameter of the optic nerve sheath, and combine it with the detection of physiological signals when the eyes are stimulated to jointly realize non-invasive detection of brain nerves.

[0190] like Figure 2 , which is a functional module diagram of an intelligent detection system for realizing cranial nerves by using ophthalmic nerves provided by an embodiment of the present invention.

[0191] The intelligent detection system 100 for realizing cranial nerves by ophthalmic nerves of the present invention can be installed in an electronic device. According to the functions realized, the intelligent detection system 100 for realizing cranial nerves by ophthalmic nerves may include a sensor pre-adjustment module 101, a signal decomposition module 102, a signal processing module 103 and a report generation module 104. The module of the present invention may also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and is stored in the memory of the electronic device.

[0192] The sensor pre-adjustment module 101 is used to obtain an ultrasonic imager, wherein the ultrasonic imager includes: a pressure sensor, a detector, a guide rail positioning unit and an imaging processing unit, wherein the pressure sensor is arranged on the detector, the guide rail positioning unit includes a guide rail and a positioning processing unit, the detector is slidably arranged on the guide rail, the pressure detected by the pressure sensor is the pressure applied by the detector, and the pressure sensor is used to detect whether the pressure applied by the detector in the detection area is reasonable;

[0193] Performing a pre-calibration operation on the pressure sensor based on an ultrasonic imager, after confirming that the pressure sensor has completed calibration, transporting the pressure sensor and the detector to a pre-constructed detection area based on a guide rail and a positioning processing unit, wherein the detection area is an orbital area of ​​a patient provided with a dressing;

[0194] The signal decomposition module 102 is used to obtain a detection time series of the pressure sensor based on a preset pressure detection frequency, wherein the time series includes a plurality of unit detection times, and the unit detection times are sequentially extracted from the detection time series, and the following operations are performed on each of the extracted unit detection times:

[0195] Acquire an initial signal based on the extracted unit detection time, and perform a decomposition operation on the initial signal to obtain a plurality of decomposed signals;

[0196] The signal processing module 103 is used to extract decomposed signals from the multiple decomposed signals in sequence, and perform the following operations on the extracted decomposed signals:

[0197] Calculating the relationship value between the extracted decomposition signal and the initial signal using a pre-constructed relationship value formula, obtaining a local noise reduction signal based on the relationship value, and performing a correction operation on the local noise reduction signal to obtain a local calibration signal;

[0198] Wherein, obtaining the local noise reduction signal based on the relationship value includes:

[0199] Comparing the relationship value with a preset relationship threshold;

[0200] If the relationship value is less than the relationship threshold, a symmetric decomposition operation is performed on the extracted decomposition signal to obtain a local noise reduction signal;

[0201] Otherwise, confirming that the decomposed signal corresponding to the relationship value is a local noise reduction signal;

[0202] Acquire the pressure value corresponding to the extracted unit detection time based on multiple local calibration signals, and after confirming that the pressure value is within a preset pressure range, acquire unit image data using a detector and an imaging processing unit;

[0203] The report generation module 104 is used to aggregate multiple unit image data to obtain an image data set, and construct an optic nerve sheath image using the imaging processing unit and the image data set;

[0204] Obtaining the optic nerve sheath diameter based on the optic nerve sheath image, and obtaining a first detection report based on a preset healthy diameter interval and the optic nerve sheath diameter;

[0205] Constructing a second electrooculogram detection unit, wherein the second electrooculogram detection unit includes: a stimulation unit, a signal amplification unit and an information processing unit;

[0206] Obtaining a second detection report using a second electrooculographic detection unit;

[0207] A cranial nerve detection report is obtained according to the first detection report and the second detection report, and intelligent detection of the cranial nerves based on the ocular nerves is completed based on the cranial nerve detection report.

[0208] In detail, the modules in the intelligent detection system 100 for realizing brain nerves by the eye nerves in the embodiment of the present invention are used in the same manner as described above. Figure 1 The technical means for realizing the intelligent detection method of cranial nerves by the eye nerve described in the text are the same and can produce the same technical effects, so I will not go into details here.

[0209] like Figure 3, is a schematic diagram of the structure of an electronic device for implementing an intelligent detection method of eye nerves and cranial nerves provided by an embodiment of the present invention.

[0210] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a program for an intelligent detection method for implementing brain nerves by using eye nerves.

[0211] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the program of the intelligent detection method of the eye nerve to realize the brain nerve, but also can be used to temporarily store data that has been output or is to be output.

[0212] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as an intelligent detection method program for brain nerves using the eye nerve, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0213] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0214] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0215] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0216] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0217] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0218] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0219] The program of the intelligent detection method of the eye nerve to realize the brain nerve stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0220] Acquire an ultrasonic imager, wherein the ultrasonic imager comprises: a pressure sensor, a detector, a guide rail positioning unit and an imaging processing unit, wherein the pressure sensor is arranged on the detector, the guide rail positioning unit comprises a guide rail and a positioning processing unit, the detector is slidably arranged on the guide rail, the pressure detected by the pressure sensor is the pressure applied by the detector, and whether the pressure applied by the detector in the detection area is reasonable is detected by the pressure sensor;

[0221] Performing a pre-calibration operation on the pressure sensor based on an ultrasonic imager, after confirming that the pressure sensor has completed calibration, transporting the pressure sensor and the detector to a pre-constructed detection area based on a guide rail and a positioning processing unit, wherein the detection area is an orbital area of ​​a patient provided with a dressing;

[0222] A detection time sequence of the pressure sensor is obtained based on a preset pressure detection frequency, wherein the time sequence includes a plurality of unit detection times, the unit detection times are sequentially extracted from the detection time sequence, and the following operations are performed on the extracted unit detection times:

[0223] An initial signal is acquired based on the extracted unit detection time, a decomposition operation is performed on the initial signal to obtain a plurality of decomposed signals, decomposed signals are sequentially extracted from the plurality of decomposed signals, and the following operations are performed on the extracted decomposed signals:

[0224] Calculating the relationship value between the extracted decomposition signal and the initial signal using a pre-constructed relationship value formula, obtaining a local noise reduction signal based on the relationship value, and performing a correction operation on the local noise reduction signal to obtain a local calibration signal;

[0225] Wherein, obtaining the local noise reduction signal based on the relationship value includes:

[0226] Comparing the relationship value with a preset relationship threshold;

[0227] If the relationship value is less than the relationship threshold, a symmetric decomposition operation is performed on the extracted decomposition signal to obtain a local noise reduction signal;

[0228] Otherwise, confirming that the decomposed signal corresponding to the relationship value is a local noise reduction signal;

[0229] Acquire the pressure value corresponding to the extracted unit detection time based on multiple local calibration signals, and after confirming that the pressure value is within a preset pressure range, acquire unit image data using a detector and an imaging processing unit;

[0230] Aggregating multiple unit image data to obtain an image data set, and constructing an optic nerve sheath image using an imaging processing unit and the image data set;

[0231] Obtaining the optic nerve sheath diameter based on the optic nerve sheath image, and obtaining a first detection report based on a preset healthy diameter interval and the optic nerve sheath diameter;

[0232] Constructing a second electrooculogram detection unit, wherein the second electrooculogram detection unit includes: a stimulation unit, a signal amplification unit and an information processing unit;

[0233] Obtaining a second detection report using a second electrooculographic detection unit;

[0234] A cranial nerve detection report is obtained according to the first detection report and the second detection report, and intelligent detection of the cranial nerves based on the ocular nerves is completed based on the cranial nerve detection report.

[0235] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0236] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0237] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0238] Acquire an ultrasonic imager, wherein the ultrasonic imager comprises: a pressure sensor, a detector, a guide rail positioning unit and an imaging processing unit, wherein the pressure sensor is arranged on the detector, the guide rail positioning unit comprises a guide rail and a positioning processing unit, the detector is slidably arranged on the guide rail, the pressure detected by the pressure sensor is the pressure applied by the detector, and whether the pressure applied by the detector in the detection area is reasonable is detected by the pressure sensor;

[0239] Performing a pre-calibration operation on the pressure sensor based on an ultrasonic imager, after confirming that the pressure sensor has completed calibration, transporting the pressure sensor and the detector to a pre-constructed detection area based on a guide rail and a positioning processing unit, wherein the detection area is an orbital area of ​​a patient provided with a dressing;

[0240] A detection time sequence of the pressure sensor is obtained based on a preset pressure detection frequency, wherein the time sequence includes a plurality of unit detection times, the unit detection times are sequentially extracted from the detection time sequence, and the following operations are performed on the extracted unit detection times:

[0241] An initial signal is acquired based on the extracted unit detection time, a decomposition operation is performed on the initial signal to obtain a plurality of decomposed signals, decomposed signals are sequentially extracted from the plurality of decomposed signals, and the following operations are performed on the extracted decomposed signals:

[0242] Calculating the relationship value between the extracted decomposition signal and the initial signal using a pre-constructed relationship value formula, obtaining a local noise reduction signal based on the relationship value, and performing a correction operation on the local noise reduction signal to obtain a local calibration signal;

[0243] Wherein, obtaining the local noise reduction signal based on the relationship value includes:

[0244] Comparing the relationship value with a preset relationship threshold;

[0245] If the relationship value is less than the relationship threshold, a symmetric decomposition operation is performed on the extracted decomposition signal to obtain a local noise reduction signal;

[0246] Otherwise, confirming that the decomposed signal corresponding to the relationship value is a local noise reduction signal;

[0247] Acquire the pressure value corresponding to the extracted unit detection time based on multiple local calibration signals, and after confirming that the pressure value is within a preset pressure range, acquire unit image data using a detector and an imaging processing unit;

[0248] Aggregating multiple unit image data to obtain an image data set, and constructing an optic nerve sheath image using an imaging processing unit and the image data set;

[0249] Obtaining the optic nerve sheath diameter based on the optic nerve sheath image, and obtaining a first detection report based on a preset healthy diameter interval and the optic nerve sheath diameter;

[0250] Constructing a second electrooculogram detection unit, wherein the second electrooculogram detection unit includes: a stimulation unit, a signal amplification unit and an information processing unit;

[0251] Obtaining a second detection report using a second electrooculographic detection unit;

[0252] Obtain a cranial nerve detection report based on the first detection report and the second detection report, complete intelligent detection of the cranial nerves based on the ophthalmic nerves based on the cranial nerve detection report, and complete intelligent detection of the cranial nerves based on the ophthalmic nerves based on the detection report.

[0253] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0254] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0255] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0256] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0257] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.

[0258] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent detection method for cranial nerves using ophthalmic nerves, characterized in that: The method comprises: Acquire an ultrasonic imager, wherein the ultrasonic imager comprises: a pressure sensor, a detector, a guide rail positioning unit and an imaging processing unit, wherein the pressure sensor is arranged on the detector, the guide rail positioning unit comprises a guide rail and a positioning processing unit, the detector is slidably arranged on the guide rail, the pressure detected by the pressure sensor is the pressure applied by the detector, and whether the pressure applied by the detector in the detection area is reasonable is detected by the pressure sensor; Performing a pre-calibration operation on the pressure sensor based on an ultrasonic imager, after confirming that the pressure sensor has completed calibration, transporting the pressure sensor and the detector to a pre-constructed detection area based on a guide rail and a positioning processing unit, wherein the detection area is an orbital area of ​​a patient provided with a dressing; A detection time sequence of the pressure sensor is obtained based on a preset pressure detection frequency, wherein the time sequence includes a plurality of unit detection times, the unit detection times are sequentially extracted from the detection time sequence, and the following operations are performed on the extracted unit detection times: An initial signal is acquired based on the extracted unit detection time, a decomposition operation is performed on the initial signal to obtain a plurality of decomposed signals, decomposed signals are sequentially extracted from the plurality of decomposed signals, and the following operations are performed on the extracted decomposed signals: Calculating the relationship value between the extracted decomposition signal and the initial signal using a pre-constructed relationship value formula, obtaining a local noise reduction signal based on the relationship value, and performing a correction operation on the local noise reduction signal to obtain a local calibration signal; Wherein, obtaining the local noise reduction signal based on the relationship value includes: Comparing the relationship value with a preset relationship threshold; If the relationship value is less than the relationship threshold, a symmetric decomposition operation is performed on the extracted decomposition signal to obtain a local noise reduction signal; Otherwise, confirming that the decomposed signal corresponding to the relationship value is a local noise reduction signal; Acquire the pressure value corresponding to the extracted unit detection time based on multiple local calibration signals, and after confirming that the pressure value is within a preset pressure range, acquire unit image data using a detector and an imaging processing unit; Aggregating multiple unit image data to obtain an image data set, and constructing an optic nerve sheath image using an imaging processing unit and the image data set; Obtaining the optic nerve sheath diameter based on the optic nerve sheath image, and obtaining a first detection report based on a preset healthy diameter interval and the optic nerve sheath diameter; Constructing a second electrooculogram detection unit, wherein the second electrooculogram detection unit includes: a stimulation unit, a signal amplification unit and an information processing unit; Obtaining a second detection report using a second electrooculographic detection unit; A cranial nerve detection report is obtained according to the first detection report and the second detection report, and intelligent detection of the cranial nerves based on the ocular nerves is completed based on the cranial nerve detection report.

2. The method for realizing intelligent detection of cranial nerves by using ophthalmic nerves according to claim 1, characterized in that: The pre-calibration operation of the pressure sensor based on the ultrasonic imager comprises: The pressure sensor is introduced into a pre-built standard load measurement chamber, and a plurality of preset load sets are obtained based on the standard load measurement chamber, wherein each of the plurality of preset load sets includes a plurality of preset loads, and the magnitude of each of the plurality of preset loads is different; Preset load sets are sequentially extracted from the plurality of preset load sets, and the following operations are performed on the extracted preset load sets: Preset loads are extracted from the preset load set in sequence, and the following operations are performed on the extracted preset loads: Receiving a pressure measurement signal based on the pressure sensor, obtaining a pressure measurement value corresponding to the pressure sensor based on the pressure measurement signal, comparing the pressure measurement value with the size of a preset load, and if the pressure measurement value is equal to the preset load, confirming that the pressure sensor is normal, otherwise, confirming that the pressure sensor is calibrated using a pre-built adjustment module, and returning to the step of receiving a pressure measurement signal based on the pressure sensor; Summarizing the pressure measurement values ​​corresponding to each preset load in the plurality of preset loads to obtain a pressure measurement value set, constructing a calibration curve based on the pressure measurement value set and the extracted preset load set, and determining a unit compensation coefficient corresponding to the extracted preset load set based on the calibration curve; The unit compensation coefficient corresponding to each preset load set in the plurality of preset load sets is aggregated to obtain a unit compensation coefficient set, and a compensation coefficient is obtained based on the unit compensation coefficient set, wherein the compensation coefficient is an average value of all unit compensation coefficients in the unit compensation coefficient set.

3. The method for realizing intelligent detection of cranial nerves by using ophthalmic nerves as claimed in claim 2, characterized in that: The step of constructing a calibration curve based on the pressure measurement value set and the extracted preset load set, and determining a unit compensation coefficient corresponding to the extracted preset load set based on the calibration curve, includes: Constructing a plane rectangular coordinate system, wherein the horizontal axis of the plane rectangular coordinate system is the preset load and the vertical axis is the pressure measurement value; A calibration curve is obtained by fitting the pressure measurement value set, the extracted preset load set and the plane rectangular coordinate system, a linear fitting operation is performed on the calibration curve using a pre-constructed least squares method to obtain a pressure working straight line, and a unit compensation coefficient is obtained based on the pressure working straight line.

4. The method for realizing intelligent detection of cranial nerves by using ophthalmic nerves as claimed in claim 3, characterized in that: After confirming that the pressure sensor has completed calibration, the method includes: A pressure numerical expression of the pressure sensor is determined based on the compensation coefficient, wherein the pressure numerical expression is: in, Indicates the pressure value output by the pressure sensor. represents the pressure sensitivity coefficient of the pressure sensor, and , Indicates the wavelength change of the pressure sensor, represents the change in cavity length of the resonant cavity of the pressure sensor, represents the compensation coefficient, represents the Young's modulus of the pressure sensitive diaphragm, Indicates the thickness of the pressure sensitive diaphragm, represents the effective radius of the pressure sensitive diaphragm, represents the Poisson's ratio of the pressure sensitive diaphragm; The calibration of the pressure sensor is confirmed to be completed based on the pressure numerical expression.

5. The method for realizing intelligent detection of cranial nerves by using ophthalmic nerves according to claim 1, characterized in that: The performing a decomposition operation on the initial signal to obtain a plurality of decomposed signals comprises: Based on the extracted initial signal, an extreme value point sequence in the extracted initial signal is obtained, wherein the extreme value point sequence includes a plurality of maximum value points and a plurality of minimum value points, extreme value points are sequentially extracted from the extreme value point sequence, and the following operations are performed on the extracted extreme value points: Based on the extracted extreme point, an adjacent extreme point is obtained, wherein the adjacent extreme point is the next extreme point adjacent to the extracted extreme point in the extreme point sequence, and an adjacent local mean is calculated according to the extracted extreme point and the adjacent extreme point, wherein the calculation formula of the adjacent local mean is: in, is the adjacent local mean, represents the time corresponding to the adjacent extreme point, represents the time corresponding to the extracted extreme point, represents the median value corresponding to the adjacent local means, represents the initial signal, represents the time variable in the initial signal; Aggregating multiple adjacent local means to obtain an adjacent local mean sequence, and obtaining a weighted mean sequence based on the adjacent local mean sequence and a pre-constructed weighted mean method, wherein the time corresponding to the weighted mean in the weighted mean sequence corresponds one-to-one to the time corresponding to the extreme point in the extreme point sequence; A mean curve is constructed based on a weighted mean sequence, and an iterative operation is performed on an initial signal using the mean curve to obtain a plurality of decomposed signals, wherein the decomposed signal of each of the plurality of decomposed signals is a basic mode function.

6. The method for realizing intelligent detection of cranial nerves by using ophthalmic nerves as claimed in claim 5, characterized in that: The step of aggregating multiple adjacent local means to obtain an adjacent local mean sequence, and obtaining a weighted mean sequence based on the adjacent local mean sequence and a pre-constructed weighted mean method includes: Adjacent local means are sequentially extracted from the adjacent local mean sequence, and the following operations are performed on the extracted adjacent local means: The weighted mean of the time corresponding to the extreme point is calculated using the pre-constructed weighted mean formula and the extracted adjacent local means, wherein the weighted mean formula is: in, represents the weighted mean of the moments corresponding to the extracted extreme points, represents the previous moment adjacent to the moment corresponding to the extracted extreme point, represents the extracted adjacent local mean, represents the previous adjacent local mean adjacent to the extracted adjacent local mean; Aggregate multiple weighted means to obtain a sequence of weighted means.

7. The method for realizing intelligent detection of cranial nerves by using ophthalmic nerves according to claim 1, characterized in that: After confirming that the pressure value is within the preset pressure range, the method includes: Get the minimum pressure value and the maximum pressure value based on the pressure range; Compare the pressure value with the minimum pressure value; If the pressure value is less than the minimum pressure value, the positioning processing unit is used to obtain a boost correction path, the detector is transported to a pre-constructed correction area based on the boost correction path and the guide rail, and the step of obtaining a detection time sequence of the pressure sensor based on a preset pressure detection frequency is returned; If the pressure value is greater than or equal to the minimum pressure value, comparing the pressure value with the maximum pressure value; If the pressure value is greater than the maximum pressure value, the positioning processing unit is used to obtain a decompression correction path, the detector is transported to the correction area based on the decompression correction path and the guide rail, and the step of obtaining the detection time sequence of the pressure sensor based on the preset pressure detection frequency is returned; If the pressure value is less than or equal to the maximum pressure value, it is confirmed that the pressure value is within the pressure range.

8. The method for realizing intelligent detection of cranial nerves by using ophthalmic nerves according to claim 1, characterized in that: The obtaining of the first detection report based on the preset healthy diameter interval and the optic nerve sheath diameter includes: comparing the optic nerve sheath diameter with a healthy diameter interval; If the optic nerve sheath diameter is outside the healthy diameter range, it is confirmed that the patient's intracranial pressure is abnormal, and a brain abnormality reminder is generated based on the imaging processing unit; If the optic nerve sheath diameter is within the healthy diameter range, it is confirmed that the patient's intracranial pressure is normal, and a normal brain reminder is generated based on the imaging processing unit; Obtain the first test report based on abnormal brain reminder or normal brain reminder.

9. The method for realizing intelligent detection of cranial nerves by using ophthalmic nerves according to claim 1, characterized in that: The method of obtaining a second detection report by using a second electrooculographic detection unit includes: After confirming that the patient has completed the pretreatment, the number of electrooculogram detections is obtained based on the stimulation unit, wherein the number of electrooculogram detections is greater than or equal to 1, a plurality of detection times are obtained based on the number of electrooculogram detections, the detection times are sequentially extracted from the plurality of detection times, and the following operations are performed on the extracted detection times: Starting the second electrooculogram detection unit based on the extracted detection time, after confirming that the second electrooculogram detection unit is started, acquiring the electrode coordinates and the ground electrode coordinates based on the stimulation unit, after confirming that the patient is located in the preset electrooculogram detection area based on the information processing unit, the electrode coordinates and the ground electrode coordinates, acquiring the interference impedance between the electrode and the patient based on the electrode coordinates and the ground electrode coordinates, after confirming that the interference impedance is within a preset negligible impedance interval, generating a stimulation signal using the stimulation unit, wherein the negligible impedance interval is greater than or equal to 0 ohms and less than or equal to 10 ohms; Using an amplification unit to receive a physiological signal corresponding to the stimulation signal, and amplifying the physiological signal to obtain an amplified signal, sending the amplified signal to an information processing unit, and using the information processing unit and the amplified signal to obtain a unit diagnosis curve graph; A plurality of unit diagnostic curve graphs are aggregated to obtain a diagnostic atlas, and a second test report is obtained based on the diagnostic atlas.

10. The method for realizing intelligent detection of cranial nerves by using ophthalmic nerves according to claim 9, characterized in that: The step of generating a stimulation signal by using a stimulation unit comprises: Constructing a plurality of stimulation signals using a stimulation unit, wherein the plurality of stimulation signals are respectively: a graphic visual signal, a flash signal, a light on / off signal, a nystagmus image signal, and a visual acuity detection signal; A detection item corresponding to the electrooculographic detection is acquired based on the information processing unit, and a stimulation signal corresponding to the detection item is extracted from a plurality of stimulation signals based on the detection item.

11. An intelligent detection system for optic nerves to detect cranial nerves, characterized in that: The system comprises: A sensor pre-adjustment module is used to obtain an ultrasonic imager, wherein the ultrasonic imager includes: a pressure sensor, a detector, a guide rail positioning unit and an imaging processing unit, wherein the pressure sensor is arranged on the detector, the guide rail positioning unit includes a guide rail and a positioning processing unit, the detector is slidably arranged on the guide rail, the pressure detected by the pressure sensor is the pressure applied by the detector, and the pressure sensor is used to detect whether the pressure applied by the detector in the detection area is reasonable; Performing a pre-calibration operation on the pressure sensor based on an ultrasonic imager, after confirming that the pressure sensor has completed calibration, transporting the pressure sensor and the detector to a pre-constructed detection area based on a guide rail and a positioning processing unit, wherein the detection area is an orbital area of ​​a patient provided with a dressing; The signal decomposition module is used to obtain a detection time sequence of the pressure sensor based on a preset pressure detection frequency, wherein the time sequence includes a plurality of unit detection times, and the unit detection times are sequentially extracted from the detection time sequence, and the following operations are performed on the extracted unit detection times: Acquire an initial signal based on the extracted unit detection time, and perform a decomposition operation on the initial signal to obtain a plurality of decomposed signals; The signal processing module is used to extract decomposed signals from the multiple decomposed signals in sequence, and perform the following operations on the extracted decomposed signals: Calculating the relationship value between the extracted decomposition signal and the initial signal using a pre-constructed relationship value formula, obtaining a local noise reduction signal based on the relationship value, and performing a correction operation on the local noise reduction signal to obtain a local calibration signal; Wherein, obtaining the local noise reduction signal based on the relationship value includes: Comparing the relationship value with a preset relationship threshold; If the relationship value is less than the relationship threshold, a symmetric decomposition operation is performed on the extracted decomposition signal to obtain a local noise reduction signal; Otherwise, confirming that the decomposed signal corresponding to the relationship value is a local noise reduction signal; Acquire the pressure value corresponding to the extracted unit detection time based on multiple local calibration signals, and after confirming that the pressure value is within a preset pressure range, acquire unit image data using a detector and an imaging processing unit; A report generation module, for summarizing multiple unit image data to obtain an image data set, and constructing an optic nerve sheath image using the imaging processing unit and the image data set; Obtaining the optic nerve sheath diameter based on the optic nerve sheath image, and obtaining a first detection report based on a preset healthy diameter interval and the optic nerve sheath diameter; Constructing a second electrooculogram detection unit, wherein the second electrooculogram detection unit includes: a stimulation unit, a signal amplification unit and an information processing unit; Obtaining a second detection report using a second electrooculographic detection unit; A cranial nerve detection report is obtained according to the first detection report and the second detection report, and intelligent detection of the cranial nerves based on the ocular nerves is completed based on the cranial nerve detection report.

Images