A method and system for detecting otolithiasis based on 5G technology

Abstract

The present invention discloses a method and system for detecting otolithiasis based on 5G technology, which relates to the field of medical detection technology. Through three-dimensional scanning, neural network technology and 5G high-speed data transmission, accurate scanning of a patient's head at multiple angles and real-time capture of eye movement trajectories are achieved, and the eye movement trajectories are analyzed in combination with physiological signal data. By constructing a nystagmus difference factor Yzz, the system accurately identifies abnormal nystagmus and sends an adjustment command. The otolith position analysis module generates a misdiagnosis rate coefficient Cwxs by comparing the captured three-dimensional scanning data with the standard data in a reference database, locates the otolith detachment position and provides accurate diagnosis results, thereby improving the diagnosis accuracy. The system calculates and evaluates the misdiagnosis rate coefficient Cwxs, generates a diagnosis report and corresponding treatment suggestions, and transmits them to the mobile terminals of doctors and patients in real time, thereby reducing dependence on operators and allowing doctors to remotely monitor and adjust plans, thereby improving the intelligence and automation level of the system.

Description

Technical Field

[0001] The present invention relates to the field of medical detection technology, and specifically to an otolithiasis detection method and system based on 5G technology. Background Art

[0002] The otolithiasis detection system is used to study inner ear balance disorders. Otolithiasis is the dizziness caused by the loss of otoliths into the semicircular canals. Early detection mainly relies on subjective symptom descriptions and simple balance tests. With the development of medical imaging technology and biosensors, modern otolithiasis detection systems integrate precise measurement technologies such as nystagmus analysis, posture control, and three-dimensional displacement, which greatly improves diagnostic accuracy and promotes its widespread application in clinical practice.

[0003] However, in practical applications, the existing technology of otolithiasis detection system has the following disadvantages:

[0004] 1. Limited diagnostic accuracy: Although modern systems integrate nystagmus analysis and three-dimensional displacement measurement, the misdiagnosis rate still exists due to the limitations of equipment accuracy and algorithm complexity. Especially in mild symptoms or atypical cases, the system may not be able to accurately identify the location and detachment of otoliths.

[0005] 2. Strong dependence on operators: The test results of existing systems often require interpretation by experienced doctors. During the operation, factors such as the angle and posture control of the testing equipment also need to be precisely adjusted, otherwise it is easy to affect the accuracy of the diagnosis results. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides a method and system for detecting otolithiasis based on 5G technology, which solves the technical shortcomings of the background technology such as limited diagnostic accuracy and high dependence on operators.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a 5G-based otolith disease detection system, including a patient positioning module, a data capture module, a data processing module, an otolith position analysis module, and a diagnosis feedback module;

[0008] The patient positioning module is used to accurately adjust the head position of the patient to be examined, use a three-dimensional scanner to scan the patient's head at multiple angles to capture multiple sets of three-dimensional position information, and upload multiple sets of scan data of standard patient postures to the reference database;

[0009] The data capture module is used to process multiple groups of scan data of the patient's head obtained in the patient positioning module, and use 5G technology for data transmission, combine neural network technology to analyze the head scan data, capture the patient's eye movement trajectory in real time, and extract relevant physiological signal data;

[0010] The data processing module is used to filter the captured eye movement trajectory and physiological signal data for noise, remove the noise component through wavelet transform, and convert the processed data into an eigenvalue image, and at the same time construct and evaluate the nystagmus difference factor Yzz, and identify whether there is abnormal nystagmus according to the evaluation content, and if so, send an adjustment command to the otolith position analysis module;

[0011] After receiving the adjustment command, the otolith position analysis module uses the 5G network to scan the patient again from multiple angles to obtain new three-dimensional scanning data, compares the captured new patient scanning data with the standard data in the reference database, locates the otolith shedding position, and generates the misdiagnosis rate coefficient Cwxs of the otolith shedding position through the comparison result;

[0012] The diagnostic feedback module is used to feedback the accurate diagnosis result of the patient's otolith detachment through the 5G network, combine the comparison results with the doctor's auxiliary diagnosis, comprehensively evaluate and generate a diagnostic report, and make treatment plan recommendations based on the diagnostic results.

[0013] Preferably, the patient positioning module includes a head fixing unit and a standard position information unit;

[0014] The head fixing unit is used to fix the head position of the patient to be tested on the detection device, and automatically deploy multiple groups of three-dimensional scanning instruments according to the spatial position coordinates of the patient's head, scan the head at multiple angles, and mark the corresponding positions of the scanned images at each angle;

[0015] The standard position information unit is used to store the pre-selected three-dimensional scanning data of the healthy patient's head in a reference database, and to scan and capture the healthy patient's head from multiple angles through multiple sets of three-dimensional scanning instruments, and transmit the corresponding position information to the reference database.

[0016] Preferably, the data capture module includes a scanning data processing unit and a motion trajectory extraction unit;

[0017] The scan data processing unit is used to receive multiple groups of scan data of the patient's head obtained by the patient positioning module, and pre-process the scan data, including data format conversion and noise removal, and then further transmit and analyze the scan data;

[0018] The motion trajectory extraction unit is used to analyze the processed head scan data using neural network technology, capture the patient's eye movement trajectory in real time, and extract corresponding physiological signal data.

[0019] Preferably, the data processing module includes an eigenvalue image generation unit and an eigenvalue calculation and evaluation unit;

[0020] After denoising the eye movement trajectory data, the eigenvalue image generating unit maps the characteristic related parameters of the eye movement to grayscale values ​​according to the characteristic related parameters of the eye movement, including velocity, acceleration and displacement, and then generates the eigenvalue image.

[0021] Preferably, the eigenvalue calculation and evaluation unit is used to perform statistical analysis on the eigenvalue image of the eye movement trajectory to extract key feature parameters therein, including the position information value Wx, the position information mean Wavg and the number of images n, and calculate the spatial difference factor Sjz by the following formula:

[0022] ;

[0023] Where Wx i Represented as the position information value in the i-th scanned image;

[0024] By comparing and evaluating the preset spatial difference threshold Q with the spatial difference factor Sjz, it is possible to identify whether there is otolith shedding. The specific evaluation contents are as follows:

[0025] If the spatial difference factor Sjz ≥ the spatial difference threshold Q, it means that abnormal otolith shedding exists in the current detection data, and a re-detection command is issued to the otolith position analysis module;

[0026] If the spatial difference factor Sjz is less than the spatial difference threshold Q, it means that there is no abnormal otolith shedding phenomenon in the current detection data, and no additional command is issued at this time.

[0027] Preferably, the otolith position analysis module includes a rescanning unit and an otolith positioning unit;

[0028] After receiving the re-detection command, the re-scanning unit re-scans the patient's head at multiple angles by adjusting the scanning angle of the three-dimensional scanning instrument and switching to a polarized light mode;

[0029] The otolith positioning unit is used to extract the position information of otolith shedding according to the image data obtained by the rescanning unit and the standard image data in the reference database through a feature comparison algorithm, and calculate the otolith displacement coefficient Dyz. The specific calculation is as follows:

[0030] ;

[0031] In the formula, m represents the number of scanned images, Yx j It is represented as the otolith displacement information value in the jth image, and Yavg is represented as the mean otolith displacement in all images.

[0032] Preferably, the otolith positioning unit further includes a misdiagnosis rate analysis subunit;

[0033] The misdiagnosis rate analysis subunit calculates and obtains the misdiagnosis rate coefficient Cwxs of otolith shedding by fitting the threshold value Ystd of the preset standard otolith displacement information with the otolith displacement coefficient Dyz through calculation and comparison; the misdiagnosis rate coefficient Cwxs is specifically obtained by the following formula:

[0034] .

[0035] Preferably, the diagnosis feedback module includes a diagnosis report generating unit and a treatment suggestion generating unit;

[0036] The diagnosis report generation unit is used to preset a first misdiagnosis rate threshold W1 and a second misdiagnosis rate threshold W2, and compare and evaluate the misdiagnosis rate coefficient Cwxs, and the first misdiagnosis rate threshold W1 < the second misdiagnosis rate threshold W2, specifically:

[0037] When the misdiagnosis rate coefficient Cwxs> the second misdiagnosis rate threshold W2, it indicates that the credibility of the current diagnosis result is unqualified and there is a misdiagnosis rate of more than 20%, and the first misdiagnosis result is generated at this time;

[0038] When the first misdiagnosis rate threshold W1 < misdiagnosis rate coefficient Cwxs ≤ second misdiagnosis rate threshold W2, it indicates that the credibility of the current diagnosis result is qualified, but the misdiagnosis rate does not exceed 20%, and the second misdiagnosis result is generated at this time;

[0039] When the misdiagnosis rate coefficient Cwxs is less than the first misdiagnosis rate threshold W1, it indicates that the credibility of the current diagnosis result is qualified, and the third misdiagnosis result is generated at this time, and a treatment suggestion is generated based on the diagnosis result;

[0040] Then, the comparative evaluation results of the otolith detachment position information and the misdiagnosis rate coefficient Cwxs are integrated to generate a diagnosis report;

[0041] Preferably, the treatment suggestion generating unit is used to automatically generate treatment suggestions according to the first misdiagnosis result, the second misdiagnosis result and the third misdiagnosis result, and the specific suggestions are as follows:

[0042] When the first misdiagnosis is made: a comprehensive reexamination is conducted and more accurate diagnostic tools are used, including MRI, CT and enhanced imaging techniques;

[0043] When the second misdiagnosis result is generated: At this time, based on the actual situation of the patient, sedatives and anti-vertigo drugs are used for auxiliary treatment to alleviate the patient's symptoms, and the patient is arranged to be re-examined within a fixed period;

[0044] When the third misdiagnosis result is generated: generating treatment recommendations, including physical otolith repositioning maneuvers and vestibular rehabilitation training;

[0045] Finally, the diagnostic report and treatment recommendations are transmitted to the patient's mobile terminal in real time through the 5G network, allowing doctors to remotely monitor and adjust the treatment plan in a timely manner.

[0046] A method for detecting otolithiasis based on 5G technology comprises the following steps:

[0047] Step 1: accurately adjust the head position of the patient to be examined, use a 3D scanner to scan the patient's head at multiple angles to capture multiple sets of 3D position information, and upload multiple sets of scan data of standard patient postures to a reference database;

[0048] Step 2: Process multiple groups of scan data of the patient's head obtained in the patient positioning module, use 5G technology for data transmission, combine neural network technology to analyze the head scan data, capture the patient's eye movement trajectory in real time, and extract relevant physiological signal data;

[0049] Step 3: filter the captured eye movement trajectory and physiological signal data, remove the noise component through wavelet transform, and convert the processed data into eigenvalue image, and construct and evaluate the nystagmus difference factor Yzz, and identify whether there is abnormal nystagmus according to the evaluation content. If so, send an adjustment command to the otolith position analysis module;

[0050] Step 4: After receiving the adjustment command, the patient is scanned again at multiple angles using the 5G network to obtain new three-dimensional scanning data, and the captured new scanning data of the patient is compared with the standard data in the reference database to locate the detached position of the otolith, and the misdiagnosis rate coefficient Cwxs of the detached position of the otolith is generated through the comparison results;

[0051] Step 5. Through the 5G network, compare and analyze the misdiagnosis rate coefficient Cwxs of the otolith detachment location with the preset diagnostic accuracy threshold E, and feedback the accurate diagnosis result of the patient's otolith detachment based on the comparison result. Combined with the doctor's auxiliary diagnosis, a comprehensive evaluation is made and a diagnostic report is generated, and treatment plans are recommended based on the diagnosis results.

[0052] The present invention provides a method and system for detecting otolithiasis based on 5G technology, which has the following beneficial effects:

[0053] (1) This 5G-based otolith disease detection method and system uses three-dimensional scanning, neural network technology, and 5G high-speed data transmission to achieve accurate scanning of the patient's head at multiple angles and real-time capture of eye movement trajectories, and analyzes them in combination with physiological signal data. By removing noise through wavelet transform and constructing the nystagmus difference factor Yzz, the system can accurately identify abnormal nystagmus and send adjustment commands in a timely manner, thereby improving the accuracy of diagnosis. The otolith position analysis module further compares the captured three-dimensional scanning data with the standard data in the reference database to generate the misdiagnosis rate coefficient Cwxs, so that the system can locate the location of otolith detachment and provide accurate diagnostic results, thereby effectively solving the problem of limited diagnostic accuracy in the existing technology.

[0054] (2) This 5G-based otolithiasis detection method and system, by presetting the first misdiagnosis rate threshold W1 and the second misdiagnosis rate threshold W2, performs comparison analysis with the misdiagnosis rate coefficient Cwxs, and automatically generates a diagnosis report and corresponding treatment recommendations, reducing dependence on operators. The system provides a standardized diagnosis plan based on the comparison and analysis results, and transmits the diagnosis report and treatment recommendations to the doctor's and patient's mobile terminals in real time through the 5G network, allowing doctors to remotely monitor and adjust the treatment plan in a timely manner, reducing the need for experienced doctors to interpret data, and improving the intelligence and automation level of the detection system. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a schematic diagram of the framework structure of an otolithiasis detection system based on 5G technology in the present invention;

[0056] Figure 2 A schematic diagram of the steps of a method for detecting otolithiasis based on 5G technology according to the present invention; DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Example 1

[0059] See also Figure 1 , the present invention provides an otolith disease detection system based on 5G technology, including a patient positioning module, a data capture module, a data processing module, an otolith position analysis module and a diagnosis feedback module;

[0060] The patient positioning module is used to accurately adjust the head position of the patient to be examined, use a three-dimensional scanner to scan the patient's head at multiple angles to capture multiple sets of three-dimensional position information, and upload multiple sets of scan data of standard patient postures to the reference database;

[0061] The data capture module is used to process multiple groups of scan data of the patient's head obtained in the patient positioning module, and use 5G technology for data transmission, combine neural network technology to analyze the head scan data, capture the patient's eye movement trajectory in real time, and extract relevant physiological signal data;

[0062] The data processing module is used to filter the captured eye movement trajectory and physiological signal data for noise, remove the noise component through wavelet transform, and convert the processed data into an eigenvalue image, and at the same time construct and evaluate the nystagmus difference factor Yzz, and identify whether there is abnormal nystagmus according to the evaluation content, and if so, send an adjustment command to the otolith position analysis module;

[0063] After receiving the adjustment command, the otolith position analysis module uses the 5G network to scan the patient again from multiple angles to obtain new three-dimensional scanning data, compares the captured new patient scanning data with the standard data in the reference database, locates the otolith shedding position, and generates the misdiagnosis rate coefficient Cwxs of the otolith shedding position through the comparison result;

[0064] The diagnostic feedback module is used to feedback the accurate diagnosis result of the patient's otolith detachment through the 5G network, combine the comparison results with the doctor's auxiliary diagnosis, comprehensively evaluate and generate a diagnostic report, and make treatment plan recommendations based on the diagnostic results.

[0065] In this embodiment, the patient positioning module can accurately adjust the patient's head position, use a three-dimensional scanner to capture three-dimensional position information from multiple angles and upload it to a reference database to ensure the accuracy of positioning; the data capture module uses 5G technology to achieve high-speed data transmission, combines neural network technology to analyze head scan data, captures the patient's eye movement trajectory in real time and extracts physiological signal data, ensuring the real-time and accuracy of data processing; the data processing module removes noise through wavelet transform, converts the eye movement trajectory and physiological signal data into eigenvalue images, and constructs the nystagmus difference factor Yzz to ensure accurate identification of abnormal nystagmus; after receiving the adjustment command, the otolith position analysis module generates the misdiagnosis rate coefficient Cwxs of the otolith detachment position by comparing the new scan data with the standard data in the reference database, locates the otolith detachment position, and ensures the accuracy of the diagnosis; the diagnostic feedback module transmits the comparison results through the 5G network, generates a diagnostic report in combination with doctor-assisted diagnosis, and proposes treatment plan recommendations to ensure the effectiveness of diagnostic feedback and remote monitoring capabilities.

[0066] Example 2

[0067] The patient positioning module includes a head fixing unit and a standard position information unit;

[0068] The head fixing unit is used to fix the head position of the patient to be tested on the detection device, and automatically deploy multiple groups of three-dimensional scanning instruments according to the spatial position coordinates of the patient's head, scan the head at multiple angles, and mark the corresponding positions of the scanned images at each angle;

[0069] The standard position information unit is used to store the pre-selected three-dimensional scanning data of the healthy patient's head in a reference database, and to scan and capture the healthy patient's head from multiple angles through multiple sets of three-dimensional scanning instruments, and transmit the corresponding position information to the reference database.

[0070] In this embodiment, accurate positioning and scanning of the patient's head position are achieved through the cooperation of the head fixing unit and the standard position information unit; the head fixing unit can fix the head of the patient to be tested on the detection equipment, and automatically deploy the three-dimensional scanning instrument to perform multi-angle scanning according to the spatial position coordinates of the patient's head, and mark the position of the scanned images at each angle to ensure the comprehensive collection of the patient's head data and the accuracy of the scanning; the standard position information unit stores the three-dimensional scanning data of healthy patients and uses this data as a reference to transmit the multi-angle scanning data of healthy patients to the reference database to ensure the accuracy of the comparison data; by collecting the spatial position coordinates, three-dimensional scanning data and corresponding position information of the patient's head, the system can obtain a comprehensive three-dimensional image of the patient's head to achieve subsequent accurate diagnosis and comparative analysis.

[0071] Example 3

[0072] The data capture module includes a scanning data processing unit and a motion trajectory extraction unit;

[0073] The scan data processing unit is used to receive multiple groups of scan data of the patient's head obtained by the patient positioning module, and pre-process the scan data, including data format conversion and noise removal, and then further transmit and analyze the scan data;

[0074] The motion trajectory extraction unit is used to analyze the processed head scan data using neural network technology, capture the patient's eye movement trajectory in real time, and extract corresponding physiological signal data.

[0075] In this embodiment, the data capture module realizes efficient processing and analysis of the patient's head scanning data through the combination of the scanning data processing unit and the motion trajectory extraction unit; the scanning data processing unit receives multiple sets of scanning data from the patient positioning module, and performs data format conversion and denoising processing to ensure the accuracy and clarity of the data, providing a high-quality data basis for subsequent analysis; the motion trajectory extraction unit uses neural network technology to perform real-time analysis on the processed head scanning data, accurately captures the patient's eye movement trajectory, and extracts relevant physiological signal data to ensure comprehensive monitoring and analysis of the patient's status; through the collaborative work of these two units, the system can obtain the patient's key physiological data and head position information in real time and accurately, thereby improving diagnostic accuracy and efficiency.

[0076] Example 4

[0077] The data processing module includes an eigenvalue image generating unit and an eigenvalue calculating and evaluating unit;

[0078] After denoising the eye movement trajectory data, the eigenvalue image generating unit maps the characteristic related parameters of the eye movement to grayscale values ​​according to the characteristic related parameters of the eye movement, including velocity, acceleration and displacement, and then generates the eigenvalue image.

[0079] The characteristic value calculation and evaluation unit is used to perform statistical analysis on the characteristic value image of the eye movement trajectory, extract key characteristic parameters therein, including the position information value Wx, the position information mean value Wavg and the number of images n, and calculate the spatial difference factor Sjz by the following formula:

[0080] ;

[0081] Where Wx i Represented as the position information value in the i-th scanned image;

[0082] By comparing and evaluating the preset spatial difference threshold Q with the spatial difference factor Sjz, it is possible to identify whether there is otolith shedding. The specific evaluation contents are as follows:

[0083] If the spatial difference factor Sjz ≥ the spatial difference threshold Q, it means that abnormal otolith shedding exists in the current detection data, and a re-detection command is issued to the otolith position analysis module;

[0084] If the spatial difference factor Sjz is less than the spatial difference threshold Q, it means that there is no abnormal otolith shedding phenomenon in the current detection data, and no additional command is issued at this time.

[0085] In this embodiment, through the eigenvalue image generation unit and the eigenvalue calculation and evaluation unit, in-depth analysis and processing of eye movement trajectory data are achieved; the eigenvalue image generation unit first performs denoising on the eye movement trajectory data to ensure the accuracy and completeness of the data; then, according to feature-related parameters such as speed, acceleration and displacement, these parameters are mapped to grayscale values ​​to generate eigenvalue images for subsequent image analysis; the eigenvalue calculation and evaluation unit performs statistical analysis on the eigenvalue images, extracts key parameters, including position information value Wx, position information mean Wavg and number of images n, and uses these parameters to calculate the spatial difference factor Sjz through a formula to identify the possibility of otolith shedding; by comparing the spatial difference factor Sjz with a preset spatial difference threshold Q, the system can accurately evaluate the situation of otolith shedding, and issue a corresponding re-detection command based on the evaluation result; the collection and analysis of these parameters ensure that the system can judge the situation of otolith shedding in real time and accurately, thereby improving the accuracy and efficiency of diagnosis.

[0086] Example 5

[0087] The otolith position analysis module includes a rescanning unit and an otolith positioning unit;

[0088] After receiving the re-detection command, the re-scanning unit re-scans the patient's head at multiple angles by adjusting the scanning angle of the three-dimensional scanning instrument and switching to a polarized light mode;

[0089] The otolith positioning unit is used to extract the position information of otolith shedding according to the image data obtained by the rescanning unit and the standard image data in the reference database through a feature comparison algorithm, and calculate the otolith displacement coefficient Dyz. The specific calculation is as follows:

[0090] ;

[0091] In the formula, m represents the number of scanned images, Yx j It is represented as the otolith displacement information value in the jth image, and Yavg is represented as the mean otolith displacement in all images.

[0092] The otolith positioning unit also includes a misdiagnosis rate analysis subunit;

[0093] The misdiagnosis rate analysis subunit calculates and obtains the misdiagnosis rate coefficient Cwxs of otolith shedding by fitting the threshold value Ystd of the preset standard otolith displacement information with the otolith displacement coefficient Dyz through calculation and comparison; the misdiagnosis rate coefficient Cwxs is specifically obtained by the following formula:

[0094] .

[0095] In this embodiment, the combination of the rescanning unit and the otolith positioning unit ensures accurate identification of the otolith detachment position; after receiving the re-detection command, the rescanning unit can adjust the scanning angle of the three-dimensional scanning instrument and switch to the polarized light mode to re-scan the patient's head at multiple angles to ensure that more comprehensive and clear image data are obtained; the otolith positioning unit extracts the position information of otolith detachment through a feature comparison algorithm based on the image data obtained by the rescanning unit and in combination with the standard image data in the reference database, and calculates the otolith displacement coefficient Dyz, which is specifically calculated through the number of scanned images m, the otolith displacement information value Yxj in each image, and the otolith displacement mean value Yavg of all images; the misdiagnosis rate analysis subunit calculates the misdiagnosis rate coefficient Cwxs of otolith detachment through a preset standard otolith displacement information threshold value Ystd and the otolith displacement coefficient Dyz; the collection and analysis of these parameters ensure that the system can accurately evaluate the position and misdiagnosis rate of otolith detachment, which helps to improve the reliability and accuracy of the diagnosis results.

[0096] Example 6

[0097] The diagnosis feedback module includes a diagnosis report generating unit and a treatment suggestion generating unit;

[0098] The diagnosis report generation unit is used to preset a first misdiagnosis rate threshold W1 and a second misdiagnosis rate threshold W2, and compare and evaluate the misdiagnosis rate coefficient Cwxs, and the first misdiagnosis rate threshold W1 < the second misdiagnosis rate threshold W2, specifically:

[0099] When the misdiagnosis rate coefficient Cwxs> the second misdiagnosis rate threshold W2, it indicates that the credibility of the current diagnosis result is unqualified and there is a misdiagnosis rate of more than 20%, and the first misdiagnosis result is generated at this time;

[0100] When the first misdiagnosis rate threshold W1 < misdiagnosis rate coefficient Cwxs ≤ second misdiagnosis rate threshold W2, it indicates that the credibility of the current diagnosis result is qualified, but the misdiagnosis rate does not exceed 20%, and the second misdiagnosis result is generated at this time;

[0101] When the misdiagnosis rate coefficient Cwxs is less than the first misdiagnosis rate threshold W1, it indicates that the credibility of the current diagnosis result is qualified, and the third misdiagnosis result is generated at this time, and a treatment suggestion is generated based on the diagnosis result;

[0102] Then, the comparative evaluation results of the otolith detachment position information and the misdiagnosis rate coefficient Cwxs are integrated to generate a diagnosis report;

[0103] The treatment suggestion generating unit is used to automatically generate treatment suggestions according to the first misdiagnosis result, the second misdiagnosis result and the third misdiagnosis result, and the specific suggestions are as follows:

[0104] When the first misdiagnosis is made: a comprehensive reexamination is conducted and more accurate diagnostic tools are used, including MRI, CT and enhanced imaging techniques;

[0105] When the second misdiagnosis result is generated: At this time, based on the actual situation of the patient, sedatives and anti-vertigo drugs are used for auxiliary treatment to alleviate the patient's symptoms, and the patient is arranged to be re-examined within a fixed period;

[0106] When the third misdiagnosis result is generated: generating treatment recommendations, including physical otolith repositioning maneuvers and vestibular rehabilitation training;

[0107] Finally, the diagnostic report and treatment recommendations are transmitted to the patient's mobile terminal in real time through the 5G network, allowing doctors to remotely monitor and adjust the treatment plan in a timely manner.

[0108] In this embodiment, the accuracy of the diagnosis result and the effectiveness of the treatment suggestion are ensured by the diagnosis report generation unit and the treatment suggestion generation unit; the diagnosis report generation unit compares and evaluates the preset first misdiagnosis rate threshold W1 and the second misdiagnosis rate threshold W2 with the misdiagnosis rate coefficient Cwxs to generate three different misdiagnosis results to evaluate the credibility of the diagnosis result; through the analysis and comparison of these parameters, the system can generate personalized treatment suggestions and transmit them to patients and doctors in real time through the 5G network, ensuring effective feedback and remote monitoring of the diagnosis results.

[0109] Example 7

[0110] A method for detecting otolithiasis based on 5G technology comprises the following steps:

[0111] Step 1: accurately adjust the head position of the patient to be examined, use a 3D scanner to scan the patient's head at multiple angles to capture multiple sets of 3D position information, and upload multiple sets of scan data of standard patient postures to a reference database;

[0112] Step 2: Process multiple groups of scan data of the patient's head obtained in the patient positioning module, use 5G technology for data transmission, combine neural network technology to analyze the head scan data, capture the patient's eye movement trajectory in real time, and extract relevant physiological signal data;

[0113] Step 3: filter the captured eye movement trajectory and physiological signal data, remove the noise component through wavelet transform, and convert the processed data into eigenvalue image, and construct and evaluate the nystagmus difference factor Yzz, and identify whether there is abnormal nystagmus according to the evaluation content. If so, send an adjustment command to the otolith position analysis module;

[0114] Step 4: After receiving the adjustment command, the patient is scanned again at multiple angles using the 5G network to obtain new three-dimensional scanning data, and the captured new scanning data of the patient is compared with the standard data in the reference database to locate the detached position of the otolith, and the misdiagnosis rate coefficient Cwxs of the detached position of the otolith is generated through the comparison results;

[0115] Step 5. Through the 5G network, compare and analyze the misdiagnosis rate coefficient Cwxs of the otolith detachment location with the preset diagnostic accuracy threshold E, and feedback the accurate diagnosis result of the patient's otolith detachment based on the comparison result. Combined with the doctor's auxiliary diagnosis, a comprehensive evaluation is made and a diagnostic report is generated, and treatment plans are recommended based on the diagnosis results.

[0116] In this embodiment, the problems of limited diagnostic accuracy and strong dependence on operators in traditional otolith disease detection are solved through efficient collaboration of each step; step 1 ensures that the collected three-dimensional position information is complete and accurate by accurately adjusting the patient's head position and using a three-dimensional scanner for multi-angle scanning, providing a reliable data basis for subsequent analysis, and reducing diagnostic deviations caused by scanning angle errors; step 2 combines 5G technology and neural network technology to achieve rapid data transmission and real-time analysis, ensuring real-time capture of eye movement trajectories and physiological signal data, greatly reducing dependence on operators; step 3 removes data noise through wavelet transform, constructs nystagmus difference factor Yzz, accurately identifies abnormal nystagmus phenomena, and improves diagnostic accuracy; step 4 generates the misdiagnosis rate coefficient Cwxs of the otolith detachment position by comparing the new scan data with the standard data in the reference database, and realizes accurate positioning of the otolith position; step 5 generates an accurate diagnosis report by comparing and analyzing the misdiagnosis rate coefficient Cwxs with the diagnostic accuracy threshold E, and proposes a treatment plan in combination with doctor-assisted diagnosis, ensuring the reliability of the diagnosis results, and realizing remote diagnosis feedback through the 5G network.

[0117] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A 5G-based otolithiasis detection system, characterized by: It includes a patient positioning module, a data capture module, a data processing module, an otolith position analysis module and a diagnosis feedback module; The patient positioning module is used to accurately adjust the head position of the patient to be examined, use a three-dimensional scanner to scan the patient's head at multiple angles to capture multiple sets of three-dimensional position information, and upload multiple sets of scan data of standard patient postures to the reference database; The data capture module is used to process multiple groups of scan data of the patient's head obtained in the patient positioning module, and use 5G technology for data transmission, combine neural network technology to analyze the head scan data, capture the patient's eye movement trajectory in real time, and extract relevant physiological signal data; The data processing module is used to filter the captured eye movement trajectory and physiological signal data for noise, remove the noise component through wavelet transform, and convert the processed data into an eigenvalue image, and at the same time construct and evaluate the nystagmus difference factor Yzz, and identify whether there is abnormal nystagmus according to the evaluation content, and if so, send an adjustment command to the otolith position analysis module; After receiving the adjustment command, the otolith position analysis module uses the 5G network to scan the patient again from multiple angles to obtain new three-dimensional scanning data, compares the captured new patient scanning data with the standard data in the reference database, locates the otolith shedding position, and generates the misdiagnosis rate coefficient Cwxs of the otolith shedding position through the comparison result; The diagnostic feedback module is used to feedback the accurate diagnosis result of the patient's otolith detachment through the 5G network, combine the comparison results with the doctor's auxiliary diagnosis, comprehensively evaluate and generate a diagnostic report, and make treatment plan recommendations based on the diagnostic results.

2. According to claim 1, a 5G-based otolithiasis detection system is characterized by: The patient positioning module includes a head fixing unit and a standard position information unit; The head fixing unit is used to fix the head position of the patient to be tested on the detection device, and automatically deploy multiple groups of three-dimensional scanning instruments according to the spatial position coordinates of the patient's head, scan the head at multiple angles, and mark the corresponding positions of the scanned images at each angle; The standard position information unit is used to store the pre-selected three-dimensional scanning data of the healthy patient's head in a reference database, and to scan and capture the healthy patient's head from multiple angles through multiple sets of three-dimensional scanning instruments, and transmit the corresponding position information to the reference database.

3. The otolithiasis detection system based on 5G technology according to claim 2, characterized in that: The data capture module includes a scanning data processing unit and a motion trajectory extraction unit; The scan data processing unit is used to receive multiple groups of scan data of the patient's head obtained by the patient positioning module, and pre-process the scan data, including data format conversion and noise removal, and then further transmit and analyze the scan data; The motion trajectory extraction unit is used to analyze the processed head scan data using neural network technology, capture the patient's eye movement trajectory in real time, and extract corresponding physiological signal data.

4. The otolithiasis detection system based on 5G technology according to claim 3 is characterized in that: The data processing module includes an eigenvalue image generating unit and an eigenvalue calculating and evaluating unit; After denoising the eye movement trajectory data, the eigenvalue image generating unit maps the characteristic related parameters of the eye movement to grayscale values ​​according to the characteristic related parameters of the eye movement, including velocity, acceleration and displacement, and then generates the eigenvalue image.

5. The otolithiasis detection system based on 5G technology according to claim 4 is characterized in that: The characteristic value calculation and evaluation unit is used to perform statistical analysis on the characteristic value image of the eye movement trajectory, extract key characteristic parameters therein, including the position information value Wx, the position information mean value Wavg and the number of images n, and calculate the spatial difference factor Sjz by the following formula: Where Wx i Represented as the position information value in the i-th scanned image; By comparing and evaluating the preset spatial difference threshold Q with the spatial difference factor Sjz, it is possible to identify whether there is otolith shedding. The specific evaluation contents are as follows: If the spatial difference factor Sjz ≥ the spatial difference threshold Q, it means that abnormal otolith shedding exists in the current detection data, and a re-detection command is issued to the otolith position analysis module; If the spatial difference factor Sjz is less than the spatial difference threshold Q, it means that there is no abnormal otolith shedding phenomenon in the current detection data, and no additional command is issued at this time.

6. The otolithiasis detection system based on 5G technology according to claim 5, characterized in that: The otolith position analysis module includes a rescanning unit and an otolith positioning unit; After receiving the re-detection command, the re-scanning unit re-scans the patient's head at multiple angles by adjusting the scanning angle of the three-dimensional scanning instrument and switching to a polarized light mode; The otolith positioning unit is used to extract the position information of otolith shedding according to the image data obtained by the rescanning unit and the standard image data in the reference database through a feature comparison algorithm, and calculate the otolith displacement coefficient Dyz. The specific calculation is as follows: In the formula, m represents the number of scanned images, Yx j It is represented as the otolith displacement information value in the jth image, and Yavg is represented as the mean otolith displacement in all images.

7. The otolithiasis detection system based on 5G technology according to claim 6, characterized in that: The otolith positioning unit also includes a misdiagnosis rate analysis subunit; The misdiagnosis rate analysis subunit calculates and obtains the misdiagnosis rate coefficient Cwxs of otolith shedding by fitting the threshold value Ystd of the preset standard otolith displacement information with the otolith displacement coefficient Dyz through calculation and comparison; the misdiagnosis rate coefficient Cwxs is specifically obtained by the following formula:

8. The otolithiasis detection system based on 5G technology according to claim 7, characterized in that: The diagnosis feedback module includes a diagnosis report generating unit and a treatment suggestion generating unit; The diagnosis report generation unit is used to preset a first misdiagnosis rate threshold W1 and a second misdiagnosis rate threshold W2, and compare and evaluate the misdiagnosis rate coefficient Cwxs, and the first misdiagnosis rate threshold W1 < the second misdiagnosis rate threshold W2, specifically: When the misdiagnosis rate coefficient Cwxs> the second misdiagnosis rate threshold W2, it indicates that the credibility of the current diagnosis result is unqualified and there is a misdiagnosis rate of more than 20%, and the first misdiagnosis result is generated at this time; When the first misdiagnosis rate threshold W1 < misdiagnosis rate coefficient Cwxs ≤ second misdiagnosis rate threshold W2, it indicates that the credibility of the current diagnosis result is qualified, but the misdiagnosis rate does not exceed 20%, and the second misdiagnosis result is generated at this time; When the misdiagnosis rate coefficient Cwxs is less than the first misdiagnosis rate threshold W1, it indicates that the credibility of the current diagnosis result is qualified, and the third misdiagnosis result is generated at this time, and a treatment suggestion is generated based on the diagnosis result; Then, the comparative evaluation results of the otolith detachment location information and the misdiagnosis rate coefficient Cwxs are integrated to generate a diagnosis report.

9. The otolithiasis detection system based on 5G technology according to claim 8, characterized in that: The treatment suggestion generating unit is used to automatically generate treatment suggestions according to the first misdiagnosis result, the second misdiagnosis result and the third misdiagnosis result, and the specific suggestions are as follows: When the first misdiagnosis is made: a comprehensive reexamination is conducted and more accurate diagnostic tools are used, including MRI, CT and enhanced imaging techniques; When the second misdiagnosis result is generated: At this time, based on the actual situation of the patient, sedatives and anti-vertigo drugs are used for auxiliary treatment to alleviate the patient's symptoms, and the patient is arranged to be re-examined within a fixed period; When the third misdiagnosis result is generated: generating treatment recommendations, including physical otolith repositioning maneuvers and vestibular rehabilitation training; Finally, the diagnostic report and treatment recommendations are transmitted to the patient's mobile terminal in real time through the 5G network, allowing doctors to remotely monitor and adjust the treatment plan in a timely manner.

Images