A diagnostic auxiliary method and system for skeletal muscle injury

Abstract

The present invention discloses a diagnosis auxiliary method and system for skeletal muscle injury. The present invention relates to the field of auxiliary diagnosis, and comprises a skeletal muscle auxiliary diagnosis platform, wherein a data acquisition module, a data processing module, a data analysis module, a personalized analysis module, an auxiliary diagnosis module and a comprehensive diagnosis module are provided; the data acquisition module is used to acquire three types of signal data; the data processing module acquires corresponding characteristic signals according to the acquired signal data; the data analysis module is used to construct a skeletal muscle characteristic signal spectrum corresponding to the patient according to the characteristic signals; the personalized analysis module is used to perform correction processing on the acquired skeletal muscle characteristic signal spectrum and complete regional division; the auxiliary diagnosis module is used to acquire corresponding injury regions according to the regional division results; the comprehensive diagnosis module performs comprehensive analysis on the acquired injury regions to acquire comprehensive diagnosis data; the present invention improves the accuracy rate in the skeletal muscle diagnosis process.

Description

Technical Field

[0001] The present invention relates to the field of auxiliary diagnosis, and in particular to an auxiliary diagnosis method and system for skeletal muscle injury. Background Art

[0002] Skeletal muscle injuries are very common in athletes, the elderly, and certain occupational groups, especially in cases of strenuous exercise, accidental injuries, or chronic diseases. Traditional methods for diagnosing skeletal muscle injuries mainly include clinical examinations, imaging examinations, and biochemical tests. These methods have their own advantages and disadvantages, but also have certain limitations. With the development of sensor technology, artificial intelligence, and big data analysis technology, applying them in the medical scenario of skeletal muscle injuries is an issue that we urgently need to solve.

[0003] However, at present, during the corresponding data diagnosis process, the degree of skeletal muscle injury cannot be obtained and the corresponding area cannot be determined, and the degree of injury in different areas is different, resulting in inaccurate auxiliary diagnosis results of skeletal muscle injury. Therefore, how to improve the accuracy of auxiliary diagnosis results of skeletal muscle injury is a problem we need to solve. To this end, a diagnostic auxiliary method and system for skeletal muscle injury are provided. Summary of the invention

[0004] In order to solve the above technical problems, the object of the present invention is to provide a diagnosis assistance method and system for skeletal muscle injuries.

[0005] The object of the present invention can be achieved by the following technical solutions: A diagnosis auxiliary system for skeletal muscle injury, comprising a skeletal muscle auxiliary diagnosis platform, wherein the skeletal muscle auxiliary diagnosis platform is provided with a data acquisition module, a data processing module, a data analysis module, a personalized analysis module, an auxiliary diagnosis module and a comprehensive diagnosis module;

[0006] The data acquisition module is used to collect three types of signal data: physiological signal data, motion signal data and image signal data;

[0007] The data processing module is used to extract features from different types of collected signal data to obtain corresponding physiological feature signals, motion feature signals and image feature signals;

[0008] The data analysis module is used to analyze and process the obtained characteristic signals of the corresponding type, and construct a skeletal muscle characteristic signal spectrum of the patient's corresponding type;

[0009] The personalized analysis module is used to perform correction processing on the obtained skeletal muscle characteristic signal spectrum, and divide the skeletal muscle characteristic signal spectrum into regions according to the correction processing result;

[0010] The auxiliary diagnosis module is used to obtain the damaged area of ​​the corresponding data type in the skeletal muscle characteristic signal spectrum according to the area division result;

[0011] The comprehensive diagnosis module is used to perform a comprehensive analysis on the obtained damage area, obtain corresponding damage degree data, and obtain comprehensive diagnosis data based on the corresponding damage degree data.

[0012] Furthermore, the process of the data acquisition module acquiring three types of signal data, namely physiological signal data, motion signal data and image signal data, includes:

[0013] The data acquisition modules are respectively associated with corresponding physiological acquisition devices, motion acquisition devices and image acquisition devices;

[0014] Collect physiological signal data of the patient corresponding to the patient account according to the physiological collection device;

[0015] Collecting motion signal data of the patient corresponding to the patient account using a motion collection device;

[0016] The image signal data of the patient corresponding to the patient account is collected according to the image acquisition device.

[0017] Furthermore, the data processing module extracts features from the collected signal data of different types to obtain corresponding physiological feature signals, motion feature signals and image feature signals, including:

[0018] The obtained physiological signal data and motion characteristic information are analyzed and processed, and the obtained physiological signal data and motion characteristic information are marked according to the acquisition time, and converted into corresponding time domain signals; the obtained time domain signal with a length of N is The corresponding frequency domain signal is obtained by Fourier transformation, and the corresponding physiological characteristic signal and motion characteristic signal are obtained by analysis and processing according to the frequency domain signal;

[0019] Acquire image signal data, perform grayscale value processing on the acquired image signal data, acquire corresponding grayscale images, construct grayscale co-occurrence matrix, and acquire image feature signals corresponding to the corresponding grayscale images according to the grayscale co-occurrence matrix;

[0020] The acquired physiological characteristic signals, motion characteristic signals and image characteristic signals are sent to the data analysis module.

[0021] Furthermore, the data analysis module performs analysis and processing based on the obtained characteristic signals of the corresponding type, and the process of constructing a skeletal muscle characteristic signal atlas of the patient's corresponding type includes:

[0022] Acquire physiological characteristic signals, motion characteristic signals and image characteristic signals, and store them;

[0023] Acquire historical physiological characteristic signals and historical motion characteristic signals, and analyze and process the historical characteristic data corresponding to the acquired historical physiological characteristic signals and historical motion characteristic signals;

[0024] Analyze and process the historical feature data corresponding to the historical physiological feature signal and the historical feature data corresponding to the historical motion feature signal respectively, construct a corresponding historical feature data set, perform correlation analysis on the feature data in the historical feature data set, and obtain correlation data of the corresponding historical feature data respectively;

[0025] According to the correlation data, the corresponding physiological characteristic signals and motion characteristic signals are analyzed and processed respectively, and a physiological skeletal muscle characteristic signal spectrum and a motion skeletal muscle characteristic signal spectrum are constructed;

[0026] For the image feature signal, the obtained image feature signal includes the texture features and tissue structure features of the corresponding patient, and a skeletal muscle feature signal atlas is generated according to the texture features and tissue structure features corresponding to the patient.

[0027] Furthermore, the process of the personalized analysis module performing correction processing according to the obtained skeletal muscle characteristic signal spectrum according to the patient account includes:

[0028] Acquire a skeletal muscle characteristic signal spectrum and a corresponding patient location, and correct the skeletal muscle characteristic signal spectrum according to the patient location information;

[0029] Obtain the corresponding standard skeletal muscle characteristic signal atlas according to the patient's location information;

[0030] Compare and analyze the skeletal muscle characteristic signal spectrum corresponding to the patient account with the corresponding standard skeletal muscle characteristic signal spectrum;

[0031] Obtain edge pixel points corresponding to the skeletal muscle characteristic signal map and the standard skeletal muscle characteristic signal map, and mark them as image pixel points and standard pixel points respectively;

[0032] Compare and analyze the obtained image pixels with the standard pixels in turn, obtain the position distance of the corresponding pixels, and adjust the skeletal muscle characteristic signal spectrum by the position distance between the two corresponding pixels until the deviation rate corresponding to the position distance is less than the preset standard, and the skeletal muscle characteristic signal spectrum completes the correction process;

[0033] The corrected skeletal muscle characteristic signal atlas is divided into regions according to its corresponding standard skeletal muscle characteristic signal atlas, the corresponding muscle group regions are obtained, and the muscle group regions of the skeletal muscle characteristic signal atlas are marked according to the division results.

[0034] Furthermore, the process of the auxiliary diagnosis module obtaining the damaged area of ​​the corresponding data type in the skeletal muscle characteristic signal spectrum according to the area division result includes:

[0035] Analyze and process the muscle group area marks corresponding to the skeletal muscle characteristic signal spectrum corresponding to the patient account in sequence;

[0036] Acquire the image feature signal in the corresponding muscle group area, perform texture analysis on the obtained image feature signal, obtain the pixel point in the central area of ​​the corresponding muscle group area, mark it as the central pixel, compare the obtained central pixel with the pixels around it, generate a texture code according to the comparison result, perform conversion according to the obtained texture code, and obtain the feature value of the central pixel;

[0037] The obtained feature values ​​are compared with texture features, and the corresponding muscle group area is judged whether there is damage according to the comparison results. If there is damage, it is marked as an image damage area;

[0038] The physiological characteristic signals and the motion characteristic signals are mapped to the corresponding muscle group areas, and it is determined whether there are abnormalities in the physiological characteristic signals and the motion characteristic signals in the corresponding muscle group areas. If there are abnormalities, they are marked as physiological damage areas and motion damage areas respectively.

[0039] Furthermore, the comprehensive diagnosis module performs a comprehensive analysis on the obtained damage area to obtain corresponding damage degree data. The process of obtaining comprehensive diagnosis data according to the corresponding damage degree data includes:

[0040] Obtain the skeletal muscle characteristic signal spectrum corresponding to the patient account, map the analysis results corresponding to the physiological characteristic signal, the motion characteristic signal and the image characteristic signal into the skeletal muscle characteristic signal spectrum; obtain the injury condition corresponding to the corresponding muscle group area;

[0041] Obtain the injury deviation value of the injury type corresponding to the muscle group area, set the corresponding weight factor according to the injury type, integrate the injury deviation value and weight factor corresponding to the injury type in each muscle group area, and obtain the injury degree data of each muscle group area;

[0042] The corresponding comprehensive diagnosis interval is preset, the obtained damage degree data is compared and analyzed with the comprehensive diagnosis area, and the corresponding comprehensive diagnosis data is obtained according to the comparative analysis results.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. By acquiring different types of signal data and obtaining corresponding characteristic signals according to different types of signal data, the patient's skeletal muscle injury can be assisted in diagnosis according to different types of characteristic signals, which improves the accuracy of the auxiliary diagnosis process to a certain extent;

[0045] 2. By obtaining the characteristic signal spectrum of skeletal muscle and analyzing and processing it, the corresponding muscle group area is obtained, and the obtained muscle group area is combined with different types of signal data for analysis and processing to obtain different types of injury areas. The corresponding types of injury areas in the muscle group area are combined for integrated analysis, which improves the accuracy of the skeletal muscle injury diagnosis process to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a schematic diagram of a diagnostic assistance system for skeletal muscle injury according to an embodiment of the present application;

[0047] Figure 2 This is a schematic diagram of a diagnostic assistance method for skeletal muscle injury according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] like Figure 1 As shown, a diagnosis auxiliary system for skeletal muscle injury includes a skeletal muscle auxiliary diagnosis platform, wherein the skeletal muscle auxiliary diagnosis platform is provided with a data acquisition module, a data processing module, a data analysis module, a personalized analysis module, an auxiliary diagnosis module and a comprehensive diagnosis module;

[0049] The skeletal muscle diagnosis platform is used to input the corresponding medical institutions or scientific research institutions, grant corresponding permissions to them according to the verification information of the medical institutions and scientific research institutions, and set corresponding auxiliary management spaces according to the permissions. The auxiliary management space is used to obtain the corresponding data information in the corresponding medical institutions, and analyze and process it to avoid the data information in different medical institutions from being stolen;

[0050] The skeletal muscle diagnosis platform obtains equipment information and user identity information in the corresponding medical institution;

[0051] The user identity information includes patient identity information and medical identity information. Verification is performed based on the patient identity information and medical identity information, and it is determined whether to set the corresponding patient account and medical account based on the verification result.

[0052] The data acquisition module is provided with a physiological acquisition device, a motion acquisition device and an image acquisition device, and the physiological signal data, the motion signal data and the image signal data are respectively acquired according to the corresponding acquisition devices. The specific implementation process includes:

[0053] The data acquisition module is provided with a physiological acquisition unit, a motion acquisition unit and an image acquisition unit;

[0054] The physiological acquisition unit is provided with a physiological acquisition device, and the physiological acquisition device includes an electromyography device, a bioelectrical impedance analyzer and a biochemical detection device;

[0055] The electromyography device is used to collect electrical activity signals at the patient's muscles through electrodes;

[0056] The bioelectrical impedance analyzer is used to evaluate muscle mass, body fat percentage and water content by measuring the electrical impedance of various parts of the body, marking it as an electrical impedance detection signal;

[0057] The biochemical detection equipment is used to obtain blood samples from patients, analyze and process the obtained blood samples, and obtain key muscle enzyme data;

[0058] The obtained electrical activity signals, electrical impedance detection signals and key muscle enzyme data are labeled, and are collectively referred to as physiological signal data according to the labeling results;

[0059] The motion acquisition unit is provided with a motion acquisition device, and the motion acquisition device includes a pressure sensor and a motion analysis device;

[0060] The pressure distribution data and the pressure data of the contact points of the corresponding patient during the exercise are obtained through the pressure sensor;

[0061] Analyze and process the obtained pressure distribution data and the motion contact point pressure data to obtain corresponding motion signal data;

[0062] The image acquisition unit is provided with an image acquisition device, and the image acquisition device includes an ultrasonic device and an MRI device;

[0063] The ultrasonic device is used to collect real-time status images of corresponding parts of the patient's organs;

[0064] The MRI device is used to acquire high-resolution muscle tissue images;

[0065] Marking the obtained real-time state image and muscle tissue image, and setting image signal data according to the marking processing result;

[0066] The obtained physiological signal data, motion signal data and image signal data are associated with the patient account corresponding to the corresponding patient, a corresponding skeletal muscle acquisition data packet is set according to the association result, and the skeletal muscle acquisition data packet is sent to the data processing module.

[0067] The data processing module is used to extract features based on the collected signal data to obtain physiological feature signals, motion feature signals and image feature signals. The specific implementation process includes:

[0068] The data processing module is associated with the auxiliary management space corresponding to the corresponding medical institution, obtains the skeletal muscle acquisition data packet corresponding to the patient account in the corresponding auxiliary management space, analyzes and processes the signal data in the skeletal muscle acquisition data packet, and obtains the corresponding characteristic signal;

[0069] Acquire physiological signal data, motion signal data and image signal data in the skeletal muscle acquisition data packet, and set corresponding filters to remove high-frequency noise in the signal data;

[0070] Extracting features from the electrical activity signal and the electrical impedance detection signal in the physiological signal data and the pressure distribution data and the motion contact point pressure data in the motion signal data;

[0071] Marking the obtained electrical activity signal, electrical impedance detection signal pressure distribution data and moving contact point pressure number according to the acquisition time, and converting the electrical activity signal, electrical impedance detection signal, pressure distribution data and moving contact point pressure number into their corresponding time domain signals;

[0072] The obtained time domain signal of length N is The conversion is performed through Fourier transform to the corresponding frequency domain signal, and the corresponding frequency domain signal and the corresponding power spectrum density are obtained. The specific implementation process includes:

[0073] ;

[0074] in is the frequency domain signal, k is the complex Fourier coefficient, and N is the total number of samples of the signal;

[0075] ;

[0076] in, is the power spectral density corresponding to frequency k, is the amplitude of the Fourier coefficient;

[0077] The obtained main features are extracted to obtain the corresponding main frequency components, root mean square frequency and peak data of the frequency components;

[0078] The main frequency component is the position with the highest power in the frequency, and the main frequency component is marked as ZP;

[0079] ;

[0080] in, is the index of the maximum value in the power spectral density, is the corresponding frequency;

[0081] The RMS frequency is the 'center frequency' of the signal, and is denoted by f. rns ;

[0082] ;

[0083] The main peak of the frequency component is the significant peak in the identified spectrum. It is usually necessary to determine the peak point in the spectrum and mark the location and amplitude of the peak point;

[0084] The obtained main frequency component, root mean square frequency and peak value data of the frequency component are marked as corresponding physiological characteristic signals and motion characteristic signals respectively;

[0085] Acquire image signal data, and analyze and process the acquired image signal data. The specific implementation process includes:

[0086] Extracting features from the obtained real-time state image and muscle tissue image;

[0087] Performing grayscale value processing on the muscle tissue image to obtain pixel values ​​of corresponding pixel points in the corresponding muscle tissue image, thereby converting it into a grayscale image;

[0088] Preset the parameter information of the co-occurrence matrix and construct the gray-level co-occurrence matrix;

[0089] Obtain contrast data, homogeneity data, energy data, entropy data, correlation data and inverse moment in the muscle tissue image according to the gray-level co-occurrence matrix;

[0090] Obtain corresponding texture features and tissue structure features according to the data information obtained from the gray level co-occurrence matrix;

[0091] Perform motion capture on the real-time state image memory, and obtain the motion state image of the corresponding unit time according to the motion capture result;

[0092] Analyze and process the motion state images within a unit time respectively, and obtain unit state information according to the analysis results;

[0093] Set the unit status information of all unit time periods to a unit status information set;

[0094] A time series is set according to the order of the unit time, state curve data is set for the corresponding unit state information according to the time series, and feature extraction is performed on the obtained state curve data;

[0095] Acquire corresponding state characteristic signals according to the method of acquiring physiological characteristic signals;

[0096] Marking the obtained state feature signals, texture features and tissue structure features as image feature signals;

[0097] The acquired physiological characteristic signals, motion characteristic signals and image characteristic signals are sent to the data analysis module.

[0098] The data analysis module is used to analyze and process the obtained characteristic signals of corresponding types to construct a skeletal muscle characteristic signal spectrum of the patient's corresponding type, and the specific implementation process includes:

[0099] Acquire physiological characteristic signals, motion characteristic signals and image characteristic signals, and store them;

[0100] Acquire historical physiological characteristic signals and historical motion characteristic signals, and analyze and process the historical characteristic data corresponding to the acquired historical physiological characteristic signals and historical motion characteristic signals;

[0101] Analyze and process the historical feature data corresponding to the historical physiological feature signal and the historical feature data corresponding to the historical motion feature signal respectively, construct a corresponding historical feature data set, perform correlation analysis on the feature data in the historical feature data set, and obtain correlation data of the corresponding historical feature data respectively;

[0102] According to the correlation data, the corresponding physiological characteristic signals and motion characteristic signals are analyzed and processed respectively, and a physiological skeletal muscle characteristic signal spectrum and a motion skeletal muscle characteristic signal spectrum are constructed;

[0103] For the image feature signal, the obtained image feature signal includes the texture feature and tissue structure feature of the corresponding patient, and an image skeletal muscle feature signal atlas is generated according to the texture feature and tissue structure feature corresponding to the patient.

[0104] The personalized analysis module is used to perform correction processing on the obtained skeletal muscle characteristic signal spectrum, and divide the skeletal muscle characteristic signal spectrum into regions according to the correction processing result. The specific implementation process includes:

[0105] Acquire a skeletal muscle characteristic signal spectrum and a corresponding patient location, and correct the skeletal muscle characteristic signal spectrum according to the patient location information;

[0106] Obtain the corresponding standard skeletal muscle characteristic signal atlas according to the patient's location information;

[0107] Compare and analyze the skeletal muscle characteristic signal spectrum corresponding to the patient account with the corresponding standard skeletal muscle characteristic signal spectrum;

[0108] Obtain edge pixel points corresponding to the skeletal muscle characteristic signal map and the standard skeletal muscle characteristic signal map, and mark them as image pixel points and standard pixel points respectively;

[0109] Obtaining a proportionality coefficient between a skeletal muscle characteristic signal spectrum and a standard skeletal muscle characteristic signal spectrum, selecting image pixel points of a corresponding number of digits and standard pixel points of a corresponding number of digits according to the obtained proportionality coefficient for association, and obtaining an associated pixel point combination;

[0110] Compare and analyze the image pixels corresponding to the associated pixel combination with the standard pixels in turn, obtain the position distance of the corresponding pixels, analyze and process the position distance between the associated pixels, and preset the distance deviation threshold;

[0111] When the position distance is greater than the distance deviation threshold, the corresponding associated pixel point is marked as abnormal;

[0112] When the position distance is less than or equal to the distance deviation threshold, the corresponding associated pixel point is marked as normal;

[0113] Obtaining the abnormality rate of the corresponding associated pixel point combination in the skeletal muscle characteristic signal spectrum and the standard skeletal muscle characteristic signal spectrum;

[0114] A preset adjustment standard is set, and when the abnormality rate is greater than or equal to the adjustment standard, the correction process is continued; when the abnormality rate is less than the adjustment standard, the skeletal muscle characteristic signal spectrum completes the correction process;

[0115] The corrected skeletal muscle characteristic signal atlas is divided into regions according to its corresponding standard skeletal muscle characteristic signal atlas, the corresponding muscle group regions are obtained, and the muscle group regions of the skeletal muscle characteristic signal atlas are marked according to the division results.

[0116] The auxiliary diagnosis module is used to obtain the damaged area of ​​the corresponding data type in the skeletal muscle characteristic signal spectrum according to the area division result, and its specific implementation process includes:

[0117] Analyze and process the muscle group area marks corresponding to the skeletal muscle characteristic signal spectrum corresponding to the patient account in sequence;

[0118] Acquire image feature signals in the corresponding muscle group area, perform texture analysis on the acquired image feature signals, acquire pixel points in the central area of ​​the corresponding muscle group area, mark them as central pixels, compare the acquired central pixels with the pixels around them, generate texture codes according to the comparison results, and perform conversion according to the acquired texture codes;

[0119] According to the number of bits of texture coding, the corresponding mixed operation symbol is set, and the corresponding characters are calculated according to the mixed operation symbol to obtain the characteristic value of the central pixel;

[0120] The obtained feature value is compared with the texture feature. When the difference between the feature value and the standard texture feature value in the corresponding muscle group area is within the deviation threshold, there is no damage in the corresponding muscle group area.

[0121] When the difference between the feature value and the standard texture feature value in the corresponding muscle group area is not within the deviation threshold, there is damage in the corresponding muscle group area, and it is marked as an image damage area;

[0122] The physiological characteristic signals and the motion characteristic signals are mapped to the corresponding muscle group areas, and it is determined whether there are abnormalities in the physiological characteristic signals and the motion characteristic signals in the corresponding muscle group areas. If there are abnormalities, they are marked as physiological damage areas and motion damage areas respectively.

[0123] The comprehensive diagnosis module is used to perform comprehensive analysis on the obtained damage area, obtain corresponding damage degree data, and obtain comprehensive diagnosis data according to the corresponding damage degree data. The specific implementation process includes:

[0124] Obtaining a skeletal muscle characteristic signal atlas corresponding to the patient account, and mapping the analysis results corresponding to the physiological characteristic signals, the motion characteristic signals, and the image characteristic signals into the skeletal muscle characteristic signal atlas;

[0125] Obtaining whether the physiological characteristic signals and the motion characteristic signals meet the physiological characteristic standards and the motion characteristic standards in the corresponding muscle group area;

[0126] If it is in compliance, there is no injury in the corresponding muscle group area; if it is not in compliance, there is injury in the corresponding muscle group area, and the corresponding injury deviation value is obtained;

[0127] Obtain the injury deviation value of the injury type corresponding to the muscle group area, set the corresponding weight factor according to the injury type, integrate the injury deviation value and weight factor corresponding to the injury type in each muscle group area, and obtain the injury degree data of each muscle group area;

[0128] The corresponding type of injury deviation value in the corresponding muscle group area is multiplied by the weight factor, and the obtained products are added to obtain the injury degree data in the corresponding muscle group area;

[0129] The corresponding comprehensive diagnosis interval is preset according to the location information of the muscle group area, and the injury degree data obtained for the corresponding muscle group area is compared and analyzed with the corresponding comprehensive diagnosis area. The corresponding comprehensive diagnosis data is the injury degree, including no injury, general injury and severe injury.

[0130] like Figure 1 As shown, a diagnostic auxiliary method for skeletal muscle injury comprises the following steps:

[0131] Step S1: Collecting three types of signal data: physiological signal data, motion signal data, and image signal data; performing feature extraction on the collected different types of signal data to obtain corresponding physiological feature signals, motion feature signals, and image feature signals;

[0132] Step S2: Analyze and process the obtained characteristic signals of corresponding types, construct a skeletal muscle characteristic signal spectrum corresponding to the patient, perform correction processing on the obtained skeletal muscle characteristic signal spectrum, and divide the skeletal muscle characteristic signal spectrum into regions according to the correction processing results;

[0133] Step S3: Obtain the damaged area of ​​the corresponding data type in the skeletal muscle characteristic signal spectrum according to the regional division result; perform a comprehensive analysis on the obtained damaged area to obtain the corresponding damage degree data, and obtain comprehensive diagnostic data according to the corresponding damage degree data.

[0134] The above embodiments are only used to illustrate the technical method 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 method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A diagnosis assistance system for skeletal muscle injury, comprising a skeletal muscle auxiliary diagnosis platform, characterized in that: The skeletal muscle auxiliary diagnosis platform is provided with a data acquisition module, a data processing module, a data analysis module, a personalized analysis module, an auxiliary diagnosis module and a comprehensive diagnosis module; The data acquisition module is used to collect three types of signal data: physiological signal data, motion signal data and image signal data; The data processing module is used to extract features from different types of collected signal data to obtain corresponding physiological feature signals, motion feature signals and image feature signals; The data analysis module is used to analyze and process the obtained characteristic signals of the corresponding type, and construct a skeletal muscle characteristic signal spectrum of the patient's corresponding type; The personalized analysis module is used to perform correction processing on the obtained skeletal muscle characteristic signal spectrum, and divide the skeletal muscle characteristic signal spectrum into regions according to the correction processing result; The auxiliary diagnosis module is used to obtain the damaged area of ​​the corresponding data type in the skeletal muscle characteristic signal spectrum according to the area division result; The comprehensive diagnosis module is used to comprehensively analyze the obtained damage area, obtain corresponding damage degree data, and obtain comprehensive diagnosis data based on the corresponding damage degree data; The process of the data acquisition module acquiring three types of signal data, namely physiological signal data, motion signal data and image signal data, includes: The data acquisition modules are respectively associated with corresponding physiological acquisition devices, motion acquisition devices and image acquisition devices; Collect physiological signal data of the patient corresponding to the patient account according to the physiological collection device; Collecting motion signal data of the patient corresponding to the patient account using a motion collection device; Collecting image signal data of the patient corresponding to the patient account using an image acquisition device; The process of the personalized analysis module performing correction processing according to the obtained skeletal muscle characteristic signal spectrum and the patient account includes: Acquire a skeletal muscle characteristic signal spectrum and a corresponding patient location, and correct the skeletal muscle characteristic signal spectrum according to the patient location information; Obtain the corresponding standard skeletal muscle characteristic signal atlas according to the patient's location information; Compare and analyze the skeletal muscle characteristic signal spectrum corresponding to the patient account with the corresponding standard skeletal muscle characteristic signal spectrum; Obtain edge pixel points corresponding to the skeletal muscle characteristic signal map and the standard skeletal muscle characteristic signal map, and mark them as image pixel points and standard pixel points respectively; Compare and analyze the obtained image pixels with the standard pixels in turn, obtain the position distance of the corresponding pixels, and adjust the skeletal muscle characteristic signal spectrum by the position distance between the two corresponding pixels until the deviation rate corresponding to the position distance is less than the preset standard, and the skeletal muscle characteristic signal spectrum completes the correction process; Divide the corrected skeletal muscle characteristic signal spectrum into regions according to the corresponding standard skeletal muscle characteristic signal spectrum, obtain the corresponding muscle group regions, and mark the muscle group regions of the skeletal muscle characteristic signal spectrum according to the division results; The process of the auxiliary diagnosis module obtaining the damaged area of ​​the corresponding data type in the skeletal muscle characteristic signal spectrum according to the area division result includes: Analyze and process the muscle group area marks corresponding to the skeletal muscle characteristic signal spectrum corresponding to the patient account in sequence; Acquire the image feature signal in the corresponding muscle group area, perform texture analysis on the obtained image feature signal, obtain the pixel point in the central area of ​​the corresponding muscle group area, mark it as the central pixel, compare the obtained central pixel with the pixels around it, generate a texture code according to the comparison result, perform conversion according to the obtained texture code, and obtain the feature value of the central pixel; The obtained feature values ​​are compared with texture features, and the corresponding muscle group area is judged whether there is damage according to the comparison results. If there is damage, it is marked as an image damage area; Mapping the physiological characteristic signals and the motion characteristic signals to the corresponding muscle group areas, determining whether the physiological characteristic signals and the motion characteristic signals in the corresponding muscle group areas are abnormal, and if abnormal, marking them as physiological damage areas and motion damage areas respectively; The comprehensive diagnosis module performs a comprehensive analysis on the obtained damage area to obtain corresponding damage degree data. The process of obtaining comprehensive diagnosis data according to the corresponding damage degree data includes: Obtain the skeletal muscle characteristic signal spectrum corresponding to the patient account, map the analysis results corresponding to the physiological characteristic signal, the motion characteristic signal and the image characteristic signal into the skeletal muscle characteristic signal spectrum; obtain the injury condition corresponding to the corresponding muscle group area; Obtain the injury deviation value of the injury type corresponding to the muscle group area, set the corresponding weight factor according to the injury type, integrate the injury deviation value and weight factor corresponding to the injury type in each muscle group area, and obtain the injury degree data of each muscle group area; The corresponding comprehensive diagnosis interval is preset, the obtained damage degree data is compared and analyzed with the comprehensive diagnosis area, and the corresponding comprehensive diagnosis data is obtained according to the comparative analysis results.

2. A diagnostic assistance system for skeletal muscle injury according to claim 1, characterized in that: The data processing module extracts features from different types of collected signal data to obtain corresponding physiological feature signals, motion feature signals and image feature signals, including: Analyze and process the obtained physiological signal data and motion characteristic information, mark the obtained physiological signal data and motion characteristic information according to the acquisition time, and convert them into corresponding time domain signals; convert the obtained time domain signal of length N through Fourier transform to obtain the corresponding frequency domain signal, analyze and process the frequency domain signal to obtain the corresponding physiological characteristic signal and motion characteristic signal; Acquire image signal data, perform grayscale value processing on the acquired image signal data, acquire corresponding grayscale images, construct grayscale co-occurrence matrix, and acquire image feature signals corresponding to the corresponding grayscale images according to the grayscale co-occurrence matrix; The acquired physiological characteristic signals, motion characteristic signals and image characteristic signals are sent to the data analysis module.

3. A diagnostic assistance system for skeletal muscle injury according to claim 2, characterized in that: The data analysis module analyzes and processes the obtained characteristic signals of the corresponding type, and the process of constructing a skeletal muscle characteristic signal map of the patient's corresponding type includes: Acquire physiological characteristic signals, motion characteristic signals and image characteristic signals, and store them; For the image feature signal, the obtained image feature signal includes the texture features and tissue structure features of the corresponding patient, and a skeletal muscle feature signal atlas is generated according to the texture features and tissue structure features corresponding to the patient.

4. A method for diagnosing skeletal muscle injury according to a diagnosis assistance system for skeletal muscle injury according to any one of claims 1 to 3, characterized in that: The following steps are involved: Step S1: Collecting three types of signal data: physiological signal data, motion signal data, and image signal data; performing feature extraction on the collected different types of signal data to obtain corresponding physiological feature signals, motion feature signals, and image feature signals; Step S2: Analyze and process the obtained characteristic signals of corresponding types, construct a skeletal muscle characteristic signal spectrum corresponding to the patient, perform correction processing on the obtained skeletal muscle characteristic signal spectrum, and divide the skeletal muscle characteristic signal spectrum into regions according to the correction processing results; Step S3: Obtain the damaged area of ​​the corresponding data type in the skeletal muscle characteristic signal spectrum according to the regional division result; perform a comprehensive analysis on the obtained damaged area to obtain the corresponding damage degree data, and obtain comprehensive diagnostic data according to the corresponding damage degree data.

Images