Cerebral cortex state detection method and system based on disturbance of consciousness detection model

Abstract

The invention relates to the field of medical care, and particularly discloses a cerebral cortex state detection method and system based on a disturbance of consciousness detection model, and the method comprises the steps: dividing a cerebral cortex region according to different functional regions of the cerebral cortex, and obtaining different cerebral cortex monitoring sub-regions; the corresponding relation between the cerebral cortex monitoring sub-areas and the data acquisition point density is obtained in a cloud medical data server, and a data acquisition point distribution scheme of each cerebral cortex monitoring sub-area is obtained; the data acquisition point data management module acquires initial monitoring data of each cerebral cortex monitoring sub-region according to the data acquisition point distribution scheme; and comparing the monitoring data sequence of the cerebral cortex monitoring sub-region sequence of the corresponding stimulation type with the initial monitoring data sequence of the corresponding cerebral cortex monitoring sub-region one by one to complete the state detection of the cerebral cortex state. According to the invention, the neural activity state of the cerebral cortex can be monitored and evaluated in real time.

Description

Technical Field

[0001] The present invention relates to the field of medical care, and in particular to a method and system for detecting a cerebral cortex state based on a consciousness disorder detection model. Background Art

[0002] In the field of neuroscience and medicine, real-time monitoring and evaluation of the state of the cerebral cortex has always been a hot topic and a difficult point of research. As the center of human thinking, perception, and motor control, the normal function of the cerebral cortex is directly related to the health status of the individual. However, due to the complexity and inability to directly observe the cerebral cortex, traditional monitoring methods often have difficulty in accurately and timely capturing changes in the neural activity of the cerebral cortex.

[0003] In recent years, with the rapid development of neuroimaging, electrophysiology and computer technology, some new monitoring technologies have gradually emerged, providing new possibilities for monitoring the state of the cerebral cortex. Among them, the cerebral cortex state detection method based on the consciousness disorder detection model has attracted much attention due to its high precision and real-time performance.

[0004] Traditional cerebral cortex monitoring methods, such as electroencephalogram (EEG) and magnetic resonance imaging (MRI), can provide certain information about neural activity, but they often have limitations such as low resolution, susceptibility to interference, and inability to continuously monitor. The method based on the consciousness disorder detection model, by combining advanced signal processing technology, machine learning algorithms and big data analysis, can achieve comprehensive and accurate monitoring and evaluation of the cerebral cortex state. Summary of the invention

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a method for detecting the state of the cerebral cortex based on a consciousness disorder detection model, comprising the following steps:

[0006] Step 1: divide the cerebral cortex area according to different functional areas of the cerebral cortex to obtain different cerebral cortex monitoring sub-areas;

[0007] Step 2: Obtain the corresponding relationship between the cerebral cortex monitoring sub-areas and the data collection point density in the cloud medical data server, and obtain the data collection point distribution plan of each cerebral cortex monitoring sub-area according to the data collection point density corresponding to the cerebral cortex monitoring sub-area and the range of each cerebral cortex monitoring sub-area;

[0008] Step 3: The data collection point data management module arranges data collection points in each cerebral cortex monitoring sub-area according to the data collection point distribution plan, generates a data collection point distribution map corresponding to the cerebral cortex monitoring sub-area, and collects initial monitoring data of each cerebral cortex monitoring sub-area according to the set monitoring parameters;

[0009] Step 4: The state detection module obtains the detection scheme, generates a cerebral cortex monitoring sub-region sequence corresponding to the stimulation type according to the stimulation type in the detection scheme, obtains a monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type, and simultaneously obtains a corresponding cerebral cortex monitoring sub-region initial monitoring data sequence;

[0010] Step 5, comparing the monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type with the corresponding initial monitoring data sequence of the cerebral cortex monitoring sub-region one by one, respectively obtaining the cerebral cortex state data corresponding to each cerebral cortex monitoring sub-region, if there is cerebral cortex state data that is not within the normal data range corresponding to the cerebral cortex monitoring sub-region, then the cerebral cortex state is abnormal, and the process proceeds to step 6; otherwise, the cerebral cortex monitoring sub-region state is normal, and the monitoring data of the cerebral cortex monitoring sub-region is recorded, and the process proceeds to step 7;

[0011] Step 6: According to the data collection point distribution map corresponding to the abnormal cerebral cortex monitoring sub-region, locate the abnormal region in the cerebral cortex monitoring sub-region, send the abnormal region information and warning information to the warning module and the display module, and enter step 7;

[0012] Step seven, complete the state detection of the cerebral cortex state.

[0013] Furthermore, the cerebral cortex area is divided according to different functional areas of the cerebral cortex to obtain different cerebral cortex monitoring sub-areas, including:

[0014] The different functional areas of the cerebral cortex are preset functional areas with different functions, and the functional areas include the frontal lobe, parietal lobe, occipital lobe and temporal lobe. According to the range of each functional area, the cerebral cortex area is divided to obtain different cerebral cortex monitoring sub-areas.

[0015] Furthermore, the obtaining of the correspondence between the cerebral cortex monitoring sub-areas and the density of data collection points in the cloud medical data server includes:

[0016] The corresponding relationship is: obtaining the data collection point density of the functional area corresponding to the cerebral cortex monitoring sub-area in the cloud medical data server.

[0017] Furthermore, the data collection point distribution scheme of each cerebral cortex monitoring sub-region is obtained according to the density of data collection points corresponding to the cerebral cortex monitoring sub-region and the range of each cerebral cortex monitoring sub-region, including:

[0018] According to the density of data collection points and the range of the corresponding cerebral cortex monitoring sub-area, the number of data collection points and the distance between data collection points in the corresponding cerebral cortex monitoring sub-area are obtained; the number of data collection points and the distance between data collection points in each corresponding cerebral cortex monitoring sub-area constitute a data collection point distribution plan.

[0019] Furthermore, the data collection points are arranged in each cerebral cortex monitoring sub-area, a data collection point distribution map corresponding to the cerebral cortex monitoring sub-area is generated, and initial monitoring data of each cerebral cortex monitoring sub-area is collected according to the set monitoring parameters, including:

[0020] According to the number of data collection points and the data collection point spacing of each corresponding cerebral cortex monitoring sub-area, a data collection point distribution map of the corresponding cerebral cortex monitoring sub-area is obtained. According to the data collection point distribution map of the corresponding cerebral cortex monitoring sub-area and the set monitoring parameters, the initial monitoring data of the cerebral cortex monitoring sub-area is obtained.

[0021] Further, the method of generating a cerebral cortex monitoring sub-region sequence corresponding to the stimulation type according to the stimulation type in the detection scheme, obtaining a monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type, and obtaining a corresponding cerebral cortex monitoring sub-region initial monitoring data sequence at the same time includes:

[0022] According to the cerebral cortex functional area corresponding to the stimulation type, the cerebral cortex monitoring sub-area corresponding to the stimulation type is obtained, and the cerebral cortex monitoring sub-area corresponding to the stimulation type is sorted first. According to the set order, a cerebral cortex monitoring sub-area sequence corresponding to the stimulation type is obtained, and according to the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type, a monitoring data sequence of the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type is obtained; according to the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type, an initial monitoring data sequence of the cerebral cortex monitoring sub-area corresponding to the stimulation type is obtained.

[0023] Furthermore, the monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type is compared with the initial monitoring data sequence of the corresponding cerebral cortex monitoring sub-region one by one, and the cerebral cortex state data corresponding to each cerebral cortex monitoring sub-region is obtained respectively, including:

[0024] The state data are: the data difference between each detection data in the monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type and the corresponding initial monitoring data of the cerebral cortex monitoring sub-region.

[0025] A cerebral cortex state detection system based on a consciousness disorder detection model, applying a cerebral cortex state detection method based on a consciousness disorder detection model, including a cloud data server, a state detection module, a data processing module, a data acquisition module, a display module, an early warning module and a communication module;

[0026] The state detection module, data acquisition module, display module, warning module and communication module are respectively connected to the data processing module; the cloud data server is communicatively connected to the communication module.

[0027] The beneficial effects of the present invention are: through the cerebral cortex state detection method based on the consciousness disorder detection model, the neural activity state of the cerebral cortex can be monitored and evaluated in real time. This method can capture tiny changes in neural activity, thereby issuing early warnings in the early stages of the disease and improving the accuracy and timeliness of diagnosis. It can provide detailed cerebral cortex state data and abnormal area location information, providing an important reference for the rehabilitation team to formulate a personalized rehabilitation plan. According to the patient's specific situation and type of functional disorder, the rehabilitation team can formulate targeted rehabilitation measures to improve the rehabilitation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a flowchart of a method for detecting the state of the cerebral cortex based on a consciousness disorder detection model;

[0029] Figure 2 Schematic diagram of the principle of the cerebral cortex state detection system based on the consciousness disorder detection model. DETAILED DESCRIPTION

[0030] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0031] The features and performance of the present invention are further described in detail below in conjunction with the embodiments.

[0032] like Figure 1 As shown, the cerebral cortex state detection method based on the consciousness disorder detection model includes the following steps:

[0033] Step 1: divide the cerebral cortex area according to different functional areas of the cerebral cortex to obtain different cerebral cortex monitoring sub-areas;

[0034] Step 2: Obtain the corresponding relationship between the cerebral cortex monitoring sub-areas and the data collection point density in the cloud medical data server, and obtain the data collection point distribution plan of each cerebral cortex monitoring sub-area according to the data collection point density corresponding to the cerebral cortex monitoring sub-area and the range of each cerebral cortex monitoring sub-area;

[0035] Step 3: The data collection point data management module arranges data collection points in each cerebral cortex monitoring sub-area according to the data collection point distribution plan, generates a data collection point distribution map corresponding to the cerebral cortex monitoring sub-area, and collects initial monitoring data of each cerebral cortex monitoring sub-area according to the set monitoring parameters;

[0036] Step 4: The state detection module obtains the detection scheme, generates a cerebral cortex monitoring sub-region sequence corresponding to the stimulation type according to the stimulation type in the detection scheme, obtains a monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type, and simultaneously obtains a corresponding cerebral cortex monitoring sub-region initial monitoring data sequence;

[0037] Step 5, comparing the monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type with the corresponding initial monitoring data sequence of the cerebral cortex monitoring sub-region one by one, respectively obtaining the cerebral cortex state data corresponding to each cerebral cortex monitoring sub-region, if there is cerebral cortex state data that is not within the normal data range corresponding to the cerebral cortex monitoring sub-region, then the cerebral cortex state is abnormal, and the process proceeds to step 6; otherwise, the cerebral cortex monitoring sub-region state is normal, and the monitoring data of the cerebral cortex monitoring sub-region is recorded, and the process proceeds to step 7;

[0038] Step 6: According to the data collection point distribution map corresponding to the abnormal cerebral cortex monitoring sub-region, locate the abnormal region in the cerebral cortex monitoring sub-region, send the abnormal region information and warning information to the warning module and the display module, and enter step 7;

[0039] Step seven, complete the state detection of the cerebral cortex state.

[0040] The cerebral cortex area is divided according to different functional areas of the cerebral cortex to obtain different cerebral cortex monitoring sub-areas, including:

[0041] The different functional areas of the cerebral cortex are preset functional areas with different functions, and the functional areas include the frontal lobe, parietal lobe, occipital lobe and temporal lobe. According to the range of each functional area, the cerebral cortex area is divided to obtain different cerebral cortex monitoring sub-areas.

[0042] The obtaining of the correspondence between the cerebral cortex monitoring sub-areas and the density of data collection points in the cloud medical data server includes:

[0043] The corresponding relationship is: obtaining the data collection point density of the functional area corresponding to the cerebral cortex monitoring sub-area in the cloud medical data server.

[0044] The data collection point distribution scheme of each cerebral cortex monitoring sub-region is obtained according to the density of data collection points corresponding to the cerebral cortex monitoring sub-region and the range of each cerebral cortex monitoring sub-region, including:

[0045] According to the density of data collection points and the range of the corresponding cerebral cortex monitoring sub-area, the number of data collection points and the distance between data collection points in the corresponding cerebral cortex monitoring sub-area are obtained; the number of data collection points and the distance between data collection points in each corresponding cerebral cortex monitoring sub-area constitute a data collection point distribution plan.

[0046] The data collection points are arranged in each cerebral cortex monitoring sub-area, a data collection point distribution map corresponding to the cerebral cortex monitoring sub-area is generated, and initial monitoring data of each cerebral cortex monitoring sub-area is collected according to the set monitoring parameters, including:

[0047] According to the number of data collection points and the data collection point spacing of each corresponding cerebral cortex monitoring sub-area, a data collection point distribution map of the corresponding cerebral cortex monitoring sub-area is obtained. According to the data collection point distribution map of the corresponding cerebral cortex monitoring sub-area and the set monitoring parameters, the initial monitoring data of the cerebral cortex monitoring sub-area is obtained.

[0048] The method of generating a cerebral cortex monitoring sub-region sequence corresponding to the stimulation type according to the stimulation type in the detection scheme, obtaining a monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type, and obtaining a corresponding cerebral cortex monitoring sub-region initial monitoring data sequence at the same time, includes:

[0049] According to the cerebral cortex functional area corresponding to the stimulation type, the cerebral cortex monitoring sub-area corresponding to the stimulation type is obtained, and the cerebral cortex monitoring sub-area corresponding to the stimulation type is sorted first. According to the set order, a cerebral cortex monitoring sub-area sequence corresponding to the stimulation type is obtained, and according to the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type, a monitoring data sequence of the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type is obtained; according to the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type, an initial monitoring data sequence of the cerebral cortex monitoring sub-area corresponding to the stimulation type is obtained.

[0050] The monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type is compared with the initial monitoring data sequence of the corresponding cerebral cortex monitoring sub-region one by one to obtain the cerebral cortex state data corresponding to each cerebral cortex monitoring sub-region, including:

[0051] The state data are: the data difference between each detection data in the monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type and the corresponding initial monitoring data of the cerebral cortex monitoring sub-region.

[0052] like Figure 2 As shown, a cerebral cortex state detection system based on a consciousness disorder detection model applies a cerebral cortex state detection method based on a consciousness disorder detection model, including a cloud data server, a state detection module, a data processing module, a data acquisition module, a display module, an early warning module and a communication module;

[0053] The state detection module, data acquisition module, display module, warning module and communication module are respectively connected to the data processing module; the cloud data server is communicatively connected to the communication module.

[0054] Specifically, a method for detecting the state of the cerebral cortex based on a consciousness disorder detection model

[0055] Step 1: Division of the cerebral cortex

[0056] As a key component of the central nervous system, the cerebral cortex undertakes complex information processing and integration functions. According to the different functional areas of the cerebral cortex, we can divide it into several sub-areas for more refined monitoring. Specifically, these functional areas usually include the frontal lobe (responsible for thinking, emotion and motor control), the parietal lobe (processing information such as touch and spatial perception), the occipital lobe (mainly processing visual information) and the temporal lobe (involving hearing, memory and other functions). Through medical imaging technology, such as magnetic resonance imaging (MRI) or computed tomography (CT), the boundaries of these functional areas can be clearly defined, thereby achieving accurate division of the cerebral cortex area and obtaining different cerebral cortex monitoring sub-areas.

[0057] Step 2: Development of data collection point distribution plan

[0058] In the cloud medical data server, a large amount of historical research data on the density of data collection points in various functional areas of the cerebral cortex is stored. These data reflect the number of data collection points and their distribution density required for effective monitoring in different functional areas. According to the functional area corresponding to the cerebral cortex monitoring sub-area, we can retrieve the corresponding data collection point density information from the server. Combined with the specific range of each cerebral cortex monitoring sub-area, we can further calculate the number of data collection points required for each sub-area and the reasonable spacing between them, so as to formulate a detailed data collection point distribution plan.

[0059] Step 3: Data collection and acquisition of initial monitoring data

[0060] The data collection point data management module is responsible for accurately arranging data collection points in each cerebral cortex monitoring sub-area according to the data collection point distribution plan formulated in the previous step, and generating the corresponding data collection point distribution map. These data collection points may be implanted or attached to the surface of the cerebral cortex in a non-invasive or minimally invasive manner using technical means such as electrodes, optical sensors, or magnetic resonance imaging. Subsequently, according to the preset monitoring parameters (such as sampling frequency, signal amplification factor, etc.), the data acquisition module begins to collect initial monitoring data for each cerebral cortex monitoring sub-area, providing a basis for subsequent status analysis.

[0061] Step 4: Construction of monitoring data series

[0062] The state detection module first obtains the detection scheme, which usually includes the stimulus type (such as visual stimulation, auditory stimulation or tactile stimulation, etc.) and its presentation method. According to the cerebral cortex functional area corresponding to the stimulus type, the state detection module generates a cerebral cortex monitoring sub-area sequence corresponding to the stimulus type. This sequence is sorted according to the order or importance of the stimulus's impact on the cerebral cortex to ensure the timeliness and accuracy of the monitoring data. Next, the state detection module obtains the monitoring data sequence of the cerebral cortex monitoring sub-area sequence corresponding to the stimulus type from the data acquisition module, as well as the corresponding cerebral cortex monitoring sub-area initial monitoring data sequence, to provide a basis for subsequent state comparison.

[0063] Step 5: Comparison and analysis of cerebral cortex state data

[0064] After obtaining the monitoring data sequence, the state detection module will compare the monitoring data sequence of the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type with the initial monitoring data sequence one by one. By calculating the difference between each detection data and the initial monitoring data, the cerebral cortex state data corresponding to each cerebral cortex monitoring sub-area can be obtained. These state data reflect the activity state and changes of each functional area of ​​the cerebral cortex under specific stimulation. If there is cerebral cortex state data that is not within the preset normal data range, it indicates that the cerebral cortex state is abnormal and it is necessary to enter the next abnormal handling process; otherwise, it is considered that the state of the cerebral cortex monitoring sub-area is normal, and the monitoring data is recorded for subsequent analysis.

[0065] Step 6: Location and early warning of abnormal areas

[0066] When an abnormal state of the cerebral cortex is detected, the state detection module will quickly locate the abnormal area based on the distribution map of data collection points corresponding to the cerebral cortex monitoring sub-area with abnormal state. This process usually involves analyzing the spatial distribution characteristics of abnormal data to determine the specific location and range of the abnormal area. Subsequently, the state detection module will send the abnormal area information and warning information to the warning module and display module. The warning module is responsible for triggering the alarm mechanism and notifying medical staff in time for processing; while the display module is responsible for displaying the abnormal area in an intuitive way, so that medical staff can quickly understand and locate the problem.

[0067] Step 7: Completion and recording of status detection

[0068] After completing all the above steps, the entire cerebral cortex status detection process is also completed. At this point, the system will store all monitoring data, analysis results and abnormal processing records in the cloud data server for subsequent review and analysis. At the same time, the system will also generate a detailed test report, including the status data of each monitored sub-area of ​​the cerebral cortex, the location information of the abnormal area, and the treatment suggestions of medical staff, etc., to provide strong support for the patient's diagnosis and treatment.

[0069] Cerebral cortex state detection system based on consciousness disorder detection model

[0070] In order to implement the above detection method efficiently, a cerebral cortex state detection system based on the consciousness disorder detection model is designed. The system is mainly composed of a cloud data server, a state detection module, a data processing module, a data acquisition module, a display module, an early warning module and a communication module.

[0071] As the data storage and processing center of the system, the cloud data server is responsible for storing historical research data of various functional areas of the cerebral cortex, data collection point density information, and patient monitoring data. With powerful computing and data storage capabilities, the cloud data server can provide strong support for the system's real-time monitoring and data analysis.

[0072] The state detection module is one of the core components of the system. It is responsible for generating the corresponding cerebral cortex monitoring sub-area sequence according to the stimulation type in the detection scheme, and comparing and analyzing the monitoring data. Through the precise state detection algorithm, the state detection module can judge in real time whether the state of the cerebral cortex is normal, and promptly discover potential risks of impaired consciousness.

[0073] The data processing module is responsible for preprocessing and analyzing the received monitoring data. Through filtering, denoising and other processing methods, the data processing module can extract effective neural signal features and provide accurate data support for subsequent state detection. At the same time, the data processing module is also responsible for sending the processed data to the cloud data server for storage and backup.

[0074] The data acquisition module is the interface between the system and the cerebral cortex. It is responsible for arranging data acquisition points in each monitoring sub-area of ​​the cerebral cortex according to the data acquisition point distribution plan and collecting monitoring data in real time. Through high-precision sensors and advanced signal processing technology, the data acquisition module can ensure the accuracy and reliability of monitoring data.

[0075] The display module is responsible for displaying the system's monitoring results in an intuitive way, making it easy for medical staff to view and analyze. Through a graphical interface and dynamic display function, the display module can clearly display key information such as the status data of each monitored sub-area of ​​the cerebral cortex, the location information of abnormal areas, and the patient's state of consciousness.

[0076] The early warning module is responsible for triggering the alarm mechanism when an abnormal state of the cerebral cortex is detected, and promptly notifying medical staff for treatment. Through various means such as sound, light or vibration, the early warning module can ensure that medical staff receive abnormal information in the first place and take effective intervention measures.

[0077] The communication module is responsible for data transmission and communication between the components of the system. Through high-speed and stable network connection, the communication module can ensure real-time data interaction and collaborative work between components. At the same time, the communication module also supports remote communication with cloud data servers to achieve remote storage and access of data.

[0078] Example 1: Application of cerebral cortical state detection based on consciousness disorder detection model in epilepsy patients

[0079] Epilepsy is a chronic disease caused by abnormal discharges of brain neurons, with various clinical manifestations, including loss of consciousness, convulsions, paresthesias, etc. Epilepsy attacks are often difficult to predict, causing great distress to patients' daily lives, and also placing a burden on their families and society. Therefore, it is particularly important to develop a technology that can monitor the state of the cerebral cortex in real time and warn of epileptic seizures. This embodiment will introduce in detail the application of a cerebral cortex state detection method based on a consciousness disorder detection model in epilepsy patients.

[0080] First, we used magnetic resonance imaging (MRI) technology to scan the brains of epilepsy patients and obtain high-resolution brain structural images. According to the different functional areas of the cerebral cortex, we divided the cerebral cortex into four main monitoring sub-areas: frontal lobe, parietal lobe, occipital lobe and temporal lobe. In particular, since the temporal lobe is one of the common origin areas of epileptic seizures, we divided the temporal lobe more finely in order to more accurately monitor the activity status of this area.

[0081] In the cloud medical data server, we retrieved historical research data on the density of cerebral cortical data collection points related to epilepsy. Based on this data, we developed a data collection point distribution plan for epilepsy patients. In key areas such as the temporal lobe, we increased the density of data collection points to ensure that more neural activity information can be captured. At the same time, we also considered the uniformity of the distribution of data collection points to avoid monitoring bias caused by too much or too little local data.

[0082] We used minimally invasive electrode implantation technology to precisely arrange data collection points in each monitoring sub-area of ​​the cerebral cortex of epileptic patients. These electrodes can collect neural activity signals from the cerebral cortex in real time and convert them into digital signals for transmission. During the data collection process, we strictly controlled monitoring parameters such as sampling frequency and signal amplification to ensure the accuracy and reliability of the data. Through continuous monitoring for several days, we obtained initial monitoring data of the cerebral cortex of epileptic patients.

[0083] According to the specific condition and detection needs of epilepsy patients, we developed a corresponding detection plan. In this plan, we chose visual stimulation as the type of stimulation to induce epileptic seizures. Therefore, we generated a sequence of cerebral cortex monitoring sub-areas corresponding to visual stimulation, which was ranked first by the occipital lobe that processes visual information, followed by the temporal lobe, parietal lobe, and frontal lobe. Through the data acquisition module, we obtained the monitoring data sequence of the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type, as well as the corresponding cerebral cortex monitoring sub-area initial monitoring data sequence.

[0084] We used the state detection module to compare and analyze the monitoring data sequence. By calculating the difference between each detection data and the initial monitoring data, we obtained the cerebral cortex state data corresponding to each cerebral cortex monitoring sub-area. During the comparison process, we found that the state data of the temporal lobe area showed significant abnormal fluctuations, which suggested that there may be a risk of epileptic seizures in this area.

[0085] Based on the analysis results of the status detection module, we located the abnormal area in the temporal lobe. Through data analysis, we found that the neural activity signal in this area showed high-frequency and high-amplitude abnormal discharge, which is a typical feature of epileptic seizures. Therefore, we immediately triggered the early warning mechanism, sent an alarm to the medical staff through the early warning module, and sent the abnormal area information and early warning information to the display module at the same time.

[0086] After confirming that the patient did not have an actual seizure, we ended the status detection process. We stored all monitoring data, analysis results, and abnormal processing records in the cloud data server for subsequent review and analysis. At the same time, we also generated a detailed test report, including the status data of each monitored sub-area of ​​the cerebral cortex, the location information of the abnormal area, and the treatment suggestions of medical staff. This report provides strong support for the patient's subsequent treatment.

[0087] Example 2: Application of cerebral cortical state detection based on consciousness disorder detection model in brain injury rehabilitation

[0088] Brain injury is a type of brain tissue damage caused by external forces, and its clinical manifestations include impaired consciousness, movement disorders, cognitive impairment, etc. The rehabilitation process of brain injury is long and complicated, and requires continuous monitoring and evaluation to guide the formulation and implementation of rehabilitation plans. This embodiment will introduce in detail the application of the cerebral cortex state detection method based on the consciousness disorder detection model in brain injury rehabilitation.

[0089] According to the specific situation of patients with brain injury, we use computed tomography (CT) technology to scan the patient's brain and obtain clear images of brain tissue structure. According to the different functional areas of the cerebral cortex, we divide the cerebral cortex into four main monitoring sub-areas: frontal lobe, parietal lobe, occipital lobe and temporal lobe. At the same time, we also pay special attention to the functional areas of the brain injury area and its surrounding areas in order to more accurately evaluate the impact of brain injury on the function of the cerebral cortex.

[0090] In the cloud medical data server, we retrieved historical research data on the density of cerebral cortical data collection points related to brain injury. Based on this data, we developed a data collection point distribution plan for patients with brain injury. We increased the density of data collection points in the brain injury area and its surrounding functional areas to ensure that more neural activity information can be captured. At the same time, we also took into account the actual situation and rehabilitation needs of the patients and developed a personalized data collection point distribution plan.

[0091] We used non-invasive optical sensor technology and arranged data collection points in each monitoring sub-area of ​​the cerebral cortex of brain-injured patients. These sensors can collect neural activity signals from the cerebral cortex in real time and convert them into digital signals for transmission. During the data collection process, we strictly controlled monitoring parameters such as sampling frequency and signal amplification to ensure the accuracy and reliability of the data. Through continuous monitoring for several weeks, we obtained initial monitoring data of the cerebral cortex of brain-injured patients.

[0092] According to the rehabilitation plan and testing needs of brain-injured patients, we developed a corresponding testing plan. In this plan, we selected multiple stimulation types, including tactile stimulation, auditory stimulation, and visual stimulation, to comprehensively evaluate the patient's cerebral cortex function. We generated cerebral cortex monitoring sub-area sequences corresponding to various stimulation types, and obtained the corresponding monitoring data sequences and initial monitoring data sequences through the data acquisition module.

[0093] We used the state detection module to compare and analyze the monitoring data sequence. By calculating the difference between each detection data and the initial monitoring data, we obtained the cerebral cortex state data corresponding to each cerebral cortex monitoring sub-area. During the comparison process, we found that the state data of the brain damage area and its surrounding functional areas showed obvious abnormal changes, which suggested that the function of this area may be damaged.

[0094] Based on the analysis results of the status detection module, we located the abnormal areas in the brain injury area and its surrounding functional areas. Through data analysis, we found that the neural activity signals in these areas weakened or disappeared, which is a typical functional disorder caused by brain injury. Therefore, we sent an early warning message to the rehabilitation team and provided the location information of the abnormal area and a functional assessment report.

[0095] After completing this status test, we stored all monitoring data, analysis results and abnormal processing records in the cloud data server for subsequent review and analysis. At the same time, we also generated a detailed test report, including the status data of each monitored sub-area of ​​the cerebral cortex, the location information of the abnormal area, the functional evaluation report and rehabilitation suggestions. This report provides strong support for the patient's subsequent rehabilitation plan.

[0096] The above is only a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art shall not deviate from the spirit and scope of the present invention, and shall be within the scope of protection of the claims attached to the present invention.

Claims

1. A method for detecting cerebral cortex state based on a consciousness disorder detection model, characterized in that: The steps include: Step 1: divide the cerebral cortex area according to different functional areas of the cerebral cortex to obtain different cerebral cortex monitoring sub-areas; Step 2: Obtain the corresponding relationship between the cerebral cortex monitoring sub-areas and the data collection point density in the cloud medical data server, and obtain the data collection point distribution plan of each cerebral cortex monitoring sub-area according to the data collection point density corresponding to the cerebral cortex monitoring sub-area and the range of each cerebral cortex monitoring sub-area; Step 3: The data collection point data management module arranges data collection points in each cerebral cortex monitoring sub-area according to the data collection point distribution plan, generates a data collection point distribution map corresponding to the cerebral cortex monitoring sub-area, and collects initial monitoring data of each cerebral cortex monitoring sub-area according to the set monitoring parameters; Step 4: The state detection module obtains the detection scheme, generates a cerebral cortex monitoring sub-region sequence corresponding to the stimulation type according to the stimulation type in the detection scheme, obtains a monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type, and simultaneously obtains a corresponding cerebral cortex monitoring sub-region initial monitoring data sequence; Step 5, comparing the monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type with the initial monitoring data sequence of the corresponding cerebral cortex monitoring sub-region one by one, respectively obtaining the cerebral cortex state data corresponding to each cerebral cortex monitoring sub-region, if there is cerebral cortex state data that is not within the normal data range corresponding to the cerebral cortex monitoring sub-region, then the cerebral cortex state is abnormal, and the process proceeds to step 6; otherwise, the cerebral cortex monitoring sub-region state is normal, and the monitoring data of the cerebral cortex monitoring sub-region is recorded, and the process proceeds to step 7; Step 6: According to the data collection point distribution map corresponding to the abnormal cerebral cortex monitoring sub-region, locate the abnormal region in the cerebral cortex monitoring sub-region, send the abnormal region information and warning information to the warning module and the display module, and enter step 7; Step seven, complete the state detection of the cerebral cortex state.

2. The method for detecting cerebral cortex state based on the consciousness disorder detection model according to claim 1, characterized in that: The cerebral cortex area is divided according to different functional areas of the cerebral cortex to obtain different cerebral cortex monitoring sub-areas, including: The different functional areas of the cerebral cortex are preset functional areas with different functions, and the functional areas include the frontal lobe, parietal lobe, occipital lobe and temporal lobe. According to the range of each functional area, the cerebral cortex area is divided to obtain different cerebral cortex monitoring sub-areas.

3. The method for detecting cerebral cortex state based on the consciousness disorder detection model according to claim 2, characterized in that: The obtaining of the correspondence between the cerebral cortex monitoring sub-areas and the density of data collection points in the cloud medical data server includes: The corresponding relationship is: obtaining the data collection point density of the functional area corresponding to the cerebral cortex monitoring sub-area in the cloud medical data server.

4. The method for detecting cerebral cortex state based on the consciousness disorder detection model according to claim 3, characterized in that: The data collection point distribution scheme of each cerebral cortex monitoring sub-region is obtained according to the density of data collection points corresponding to the cerebral cortex monitoring sub-region and the range of each cerebral cortex monitoring sub-region, including: According to the density of data collection points and the range of the corresponding cerebral cortex monitoring sub-area, the number of data collection points and the distance between data collection points in the corresponding cerebral cortex monitoring sub-area are obtained; the number of data collection points and the distance between data collection points in each corresponding cerebral cortex monitoring sub-area constitute a data collection point distribution plan.

5. The method for detecting cerebral cortex state based on the consciousness disorder detection model according to claim 1, characterized in that: The data collection points are arranged in each cerebral cortex monitoring sub-area, a data collection point distribution map corresponding to the cerebral cortex monitoring sub-area is generated, and initial monitoring data of each cerebral cortex monitoring sub-area is collected according to the set monitoring parameters, including: According to the number of data collection points and the data collection point spacing of each corresponding cerebral cortex monitoring sub-area, a data collection point distribution map of the corresponding cerebral cortex monitoring sub-area is obtained. According to the data collection point distribution map of the corresponding cerebral cortex monitoring sub-area and the set monitoring parameters, the initial monitoring data of the cerebral cortex monitoring sub-area is obtained.

6. The method for detecting cerebral cortex state based on the consciousness disorder detection model according to claim 1, characterized in that: The method of generating a cerebral cortex monitoring sub-region sequence corresponding to the stimulation type according to the stimulation type in the detection scheme, obtaining a monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type, and obtaining a corresponding cerebral cortex monitoring sub-region initial monitoring data sequence at the same time, includes: According to the cerebral cortex functional area corresponding to the stimulation type, the cerebral cortex monitoring sub-area corresponding to the stimulation type is obtained, and the cerebral cortex monitoring sub-area corresponding to the stimulation type is sorted first. According to the set order, a cerebral cortex monitoring sub-area sequence corresponding to the stimulation type is obtained, and according to the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type, a monitoring data sequence of the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type is obtained; according to the cerebral cortex monitoring sub-area sequence corresponding to the stimulation type, an initial monitoring data sequence of the cerebral cortex monitoring sub-area corresponding to the stimulation type is obtained.

7. The method for detecting cerebral cortex state based on the consciousness disorder detection model according to claim 6, characterized in that: The monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type is compared with the initial monitoring data sequence of the corresponding cerebral cortex monitoring sub-region one by one to obtain the cerebral cortex state data corresponding to each cerebral cortex monitoring sub-region, including: The state data are: the data difference between each detection data in the monitoring data sequence of the cerebral cortex monitoring sub-region sequence corresponding to the stimulation type and the corresponding initial monitoring data of the cerebral cortex monitoring sub-region.

8. A cerebral cortex state detection system based on a consciousness disorder detection model, characterized in that: A method for detecting the state of the cerebral cortex based on the consciousness disorder detection model according to any one of claims 1 to 7 is applied, comprising a cloud data server, a state detection module, a data processing module, a data acquisition module, a display module, an early warning module and a communication module; The state detection module, data acquisition module, display module, warning module and communication module are respectively connected to the data processing module; the cloud data server is communicatively connected to the communication module.

Images