Dynamic brain network construction and analysis method based on depression diagnosis

Abstract

The invention discloses a dynamic brain network construction and analysis method based on depression diagnosis, and relates to the technical field of depression diagnosis brain network monitoring. The equipment connection master control platform is connected with electroencephalogram observation equipment, scene simulation equipment, a parameter synchronization platform and a data transmission platform; the equipment connection master control platform is associated with the data acquisition unit, the data acquisition unit is connected with the processing center, the data processing unit and the user interaction unit are arranged in the data acquisition unit, and the processing center is connected with the report generation unit; the data processing unit is associated with the user interaction unit, the data processing unit is associated with the equipment connection main control platform, and the data processing center can establish an electroencephalogram model of real-time data. Through the arrangement of the electroencephalogram observation equipment and the scene simulation equipment, an administrator can effectively observe the electroencephalogram condition of a patient by adjusting the scene simulation equipment, so that brain network data construction is more convenient.

Description

Technical Field

[0001] The present invention relates to the technical field of brain network monitoring for depression diagnosis, and specifically to a dynamic brain network construction and analysis method based on depression diagnosis. Background Art

[0002] Depression is one of the common mental illnesses in modern society. It often puts people in a state of long-term depression and depression without the patient knowing it. Severe depression patients may lose the ability to communicate emotionally. Therefore, there is an urgent need for a dynamic brain network construction and analysis method for depression diagnosis to observe the patient's electroencephalogram to establish the patient's brain network status during depression and then treat it. However, the existing dynamic brain network construction and analysis method based on depression diagnosis has some shortcomings, such as:

[0003] Application number: CN202410128454.0, a method and system for analyzing depression characteristics based on the LSTM effective connection brain network model, which uses connection fusion strength to judge depression in subjects, can effectively eliminate the interference of images between different patients, improve the accuracy of depression classification, greatly reduce the time required for disease diagnosis, and improve diagnostic efficiency. However, in actual use, it is difficult to effectively observe the brain activity of patients in different scenarios, which may cause the system to be difficult to effectively analyze the symptoms of depression when determining the condition of depression.

[0004] Therefore, we proposed a dynamic brain network construction and analysis method based on depression diagnosis, in order to solve the problem that most of the depression feature analysis methods and systems mentioned above are difficult to effectively observe the brain activities of patients in different scenarios, which may cause the system to be difficult to effectively analyze the symptoms of depression when judging the condition of depression. Summary of the invention

[0005] The purpose of the present invention is to provide a method for constructing and analyzing a dynamic brain network based on depression diagnosis to solve the current market problems raised by the above background technology.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a method for constructing and analyzing a dynamic brain network based on depression diagnosis, comprising a device connected to a main control platform and a data acquisition unit connected to the device connected to the main control platform; the device connected to the main control platform is connected to an electroencephalogram observation device, a scene simulation device, a parameter synchronization platform, and a data transmission platform; and the device connected to the main control platform is associated with the data acquisition unit, and the data acquisition unit is connected to a processing center, wherein a data processing unit and a user interaction unit are arranged inside the data acquisition unit, and the processing center is connected to a report generation unit;

[0007] The data processing unit is associated with the user interaction unit, and the data processing unit is associated with the device connection main control platform, and the data processing center can establish an electroencephalogram model of real-time data.

[0008] Through the setting of EEG observation equipment and scene simulation equipment, the administrator can effectively observe the patient's EEG condition by adjusting the equipment of the scene simulation equipment, and through the setting of the parameter synchronization platform, the EEG observation equipment and the scene simulation equipment can be in the same operating state, so that the data acquisition unit can collect the patient's EEG data more conveniently.

[0009] As a preferred technical solution of the present invention, a frequency adjustment unit, a data recording unit and an abnormality recording unit are provided inside the device connected to the main control platform; and the frequency adjustment unit can adjust the use frequency of the EEG observation device and the scene simulation device, and an alarm mechanism is provided inside the abnormality recording unit.

[0010] The above technical solution enables the device to be connected to the main control platform and adjust the use frequency of the EEG observation device and the scene simulation device through the frequency adjustment unit, thereby increasing the adjustability of the device.

[0011] As a preferred technical solution of the present invention, the EEG observation device includes an EEG monitoring module, a heart rate monitoring module and a signal extraction module, wherein the signal extraction module can extract monitoring data of the EEG monitoring module and the heart rate monitoring module;

[0012] The scene simulation device includes a VR simulation module and a tactile simulation module, and the parameter synchronization platform can control the operating frequencies of the EEG observation device and the scene simulation device at the same level, and the parameter synchronization platform is associated with the data recording unit inside the device connection main control platform.

[0013] The adoption of the above technical solution can make it more convenient for the data acquisition unit to collect data received by the EEG observation device and the scene simulation device, thereby increasing the efficiency of the device in extracting data.

[0014] As a preferred technical solution of the present invention, a decoding modeling module is provided inside the data processing unit, and the decoding modeling module includes a data identification module, a data modeling module and a model comparison module, wherein the data identification module can decode and identify the electroencephalogram and heart rate data received by the decoding modeling module, and the data modeling module can model the data received by the decoding modeling module, and the model comparison module can compare the data status of the previous and next models in real time.

[0015] The use of the above technical solution can make the device more convenient when establishing a brain network data model, and can compare the previous and subsequent data models.

[0016] As a preferred technical solution of the present invention, the data processing unit includes a model database, and the model database is provided with a model storage unit and a large behavior database.

[0017] The adoption of the above technical solution enables administrators to more conveniently search for past data models or similar cases, thereby increasing the scalability of the device.

[0018] As a preferred technical solution of the present invention, a data diagnosis module is provided inside the user interaction unit, and the data diagnosis module includes an information recording module and an auxiliary data adding module, and the auxiliary data adding module can record and integrate the data added by the administrator and transmit it to the data processing unit for processing.

[0019] The adoption of the above technical solution enables the data processing unit to transmit auxiliary data to the data processing unit through the auxiliary data adding module when establishing brain network data.

[0020] As a preferred technical solution of the present invention, a behavior record tag is provided inside the user interaction unit, and the behavior record tag is provided inside with a rehabilitation behavior record and a behavior time record.

[0021] The adoption of the above technical solution can make it more convenient to record the patient's behavior and behavior time during rehabilitation, thereby making it more convenient for the processing center to record the patient's rehabilitation status.

[0022] As a preferred technical solution of the present invention, when the device is connected to the main control platform to connect the EEG observation device and the scene simulation device for use, the data recording unit can record the real-time usage of the EEG observation device and the scene simulation device.

[0023] The adoption of the above technical solution can make it more convenient for the data recording unit to record the usage of the EEG observation device and the scene simulation device connected to the main control platform.

[0024] As a preferred technical solution of the present invention, the EEG monitoring module is an EEG monitoring helmet, and when the patient wears the EEG monitoring module, the EEG monitoring module needs to be turned off by the frequency adjustment unit to prevent accidental touch and accidents. In addition, when using the EEG monitoring module, an EEG generation test needs to be performed first to ensure that the EEG monitoring module can be used normally.

[0025] The adoption of the above technical solution can reduce the occurrence of abnormal situations when the EEG monitoring module is in use, thereby increasing the stability of the EEG monitoring module when in use.

[0026] As a preferred technical solution of the present invention, a method for constructing and analyzing a dynamic brain network based on depression diagnosis comprises the following steps:

[0027] Step 1: The patient wears the EEG monitoring module and the heart rate monitoring module in the EEG observation device, and then connects the device to the main control platform, so that the EEG monitoring module and the heart rate monitoring module are controlled by the device connected to the main control platform;

[0028] Step 2: Make the patient wear the VR simulation module in the scene simulation device, and use the tactile simulation module to simulate the patient's tactile sensation in the scene, and then synchronize the parameters of the EEG observation device and the scene simulation device through the parameter synchronization platform;

[0029] Step 3: Adjust the use frequency of the EEG observation device and the scene simulation device by connecting the device to the frequency adjustment unit inside the main control platform;

[0030] Step 4: The EEG data and heart rate data are transmitted to the processing center through the data acquisition unit, so that the data processing unit can perform modeling. At the same time, the patient's behavior data can be transmitted to the data processing unit through the user interaction unit, thereby forming a dynamic brain network model.

[0031] Step 5: Establish an EEG model through the decoding modeling module set inside the data processing unit, and search for similar EEG model data through the model database for comparison, so as to find the common points of previous cases;

[0032] Step 6: Record the patient's behavior during the rehabilitation process and the time when the behavior occurred during the rehabilitation process through the behavior record tag set in the user interaction unit;

[0033] Step 7: The report generation unit generates a rehabilitation report based on the real-time EEG model data, the patient's behavior during rehabilitation, and the time when the behavior occurs during rehabilitation to complete the dynamic brain network construction and analysis.

[0034] Compared with the prior art, the present invention has the following beneficial effects: through the setting of the EEG observation device and the scene simulation device, the administrator can effectively observe the patient's EEG condition by adjusting the device of the scene simulation device, and through the setting of the parameter synchronization platform, the EEG observation device and the scene simulation device can be in the same operating state, so that the data acquisition unit can be more convenient when collecting the patient's EEG data;

[0035] Furthermore, by setting up the signal extraction module, the data acquisition unit can be more convenient when collecting data received by the EEG observation device and the scene simulation device, thereby increasing the efficiency of the device in extracting data;

[0036] Furthermore, through the setting of the auxiliary data adding module, when the data processing unit is establishing brain network data, the auxiliary data can be transmitted to the data processing unit through the auxiliary data adding module. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0038] Figure 2 A schematic diagram of the structure of the device of the present invention connected to the main control platform;

[0039] Figure 3 It is a schematic diagram of the structure of the processing center of the present invention;

[0040] Figure 4 It is a schematic diagram of the process structure of the present invention;

[0041] Figure 5 It is a detailed process structure schematic diagram of the present invention.

[0042] In the figure: 100, equipment connection main control platform; 101, frequency adjustment unit; 102, data recording unit; 103, abnormal recording unit; 110, EEG observation equipment; 111, EEG monitoring module; 112, heart rate monitoring module; 113, signal extraction module; 120, scene simulation equipment; 121, VR simulation module; 122, tactile simulation module; 130, parameter synchronization platform; 140, data transmission platform; 200, data acquisition unit; 300, processing center; 400, Data processing unit; 410, decoding modeling module; 411, data identification module; 412, data modeling module; 413, model comparison module; 420, model database; 421, model storage unit; 422, behavior database; 500, user interaction unit; 510, data diagnosis module; 511, information recording module; 512, auxiliary data adding module; 520, behavior record label; 521, behavior record during rehabilitation; 522, behavior time record; 600, report generation unit. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0044] Embodiment 1:

[0045] See also Figure 1-5The present invention provides a technical solution: a method for constructing and analyzing a dynamic brain network based on depression diagnosis, comprising a device connection main control platform 100, and a data acquisition unit 200 connected to the device connection main control platform 100; the device connection main control platform 100 is connected with an electroencephalogram observation device 110, a scene simulation device 120, a parameter synchronization platform 130, and a data transmission platform 140; and the device connection main control platform 100 is associated with the data acquisition unit 200, and the data acquisition unit 200 is connected to a processing center 300, and the data acquisition unit 200 is provided with a data processing unit 400 and a user interaction unit 500 inside the data acquisition unit 200, and the processing center 300 is connected with a report generation unit 600;

[0046] The data processing unit 400 is associated with the user interaction unit 500, and the data processing unit 400 is associated with the device connection control platform 100, and the data processing center 300 is capable of establishing an EEG model of real-time data;

[0047] The device connection main control platform 100 is internally provided with a frequency adjustment unit 101, a data recording unit 102 and an abnormality recording unit 103; and the frequency adjustment unit 101 can adjust the use frequency of the EEG observation device 110 and the scene simulation device 120, and the abnormality recording unit 103 is internally provided with an alarm mechanism;

[0048] The EEG observation device 110 includes an EEG monitoring module 111, a heart rate monitoring module 112 and a signal extraction module 113, wherein the signal extraction module 113 can extract monitoring data of the EEG monitoring module 111 and the heart rate monitoring module 112; the scene simulation device 120 includes a VR simulation module 121 and a tactile simulation module 122, and the parameter synchronization platform 130 can control the operating frequencies of the EEG observation device 110 and the scene simulation device 120 at the same level, and the parameter synchronization platform 130 is associated with the data recording unit 102 inside the device connection main control platform 100;

[0049] The data processing unit 400 is internally provided with a decoding modeling module 410, and the decoding modeling module 410 internally includes a data identification module 411, a data modeling module 412 and a model comparison module 413, wherein the data identification module 411 can decode and identify the electroencephalogram and heart rate data received by the decoding modeling module 410, and the data modeling module 412 can model the data received by the decoding modeling module 410, and the model comparison module 413 can compare the data status of the models before and after in real time;

[0050] The data processing unit 400 includes a model database 420, and the model database 420 is provided with a model storage unit 421 and a behavior database 422; the user interaction unit 500 is provided with a data diagnosis module 510, and the data diagnosis module 510 includes an information recording module 511 and an auxiliary data adding module 512, and the auxiliary data adding module 512 can record and integrate the data added by the administrator, and transmit it to the data processing unit 400 for processing;

[0051] The user interaction unit 500 is provided with a behavior record tag 520, and the behavior record tag 520 is provided with a behavior record 521 and a behavior time record 522 during rehabilitation; when the device is connected to the main control platform 100 and connected to the EEG observation device 110 and the scene simulation device 120 for use, the data recording unit 102 can record the real-time use of the EEG observation device 110 and the scene simulation device 120;

[0052] The EEG monitoring module 111 is an EEG monitoring helmet, and when the patient wears the EEG monitoring module 111, the frequency adjustment unit 101 needs to be used to turn off the EEG monitoring module 111 to prevent accidental touch and an accident. When the EEG monitoring module 111 is used, an EEG generation test needs to be performed first to ensure that the EEG monitoring module 111 can be used normally.

[0053] A method for constructing and analyzing a dynamic brain network based on depression diagnosis includes the following steps:

[0054] Step 1: The patient wears the EEG monitoring module 111 and the heart rate monitoring module 112 in the EEG observation device 110, and then connects the device to the main control platform 100, so that the EEG monitoring module 111 and the heart rate monitoring module 112 are controlled by the device to the main control platform 100;

[0055] Step 2: Make the patient wear the VR simulation module 121 in the scene simulation device 120, and simulate the tactile sensation of the patient in the scene through the tactile simulation module 122, and then synchronize the parameters of the EEG observation device 110 and the scene simulation device 120 through the parameter synchronization platform 130;

[0056] Step 3: Adjust the use frequency of the EEG observation device 110 and the scene simulation device 120 by connecting the device to the frequency adjustment unit 101 inside the main control platform 100;

[0057] Step 4: The EEG data and the heart rate data are transmitted to the processing center 300 through the data acquisition unit 200, so that the data processing unit 400 performs modeling. At the same time, the patient's behavior data can be transmitted to the data processing unit 400 through the user interaction unit 500, thereby forming a dynamic brain network model.

[0058] Step 5: The EEG model is established by the decoding modeling module 410 provided in the data processing unit 400, and similar EEG model data are searched for comparison through the model database 420, so as to find the common points of previous cases;

[0059] Step 6: Record the patient's behavior during the rehabilitation process and the time when the behavior occurred during the rehabilitation process through the behavior recording tag 520 set inside the user interaction unit 500;

[0060] Step 7: The report generating unit 600 generates a rehabilitation report based on the real-time EEG model data, the patient's behavior during rehabilitation, and the time when the behavior occurs during rehabilitation to complete the dynamic brain network construction and analysis;

[0061] Embodiment 2:

[0062] The difference between this embodiment and embodiment 1 is that: a method for constructing and analyzing a dynamic brain network based on depression diagnosis comprises the following steps:

[0063] Step 1: The patient wears the EEG monitoring module 111 and the heart rate monitoring module 112 in the EEG observation device 110, and then connects the device to the main control platform 100, so that the EEG monitoring module 111 and the heart rate monitoring module 112 are controlled by the device to the main control platform 100;

[0064] Step 2: Make the patient wear the VR simulation module 121 in the scene simulation device 120, and simulate the tactile sensation of the patient in the scene through the tactile simulation module 122, and then synchronize the parameters of the EEG observation device 110 and the scene simulation device 120 through the parameter synchronization platform 130;

[0065] The auxiliary data is transmitted to the scene simulation device 120 through the auxiliary data adding module 512 in the data diagnosis module 510 to change the scene, so as to observe the patient's electroencephalogram through the electroencephalogram observation device 110;

[0066] When abnormal usage occurs in the EEG observation device 110 and the scene simulation device 120, the abnormal recording unit 103 set inside the device connection control platform 100 will record this node and issue an alarm so that the administrator can make adjustments;

[0067] Step 3: Adjust the use frequency of the EEG observation device 110 and the scene simulation device 120 by connecting the device to the frequency adjustment unit 101 inside the main control platform 100;

[0068] Step 4: The EEG data and the heart rate data are transmitted to the processing center 300 through the data acquisition unit 200, so that the data processing unit 400 performs modeling. At the same time, the patient's behavior data can be transmitted to the data processing unit 400 through the user interaction unit 500, thereby forming a dynamic brain network model.

[0069] During the modeling process of the data processing unit 400, the patient's recent behavior data is added to the data processing unit 400 through the auxiliary data adding module 512, and the corresponding model data or behavior conditions are searched through the model database 420, so that the brain network is more accurate during construction;

[0070] Step 5: The EEG model is established by the decoding modeling module 410 provided in the data processing unit 400, and similar EEG model data are searched for comparison through the model database 420, so as to find the common points of previous cases;

[0071] Step 6: Record the patient's behavior during the rehabilitation process and the time when the behavior occurred during the rehabilitation process through the behavior recording tag 520 set inside the user interaction unit 500;

[0072] Step 7: The report generation unit 600 generates a rehabilitation report based on the real-time EEG model data, the patient's behavior during rehabilitation, and the time when the behavior occurs during rehabilitation to complete the dynamic brain network construction and analysis.

[0073] Thereby completing a series of tasks, the contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

[0074] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for constructing and analyzing a dynamic brain network based on depression diagnosis, comprising a device connected to a main control platform (100), and a data acquisition unit (200) connected to the device connected to the main control platform (100); It is characterized in that The device is connected to a main control platform (100) and is connected to an electroencephalogram observation device (110), a scene simulation device (120), a parameter synchronization platform (130), and a data transmission platform (140); the device is connected to the main control platform (100) and is associated with a data acquisition unit (200), and the data acquisition unit (200) is connected to a processing center (300); a data processing unit (400) and a user interaction unit (500) are provided inside the data acquisition unit (200), and the processing center (300) is connected to a report generation unit (600); The data processing unit (400) and the user interaction unit (500) are mutually associated, and the data processing unit (400) is associated with the device connection main control platform (100), and the data processing center (300) can establish an electroencephalogram model of real-time data.

2. The method for constructing and analyzing a dynamic brain network based on depression diagnosis according to claim 1, It is characterized in that The device is connected to a main control platform (100) and is internally provided with a frequency adjustment unit (101), a data recording unit (102) and an abnormality recording unit (103); the frequency adjustment unit (101) is capable of adjusting the use frequency of an electroencephalogram observation device (110) and a scene simulation device (120), and an alarm mechanism is internally provided in the abnormality recording unit (103).

3. The method for constructing and analyzing a dynamic brain network based on depression diagnosis according to claim 2, It is characterized in that The electroencephalogram observation device (110) comprises an electroencephalogram monitoring module (111), a heart rate monitoring module (112) and a signal extraction module (113), wherein the signal extraction module (113) is capable of extracting monitoring data of the electroencephalogram monitoring module (111) and the heart rate monitoring module (112); The scene simulation device (120) includes a VR simulation module (121) and a tactile simulation module (122), and the parameter synchronization platform (130) can control the operating frequencies of the electroencephalogram observation device (110) and the scene simulation device (120) to be at the same level, and the parameter synchronization platform (130) is associated with a data recording unit (102) inside the device connection main control platform (100).

4. The method for constructing and analyzing a dynamic brain network based on depression diagnosis according to claim 1, It is characterized in that The data processing unit (400) is internally provided with a decoding modeling module (410), and the decoding modeling module (410) internally includes a data identification module (411), a data modeling module (412) and a model comparison module (413), wherein the data identification module (411) is capable of decoding and identifying the electroencephalogram and heart rate data received by the decoding modeling module (410), and the data modeling module (412) is capable of modeling the data received by the decoding modeling module (410), and the model comparison module (413) is capable of comparing the data status of the previous and next models in real time.

5. The method for constructing and analyzing a dynamic brain network based on depression diagnosis according to claim 4, It is characterized in that The data processing unit (400) includes a model database (420) inside, and the model database (420) is provided with a model storage unit (421) and a large behavior database (422) inside.

6. The method for constructing and analyzing a dynamic brain network based on depression diagnosis according to claim 1, It is characterized in that The user interaction unit (500) is internally provided with a data diagnosis module (510), and the data diagnosis module (510) includes an information recording module (511) and an auxiliary data adding module (512), and the auxiliary data adding module (512) is capable of recording and integrating the data added by the administrator and transmitting the data to the data processing unit (400) for processing.

7. The method for constructing and analyzing a dynamic brain network based on depression diagnosis according to claim 6, It is characterized in that The user interaction unit (500) is provided with a behavior record tag (520) inside, and the behavior record tag (520) is provided with a rehabilitation behavior record (521) and a behavior time record (522) inside.

8. The method for constructing and analyzing a dynamic brain network based on depression diagnosis according to claim 3, It is characterized in that When the device is connected to the main control platform (100) and connected to the EEG observation device (110) and the scene simulation device (120) for use, the data recording unit (102) can record the real-time usage of the EEG observation device (110) and the scene simulation device (120).

9. The method for constructing and analyzing a dynamic brain network based on depression diagnosis according to claim 3, It is characterized in that The electroencephalogram monitoring module (111) is an electroencephalogram monitoring helmet, and when a patient wears the electroencephalogram monitoring module (111), the electroencephalogram monitoring module (111) needs to be turned off through the frequency adjustment unit (101) to prevent accidental touch and accidents, and when the electroencephalogram monitoring module (111) is used, an electroencephalogram generation test needs to be performed first, so as to ensure that the electroencephalogram monitoring module (111) can be used normally.

10. The method for constructing and analyzing a dynamic brain network based on depression diagnosis according to claim 1, It is characterized in that The steps include: Step 1: The patient wears the electroencephalogram (EEG) monitoring module (111) and the heart rate monitoring module (112) in the EEG observation device (110), and then connects the device to the main control platform (100), so that the EEG monitoring module (111) and the heart rate monitoring module (112) are controlled by the device to the main control platform (100); Step 2: The patient wears the VR simulation module (121) in the scene simulation device (120), and the tactile sensation in the scene where the patient is located is simulated by the tactile simulation module (122), and then the parameters of the electroencephalogram observation device (110) and the scene simulation device (120) are synchronized by the parameter synchronization platform (130); Step 3: adjusting the use frequency of the EEG observation device (110) and the scene simulation device (120) by connecting the device to the frequency adjustment unit (101) inside the main control platform (100); Step 4: The electroencephalogram data and the heart rate data are transmitted to the processing center (300) through the data acquisition unit (200), so that the data processing unit (400) performs modeling. At the same time, the patient's behavior data can be transmitted to the data processing unit (400) through the user interaction unit (500), thereby forming a dynamic brain network model. Step 5: Establishing an EEG model through the decoding modeling module (410) provided inside the data processing unit (400), and searching for similar EEG model data through the model database (420) for comparison, so as to find the common points of previous cases; Step 6: Recording the patient's behavior during the rehabilitation process and the time when the behavior occurred during the rehabilitation process through the behavior recording tag (520) set inside the user interaction unit (500); Step 7: The report generation unit (600) generates a rehabilitation report based on the real-time EEG model data, the patient's behavior during rehabilitation, and the time when the behavior occurs during rehabilitation to complete the dynamic brain network construction and analysis.

Images