A method for constructing brain function network under right intraparietal sulcus magnetic pulse stimulation

Abstract

The present application relates to the technical field of magnetic pulse measurement, and particularly relates to a brain function network construction method under right-side superior longitudinal fissure magnetic pulse stimulation. The method comprises the following steps: forming a patient group by using experimental subjects suffering from depression; forming a control group by using healthy experimental subjects; constructing an electrode topology graph according to the electrode distribution of the experimental subjects, and obtaining peripheral nodes in the electrode topology graph; obtaining a depression correlation degree according to the change in the functional connection difference between the peripheral nodes at the same position in the patient group and the control group under the condition of no transcranial magnetic stimulation and under the condition of transcranial magnetic stimulation, and dividing the peripheral nodes into peripheral categories; and further obtaining the number of electrodes in the brain surface area corresponding to the peripheral categories. By obtaining the number of electrodes, the present application accurately determines the number of electrodes corresponding to each region of the brain, effectively avoids the situation that the incomplete depression-related data is obtained due to the uniform distribution of electrodes, and improves the accuracy and reliability of the depression mechanism research results and the treatment effect of depression.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of magnetic pulse measurement, and particularly relates to a brain function network construction method under right intraparietal sulcus magnetic pulse stimulation. BACKGROUND

[0002] Depression is a common mental illness, which is manifested as low mood, slow thinking, reduced will activity, impaired cognitive function, etc., and has characteristics of high incidence, high recurrence rate and high suicide rate, etc., which seriously endangers the physical and mental health of patients. In recent years, transcranial magnetic stimulation (TMS) as a non-invasive neural regulation technology has been widely used in the treatment of depression.

[0003] Transcranial magnetic stimulation (TMS) can temporarily change the activation mode of neurons in the target area (such as the right intraparietal sulcus) by applying magnetic pulses of specific frequency, intensity and duration, so as to study the influence of the target area on a specific task, which is helpful for the treatment of depression. In the existing method, when studying the mechanism of depression, more electrodes are usually arranged in the target area (such as the right intraparietal sulcus), and the electrodes in other areas are uniformly distributed. This uniform distribution of electrodes ignores the fact that different brain regions may have different effects on depression, which limits the accuracy and reliability of the research results on the mechanism of depression, and further affects the effective treatment of depression. SUMMARY

[0004] In order to solve the technical problem that the uniform distribution of electrodes ignores the fact that different brain regions may have different effects on depression, which limits the accuracy and reliability of the research results on the mechanism of depression, the purpose of the present application is to provide a brain function network construction method under right intraparietal sulcus magnetic pulse stimulation, and the technical solution adopted is as follows:

[0005] The present application provides a brain function network construction method under right intraparietal sulcus magnetic pulse stimulation, which comprises the following steps:

[0006] The experimenters with depression are grouped into a patient group, and the healthy experimenters are grouped into a control group; the electrodes in the corresponding area of the right intraparietal sulcus of each experimenter are taken as target electrodes;

[0007] An electrode topology graph is constructed according to the electrode distribution corresponding to any experimenter, and the peripheral nodes in the electrode topology graph are obtained according to the positional relationship between each node in the electrode topology graph and the node corresponding to the target electrode;

[0008] According to the change of the functional connection difference of the peripheral nodes in the same position between the patient group and the control group under the condition of no transcranial magnetic stimulation and under the condition of transcranial magnetic stimulation, the depression correlation degree of each position of the peripheral nodes is obtained; the peripheral nodes are divided into peripheral categories based on the depression correlation degree;

[0009] According to the size of the depression correlation degree of the peripheral nodes in each peripheral category, the number of electrodes in the brain surface region corresponding to each peripheral category is obtained.

[0010] Further, the method for constructing an electrode topology graph according to the electrode distribution of any experimenter is:

[0011] For any experimenter, each electrode in the brain surface region of the experimenter is taken as a node in the graph structure, and the distance between any two nodes is taken as an edge value, and the electrode topology graph of the experimenter is obtained by a Delaunay triangulation algorithm.

[0012] Further, the method for obtaining the peripheral nodes is:

[0013] For any experimenter, the node corresponding to the target electrode in the electrode topology graph of the experimenter is taken as a target node.

[0014] The center point of each target node is obtained by the position coordinates of the target node as a target center point.

[0015] According to the distance between each node and the target center point, the degree between each node and the target node, and the degree between each node and a non-target node in the electrode topology graph, the peripheral degree of each node is obtained.

[0016] When the peripheral degree is greater than a preset peripheral degree threshold, the corresponding node is taken as a peripheral node.

[0017] Further, the method for obtaining the peripheral degree is:

[0018] For any node in the electrode topology graph, the Euclidean distance between the node and the target center point is taken as a first distance.

[0019] The degree between the node and the target node is taken as a first value, and the degree between the node and a non-target node is taken as a second value.

[0020] The result of negative correlation and normalization of the ratio of the first value to the second value is taken as the peripheral probability of the node.

[0021] The product of the normalized result of the first distance and the peripheral probability is taken as the peripheral degree of the node.

[0022] Further, the method for obtaining the depression correlation degree is:

[0023] obtaining an initial difference degree of the peripheral node of each position according to the difference in functional connection of the peripheral node of the same position between the patient group and the control group when transcranial magnetic stimulation is not applied;

[0024] obtaining a stimulation difference degree of the peripheral node of each position according to the difference in functional connection of the peripheral node of the same position between the patient group and the control group when transcranial magnetic stimulation is applied;

[0025] obtaining a depression correlation degree of the peripheral node of each position according to the initial difference degree and the stimulation difference degree of the peripheral node of each position; wherein the initial difference degree and the depression correlation degree are positively correlated, and the stimulation difference degree and the depression correlation degree are negatively correlated.

[0026] Further, the method for obtaining the initial difference degree is:

[0027] when transcranial magnetic stimulation is not applied, constructing a reference electrode topology map of each experimenter according to the EEG signal of each electrode of each experimenter, and obtaining an embedding vector of each peripheral node in the reference electrode topology map of each experimenter;

[0028] for the peripheral node of any position, obtaining a representative embedding vector of the peripheral node of the position in the patient group according to the embedding vector of the peripheral node of the position in the reference electrode topology map of each experimenter in the patient group;

[0029] obtaining a representative embedding vector of the peripheral node of the position in the control group according to the embedding vector of the peripheral node of the position in the reference electrode topology map of each experimenter in the control group;

[0030] taking the result of the negative correlation of the cosine similarity between the representative embedding vector of the peripheral node of the position in the patient group and the representative embedding vector in the control group as the initial difference degree of the peripheral node of the position.

[0031] Further, the method for obtaining the representative embedding vector is:

[0032] for any group in the patient group or the control group, taking the embedding vector of the peripheral node of the position in the reference electrode topology map of each experimenter in the group as a reference embedding vector;

[0033] for each experimenter in the group, obtaining the sum of the cosine similarity between the reference embedding vector of the experimenter and each reference embedding vector as a representative reference value of the experimenter;

[0034] obtaining the representative reference value of each experimenter in the group, and taking the reference embedding vector of the experimenter corresponding to the maximum representative reference value as the representative embedding vector of the peripheral node of the position in the group.

[0035] Further, the method for obtaining the stimulation difference degree comprises:

[0036] When the transcranial magnetic stimulation is applied, the frequency of the magnetic pulse is adjusted once every preset time interval, and a target electrode topology map of each experimenter at each frequency is constructed according to the EEG signal of each electrode of each experimenter at each frequency.

[0037] For any frequency and any position of the peripheral node, a representative embedding vector of the peripheral node at the position in the patient group at the frequency is obtained as a first vector according to the embedding vector of the peripheral node at the position in the target electrode topology map of each experimenter in the patient group at the frequency.

[0038] A representative embedding vector of the peripheral node at the position in the control group at the frequency is obtained as a second vector according to the embedding vector of the peripheral node at the position in the target electrode topology map of each experimenter in the control group at the frequency.

[0039] A result of a negative correlation of a cosine similarity between the first vector and the second vector is taken as a reference stimulation difference value of the peripheral node at the position at the frequency.

[0040] A result of normalization of an addition result of the reference stimulation difference values of the peripheral node at the position at all frequencies is taken as a stimulation difference degree of the peripheral node at the position.

[0041] Further, the method for obtaining the peripheral category comprises:

[0042] According to the depression correlation degree of the peripheral node at each position, the peripheral nodes are divided into peripheral categories by a Laplace clustering algorithm.

[0043] Further, the method for obtaining the electrode number comprises:

[0044] For any peripheral category and any peripheral node in the peripheral category, a difference between the depression correlation degree of the peripheral node and the depression correlation degree of each peripheral node other than the peripheral node in the peripheral category is taken as a first difference.

[0045] An addition result of all the first differences is taken as a representative analysis value of the peripheral node.

[0046] The depression correlation degree of the peripheral node corresponding to the smallest representative analysis value is taken as a representative depression correlation degree of the peripheral category.

[0047] A ratio between the representative depression correlation degree of each peripheral category and the smallest representative depression correlation degree is taken as an adjustment weight of each peripheral category.

[0048] taking the number of peripheral nodes in the peripheral category corresponding to the minimum depression correlation degree as a reference number;

[0049] taking the product of the reference number and the adjustment weight of each peripheral category as a reference number.

[0050] The present application has the following advantages:

[0051] The present application first constructs an electrode topology graph according to the electrode distribution corresponding to any experimenter, which is conducive to subsequent accurate and efficient analysis of the electrode distribution of the brain region, and then obtains the peripheral nodes in the electrode topology graph according to the positional relationship between each node in the electrode topology graph and the node corresponding to the target electrode, accurately determines the nodes corresponding to the brain region outside the right intraparietal sulcus, and is conducive to subsequent accurate and efficient acquisition of the electrode number corresponding to each brain region outside the right intraparietal sulcus; in order to obtain the electrode number corresponding to each brain region outside the right intraparietal sulcus, the depression correlation degree of the peripheral nodes at each position is obtained according to the change in the functional connection difference between the peripheral nodes at the same position under the condition of no transcranial magnetic stimulation and under the condition of transcranial magnetic stimulation between the patient group and the control group, which accurately reflects the correlation degree between each position and depression; in order to determine the electrode number corresponding to each brain region, the peripheral nodes are divided into peripheral categories based on the depression correlation degree, and each brain region is determined, which is conducive to subsequent efficient electrode density adjustment; and then the electrode number in the brain surface region corresponding to each peripheral category is obtained according to the size of the depression correlation degree of the peripheral nodes in each peripheral category, the electrode number corresponding to each brain region is accurately determined, the completeness and accuracy of the depression-related data acquisition are improved, the situation that the depression-related data acquisition is incomplete due to the uniform distribution of electrodes is effectively avoided, and the accuracy and reliability of the depression mechanism research results and the treatment effect of depression are improved. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0053] Figure 1 A schematic flow chart of a brain function network construction method under right intraparietal sulcus magnetic pulse stimulation provided by an embodiment of the present application;

[0054] Figure 2A flow chart of a method for obtaining a depression correlation degree provided by an embodiment of the present application;

[0055] Figure 3 A system structure diagram of a brain function network construction under right intraparietal sulcus magnetic pulse stimulation provided by an embodiment of the present application;

[0056] Figure 4 A schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined purposes, the following describes in detail the specific implementation, structure, features and effects of a method for constructing a brain function network under right intraparietal sulcus magnetic pulse stimulation according to the present application, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0059] The following describes in detail the specific scheme of a method for constructing a brain function network under right intraparietal sulcus magnetic pulse stimulation provided by the present application, with reference to the accompanying drawings. Embodiment 1

[0060] The specific implementation scenario of the present embodiment is that in the existing method, the brain surface area corresponding to the right intraparietal sulcus of the brain is taken as the stimulation target area for depression research, and more electrodes are arranged in the stimulation target area, while the electrodes in other areas are uniformly distributed to study the mechanism of depression. However, in actual situations, different brain areas have different degrees of influence on depression, and uniform distribution of electrodes cannot obtain more accurate data, and thus cannot accurately study the mechanism of depression. In order to reasonably set the number of electrodes corresponding to each brain area other than the stimulation target area, so as to accurately study the mechanism of depression, the present embodiment first determines the peripheral electrodes that do not belong to the stimulation target area, and then analyzes the signal differences between depression patients and normal people under the conditions of not applying transcranial magnetic stimulation and applying transcranial magnetic stimulation, respectively, to obtain peripheral electrodes with a larger correlation degree with depression, and then determine brain areas that have a greater influence on depression, increase the number of electrodes in brain areas that have a greater influence on depression, which is helpful for accurately studying the mechanism of depression and is also conducive to better treatment of depression. The transcranial magnetic stimulation is a known technology and will not be described again.

[0061] The application provides a brain function network construction method under right intraparietal sulcus magnetic pulse stimulation Figure 1 , which shows a schematic flow chart of a brain function network construction method under right intraparietal sulcus magnetic pulse stimulation provided by an embodiment of the application, and the method comprises the following steps:

[0062] Step S1: the experimenters suffering from depression are formed into a patient group; the healthy experimenters are formed into a control group; and the electrodes in the corresponding region of the right intraparietal sulcus of each experimenter are taken as target electrodes.

[0063] Specifically, the right intraparietal sulcus is taken as the stimulation target region in this embodiment, in order to determine the influence degree of each brain region other than the stimulation target region on depression, and then to reasonably set the electrode distribution, so as to accurately study the mechanism of depression and more effectively treat depression, a first preset number of experimenters suffering from depression are formed into a patient group, and a second preset number of healthy experimenters are formed into a control group in this embodiment, and the first preset number and the second preset number are both set to 100, and the implementer can set the size of the first preset number and the second preset number according to the actual situation, which is not limited herein. It should be noted that the experimenters in the control group have no history of nervous system diseases and mental diseases, and the experimenters in the patient group have not received transcranial magnetic stimulation treatment.

[0064] In order to reasonably determine the electrode distribution of the brain surface region in the process of treating depression, the electrodes combined with the transcranial magnetic stimulation need to be installed first, and the specific installation process is as follows:

[0065] First step: determining the stimulation target region. In order to accurately position the stimulation target region, an individualized brain image (such as structural magnetic resonance imaging) can be used to determine the specific position of the brain structure and the stimulation target region of the experimenter;

[0066] Second step: calibrating the scalp position corresponding to the electrodes. Before starting to install the electrodes, the standard 10-20 system is used for scalp calibration in this embodiment, and the electrodes can be accurately placed near the stimulation target region by measuring and marking points on the scalp of the experimenter;

[0067] Third step: placing EEG electrodes. The EEG electrodes need to cover the entire scalp of the experimenter, and a plurality of electrodes are placed near the stimulation target region, and these EEG electrodes are used to record the change of brain electrical activity;

[0068] Fourth step: calibrating the transcranial magnetic stimulation device. The transcranial magnetic stimulation device needs to set the stimulation parameters according to the experimental design before stimulation, including stimulation intensity (usually based on the activation threshold), frequency (high frequency or low frequency) and time length.

[0069] Step 5: Place the transcranial magnetic stimulation coil. The transcranial magnetic stimulation coil is usually placed on the top of the experimenter's head, above the brain region. For the right intraparietal sulcus region, the transcranial magnetic stimulation coil is usually placed near the right parietal region, and the position is adjusted according to the individualized positioning to ensure that the stimulation accurately reaches the target stimulation region;

[0070] Step 6: Apply magnetic pulses. After the transcranial magnetic stimulation coil is correctly placed and the electrodes are installed, the magnetic pulses can be applied. By adjusting the frequency and intensity of the magnetic pulses, the intervention on neural activity can be adjusted;

[0071] Step 7: Real-time record the EEG signal of each electrode. When transcranial magnetic stimulation is applied, the EEG electrode will record the electrical activity of the brain in real time, capturing the neural response of each brain region.

[0072] At this point, the electrode installation of each experimenter's head is determined.

[0073] It is known that the number of electrodes corresponding to the target stimulation region is large, and the electrodes corresponding to the brain regions other than the target stimulation region are uniformly distributed, but in actual situations, the influence of each brain region other than the target stimulation region on depression may be different. In order to more accurately study the mechanism of depression and more effectively treat depression, it is necessary to set more electrodes for the brain regions other than the target stimulation region that have a greater influence on depression, to ensure more accurate and complete data acquisition related to depression. In order to improve the analysis efficiency of the influence of the brain regions other than the target stimulation region on depression, the electrodes in the corresponding region of the right intraparietal sulcus of each experimenter are taken as target electrodes, i.e. the electrodes corresponding to the target stimulation region are marked in advance.

[0074] Step S2: Construct an electrode topology graph according to the electrode distribution corresponding to any experimenter, and obtain the peripheral nodes in the electrode topology graph according to the positional relationship between each node in the electrode topology graph and the node corresponding to the target electrode.

[0075] Specifically, it is known from step S1 that the electrode distribution of the head surface area of each subject is the same, and therefore, the embodiment constructs an electrode topology graph according to the electrode distribution of any subject. It should be noted that the overall distribution of the electrode topology graph of each subject is the same in the embodiment, that is, the positions of the nodes corresponding to the target electrodes in the electrode topology graph of each subject are the same. The method of constructing an electrode topology graph according to the electrode distribution of any subject is as follows: for any subject, each electrode in the brain surface area of the subject is taken as a node in the graph structure, and the distance between any two nodes is taken as an edge value, and the electrode topology graph of the subject is obtained by a Delaunay triangulation algorithm. The Delaunay triangulation algorithm is a known technology and will not be described in detail.

[0076] Before adjusting the number of electrodes in the peripheral area of the stimulation target area, the electrodes in the non-stimulation target area need to be found. Considering that the distribution of brain electrodes may deviate in actual situations, for example, the electrodes corresponding to the stimulation target area may all be the electrodes corresponding to the right intraparietal sulcus, or may not all be the electrodes corresponding to the right intraparietal sulcus. Therefore, the embodiment determines the peripheral nodes, that is, the electrodes in the non-stimulation target area, in combination with the position distribution of the nodes corresponding to the electrodes in the electrode topology graph. When a node is more in the central position of the nodes corresponding to the target electrodes and has more connections with the nodes corresponding to the target electrodes, the node is less likely to be a peripheral node, and vice versa. Therefore, the embodiment obtains the peripheral nodes in the electrode topology graph according to the positional relationship between each node and the nodes corresponding to the target electrodes in the electrode topology graph.

[0077] Preferably, in an implementable manner of the embodiment, the method of obtaining the peripheral nodes is as follows: for any subject, the nodes corresponding to the target electrodes in the electrode topology graph of the subject are taken as target nodes; the central point of the target nodes is obtained through the position coordinates of each target node, as a target central point. The method of obtaining the central point is a known technology and will not be described in detail. When a node is farther from the target central point and has fewer connections with the target nodes and more connections with the non-target nodes, it is indicated that the node is more likely to be in the periphery of the right intraparietal sulcus. Therefore, the embodiment obtains the peripheral degree of each node according to the distance between each node and the target central point, the degree of each node with respect to the target nodes, and the degree of each node with respect to the non-target nodes in the electrode topology graph. The method of obtaining the degree is a known technology and will not be described in detail. The greater the peripheral degree is, the more likely the corresponding node is a peripheral node.

[0078] The method for obtaining the peripheral degree is as follows: for any node in the electrode topology graph, the Euclidean distance between the node and the target center point is taken as the first distance; the greater the first distance, the smaller the probability that the node is located in the right intrasulcal corresponding region; the method for obtaining the Euclidean distance is a known technology, and thus will not be described herein. In order to more accurately analyze the possibility that the node is located outside the right intrasulcal corresponding region, the degree between the node and the target node is further obtained as a first value; the smaller the first value, the fewer the connections between the node and the target node, and the more likely the node is located outside the right intrasulcal corresponding region; the degree between the node and a non-target node is obtained as a second value; the greater the second value, the more the connections between the node and the non-target node, and the more likely the node is located outside the right intrasulcal corresponding region; and then the result of the negative correlation and normalization of the ratio of the first value to the second value is taken as the peripheral probability of the node; the greater the peripheral probability, the smaller the first value and the greater the second value, and the more likely the node is located in the periphery of the right intrasulcal corresponding region; in order to accurately represent the degree of the node being a peripheral node, the product of the result of the normalization of the first distance and the peripheral probability is taken as the peripheral degree of the node.

[0079] The calculation formula of the peripheral degree is as follows: ; in the formula, d i is the peripheral degree of the i th node; d i is the peripheral degree of the i th node; d i is the first distance between the i th node and the target center point; norm is a normalization function; a is the first value; and b is the second value; p i is the peripheral probability of the i th node; and exp is an exponential function with a natural constant as the base number.

[0080] It is known that the greater the peripheral degree, the more likely the corresponding node is a peripheral node located outside the right intrasulcal corresponding region; and thus the preset peripheral degree threshold is set to 0.5 in this embodiment, and the implementer can set the size of the preset peripheral degree threshold according to the actual situation, which is not limited herein. When the peripheral degree is greater than the preset peripheral degree threshold, the corresponding node is taken as a peripheral node.

[0081] At this point, the peripheral nodes in the electrode topology graph of each experimenter are obtained. It should be noted that the position distribution of the peripheral nodes in the electrode topology graph of each experimenter is the same. In this embodiment, the peripheral nodes are obtained for analysis with any experimenter.

[0082] Step S3: obtaining the depression correlation degree of the peripheral node at each position according to the change in the difference in functional connection between the peripheral nodes at the same position in the patient group and the control group under the conditions of no transcranial magnetic stimulation and transcranial magnetic stimulation; and dividing the peripheral nodes into peripheral categories based on the depression correlation degree.

[0083] If the functional connection difference of the peripheral node at a certain position is larger between the patient group and the control group without transcranial magnetic stimulation, and the functional connection difference of the peripheral node at the certain position is smaller between the patient group and the control group with transcranial magnetic stimulation, it indicates that the peripheral node at the certain position has a significant response in the treatment of depression, that is, the greater the degree of association with depression; then, the embodiment obtains the degree of association with depression of each peripheral node according to the change of the functional connection difference of the peripheral node at the same position between the patient group and the control group without transcranial magnetic stimulation and with transcranial magnetic stimulation. The greater the degree of association with depression, the more effective the electrode corresponding to the peripheral node at the corresponding position in the treatment of depression. In order to determine the influence of each brain region outside the right intraparietal sulcus on depression, the embodiment divides the peripheral nodes into peripheral categories based on the degree of association with depression, wherein one peripheral category corresponds to one brain region having the same influence on depression, which is beneficial to subsequent adjustment of the number of electrodes corresponding to each peripheral category.

[0084] Preferably, in an implementable manner of the embodiment, the method for obtaining the degree of association with depression is as follows: Figure 2 which shows a flowchart of a method for obtaining the degree of association with depression provided by the embodiment, and the method comprises the following steps:

[0085] Step S201: When transcranial magnetic stimulation is not applied, obtain the initial difference degree of each peripheral node at each position according to the functional connection difference of the peripheral node at the same position between the patient group and the control group.

[0086] The greater the initial difference degree, the more obvious the difference between the EEG signals of the electrodes corresponding to the peripheral node at the corresponding position between the depression patients and the normal people.

[0087] In an implementable manner of the embodiment, the method for obtaining the initial difference degree is as follows: when transcranial magnetic stimulation is not applied, construct a reference electrode topology map of each experimenter according to the EEG signals of each electrode of each experimenter, obtain the embedding vector of each peripheral node in the reference electrode topology map of each experimenter by a node2vec graph embedding algorithm, and represent the specific function of each peripheral node by the embedding vector; wherein the node2vec graph embedding algorithm is a known technology and will not be described in detail. For any peripheral node at a certain position, obtain the representative embedding vector of the peripheral node at the certain position in the patient group according to the embedding vector of the peripheral node at the certain position in the reference electrode topology map of each experimenter in the patient group; obtain the representative embedding vector of the peripheral node at the certain position in the control group according to the embedding vector of the peripheral node at the certain position in the reference electrode topology map of each experimenter in the control group;

[0088] The representative reference value of each subject in the group is obtained by summing the cosine similarity between the reference embedding vector of the subject and each reference embedding vector in the group. The greater the representative reference value, the more similar the reference embedding vector of the subject is to the reference embedding vectors of other subjects in the group, and the more representative the reference embedding vector of the subject is. Further, the reference embedding vector of the subject corresponding to the maximum representative reference value is taken as the representative embedding vector of the peripheral node at the position in the group. The method for obtaining the cosine similarity is a known technology and will not be described in detail.

[0089] The negative correlation result of the cosine similarity between the representative embedding vector of the peripheral node at the position in the patient group and the representative embedding vector in the control group is taken as the initial difference degree of the peripheral node at the position. In this embodiment, the cosine similarity between the representative embedding vector of the peripheral node at the position in the patient group and the representative embedding vector in the control group is negatively correlated by (1-the cosine similarity between the representative embedding vector of the peripheral node at the position in the patient group and the representative embedding vector in the control group).

[0090] At this point, the initial difference degree of the peripheral node at each position is obtained.

[0091] Step S202: When transcranial magnetic stimulation is applied, the stimulation difference degree of the peripheral node at each position is obtained according to the functional connection difference of the peripheral node at the same position between the patient group and the control group.

[0092] The smaller the stimulation difference degree, the more similar the EEG signal of the electrode corresponding to the peripheral node at the corresponding position is to that of a normal person after transcranial magnetic stimulation treatment, indicating that the electrode corresponding to the peripheral node at the corresponding position is more related to depression.

[0093] In an implementable manner of the embodiment, the method for obtaining the stimulation difference degree is as follows: when the transcranial magnetic stimulation is applied, the frequency of the magnetic pulse is adjusted once every preset time length, and in the embodiment, the preset time length is set to 5 minutes, and the frequency of the magnetic pulse is gradually increased from 1 Hz to 10 Hz, wherein the low frequency of the magnetic pulse is usually 1 Hz, and the high frequency is usually 10 Hz. The implementer can set the size of the preset time length and the frequency adjustment condition of the magnetic pulse according to the actual situation, which is not limited herein. According to the EEG signal of each electrode of each experimenter at each frequency, the target electrode topology graph of each experimenter at each frequency is constructed; the embedding vector of each peripheral node in the target electrode topology graph of each experimenter at each frequency is obtained through the node2vec graph embedding algorithm; for any frequency and any position of the peripheral node, according to the method for obtaining the representative embedding vector in step S201, the embedding vector of the peripheral node at the position of the target electrode topology graph of each experimenter in the patient group at the frequency is obtained as the first vector, and at the same time, the embedding vector of the peripheral node at the position of the target electrode topology graph of each experimenter in the control group at the frequency is obtained as the second vector; then, the result of the negative correlation of the cosine similarity of the first vector and the second vector is taken as the reference stimulation difference value of the peripheral node at the position at the frequency; wherein, the cosine similarity of the first vector and the second vector is negatively correlated by (1-the cosine similarity of the first vector and the second vector) in the embodiment.

[0094] In order to analyze the reflection of the magnetic pulse of the peripheral node at the position at different frequencies of the transcranial magnetic stimulation as a whole, the result of the normalization of the sum of the reference stimulation difference values of the peripheral node at the position at all frequencies is taken as the stimulation difference degree of the peripheral node at the position. It should be noted that the sum of the reference stimulation difference values of the peripheral node at the position at all frequencies is normalized by the norm normalization function.

[0095] At this point, the stimulation difference degree of the peripheral node at each position is obtained.

[0096] Step S203: obtaining the depression correlation degree of the peripheral node at each position according to the initial difference degree and the stimulation difference degree of the peripheral node at each position; wherein the initial difference degree and the depression correlation degree are positively correlated, and the stimulation difference degree and the depression correlation degree are negatively correlated.

[0097] It is known that the greater the initial difference degree of the peripheral nodes of a certain position and the smaller the stimulation difference degree, the more the EEG signals of the electrodes corresponding to the peripheral nodes of the position tend to be normal after transcranial magnetic stimulation treatment, and the greater the correlation degree of the peripheral nodes of the position with depression. Therefore, the embodiment obtains the depression correlation degree of the peripheral nodes of each position according to the initial difference degree and the stimulation difference degree of the peripheral nodes of each position; wherein the initial difference degree and the depression correlation degree are positively correlated, and the stimulation difference degree and the depression correlation degree are negatively correlated.

[0098] wherein the calculation formula of the depression correlation degree is: ; in the formula, is the depression correlation degree of the peripheral nodes of the jth position; is the initial difference degree of the peripheral nodes of the jth position; is the stimulation difference degree of the peripheral nodes of the jth position; and e is a natural constant.

[0099] At this point, the depression correlation degree of the peripheral nodes of each position is obtained.

[0100] In order to reasonably adjust the electrode distribution corresponding to other brain regions outside the right intraparietal sulcus, and then divide the peripheral nodes into peripheral categories according to the depression correlation degree of the peripheral nodes of each position by using the Laplace clustering algorithm. The depression correlation degrees of the peripheral nodes in the same peripheral category are similar. The Laplace clustering algorithm is a known technology and will not be described in detail.

[0101] Step S4: obtaining the number of electrodes in the brain surface region corresponding to each peripheral category according to the size of the depression correlation degree of the peripheral nodes in each peripheral category.

[0102] Specifically, the greater the depression correlation degree of the peripheral nodes in a certain peripheral category, the greater the correlation degree of the electrodes corresponding to the peripheral nodes in the peripheral category with depression. In order to accurately analyze the mechanism of depression and effectively treat depression, the number of electrodes in the brain surface region corresponding to the peripheral category should be greater. Therefore, the embodiment obtains the number of electrodes in the brain surface region corresponding to each peripheral category according to the size of the depression correlation degree of the peripheral nodes in each peripheral category.

[0103] Preferably, in one implementation of the embodiment, the electrode number acquisition method is as follows: for any peripheral category and any peripheral node in the peripheral category, the absolute value of the difference between the depression correlation degree of the peripheral node and that of each other peripheral node in the peripheral category is obtained as a first difference; the sum of all first differences is taken as the representative analysis value of the peripheral node; the smaller the representative analysis value, the more equal the depression correlation degree of the peripheral node is to that of other peripheral nodes in the peripheral category, and the more representative the depression correlation degree of the peripheral node is; and then the embodiment takes the depression correlation degree of the peripheral node corresponding to the smallest representative analysis value as the representative depression correlation degree of the peripheral category.

[0104] The larger the representative depression correlation degree is, the more electrodes in the brain surface area corresponding to the corresponding peripheral category should be, to ensure more complete acquisition of depression-related data and improve the treatment effect of depression; and then the embodiment takes the ratio of the representative depression correlation degree of each peripheral category to the smallest representative depression correlation degree as the adjustment weight of each peripheral category; takes the number of peripheral nodes in the peripheral category corresponding to the smallest representative depression correlation degree as the reference number; and then obtains the result of rounding up the product of the reference number and the adjustment weight of each peripheral category as the number of electrodes in the brain surface area corresponding to each peripheral category.

[0105] At this point, the number of electrodes corresponding to each brain region outside the right intraparietal sulcus is accurately determined, effectively avoiding the situation that the uniform distribution of electrodes ignores the possible differences in the influence of different brain regions on depression, facilitating more detailed collection of depression data, obtaining more information related to depression, and effectively improving the accuracy and reliability of the results of depression mechanism research, while improving the effective treatment of depression.

[0106] After the study is completed, the EEG electrodes and transcranial magnetic stimulation coils on the subject's head need to be carefully removed, and then the subject needs to rest to avoid further stimulation or neural activity interference. At the same time, during the entire study, the subject's reactions need to be closely monitored to ensure that the transcranial magnetic stimulation is within a safe range and does not cause any adverse reactions or discomfort.

[0107] To sum up, the embodiment forms a patient group by taking the experimenters with depression as the patient group, forms a control group by taking healthy experimenters as the control group, constructs an electrode topology graph according to the electrode distribution of the experimenters, obtains peripheral nodes in the electrode topology graph, obtains the depression correlation degree of the peripheral nodes according to the change in the functional connection difference of the peripheral nodes at the same position between the patient group and the control group under the conditions of no transcranial magnetic stimulation and transcranial magnetic stimulation, divides the peripheral nodes into peripheral categories, and further obtains the electrode quantity in the brain surface region corresponding to the peripheral categories. By obtaining the electrode quantity, the embodiment accurately determines the electrode quantity corresponding to each region of the brain, effectively avoids the situation that the depression-related data is incomplete due to the uniform distribution of the electrodes, and improves the accuracy and reliability of the depression mechanism research results and the treatment effect of depression. Embodiment 2

[0108] The embodiment further provides a brain function network construction system under right intraparietal sulcus magnetic pulse stimulation, please refer to Figure 3 which shows a brain function network construction system structure diagram under right intraparietal sulcus magnetic pulse stimulation provided by one embodiment of the embodiment, and the system comprises a parameter acquisition module 10, a peripheral node acquisition module 20, a peripheral category acquisition module 30 and an electrode quantity acquisition module 40.

[0109] The parameter acquisition module 10 is used to form a patient group by taking the experimenters with depression as the patient group, form a control group by taking healthy experimenters as the control group, and take the electrodes in the right intraparietal sulcus corresponding region of each experimenter as target electrodes.

[0110] The peripheral node acquisition module 20 is used to construct an electrode topology graph according to the electrode distribution corresponding to any experimenter, and obtain peripheral nodes in the electrode topology graph according to the positional relationship between each node in the electrode topology graph and the node corresponding to the target electrode.

[0111] The peripheral category acquisition module 30 is used to obtain the depression correlation degree of the peripheral nodes at each position according to the change in the functional connection difference of the peripheral nodes at the same position between the patient group and the control group under the conditions of no transcranial magnetic stimulation and transcranial magnetic stimulation, and divide the peripheral nodes into peripheral categories based on the depression correlation degree.

[0112] The electrode quantity acquisition module 40 is used to obtain the electrode quantity in the brain surface region corresponding to each peripheral category according to the size of the depression correlation degree of the peripheral nodes in each peripheral category.

[0113] It should be noted that the system provided in the above embodiment is only used as an example for the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the right intraparietal sulcus magnetic pulse stimulation brain function network construction system and the right intraparietal sulcus magnetic pulse stimulation brain function network construction method provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here. Embodiment 3

[0114] The application further provides a right intraparietal sulcus magnetic pulse stimulation brain function network construction device, which comprises a memory and a processor, wherein the memory stores executable program codes, and the processor is used to call and execute the executable program codes to execute the right intraparietal sulcus magnetic pulse stimulation brain function network construction method provided in the embodiments of the application. The device can be a chip, an assembly or a module. The chip can comprise a processor and a memory connected thereto. The memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the right intraparietal sulcus magnetic pulse stimulation brain function network construction method provided in the above embodiments.

[0115] In addition, the embodiments of the application also protect a computer device, please refer to Figure 4 The computer device comprises a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can execute any of the right intraparietal sulcus magnetic pulse stimulation brain function network construction methods introduced above. Embodiment 4

[0116] The embodiments also provide a computer readable storage medium, which stores computer program codes. When the computer program codes run on a computer, the computer executes the above related method steps to implement the right intraparietal sulcus magnetic pulse stimulation brain function network construction method provided in the above embodiments. Embodiment 5

[0117] The embodiments also provide a computer program product, which makes the computer execute the above related steps to implement the right intraparietal sulcus magnetic pulse stimulation brain function network construction method provided in the above embodiments when the computer program product runs on the computer.

[0118] The device, the computer readable storage medium, the computer program product or the chip provided in the embodiment are used for executing the corresponding method provided in the above, thus the beneficial effects that can be achieved are the beneficial effects in the corresponding method provided in the above, which will not be described here.

[0119] It should be noted that the above-mentioned sequence of the embodiments of the application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0120] Each of the embodiments in the specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments.

Claims

1. A method for constructing brain functional network under right intraparietal sulcus magnetic pulse stimulation, characterized in that, The method comprises the following steps: The experimenters suffering from depression form a patient group; healthy experimenters form a control group; the electrodes in the corresponding region of the right intraparietal sulcus of each experimenter are taken as target electrodes; An electrode topology graph is constructed according to the electrode distribution corresponding to any experimenter; the peripheral nodes in the electrode topology graph are obtained according to the positional relationship between each node in the electrode topology graph and the node corresponding to the target electrode; The depression correlation degree of each position is obtained according to the change in the functional connection difference between the peripheral nodes at the same position in the patient group and the control group under the condition of no transcranial magnetic stimulation and under the condition of transcranial magnetic stimulation; and the peripheral nodes are divided into peripheral categories based on the depression correlation degree; The number of electrodes in the brain surface region corresponding to each peripheral category is obtained according to the size of the depression correlation degree of the peripheral nodes in each peripheral category; The method for obtaining the peripheral nodes is as follows: For any experimenter, the node corresponding to the target electrode in the electrode topology graph of the experimenter is taken as a target node; The center point of the target node is obtained through the position coordinates of each target node, as a target center point; The peripheral degree of each node is obtained according to the distance between each node in the electrode topology graph and the target center point, the degree between each node and the target node, and the degree between each node and a non-target node; When the peripheral degree is greater than a preset peripheral degree threshold, the corresponding node is taken as a peripheral node; The method for obtaining the number of electrodes is as follows: For any peripheral category and any peripheral node in the peripheral category, the difference between the depression correlation degrees of the peripheral node and each peripheral node in the peripheral category is taken as a first difference; The addition result of all the first differences is taken as a representative analysis value of the peripheral node; The depression correlation degree of the peripheral node corresponding to the smallest representative analysis value is taken as a representative depression correlation degree of the peripheral category; The ratio of the representative depression correlation degree of each peripheral category to the smallest representative depression correlation degree is taken as an adjustment weight of each peripheral category; The number of peripheral nodes in the peripheral category corresponding to the smallest representative depression correlation degree is taken as a reference number; The product of the reference number and the adjustment weight of each peripheral category is taken as the number of electrodes in the brain surface region corresponding to each peripheral category.

2. The method of claim 1, wherein the method is a method of constructing brain functional networks under right superior intraparietal sulcus magnetic pulse stimulation. The method for constructing the electrode topology graph according to the electrode distribution corresponding to any experimenter is as follows: For any experimenter, each electrode in the brain surface region of the experimenter is taken as a node in a graph structure, and the distance between any two nodes is taken as an edge value; the electrode topology graph of the experimenter is obtained through a Delaunay triangulation algorithm.

3. The method of claim 1, wherein the method is a method of constructing brain functional networks under right superior intraparietal sulcus magnetic pulse stimulation. The method for obtaining the peripheral degree is as follows: For any node in the electrode topology graph, the Euclidean distance between the node and the target center point is taken as a first distance; The degree between the node and the target node is taken as a first value, and the degree between the node and a non-target node is taken as a second value; The result of negative correlation and normalization of the ratio of the first value to the second value is taken as the peripheral probability of the node; The product of the result of normalization of the first distance and the peripheral probability is taken as the peripheral degree of the node.

4. The method of claim 1, wherein the method is a method of constructing a brain functional network under right superior intraparietal sulcus magnetic pulse stimulation. The method for obtaining the depression correlation degree comprises the following steps: When the transcranial magnetic stimulation is not applied, the initial difference degree of the peripheral node of each position is obtained according to the functional connection difference of the peripheral node of the same position between the patient group and the control group; When the transcranial magnetic stimulation is applied, the stimulation difference degree of the peripheral node of each position is obtained according to the functional connection difference of the peripheral node of the same position between the patient group and the control group; The depression correlation degree of the peripheral node of each position is obtained according to the initial difference degree and the stimulation difference degree of the peripheral node of each position; wherein the initial difference degree and the depression correlation degree are in a positive correlation, and the stimulation difference degree and the depression correlation degree are in a negative correlation.

5. The method of claim 4, wherein the right intraparietal sulcus is stimulated by a magnetic pulse. The method for obtaining the initial difference degree comprises the following steps: When the transcranial magnetic stimulation is not applied, the reference electrode topology map of each experimenter is constructed according to the EEG signal of each electrode of each experimenter, and the embedding vector of each peripheral node in the reference electrode topology map of each experimenter is obtained; For the peripheral node of any position, the representative embedding vector of the peripheral node of the position in the patient group is obtained according to the embedding vector of the peripheral node of the position in the reference electrode topology map of each experimenter in the patient group; The representative embedding vector of the peripheral node of the position in the control group is obtained according to the embedding vector of the peripheral node of the position in the reference electrode topology map of each experimenter in the control group; The result of the negative correlation of the cosine similarity between the representative embedding vector of the peripheral node of the position in the patient group and the representative embedding vector in the control group is taken as the initial difference degree of the peripheral node of the position.

6. The method of claim 5, wherein the right intraparietal sulcus is stimulated by a magnetic pulse. The method for obtaining the representative embedding vector comprises the following steps: For any group in the patient group or the control group, the embedding vector of the peripheral node of the position in the reference electrode topology map of each experimenter in the group is taken as the reference embedding vector; For any experimenter in the group, the sum of the cosine similarities between the reference embedding vector of the experimenter and each reference embedding vector is taken as the representative reference value of the experimenter; The reference embedding vector of the experimenter corresponding to the maximum representative reference value is taken as the representative embedding vector of the peripheral node of the position in the group.

7. The method of claim 6, wherein the right intraparietal sulcus is stimulated by a magnetic pulse. The method for obtaining the stimulation difference degree comprises the following steps: When the transcranial magnetic stimulation is applied, the frequency of the magnetic pulse is adjusted once every interval of a preset time length, the target electrode topology map of each experimenter at each frequency is constructed according to the EEG signal of each electrode of each experimenter at each frequency; The embedding vector of each peripheral node in the target electrode topology map of each experimenter at each frequency is obtained; For any frequency and any position of the peripheral node, the representative embedding vector of the peripheral node of the position in the patient group at the frequency is taken as the first vector according to the embedding vector of the peripheral node of the position in the target electrode topology map of each experimenter in the patient group at the frequency; The representative embedding vector of the peripheral node of the position in the control group at the frequency is taken as the second vector according to the embedding vector of the peripheral node of the position in the target electrode topology map of each experimenter in the control group at the frequency; The result of the negative correlation between the first vector and the cosine similarity of the second vector is taken as a reference stimulus difference value of the peripheral node of the position at the frequency; The result of normalizing the sum of the reference stimulus difference values of the peripheral node of the position at all frequencies is taken as the stimulus difference degree of the peripheral node of the position.

8. The method of claim 1, wherein the method is a method of constructing brain functional networks under right superior intraparietal sulcus magnetic pulse stimulation. The acquisition method of the peripheral category is: According to the depression correlation degree of the peripheral node of each position, the peripheral node is divided into a peripheral category through a Laplace clustering algorithm.

Images