CN113314216B - Functional brain network construction method and device, electronic equipment and readable storage medium - Google Patents
Functional brain network construction method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN113314216B CN113314216B CN202110612381.9A CN202110612381A CN113314216B CN 113314216 B CN113314216 B CN 113314216B CN 202110612381 A CN202110612381 A CN 202110612381A CN 113314216 B CN113314216 B CN 113314216B
- Authority
- CN
- China
- Prior art keywords
- brain network
- functional brain
- data
- network connection
- time window
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The application provides a method and a device for constructing a functional brain network, an electronic device and a readable storage medium, comprising the following steps: acquiring neural data; processing the neural data by adopting a community detection algorithm to obtain a community; obtaining data representing a functional brain network connection mode according to the neural data, the community and a preset sliding time window; and combining the data representing the functional brain network connection mode with a dynamic model to fit to obtain a functional brain network connection model. In the application, the community detection algorithm is adopted to obtain the community instead of the prior knowledge of a researcher, so that the potential key brain area can be avoided being omitted due to depending on experience, and the pseudo correlation among the neural data signals can be avoided to a certain extent.
Description
Technical Field
The invention relates to the technical field of complex systems, in particular to a method and a device for constructing a functional brain network, electronic equipment and a readable storage medium.
Background
At present, analysis and research on functional brain networks are hotspot techniques in the field of complex system research. Current research methods for functional brain networks are dominated by statistical analysis. The method mainly comprises the steps that a researcher determines a target area to be researched in a functional brain network according to priori knowledge, and then the correlation of the activity degrees among different target areas is calculated, so that the positive correlation or the inverse correlation among different target areas of the functional brain network in a specific state (a resting state or a task state) is obtained. Because the target area is determined by relying on the prior knowledge of a researcher, the potential brain network connection characteristics in the neural data among all areas of the functional brain network are easily ignored in the research process. However, because potential brain network connection characteristics in neural data among various regions of a functional brain network are easily ignored, the current statistical analysis method is difficult to identify the pseudo-correlation among neural data signals, and the research result is often unreliable.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method and an apparatus for constructing a functional brain network, an electronic device, and a readable storage medium, so as to solve the problem in the prior art that it is difficult to identify pseudo-correlations between neural data signals due to ignoring potential brain network connection features in neural data caused by studying a functional brain network connection mode by using a statistical analysis method.
The embodiment of the application provides a method for constructing a functional brain network, which comprises the following steps: acquiring neural data; processing the neural data by adopting a community detection algorithm to obtain a community; obtaining data representing a functional brain network connection mode according to the neural data, the community and a preset sliding time window; and obtaining a brain network state transition model according to the data representing the functional brain network connection mode.
In the implementation process, the neural data are processed by adopting a community detection algorithm to obtain a community, the neural data are processed based on the community detection algorithm, comprehensive and objective analysis on the neural data can be realized, the prior knowledge of a researcher is compared, and then the researcher is required to screen out a target area (namely, the community in the application) according to experience.
Further, obtaining data representing a functional brain network connection mode according to the neural data, the community and a preset sliding time window, including: preprocessing the neural data in the same community to obtain preprocessed neural data; performing Hilbert transform on the preprocessed neural data to obtain a phase signal; and obtaining data representing a functional brain network connection mode according to the phase signal in the preset sliding time window.
In the implementation process, the neural data after preprocessing is subjected to Hilbert transform to obtain a phase signal, and then data representing a functional brain network connection mode is obtained according to the phase signal in a preset sliding time window. Because the phase signal can better reflect the oscillation condition of the neural data signal, the data representing the connection mode of the functional brain network can be obtained according to the phase signal in the preset sliding time window, and the connection mode of the functional brain network can be better reflected.
Further, obtaining data representing a functional brain network connection mode according to the phase signal in the preset sliding time window, including: fitting the phase signals in the preset sliding time window by adopting a hidden model to obtain a matrix representing the coupling mode among communities in the preset sliding time window; and acquiring data representing the functional brain network connection mode according to the matrix representing the coupling mode among the communities in the preset sliding time window.
In the implementation process, the phase signals in the preset sliding time window are fitted by adopting the Tibetan model, so that a matrix representing the coupling mode among communities in the preset sliding time window is obtained, and further data representing the functional brain network connection mode is obtained. By adopting the method, the obtained connection mode of the functional brain network has a physical model as a basis, and the change of brain area signals can be explained from a mechanism level, so that the causal chain of research is enhanced.
Further, obtaining data characterizing the functional brain network connection mode according to the matrix characterizing the coupling modes among the communities in the preset sliding time window, including: calculating a characteristic vector corresponding to each characteristic value in a matrix representing the coupling mode among communities in the preset sliding time window; acquiring a characteristic vector corresponding to the maximum characteristic value in the matrix; and the eigenvector corresponding to the maximum eigenvalue is data representing a functional brain network connection mode.
In the implementation mode, the characteristic vector corresponding to the maximum characteristic value is obtained by utilizing characteristic decomposition, so that the characteristic vector corresponding to the maximum characteristic value is data representing the connection mode of the functional brain network, redundant information can be filtered by using the mode, and the method is favorable for revealing the connection mode of the representative functional brain network. Alternatively, if the data itself contains less redundant information, the data may not need to be compressed (i.e., the above-mentioned feature decomposition operation may not be needed).
Further, obtaining a functional brain network connection model according to the data representing the functional brain network connection mode, comprising: clustering the data representing the functional brain network connection mode by adopting a K-means clustering algorithm to obtain a functional brain network connection model; the functional brain network connection model is a cluster center obtained after K-means clustering.
In the implementation mode, the functional brain network connection model is analyzed by adopting a K-means clustering algorithm, so that general representation of the functional brain network connection model can be obtained, and the dynamic brain connection rule can be obtained according to the functional brain network connection model in the follow-up process.
Further, the neural data includes any one of: functional magnetic resonance data, electroencephalogram data, and cortical electroencephalogram data.
The neural data commonly used in the analysis and research of brain network is functional magnetic resonance data, electroencephalogram data and cortical electroencephalogram data. The input data of the embodiment of the application can be any one of functional magnetic resonance data, electroencephalogram data and cortical electroencephalogram data, so that the scheme is favorable for brain basic research and clinical application.
The embodiment of the present application further provides a functional brain network constructing apparatus, including: the acquisition module is used for acquiring neural data; the processing module is used for processing the neural data by adopting a community detection algorithm to obtain a community; the processing module is further used for obtaining data representing a functional brain network connection mode according to the neural data, the community and a preset sliding time window; the processing module is further used for obtaining a brain network state transition model according to the data representing the functional brain network connection mode.
The embodiment of the application also provides electronic equipment, which comprises a processor, a memory and a communication bus; the communication bus is used for realizing connection communication between the processor and the memory; the processor is used for executing one or more programs stored in the memory so as to realize any one of the above functional brain network construction methods.
The embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs, where the one or more programs are executable by one or more processors to implement any one of the above-mentioned functional brain network construction methods.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of a method for constructing a functional brain network according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a more specific functional brain network construction method according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a functional brain network constructing apparatus according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
The first embodiment is as follows:
in order to solve the problem that pseudo correlation among neural data signals is difficult to identify due to the fact that potential brain network connection characteristics in neural data are ignored caused by researching a functional brain network connection mode by using a statistical analysis method in the prior art, the embodiment of the application provides a functional brain network construction method. Next, a description is given of a functional brain network construction method provided in an embodiment of the present application, with reference to a flow diagram of a functional brain network construction method shown in fig. 1.
It should be noted that the brain network refers to a very complex and large brain network formed by different neurons of the brain and different connections between different brain regions. Such connections within the brain can be classified as: structural connections, functional connections, and operative connections. Functional brain networks refer to functionally connected brain networks.
The functional connection means that signals obtained by recording different brain areas are used for calculating certain indexes reflecting the relation strength of the different brain areas. On a microscopic level, functional connection generally refers to synchronously collecting action potential signals of a plurality of neurons through an invasive multi-electrode array, and calculating the relation between the action potential signals of different neurons by adopting a corresponding algorithm. On the mesoscopic level, the functional connection generally means that Local Field Potentials (LFPs) of a plurality of brain areas are recorded simultaneously through invasive electrodes, and corresponding indexes are adopted to calculate the strength of the relationship between LFP signals of different brain areas. Where LFP reflects the overall electrical activity of the neuron population within millimeters of the electrodes. Besides LFP acquisition, another commonly used technique is intracranial cortex electroencephalogram signal acquisition, i.e. an electrode array is directly placed on the cerebral cortex, and then the strength of functional connection strength between neural signals of different brain areas is calculated by using a corresponding algorithm. On a macroscopic level, commonly used measurement techniques are electroencephalography, functional magnetic resonance, etc. The adopted indexes can be synchronous likelihood indexes, spectral coherence, transfer entropy, partial directional coherence, directional transfer functions and the like.
Referring to fig. 1, a method for constructing a functional brain network provided in an embodiment of the present application includes:
and S101, acquiring neural data.
In the embodiment of the present application, the neural data is data collected by an external device, which may reflect brain activity, and may include any one of the following: functional magnetic resonance data, electroencephalogram data and cortical electroencephalogram data, which are not limited in the embodiment of the application.
And S102, processing the neural data by adopting a community detection algorithm to obtain a community.
It should be noted that the community detection algorithm is a technique for revealing network aggregation behavior. The community detection algorithm is actually a network clustering method. A community may be understood as a collection of nodes of a type having the same characteristics. Common community detection algorithms include a spectrum scoring method, a greedy algorithm, an evolutionary multi-objective optimization algorithm, a luwen community detection algorithm, and the like, and any one of the algorithms can be adopted in the embodiment of the present application, but is not limited.
For example, in the embodiment of the present application, the neural data may be processed by using the unwen community detection algorithm to obtain communities, the size of the generated communities may be controlled by adjusting the resolution of the unwen community detection algorithm, and after the detection of the algorithm, 7-10 communities are generally obtained. In the embodiment of the present application, a community may be understood as a region where there is a strong synchronous activity, and such a region may be considered as a whole as a cognitive module.
S103, obtaining data representing a functional brain network connection mode according to the neural data, the community and a preset sliding time window.
In the embodiment of the present application, the following method may be adopted to obtain data representing a functional brain network connection mode according to the neural data, the community, and the preset sliding time window:
preprocessing the neural data in the same community to obtain preprocessed neural data; performing Hilbert transform on the preprocessed neural data to obtain a phase signal; and obtaining data representing the functional brain network connection mode according to the phase signal in the preset sliding time window.
In the embodiment of the present application, the preprocessing operation is to average the neural data signals in the same community, so that the spatial complexity of the neural data signals can be reduced.
For example, the hilbert transform is performed on the preprocessed neural data, and the obtained phase signal may be: the original signal a (t) is subjected to hilbert transform to generate an analytic signal a (t) + ib (t), and the imaginary part b (t) is a signal obtained by delaying the phase of the original signal by 90 degrees. Then use
And converting the preprocessed neural data signal into a phase signal.
Illustratively, the data representing the functional brain network connection mode is obtained according to the phase signal in the preset sliding time window, and may be: fitting the phase signals in the preset sliding time window by adopting a book hiding model to obtain a matrix representing the coupling mode among communities in the preset sliding time window; and obtaining data representing the functional brain network connection mode according to the matrix representing the coupling mode among the communities in the preset sliding time window.
It should be noted that the book model is proposed by japan physicist book, and the model can effectively describe the oscillation behavior of the coupled oscillator, so that the obtained connection mode of the functional brain network has a physical model as a basis, and the change of brain signals can be interpreted from the mechanism level, thereby enhancing the causal chain of research. In the embodiment of the present application, the basic form of the Tibetan model can be
Wherein:
is theta n The first derivative of (a); theta n Is the phase signal of the oscillator n; theta m Is the phase signal of the oscillator m; omega n To the phase signal theta n Carrying out spectrum analysis and then taking the frequency corresponding to the peak value; n is the total number of oscillators in the system; w mn In order to characterize the matrix of coupling modes between the elements, W in the present application mn And representing the matrix of the coupling modes among communities in a certain preset sliding time window.
It should be further noted that, in the embodiment of the present application, the window length of the preset sliding time window may be 54 seconds, and the starting positions of adjacent windows may be 44 seconds apart, but not limited thereto. In the actual application process, the window length of the preset sliding time window and the starting position of the adjacent window can be set by related technicians according to actual needs.
In the embodiment of the present application, in order to fit the phase signal in the preset sliding time window, the loss function may be made to be the square of the difference between the left and right terms of the following difference equation in each time window, and the phase signal θ is combined n Fitting the following differential-form Tibetan model to obtain a parameter W mn ：
In the above formula, W mn And representing a matrix of coupling modes among communities in a certain preset sliding time window. Omega n And taking the frequency corresponding to the peak value after performing spectrum analysis on the phase signal.
It should be understood that the above manner is only one possible manner of fitting the phase signal within the preset sliding time window by using the hidden model, and is not limited thereto. In fact, as long as the method of fitting the phase signal in the preset sliding time window by using the hidden model and then obtaining the matrix representing the coupling mode among the communities in the preset sliding time window can be adopted by the embodiment of the present application.
In the embodiment of the present application, a feasible implementation manner of obtaining data representing a functional brain network connection mode according to a matrix representing coupling modes among communities within a preset sliding time window is as follows: can be aligned with W mn Performing characteristic decomposition to obtain characteristic vectors corresponding to the characteristic values, and dividing W mn And a feature vector v corresponding to the medium-maximum feature value is used as data for representing the functional brain network connection mode, and the specific dimensionality of v depends on the number of communities in which researchers are interested.
Optionally, in the embodiment of the present application, the principal component analysis algorithm may also be used to pair W mn And processing to obtain data representing the functional brain network connection mode.
Optionally, in the embodiment of the present application, if the original coupling matrix W mn If there is less redundant information contained in the compressed data, compression processing such as feature decomposition or principal component analysis may not be performed.
It should be understood that the above is only a possible method for obtaining data characterizing a functional brain network connection mode exemplified in the embodiments of the present application, but not by way of limitation.
And S104, acquiring a functional brain network connection model according to the data representing the functional brain network connection mode.
For example, in the embodiment of the present application, a K-means clustering algorithm may be used to cluster data representing a functional brain network connection mode, so as to obtain a functional brain network connection model. The functional brain network connection model is a cluster center obtained after K-means clustering, and one cluster center obtained after clustering represents a representative functional brain network connection mode.
After obtaining the functional brain network connection model, the general rules involved in the functional brain network connection can be analyzed using the model.
Illustratively, the functional brain network connection model can be input into a markov model, and then the brain dynamic connection rule can be analyzed according to neural data in a preset sliding time window. It should be noted that, along with the change of time, the neural data in the preset sliding time window changes, and then the data representing the functional brain network connection mode changes, so that the dynamic brain connection rule can be analyzed by using the neural data in the preset sliding time window.
In summary, according to the functional brain network construction method provided by the embodiment of the application, the community is obtained by adopting the community detection algorithm instead of according to the priori knowledge of the researcher, so that the omission of the key community due to the dependence on experience can be avoided, and the occurrence of pseudo correlation among the neural data signals can be avoided to a certain extent. The method adopts the Tibetan model to fit the phase signals in the preset sliding time window to obtain data representing the connection mode of the functional brain network, so that the obtained connection mode of the functional brain network has a physical model as a basis, and the change of brain area signals can be explained from a mechanism level, thereby enhancing a causal chain of research.
Example two:
the present embodiment is further illustrated in the first embodiment by taking a case of using functional magnetic resonance data as neural data as an example.
Referring to fig. 2, a more specific method for constructing a functional brain network provided in the embodiment of the present application includes:
s201, acquiring functional magnetic resonance data.
S202, processing a functional network generated based on functional magnetic resonance data by adopting a Luwen community detection algorithm, and obtaining a community.
And S203, averaging the functional magnetic resonance data in the same community to obtain the averaged functional magnetic resonance data.
And S204, performing Hilbert transform on the averaged functional magnetic resonance data to obtain a phase signal.
S205, fitting the phase signals in the preset sliding time window by adopting a book hiding model, and obtaining a matrix representing the coupling mode among communities in the preset sliding time window.
And S206, performing characteristic decomposition to represent a matrix of coupling modes among communities, wherein the characteristic vector corresponding to the maximum characteristic value is data representing a functional brain network connection mode.
And S207, clustering the data representing the functional brain network connection mode by adopting a K-means clustering algorithm to obtain a functional brain network connection model.
In summary, according to the functional brain network construction method provided by the embodiment of the application, the community is obtained by adopting the community detection algorithm instead of according to the priori knowledge of the researcher, so that the omission of the key community due to the dependence on experience can be avoided, and the occurrence of pseudo correlation among the neural data signals can be avoided to a certain extent. The method adopts the Tibetan model to fit the phase signals in the preset sliding time window to obtain data representing the connection mode of the functional brain network, so that the obtained connection mode of the functional brain network has a physical model as a basis, and the change of brain area signals can be explained from a mechanism level, thereby enhancing the causality of research.
Example three:
based on the same inventive concept, the embodiment of the present application further provides a functional brain network constructing apparatus 300, please refer to fig. 3. It should be understood that the specific functions of the apparatus 300 can be referred to the above description, and the detailed description is omitted here as appropriate to avoid redundancy. The apparatus 300 includes at least one software functional module that can be stored in a memory in the form of software or firmware or solidified in an operating system of the apparatus 300. Specifically, the method comprises the following steps:
referring to fig. 3, the apparatus 300 includes: an acquisition module 301 and a processing module 302. Wherein:
the acquisition module 301 is configured to acquire neural data;
the processing module 302 is configured to process the neural data by using a community detection algorithm to obtain a community;
in this embodiment of the present application, the processing module 302 is further configured to obtain data representing a functional brain network connection mode according to the neural data, the community, and a preset sliding time window;
in this embodiment of the present application, the processing module 302 is further configured to obtain a brain network state transition model according to the data representing the functional brain network connection mode.
In a feasible implementation manner of the embodiment of the present application, the processing module 302 is further configured to perform preprocessing on the neural data in the same community to obtain preprocessed neural data; performing Hilbert transform on the preprocessed neural data to obtain a phase signal; and obtaining data representing the functional brain network connection mode according to the phase signal in the preset sliding time window.
In the above feasible embodiment, the processing module 302 is further configured to fit the phase signal in the preset sliding time window by using a book hiding model, so as to obtain a matrix representing coupling modes between communities in the preset sliding time window; and according to the matrix representing the coupling modes among the communities in the preset sliding time window, obtaining data representing the functional brain network connection mode.
In the above feasible embodiment, the processing module 302 is further configured to calculate a feature vector corresponding to each eigenvalue in a matrix representing each inter-community coupling manner within a preset sliding time window; acquiring a characteristic vector corresponding to the maximum characteristic value in the matrix; the eigenvector corresponding to the largest eigenvalue is the data characterizing the network connection mode of the functional brain.
In a feasible implementation manner of the embodiment of the present application, the processing module 302 is further configured to cluster the data representing the functional brain network connection mode by using a K-means clustering algorithm to obtain a functional brain network connection model, where the functional brain network connection model is a cluster center obtained after K-means clustering.
In a possible implementation manner of this embodiment of the present application, the obtaining module 301 is further configured to obtain the neural data including any one of the following: functional magnetic resonance data, electroencephalogram data, and cortical electroencephalogram data.
It should be understood that, for the sake of brevity, the contents described in some embodiments are not repeated in this embodiment.
Example four:
an electronic device, shown in fig. 4, includes a processor 401, a memory 402, and a communication bus 403. Wherein:
the communication bus 403 is used to enable connection communication between the processor 401 and the memory 402.
The processor 401 is configured to execute one or more programs stored in the memory 402 to implement the functional brain network construction method provided in the first embodiment.
It will be appreciated that the configuration shown in fig. 4 is merely illustrative and that the electronic device may include more or fewer components than shown in fig. 4 or have a different configuration than shown in fig. 4.
It is to be understood that the electronic device described in the embodiment of the present application may be a host, a server, or the like having a data processing function, but is not limited thereto.
The present embodiment further provides a readable storage medium, such as a floppy disk, an optical disk, a hard disk, a flash Memory, a usb (Secure Digital Memory Card), an MMC (Multimedia Card), etc., where one or more programs for implementing the above steps are stored in the readable storage medium, and the one or more programs may be executed by one or more processors to implement the steps executed by the method for building a functional brain network in the first embodiment. And will not be described in detail herein.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the units into only one type of logical function may be implemented in other ways, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
In this context, a plurality means two or more.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made to the present application by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (8)
1. A method for constructing a functional brain network, comprising:
acquiring neural data;
processing the neural data by adopting a community detection algorithm to obtain a community;
obtaining data representing a functional brain network connection mode according to the neural data, the community and a preset sliding time window;
obtaining a functional brain network connection model according to the data representing the functional brain network connection mode;
obtaining data representing a functional brain network connection mode according to the neural data, the community and a preset sliding time window, wherein the data comprises:
preprocessing the neural data in the same community to obtain preprocessed neural data;
performing Hilbert transform on the preprocessed neural data to obtain a phase signal;
obtaining data representing a functional brain network connection mode according to the phase signal in the preset sliding time window;
and acquiring data representing a functional brain network connection mode according to the phase signal in the preset sliding time window, wherein the data comprises:
fitting the phase signals in the preset sliding time window by adopting a hidden model to obtain a matrix representing the coupling mode among communities in the preset sliding time window;
and obtaining data representing the functional brain network connection mode according to the matrix representing the coupling mode among the communities in the preset sliding time window.
2. The method according to claim 1, wherein obtaining data characterizing a functional brain network connection mode according to a matrix characterizing coupling modes among communities within the preset sliding time window comprises:
calculating a characteristic vector corresponding to each characteristic value in a matrix representing coupling modes among communities in the preset sliding time window;
acquiring a characteristic vector corresponding to the maximum characteristic value in the matrix; and the eigenvector corresponding to the maximum eigenvalue is data representing a functional brain network connection mode.
3. The method according to claim 1, wherein obtaining a functional brain network connection model based on the data representing the functional brain network connection model comprises:
and clustering the data representing the functional brain network connection mode by adopting a K-means clustering algorithm to obtain a functional brain network connection model.
4. The method according to claim 3, wherein the functional brain network connection model is a cluster center obtained after K-means clustering.
5. The method of any one of claims 1 to 4, wherein the neural data comprises any one of: functional magnetic resonance data, electroencephalogram data, and cortical electroencephalogram data.
6. A functional brain network constructing apparatus, comprising:
the acquisition module is used for acquiring neural data;
the processing module is used for processing the neural data by adopting a community detection algorithm to obtain a community;
the processing module is further used for obtaining data representing a functional brain network connection mode according to the neural data, the community and a preset sliding time window;
the processing module is further used for obtaining a brain network state transition model according to the data representing the functional brain network connection mode;
the processing module is also used for preprocessing the neural data in the same community to obtain preprocessed neural data; performing Hilbert transform on the preprocessed neural data to obtain a phase signal; obtaining data representing a functional brain network connection mode according to the phase signal in the preset sliding time window;
the processing module is further used for fitting the phase signals in the preset sliding time window by adopting a book hiding model to obtain a matrix representing coupling modes among communities in the preset sliding time window; and obtaining data representing the functional brain network connection mode according to the matrix representing the coupling mode among the communities in the preset sliding time window.
7. An electronic device, comprising: a processor, a memory, and a communication bus; the communication bus is used for realizing connection communication between the processor and the memory; the processor is configured to execute one or more programs stored in the memory to implement the functional brain network construction method according to any one of claims 1 to 5.
8. A computer-readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the functional brain network construction method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110612381.9A CN113314216B (en) | 2021-06-01 | 2021-06-01 | Functional brain network construction method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110612381.9A CN113314216B (en) | 2021-06-01 | 2021-06-01 | Functional brain network construction method and device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113314216A CN113314216A (en) | 2021-08-27 |
| CN113314216B true CN113314216B (en) | 2022-11-22 |
Family
ID=77377090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110612381.9A Active CN113314216B (en) | 2021-06-01 | 2021-06-01 | Functional brain network construction method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113314216B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117952195B (en) * | 2024-03-26 | 2024-06-21 | 博睿康医疗科技(上海)有限公司 | Brain network construction method and display equipment based on task related brain electrical activity |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106963371A (en) * | 2017-03-29 | 2017-07-21 | 天津大学 | The method that learning and memory in rats and cognitive function are detected based on neural oscillatory activity |
| CN110210119A (en) * | 2019-05-30 | 2019-09-06 | 东南大学 | A kind of high efficiency phase developing method based on deep layer convolutional neural networks |
| CN110265148B (en) * | 2019-06-20 | 2021-06-01 | 上海海事大学 | Dynamic functional mode learning method inspired by fMRI brain network mechanism |
| CN112508819A (en) * | 2020-12-17 | 2021-03-16 | 广州大学 | Wrapping phase denoising method and system based on convolutional neural network and storage medium |
-
2021
- 2021-06-01 CN CN202110612381.9A patent/CN113314216B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113314216A (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Saeedi et al. | Major depressive disorder diagnosis based on effective connectivity in EEG signals: a convolutional neural network and long short-term memory approach | |
| Siuly et al. | Designing a robust feature extraction method based on optimum allocation and principal component analysis for epileptic EEG signal classification | |
| Siuly et al. | Exploring Hermite transformation in brain signal analysis for the detection of epileptic seizure | |
| Ma et al. | Dynamic changes of spatial functional network connectivity in healthy individuals and schizophrenia patients using independent vector analysis | |
| Li et al. | Extracting the nonlinear features of motor imagery EEG using parametric t-SNE | |
| Huang et al. | Cardiology knowledge free ECG feature extraction using generalized tensor rank one discriminant analysis | |
| Shen et al. | Nonlinear structural vector autoregressive models for inferring effective brain network connectivity | |
| Taran et al. | Detection of sleep apnea events using electroencephalogram signals | |
| Rahim et al. | Population shrinkage of covariance (PoSCE) for better individual brain functional-connectivity estimation | |
| Hazarika et al. | An automatic feature extraction and fusion model: application to electromyogram (EMG) signal classification | |
| CN113314216B (en) | Functional brain network construction method and device, electronic equipment and readable storage medium | |
| Jaiswal et al. | Local transformed features for epileptic seizure detection in EEG signal | |
| Mohammadi et al. | Automatic seizure detection using a highly adaptive directional time–frequency distribution | |
| Tu et al. | Semi-supervised feature extraction for EEG classification | |
| Banerjee et al. | Using complex networks towards information retrieval and diagnostics in multidimensional imaging | |
| Taherisadr et al. | EEG signal dimensionality reduction and classification using tensor decomposition and deep convolutional neural networks | |
| Siuly et al. | Exploring deep residual network based features for automatic schizophrenia detection from EEG | |
| Saidi et al. | Detection of brain stimuli using Ramanujan periodicity transforms | |
| Khosla et al. | EEG‐based automatic multi‐class classification of epileptic seizure types using recurrence plots | |
| Xiong et al. | Seizure detection algorithm based on fusion of spatio-temporal network constructed with dispersion index | |
| Chalaki et al. | Epileptic seizure classification using ConvLSTM deep classifier and rotation short-time Fourier Transform | |
| Lei et al. | Longitudinal study of early mild cognitive impairment via similarity-constrained group learning and self-attention based SBi-LSTM | |
| Nousias et al. | Uncertainty management for wearable iot wristband sensors using laplacian-based matrix completion | |
| Qin et al. | EEG signal classification based on improved variational mode decomposition and deep forest | |
| Li et al. | Tensor approximate entropy: An entropy measure for sleep scoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |