CN112274144A - Method and device for processing near-infrared brain function imaging data and storage medium - Google Patents
Method and device for processing near-infrared brain function imaging data and storage medium Download PDFInfo
- Publication number
- CN112274144A CN112274144A CN201910660196.XA CN201910660196A CN112274144A CN 112274144 A CN112274144 A CN 112274144A CN 201910660196 A CN201910660196 A CN 201910660196A CN 112274144 A CN112274144 A CN 112274144A
- Authority
- CN
- China
- Prior art keywords
- brain function
- channels
- imaging data
- infrared
- determining
- 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.)
- Pending
Links
- 230000003925 brain function Effects 0.000 title claims abstract description 323
- 238000012545 processing Methods 0.000 title claims abstract description 174
- 238000003384 imaging method Methods 0.000 title claims abstract description 172
- 238000000034 method Methods 0.000 title claims description 54
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical group [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 48
- 239000008280 blood Substances 0.000 claims description 48
- 210000004369 blood Anatomy 0.000 claims description 48
- 229910052760 oxygen Inorganic materials 0.000 claims description 48
- 239000001301 oxygen Substances 0.000 claims description 48
- 230000002490 cerebral effect Effects 0.000 claims description 47
- 239000011159 matrix material Substances 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 239000000126 substance Substances 0.000 claims description 8
- 238000003672 processing method Methods 0.000 abstract description 6
- 210000004556 brain Anatomy 0.000 description 14
- 238000012360 testing method Methods 0.000 description 9
- 108010054147 Hemoglobins Proteins 0.000 description 8
- 102000001554 Hemoglobins Human genes 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000007405 data analysis Methods 0.000 description 5
- 238000012935 Averaging Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000002610 neuroimaging Methods 0.000 description 3
- 238000011282 treatment Methods 0.000 description 3
- 238000004497 NIR spectroscopy Methods 0.000 description 2
- 210000003710 cerebral cortex Anatomy 0.000 description 2
- 238000000701 chemical imaging Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 108010064719 Oxyhemoglobins Proteins 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007177 brain activity Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000002329 infrared spectrum Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000036403 neuro physiology Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000002600 positron emission tomography Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
- A61B5/14553—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases specially adapted for cerebral tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Psychiatry (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Child & Adolescent Psychology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Neurology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Optics & Photonics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a processing method, a device and a storage medium of near-infrared brain function imaging data, comprising the following steps: acquiring near-infrared brain function imaging data of at least two channels; constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network; and processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
Description
Technical Field
The invention relates to a technology for detecting brain related data, in particular to a method and a device for processing near-infrared brain function imaging data and a computer readable storage medium.
Background
The advent of neurophysiology and neuroimaging has enhanced the understanding of the brain, and brain activity can be observed in particular by imaging means such as electroencephalogram, positron emission tomography, magnetic resonance, and the like. Near Infrared Spectroscopy imaging technology (fNIRs, functional Near-Infrared Spectroscopy) is a new brain imaging technology developed in recent years, and compared with the traditional brain imaging technology, the brain cortex function activity can be detected for a long time in a non-invasive manner, and the acquired signals are less interfered by physiology and motion, so that the method is simple, convenient and quick, and convenient for data acquisition, therefore, the fNIRs have good application prospects in many fields. For example: in the scientific research field, researchers use fNIRs to detect the blood oxygen information of the tested brain, so that different emotional states can be identified; in clinical medicine, fNIRs are used to diagnose depression.
However, the existing near infrared spectrum imaging technology only performs single analysis processing on the acquired cerebral blood oxygen signals, and information carried by the tested cerebral blood oxygen information cannot be comprehensively represented according to the characteristics extracted from the cerebral blood oxygen signals, that is, the data analysis is not comprehensive, and accurate and comprehensive cerebral information cannot be obtained according to the acquired cerebral blood oxygen signals.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus and a computer-readable storage medium for processing near-infrared brain function imaging data.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the embodiment of the invention provides a method for processing near-infrared brain function imaging data, which comprises the following steps:
acquiring near-infrared brain function imaging data of at least two channels;
constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network;
and processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
In the above scheme, after acquiring the near-infrared brain function imaging data of at least two channels, the method further includes: preprocessing near-infrared brain function imaging data of each channel of the at least two channels;
the preprocessing of the near-infrared brain function imaging data of the at least two channels comprises:
white noise removal processing is carried out on the near-infrared brain function imaging data of each channel of the at least two channels, and the near-infrared brain function imaging data after the white noise removal processing is obtained;
filtering the near-infrared brain function imaging data after the white noise removal processing to obtain at least one sub-frequency band signal;
correspondingly, the constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels comprises:
and constructing a brain function network according to the signals of at least one sub-frequency band corresponding to each channel of the at least two channels.
In the above scheme, the white noise removing processing on the near-infrared brain function imaging data of each of the at least two channels includes:
performing empirical mode decomposition on the near-infrared brain function imaging data of each channel of the at least two channels to obtain an inherent mode function decomposed from the near-infrared brain function imaging data of each channel;
and removing the inherent modal components of the white noise in the near-infrared brain function imaging data of each channel by using the statistical characteristics of the inherent modal functions, recombining the residual inherent modal components after removal to obtain a new signal, and using the new signal as the near-infrared brain function imaging data after the white noise removal processing.
In the above scheme, the near-infrared brain function imaging data includes: cerebral blood oxygen signals;
the method for constructing the brain function network according to the near-infrared brain function imaging data of the at least two channels comprises the following steps:
determining a wavelet coefficient of the cerebral blood oxygen signal of at least one sub-frequency band corresponding to each channel according to the cerebral blood oxygen signal of at least one sub-frequency band corresponding to each channel in the at least two channels;
determining a wavelet coherence coefficient between any two channels of the at least two channels according to the wavelet coefficient corresponding to each channel; the wavelet coherence coefficient represents the correlation degree of the cerebral blood oxygen signals corresponding to the two channels;
obtaining a correlation matrix corresponding to at least two channels according to a wavelet coherence coefficient between any two channels in the at least two channels;
taking each channel of the at least two channels as a node respectively, and determining the incidence relation between the nodes according to the incidence matrix;
and constructing the brain function network according to the incidence relation among the nodes.
In the foregoing solution, the network characteristic parameters include: weighted average degree, average weighted clustering coefficient, average weighted shortest path length and compact centrality;
the determining at least one network characteristic parameter according to the brain function network comprises at least one of the following:
determining the weighted average degree of the brain function network according to the weighted degree of each node in the brain function network;
determining a clustering coefficient of each node in the brain function network according to the connection relation among the nodes in the brain function network, and determining the average weighted clustering coefficient according to the clustering coefficient of each node;
determining the length of the average weighted shortest path of the brain function network according to the weight between each node in the brain function network;
and determining the tight centrality of the brain function network according to the weighted shortest path length and the total number of nodes among the nodes in the brain function network.
The embodiment of the invention provides a device for processing near-infrared brain function imaging data, which comprises: a first processing module and a second processing module; wherein the content of the first and second substances,
the first processing module is used for acquiring near-infrared brain function imaging data of at least two channels; constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network;
and the second processing module is used for processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
In the above scheme, the first processing module is further configured to perform white noise removal processing on the near-infrared brain function imaging data of each of the at least two channels to obtain near-infrared brain function imaging data after the white noise removal processing; filtering the near-infrared brain function imaging data after the white noise removal processing to obtain at least one sub-frequency band signal;
correspondingly, the first processing module is configured to construct a brain function network according to the signal of at least one sub-band corresponding to each of the at least two channels.
In the foregoing scheme, the first processing module is specifically configured to perform empirical mode decomposition on the near-infrared brain function imaging data of each of the at least two channels to obtain an inherent mode function decomposed from the near-infrared brain function imaging data of each channel;
and removing the inherent modal components of the white noise in the near-infrared brain function imaging data of each channel by using the statistical characteristics of the inherent modal functions, recombining the residual inherent modal components after removal to obtain a new signal, and using the new signal as the near-infrared brain function imaging data after the white noise removal processing.
In the above scheme, the near-infrared brain function imaging data includes: cerebral blood oxygen signals; the first processing module is configured to determine a wavelet coefficient of the cerebral blood oxygen signal of at least one sub-band corresponding to each channel according to the cerebral blood oxygen signal of at least one sub-band corresponding to each channel of the at least two channels;
determining a wavelet coherence coefficient between any two channels of the at least two channels according to the wavelet coefficient corresponding to each channel; the wavelet coherence coefficient represents the correlation degree of the cerebral blood oxygen signals corresponding to the two channels;
obtaining a correlation matrix corresponding to at least two channels according to a wavelet coherence coefficient between any two channels in the at least two channels;
taking each channel of the at least two channels as a node respectively, and determining the incidence relation between the nodes according to the incidence matrix;
and constructing the brain function network according to the incidence relation among the nodes.
In the foregoing solution, the network characteristic parameters include: weighted average degree, average weighted clustering coefficient, average weighted shortest path length and compact centrality; the first processing module is used for determining at least one network characteristic parameter according to the brain function network by using at least one of the following methods:
determining the weighted average degree of the brain function network according to the weighted degree of each node in the brain function network;
determining a clustering coefficient of each node in the brain function network according to the connection relation among the nodes in the brain function network, and determining the average weighted clustering coefficient according to the clustering coefficient of each node;
determining the length of the average weighted shortest path of the brain function network according to the weight between each node in the brain function network;
and determining the tight centrality of the brain function network according to the weighted shortest path length and the total number of nodes among the nodes in the brain function network.
The embodiment of the invention provides a device for processing near-infrared brain function imaging data, which comprises: a processor and a memory for storing a computer program capable of running on the processor; wherein the content of the first and second substances,
the processor is configured to execute the steps of any one of the methods for processing near-infrared brain function imaging data described above when the computer program is executed.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of any one of the methods for processing near-infrared brain function imaging data described above.
The processing method, the processing device and the computer-readable storage medium for the near-infrared brain function imaging data provided by the embodiment of the invention are used for acquiring the near-infrared brain function imaging data of at least two channels; constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network; and processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result. In the embodiment of the invention, the near-infrared brain function imaging data obtained by a plurality of test channels are processed to obtain more comprehensive data carrying brain blood oxygen information; and a brain function network is constructed according to the near-infrared brain function imaging data, and the brain function network is analyzed and processed, so that the obtained brain information is more comprehensive and accurate.
Drawings
Fig. 1 is a schematic flowchart of a method for processing near-infrared brain function imaging data according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a device for processing near-infrared brain function imaging data according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of another apparatus for processing near-infrared brain function imaging data according to an embodiment of the present invention
Fig. 4 is a schematic structural diagram of another apparatus for processing near-infrared brain function imaging data according to an embodiment of the present invention.
Detailed Description
In various embodiments of the present invention, near-infrared brain function imaging data is acquired for at least two channels; constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network; and processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
The present invention will be described in further detail with reference to examples.
Fig. 1 is a schematic flowchart of a method for processing near-infrared brain function imaging data according to an embodiment of the present invention; the method can be applied to a server; as shown in fig. 1, the method includes:
Specifically, the acquiring near-infrared brain function imaging data of at least two channels includes:
the near-infrared brain function imaging data of the cerebral cortex is monitored in a multi-channel mode by using a near-infrared spectral imaging technology, and the near-infrared brain function imaging data of at least two channels are obtained. The multiple channels specifically refer to at least two channels.
Specifically, after acquiring the near-infrared brain function imaging data of at least two channels, the method further comprises: preprocessing near-infrared brain function imaging data of each channel of the at least two channels;
the preprocessing of the near-infrared brain function imaging data of each channel of the at least two channels specifically comprises:
white noise removal processing is carried out on the near-infrared brain function imaging data of each channel of the at least two channels, and the near-infrared brain function imaging data after the white noise removal processing is obtained;
and filtering the near-infrared brain function imaging data subjected to the white noise removal processing to obtain signals of at least one sub-frequency band.
Specifically, the white noise removing processing of the near-infrared brain function imaging data of each of the at least two channels includes:
performing Empirical Mode Decomposition (EMD) on the near-infrared brain Function imaging data of each of the at least two channels to obtain Intrinsic Mode Functions (IMF) decomposed from the near-infrared brain Function imaging data of each channel;
and removing the inherent modal components of the white noise in the near-infrared brain function imaging data of each channel by using the statistical characteristics of the inherent modal functions, recombining the residual inherent modal components after removal to obtain a new signal, and using the new signal as the near-infrared brain function imaging data after the white noise removal processing.
Here, because the interference of noise is greatly reduced, the decomposed natural mode function component has physical significance by utilizing the space-time filtering characteristic of the EMD, and the decomposed natural mode function can be used for realizing the effects of filtering harmonic waves and retaining fundamental wave components of a signal containing white noise, thereby effectively removing the white noise of the signal.
Specifically, the filtering processing of the near-infrared brain function imaging data after the white noise removal processing to obtain a signal of at least one sub-band includes:
and filtering the near-infrared brain function imaging data after the white noise removal processing by using a Butterworth second-order band-pass filter to obtain a signal of at least one sub-frequency band.
Here, the signal of the at least one sub-band is used for data analysis. The at least one sub-band comprises at least one of: 0.01 to 0.03Hz, 0.03 to 0.08Hz, 0.08 to 0.15 Hz.
Specifically, the near-infrared brain function imaging data includes: cerebral blood oxygen signals; the cerebral blood oxygen signals include at least one of: oxygenated hemoglobin signal, deoxygenated hemoglobin signal, and relative change value signal of total hemoglobin concentration.
Here, the above-mentioned empirical mode decomposition of the near-infrared brain function imaging data of each of the at least two channels specifically means empirical mode decomposition of the cerebral blood oxygen signal (i.e., the oxygenated hemoglobin signal, the deoxygenated hemoglobin signal, and the relative change value signal of the total hemoglobin concentration) of each channel.
And the obtained signal of the at least one sub-frequency band specifically refers to a cerebral blood oxygen signal of the at least one sub-frequency band, so as to construct a cerebral function network.
In this embodiment, considering that the preprocessing means for the near-infrared brain function imaging data in the prior art is rough, and there is always noise in the analysis process, which affects the stability and reliability of the analysis result, the noise in the near-infrared brain function imaging data can be well removed through the filtering processing, so as to obtain more accurate near-infrared brain function imaging data, and thus a processing result with higher stability and reliability can be obtained based on the filtered near-infrared brain function imaging data.
And 102, constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network.
Specifically, the network characteristic parameters represent characteristic parameters of a brain function network constructed according to the near-infrared brain function imaging data, and the network characteristic parameters can reflect the health state of the brain corresponding to the infrared brain function imaging data.
The method for constructing the brain function network according to the near-infrared brain function imaging data of the at least two channels comprises the following steps:
determining a wavelet coefficient of the cerebral blood oxygen signal of at least one sub-frequency band corresponding to each channel according to the cerebral blood oxygen signal of at least one sub-frequency band corresponding to each channel in the at least two channels;
determining a wavelet coherence coefficient between any two channels of the at least two channels according to the wavelet coefficient corresponding to each channel; the wavelet coherence coefficient represents the correlation degree of the cerebral blood oxygen signals corresponding to the two channels;
obtaining a correlation matrix corresponding to at least two channels according to a wavelet coherence coefficient between any two channels in the at least two channels;
taking each channel of the at least two channels as a node respectively, and determining the incidence relation between the nodes according to the incidence matrix;
and constructing a brain function network according to the incidence relation among the nodes.
Specifically, the correlation matrix is formed by wavelet coherence coefficients of the cerebral blood oxygen signals between different pairs of test channels (the pairs of test channels may be, for example, test channels a and B, test channels B and C, etc.).
When the brain function network is constructed, each test channel corresponds to a node of the brain function network, so that the wavelet coherence coefficients corresponding to two test channels in the correlation matrix can represent the weight of the connecting edge of the corresponding two nodes.
Whether any two nodes are connected is also determined based on the wavelet coherence coefficient between the channels corresponding to the two nodes, and when the wavelet coherence coefficient is greater than or equal to a preset threshold (the threshold is set by a developer and stored in a server), the two nodes are determined to be connected; and when the wavelet coherence coefficient is smaller than a preset threshold value, determining that the two nodes are not connected.
It should be noted that, in the scheme of this embodiment, only a signal of one sub-band may be used to obtain a set of network characteristic parameter sets; signals of a plurality of sub-bands can also be adopted, specifically, cerebral blood oxygen signals of a plurality of sub-bands are obtained; if the cerebral blood oxygen signals of a plurality of sub-bands are adopted, the cerebral blood oxygen signals of each sub-band can be respectively calculated to obtain a plurality of groups of network characteristic parameter sets (each group of network characteristic parameter sets respectively comprises at least one network characteristic parameter); if multiple sets of network feature parameter sets are obtained, they may be integrated (for example, an average value is taken, or weighting processing is performed according to preset weights corresponding to each sub-band, etc., where only the expression may be used to process the multiple sets of network feature parameter sets, the specific method is not limited to the above description, and different methods may be adopted according to actual applications, which are not described herein in detail), and a final wavelet coherence coefficient is obtained by calculation according to the integrated result.
Further, the building of the brain function network according to the incidence relation between the nodes includes: and establishing a brain function network which accords with the preset network sparsity and the small world attribute value removing pseudo connection rule according to the incidence relation among the nodes.
The preset network sparsity and small world attribute value removing pseudo-connection rules comprises the following steps:
A. the network sparsity is less than 0.5;
B. the small world attribute index σ > 1.1.
Here, the sparsity can well mask the difference of different connection definitions, so the sparsity is used for threshold setting. The small world attribute can be used as a standard to determine a proper sparsity range, namely, a sparsity space of the small world network attribute can be described, a threshold space is determined by using the basic network characteristic of the small world attribute, and pseudo-connection is removed to the greatest extent while the small world attribute is ensured.
Specifically, the brain network characteristic parameters include: weighted average degree, average weighted cluster coefficient, average weighted shortest path length and compact centrality.
Specifically, the determining at least one network characteristic parameter according to the brain function network comprises at least one of the following:
determining the weighted average degree of the brain function network according to the weighted degree of each node in the brain function network;
determining a clustering coefficient of each node in the brain function network according to the connection relation among the nodes in the brain function network, and determining the average weighted clustering coefficient according to the clustering coefficient of each node;
determining the length of the average weighted shortest path of the brain function network according to the weight between each node in the brain function network;
and determining the tight centrality of the brain function network according to the weighted shortest path length and the total number of nodes among the nodes in the brain function network.
The following description is made on the determination methods of the weighted average degree, the weighted average cluster coefficient, the weighted average shortest path length, and the tight center degree, respectively.
I. For weighted averaging, it should be noted that, in a weighted brain function network, the weighting degree represents the sum of the weights of all the connecting edges connected to the nodes; here, the weighting degree of each node is determined based on the wavelet coherence coefficient, and specifically, the wavelet coherence coefficient corresponding to two test channels represents the weight of the connecting edge of the corresponding two nodes.
Here, determining the weighted average degree of the brain function network according to the weighted degree of each node in the brain function network includes:
averaging the weighted degrees of all nodes in the brain function network to obtain the weighted average degree of the brain function network, which is specifically as follows:
wherein, wijRepresenting the weight between the node i and the node j, and when the node i is not connected with the node j, wijThe value is 0, when the node i is connected with the node j, wijValues are taken as corresponding elements in the incidence matrix, namely wavelet coherence coefficients corresponding to the two test channels, namely the weights of the connecting edges of the two nodes; h isijRepresents the corresponding values of the node i and the node j in the binary matrix; n represents the total number of nodes, i.e. the total number of channels.
It should be noted that, when constructing the brain function network, a threshold (determined by a developer according to actual requirements) needs to be selected to construct a corresponding binary matrix according to the solved wavelet coherence coefficient matrix. When the wavelet coherence coefficient between the signals corresponding to the channels is larger than the correspondingly selected threshold, the value of the element at the corresponding position of the matrix is 1, and when the wavelet coherence coefficient is smaller than or equal to the threshold, the value of the element at the corresponding position of the matrix is 0, so that a binary matrix with matrix elements only being 0 and 1 can be obtained.
II. For the average weighted clustering coefficient, it should be noted that, in the weighted brain function network, the clustering coefficient is also called clustering coefficient, which is an important parameter for measuring clustering and connection tightness in the brain function network, and indicates the possibility that each neighboring node of a certain node in the brain function network is a neighbor.
Here, determining the clustering coefficient of each node in the brain function network according to the connection relationship between each node in the brain function network includes:
wherein D isiRepresenting the degree of the node i, which refers to the number of edges connected with the node i in the brain function network; di wRepresenting the degree of weighting, w, of node iijRepresenting the weight between node i and node j, wikRepresents the weight, h, between node j and node kij、hikAnd hkiRespectively representing the connection conditions between a node i and a node j, between the node j and a node k, and between the node k and the node i, wherein the connection is represented by the value of 1, and the non-connection is represented by the value of 0;
then, averaging the clustering coefficients of each node in the brain function network to obtain an average weighted clustering coefficient of the brain function network, namely:
Ci wrepresenting the clustering coefficient of node i in the brain function network.
And III, aiming at the length of the average weighted shortest path, firstly, it needs to be explained that the average path length in the brain function network represents the average value of the shortest path lengths of any two nodes, and is a key parameter for describing the internal information transmission of the complex network.
Here, determining the weighted shortest path length between any two nodes in the brain function network according to the weight between the nodes in the brain function network includes:
wherein the content of the first and second substances,
the weighted shortest path length between a node i and a node j in the brain function network is represented, w represents a weight between any two nodes, and subscripts represent the numbers of the two nodes corresponding to the weight;
averaging the weighted shortest path length between any two nodes in the brain function network to obtain the average weighted shortest path length in the brain function network, namely:
where V denotes a node sequence number matrix, and if there are 10 nodes, V ═ 1,2,3,4,5,6,7,8,9,10] each node corresponds to a different sequence number.
IV, the centrality of the brain function network usually represents an index which describes the central position degree of each node in the brain function network by adopting a quantitative method. Brain function network centrality can be used to describe whether the entire network under study exists and what core or hub nodes exist.
For the tight centrality, the tight centrality is a definition of the centrality of the brain function network, and the tight centrality in the brain function network is determined according to the length of the weighted shortest path, which is specifically as follows:
wherein the content of the first and second substances,
and the weighted shortest path length between the node i and the node j in the brain function network is represented, N represents the total number of the nodes, and N-1 represents the maximum possible number of adjacent points of the nodes in the brain function network.
And 103, processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
Here, the processing result may represent a risk probability of an illness of the brain corresponding to the near-infrared brain function imaging data.
In this embodiment, the server may further store a corresponding relationship between different processing results and different processing schemes, and query the corresponding relationship according to the obtained processing results to obtain the processing schemes corresponding to the processing results. The treatment regimen may include health advice, treatment advice, recommended daily movements, and the like. So that life advice can be given and some corresponding treatment schemes can be provided to prevent the risk of the disease.
In an embodiment, the processing the at least one network feature parameter according to a preset processing rule to obtain a processing result includes:
and determining the weight corresponding to each network characteristic parameter in the at least one network characteristic parameter, and calculating according to the weight corresponding to each network characteristic parameter and each network characteristic parameter to obtain a processing result.
In another embodiment, the processing the at least one network characteristic parameter according to a preset rule to obtain a processing result includes:
and acquiring a preset processing model, and processing the at least one network characteristic parameter by using the processing model to obtain a processing result.
Correspondingly, the method further comprises the following steps: generating the processing model; the generating a process model includes: and training by using a random forest integration algorithm to obtain a processing model. Specifically, the generating a process model includes:
obtaining at least one sample data, wherein the sample data corresponds to a training label; the sample data, comprising at least one of: sample weighted average degree, sample weighted average clustering coefficient, sample weighted average shortest path length and sample tight centrality; the training labels represent the disease risk probability of the brain corresponding to the near-infrared brain function imaging data;
inputting the at least one sample data and the training label corresponding to each sample data into a preset model for training, and taking the model obtained after training as the processing model.
Specifically, the sample weighted average degree, the sample weighted average clustering coefficient, the sample weighted average shortest path length, and the sample tight center degree may be obtained by processing the sample near-infrared brain function imaging data by using the method for obtaining the weighted average degree, the average weighted clustering coefficient, the average weighted shortest path length, and the tight center degree in step 101, which is not described herein again.
In this embodiment, in consideration of the fact that the analysis dimension of the near-infrared brain function imaging data in the prior art is relatively single, and the extracted features cannot comprehensively represent the information carried by the blood oxygen information of the tested brain, the processing method of the near-infrared brain function imaging data is provided, a plurality of network feature parameters can be obtained as a processing basis, the processing result obtained by processing according to the plurality of network feature parameters can more comprehensively and accurately reflect the brain state, and the referential property of the processing result is higher.
Fig. 2 is a schematic structural diagram of a device for processing near-infrared brain function imaging data according to an embodiment of the present invention, as shown in fig. 2, the device may include: the device comprises a data acquisition module, a data analysis module and a data processing module.
The data acquisition module is used for monitoring near-infrared brain function imaging data of cerebral cortex in a multi-channel manner by using a near-infrared spectral imaging technology to obtain near-infrared brain function imaging data of at least two channels; the near-infrared brain function imaging data includes at least one of: oxyhemoglobin signal (HbO2), deoxygenated hemoglobin signal (Hb), relative change in total hemoglobin concentration signal.
The data analysis module is used for constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels and determining at least one network characteristic parameter according to the brain function network; the data analysis module specifically comprises: a preprocessing unit and a feature extraction unit; wherein the content of the first and second substances,
the preprocessing unit is used for carrying out white noise removal processing on the near-infrared brain function imaging data of the at least two channels to obtain the near-infrared brain function imaging data after the white noise removal processing; and filtering the near-infrared brain function imaging data subjected to the white noise removal processing to obtain signals of at least one sub-frequency band.
The feature extraction unit is configured to calculate a wavelet coherence coefficient between the channels according to the cerebral blood oxygen signals between the channels in the at least two channels, so as to obtain a correlation matrix, where the correlation matrix may be used to analyze a correlation degree of the cerebral blood oxygen signals between the channels;
taking each channel of the at least two channels as a node respectively, and determining the incidence relation between the nodes according to the incidence matrix;
according to the incidence relation, a brain function network which accords with a preset network sparsity and a small world attribute value and removes a pseudo connection rule is constructed;
extracting the network characteristics of the brain function network to obtain brain network characteristic parameters; the brain network characteristic parameters comprise at least one of the following parameters: weighted average degree, average weighted cluster coefficient, average weighted shortest path length and compact centrality.
And the data processing module is used for processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
The apparatus may further include: and the report generating module is used for generating a corresponding detection report according to the processing result. The detection report may include: the processing result and the processing scheme corresponding to the processing result can comprise health-preserving suggestions, treatment suggestions, recommended daily exercises and the like.
Here, the processing device for near-infrared brain function imaging data provided in the above embodiment is only exemplified by the division of the above program modules when processing the near-infrared brain function imaging data, and in practical applications, the processing may be distributed to be completed by different program modules according to needs, that is, the internal structure of the device may be divided into different program modules so as to complete all or part of the above-described processing. In addition, the processing apparatus for near-infrared brain function imaging data provided in the foregoing embodiment and the processing method embodiment for near-infrared brain function imaging data belong to the same concept, and specific implementation processes thereof are described in the method embodiment and are not described herein again.
Fig. 3 is a schematic structural diagram of another near-infrared brain function imaging data processing apparatus according to an embodiment of the present invention; as shown in fig. 3, the apparatus includes: the device comprises a first processing module and a second processing module. Wherein the content of the first and second substances,
the first processing module is used for acquiring near-infrared brain function imaging data of at least two channels; constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network;
and the second processing module is used for processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
Specifically, the first processing module is further configured to perform white noise removal processing on the near-infrared brain function imaging data of each of the at least two channels to obtain near-infrared brain function imaging data after the white noise removal processing; filtering the near-infrared brain function imaging data after the white noise removal processing to obtain at least one sub-frequency band signal;
correspondingly, the first processing module is configured to construct a brain function network according to the signal of at least one sub-band corresponding to each of the at least two channels.
Specifically, the first processing module is specifically configured to perform empirical mode decomposition on the near-infrared brain function imaging data of each of the at least two channels to obtain an inherent mode function decomposed from the near-infrared brain function imaging data of each channel;
and removing the inherent modal components of the white noise in the near-infrared brain function imaging data of each channel by using the statistical characteristics of the inherent modal functions, recombining the residual inherent modal components after removal to obtain a new signal, and using the new signal as the near-infrared brain function imaging data after the white noise removal processing.
Specifically, the first processing module is specifically configured to perform filtering processing on the near-infrared brain function imaging data after the white noise removal processing by using a butterworth second-order band-pass filter, so as to obtain a signal of at least one sub-band.
Specifically, the near-infrared brain function imaging data includes: cerebral blood oxygen signals; the first processing module is configured to determine a wavelet coefficient of the cerebral blood oxygen signal of at least one sub-band corresponding to each channel according to the cerebral blood oxygen signal of at least one sub-band corresponding to each channel of the at least two channels;
determining a wavelet coherence coefficient between any two channels of the at least two channels according to the wavelet coefficient corresponding to each channel; the wavelet coherence coefficient represents the correlation degree of the cerebral blood oxygen signals corresponding to the two channels;
obtaining a correlation matrix corresponding to at least two channels according to a wavelet coherence coefficient between any two channels in the at least two channels;
taking each channel of the at least two channels as a node respectively, and determining the incidence relation between the nodes according to the incidence matrix;
and constructing the brain function network according to the incidence relation among the nodes.
Specifically, the network characteristic parameters include: weighted average degree, average weighted clustering coefficient, average weighted shortest path length and compact centrality; the first processing module is used for determining at least one network characteristic parameter according to the brain function network by using at least one of the following methods:
determining the weighted average degree of the brain function network according to the weighted degree of each node in the brain function network;
determining a clustering coefficient of each node in the brain function network according to the connection relation among the nodes in the brain function network, and determining the average weighted clustering coefficient according to the clustering coefficient of each node;
determining the length of the average weighted shortest path of the brain function network according to the weight between each node in the brain function network;
and determining the tight centrality of the brain function network according to the weighted shortest path length and the total number of nodes among the nodes in the brain function network.
It should be noted that: in the processing apparatus for near-infrared brain function imaging data provided in the above embodiment, when processing the near-infrared brain function imaging data, only the division of the above program modules is exemplified, and in practical applications, the above processing may be distributed to be completed by different program modules according to needs, that is, the internal structure of the apparatus is divided into different program modules to complete all or part of the above-described processing. In addition, the processing apparatus for near-infrared brain function imaging data provided in the foregoing embodiment and the processing method embodiment for near-infrared brain function imaging data belong to the same concept, and specific implementation processes thereof are described in the method embodiment and are not described herein again.
Fig. 4 is a schematic structural diagram of another apparatus for processing near-infrared brain function imaging data according to an embodiment of the present invention. The device 40 comprises: a processor 401 and a memory 402 for storing computer programs executable on said processor; wherein, the processor 401 is configured to execute, when running the computer program, the following steps: acquiring near-infrared brain function imaging data of at least two channels; constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network; and processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
In an embodiment, the processor 401 is further configured to execute, when running the computer program, the following: after acquiring near-infrared brain function imaging data of at least two channels, preprocessing the near-infrared brain function imaging data of each channel of the at least two channels; the preprocessing of the near-infrared brain function imaging data of the at least two channels comprises: white noise removal processing is carried out on the near-infrared brain function imaging data of each channel of the at least two channels, and the near-infrared brain function imaging data after the white noise removal processing is obtained; filtering the near-infrared brain function imaging data after the white noise removal processing to obtain at least one sub-frequency band signal; correspondingly, the constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels comprises: and constructing a brain function network according to the signals of at least one sub-frequency band corresponding to each channel of the at least two channels.
In an embodiment, the processor 401 is further configured to execute, when running the computer program, the following: performing empirical mode decomposition on the near-infrared brain function imaging data of each channel of the at least two channels to obtain an inherent mode function decomposed from the near-infrared brain function imaging data of each channel; and removing the inherent modal components of the white noise in the near-infrared brain function imaging data of each channel by using the statistical characteristics of the inherent modal functions, recombining the residual inherent modal components after removal to obtain a new signal, and using the new signal as the near-infrared brain function imaging data after the white noise removal processing.
In an embodiment, the processor 401 is further configured to execute, when running the computer program, the following: and filtering the near-infrared brain function imaging data after the white noise removal processing by using a Butterworth second-order band-pass filter to obtain a signal of at least one sub-frequency band. The near-infrared brain function imaging data comprising: cerebral blood oxygen signals.
In an embodiment, the processor 401 is further configured to execute, when running the computer program, the following: determining a wavelet coefficient of the cerebral blood oxygen signal of at least one sub-frequency band corresponding to each channel according to the cerebral blood oxygen signal of at least one sub-frequency band corresponding to each channel in the at least two channels; determining a wavelet coherence coefficient between any two channels of the at least two channels according to the wavelet coefficient corresponding to each channel; the wavelet coherence coefficient represents the correlation degree of the cerebral blood oxygen signals corresponding to the two channels; obtaining a correlation matrix corresponding to at least two channels according to a wavelet coherence coefficient between any two channels in the at least two channels; taking each channel of the at least two channels as a node respectively, and determining the incidence relation between the nodes according to the incidence matrix; and constructing the brain function network according to the incidence relation among the nodes. The network characteristic parameters comprise: weighted average degree, average weighted cluster coefficient, average weighted shortest path length and compact centrality.
In an embodiment, the processor 401 is further configured to execute, when running the computer program, the following: determining at least one network characteristic parameter from the brain function network using at least one of: determining the weighted average degree of the brain function network according to the weighted degree of each node in the brain function network; determining a clustering coefficient of each node in the brain function network according to the connection relation among the nodes in the brain function network, and determining the average weighted clustering coefficient according to the clustering coefficient of each node; determining the length of the average weighted shortest path of the brain function network according to the weight between each node in the brain function network; and determining the tight centrality of the brain function network according to the weighted shortest path length and the total number of nodes among the nodes in the brain function network.
It should be noted that: the processing device of the near-infrared brain function imaging data provided by the above embodiment and the processing method embodiment of the near-infrared brain function imaging data belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.
In practical applications, the apparatus 40 may further include: at least one network interface 403. The various components in the processing device 40 of near infrared brain function imaging data are coupled together by a bus system 405. It is understood that the bus system 405 is used to enable connection communication between these components. The bus system 405 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 405 in fig. 4. The number of the processors 405 may be at least one. The network interface 403 is used for wired or wireless communication between the processing apparatus 40 for near-infrared brain function imaging data and other devices.
The memory 402 in embodiments of the present invention is used to store various types of data to support the operation of the processing device 40 of near infrared brain function imaging data.
The method disclosed in the above embodiments of the present invention may be applied to the processor 401, or implemented by the processor 401. The processor 401 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 401. The Processor 401 described above may be a general purpose Processor, a DiGital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Processor 401 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed by the embodiment of the invention can be directly implemented by a hardware decoding processor, or can be implemented by combining hardware and software modules in the decoding processor. The software modules may be located in a storage medium located in the memory 402, and the processor 401 reads the information in the memory 402 and performs the steps of the aforementioned methods in conjunction with its hardware.
In an exemplary embodiment, the processing Device 40 of the near-infrared brain function imaging data may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors (gpus), controllers, Micro Controllers (MCUs), microprocessors (microprocessors), or other electronic components for performing the aforementioned methods.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs: acquiring near-infrared brain function imaging data of at least two channels; constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network; and processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
In one embodiment, the computer program, when executed by the processor, performs: after acquiring near-infrared brain function imaging data of at least two channels, preprocessing the near-infrared brain function imaging data of each channel of the at least two channels; the preprocessing of the near-infrared brain function imaging data of the at least two channels comprises: white noise removal processing is carried out on the near-infrared brain function imaging data of each channel of the at least two channels, and the near-infrared brain function imaging data after the white noise removal processing is obtained; filtering the near-infrared brain function imaging data after the white noise removal processing to obtain at least one sub-frequency band signal; correspondingly, the constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels comprises: and constructing a brain function network according to the signals of at least one sub-frequency band corresponding to each channel of the at least two channels.
In one embodiment, the computer program, when executed by the processor, performs: performing empirical mode decomposition on the near-infrared brain function imaging data of each channel of the at least two channels to obtain an inherent mode function decomposed from the near-infrared brain function imaging data of each channel; and removing the inherent modal components of the white noise in the near-infrared brain function imaging data of each channel by using the statistical characteristics of the inherent modal functions, recombining the residual inherent modal components after removal to obtain a new signal, and using the new signal as the near-infrared brain function imaging data after the white noise removal processing.
In one embodiment, the computer program, when executed by the processor, performs: and filtering the near-infrared brain function imaging data after the white noise removal processing by using a Butterworth second-order band-pass filter to obtain a signal of at least one sub-frequency band. The near-infrared brain function imaging data comprising: cerebral blood oxygen signals.
In one embodiment, the computer program, when executed by the processor, performs: determining a wavelet coefficient of the cerebral blood oxygen signal of at least one sub-frequency band corresponding to each channel according to the cerebral blood oxygen signal of at least one sub-frequency band corresponding to each channel in the at least two channels; determining a wavelet coherence coefficient between any two channels of the at least two channels according to the wavelet coefficient corresponding to each channel; the wavelet coherence coefficient represents the correlation degree of the cerebral blood oxygen signals corresponding to the two channels; obtaining a correlation matrix corresponding to at least two channels according to a wavelet coherence coefficient between any two channels in the at least two channels; taking each channel of the at least two channels as a node respectively, and determining the incidence relation between the nodes according to the incidence matrix; and constructing the brain function network according to the incidence relation among the nodes. The network characteristic parameters comprise: weighted average degree, average weighted cluster coefficient, average weighted shortest path length and compact centrality.
In one embodiment, the computer program, when executed by the processor, performs: determining at least one network characteristic parameter from the brain function network using at least one of: determining the weighted average degree of the brain function network according to the weighted degree of each node in the brain function network; determining a clustering coefficient of each node in the brain function network according to the connection relation among the nodes in the brain function network, and determining the average weighted clustering coefficient according to the clustering coefficient of each node; determining the length of the average weighted shortest path of the brain function network according to the weight between each node in the brain function network; and determining the tight centrality of the brain function network according to the weighted shortest path length and the total number of nodes among the nodes in the brain function network.
In the several 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 device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, 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.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only exemplary of the present invention and should not be taken as limiting the scope of the present invention, and any modifications, equivalents, improvements, etc. that are within the spirit and principle of the present invention should be included in the present invention.
Claims (10)
1. A method of processing near-infrared brain function imaging data, the method comprising:
acquiring near-infrared brain function imaging data of at least two channels;
constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network;
and processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
2. The method of claim 1, wherein after acquiring near-infrared brain function imaging data for at least two channels, the method further comprises: preprocessing near-infrared brain function imaging data of each channel of the at least two channels;
the preprocessing of the near-infrared brain function imaging data of the at least two channels comprises:
white noise removal processing is carried out on the near-infrared brain function imaging data of each channel of the at least two channels, and the near-infrared brain function imaging data after the white noise removal processing is obtained;
filtering the near-infrared brain function imaging data after the white noise removal processing to obtain at least one sub-frequency band signal;
correspondingly, the constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels comprises:
and constructing a brain function network according to the signals of at least one sub-frequency band corresponding to each channel of the at least two channels.
3. The method according to claim 2, wherein the performing white noise removal processing on the near-infrared brain function imaging data of each of the at least two channels comprises:
performing empirical mode decomposition on the near-infrared brain function imaging data of each channel of the at least two channels to obtain an inherent mode function decomposed from the near-infrared brain function imaging data of each channel;
and removing the inherent modal components of the white noise in the near-infrared brain function imaging data of each channel by using the statistical characteristics of the inherent modal functions, recombining the residual inherent modal components after removal to obtain a new signal, and using the new signal as the near-infrared brain function imaging data after the white noise removal processing.
4. The method of claim 1, wherein the near-infrared brain function imaging data comprises: cerebral blood oxygen signals;
the method for constructing the brain function network according to the near-infrared brain function imaging data of the at least two channels comprises the following steps:
determining a wavelet coefficient of the cerebral blood oxygen signal of at least one sub-frequency band corresponding to each channel according to the cerebral blood oxygen signal of at least one sub-frequency band corresponding to each channel in the at least two channels;
determining a wavelet coherence coefficient between any two channels of the at least two channels according to the wavelet coefficient corresponding to each channel; the wavelet coherence coefficient represents the correlation degree of the cerebral blood oxygen signals corresponding to the two channels;
obtaining a correlation matrix corresponding to at least two channels according to a wavelet coherence coefficient between any two channels in the at least two channels;
taking each channel of the at least two channels as a node respectively, and determining the incidence relation between the nodes according to the incidence matrix;
and constructing the brain function network according to the incidence relation among the nodes.
5. The method of claim 1, wherein the network characteristic parameter comprises: weighted average degree, average weighted clustering coefficient, average weighted shortest path length and compact centrality;
the determining at least one network characteristic parameter according to the brain function network comprises at least one of the following:
determining the weighted average degree of the brain function network according to the weighted degree of each node in the brain function network;
determining a clustering coefficient of each node in the brain function network according to the connection relation among the nodes in the brain function network, and determining the average weighted clustering coefficient according to the clustering coefficient of each node;
determining the length of the average weighted shortest path of the brain function network according to the weight between each node in the brain function network;
and determining the tight centrality of the brain function network according to the weighted shortest path length and the total number of nodes among the nodes in the brain function network.
6. An apparatus for processing near-infrared brain function imaging data, the apparatus comprising: a first processing module and a second processing module; wherein the content of the first and second substances,
the first processing module is used for acquiring near-infrared brain function imaging data of at least two channels; constructing a brain function network according to the near-infrared brain function imaging data of the at least two channels, and determining at least one network characteristic parameter according to the brain function network;
and the second processing module is used for processing the at least one network characteristic parameter according to a preset processing rule to obtain a processing result.
7. The apparatus of claim 6, wherein the near-infrared brain function imaging data comprises: cerebral blood oxygen signals;
the first processing module is configured to determine a wavelet coefficient of the cerebral blood oxygen signal of at least one sub-band corresponding to each channel according to the cerebral blood oxygen signal of at least one sub-band corresponding to each channel of the at least two channels;
determining a wavelet coherence coefficient between any two channels of the at least two channels according to the wavelet coefficient corresponding to each channel; the wavelet coherence coefficient represents the correlation degree of the cerebral blood oxygen signals corresponding to the two channels;
obtaining a correlation matrix corresponding to at least two channels according to a wavelet coherence coefficient between any two channels in the at least two channels;
taking each channel of the at least two channels as a node respectively, and determining the incidence relation between the nodes according to the incidence matrix;
and constructing the brain function network according to the incidence relation among the nodes.
8. The apparatus of claim 6, wherein the network characteristic parameter comprises: weighted average degree, average weighted clustering coefficient, average weighted shortest path length and compact centrality;
the first processing module is used for determining at least one network characteristic parameter according to the brain function network by using at least one of the following methods:
determining the weighted average degree of the brain function network according to the weighted degree of each node in the brain function network;
determining a clustering coefficient of each node in the brain function network according to the connection relation among the nodes in the brain function network, and determining the average weighted clustering coefficient according to the clustering coefficient of each node;
determining the length of the average weighted shortest path of the brain function network according to the weight between each node in the brain function network;
and determining the tight centrality of the brain function network according to the weighted shortest path length and the total number of nodes among the nodes in the brain function network.
9. An apparatus for processing near-infrared brain function imaging data, the apparatus comprising: a processor and a memory for storing a computer program capable of running on the processor; wherein the content of the first and second substances,
the processor is adapted to perform the steps of the method of any one of claims 1 to 5 when running the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910660196.XA CN112274144A (en) | 2019-07-22 | 2019-07-22 | Method and device for processing near-infrared brain function imaging data and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910660196.XA CN112274144A (en) | 2019-07-22 | 2019-07-22 | Method and device for processing near-infrared brain function imaging data and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112274144A true CN112274144A (en) | 2021-01-29 |
Family
ID=74419073
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910660196.XA Pending CN112274144A (en) | 2019-07-22 | 2019-07-22 | Method and device for processing near-infrared brain function imaging data and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112274144A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113571142A (en) * | 2021-06-07 | 2021-10-29 | 四川大学华西医院 | Mental image integration system |
| CN117156072A (en) * | 2023-11-01 | 2023-12-01 | 慧创科仪(北京)科技有限公司 | Device for processing near infrared data of multiple persons, processing equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006125960A2 (en) * | 2005-05-25 | 2006-11-30 | The Babraham Institute | Signal processing, transmission, data storage and representation |
| CN101972148A (en) * | 2010-11-19 | 2011-02-16 | 哈尔滨工业大学 | Disturbance elimination method of near infrared brain function detection based on empirical mode decomposition |
| CN104182645A (en) * | 2014-09-01 | 2014-12-03 | 黑龙江省计算中心 | Empirical mode decomposition and sliding time window weighted least square method based brain-computer interface extraction method |
| JP2015112418A (en) * | 2013-12-13 | 2015-06-22 | 株式会社島津製作所 | Brain function measuring device and data processor for brain function measurement |
| US20170079538A1 (en) * | 2015-09-17 | 2017-03-23 | National Central University | Method for Identifying Images of Brain Function and System Thereof |
| CN106580248A (en) * | 2016-11-03 | 2017-04-26 | 中国科学院自动化研究所 | Neurovascular coupling analytical method based on electroencephalogram and functional near infrared spectroscopy technology |
| WO2017104914A1 (en) * | 2015-12-14 | 2017-06-22 | (의료)길의료재단 | Fmri method capable of reflecting only t2* change components without time epoch information on baseline state data |
| WO2018081980A1 (en) * | 2016-11-03 | 2018-05-11 | 中国科学院自动化研究所 | Neurovascular coupling analytical method based on electroencephalogram and functional near infrared spectroscopy technology |
| CN108685577A (en) * | 2018-06-12 | 2018-10-23 | 国家康复辅具研究中心 | A kind of brain function rehabilitation efficacy apparatus for evaluating and method |
| CN109567818A (en) * | 2018-11-20 | 2019-04-05 | 苏州大学 | The recognition methods that a variety of walking step states adjustment based on hemoglobin information is intended to |
| WO2019077410A1 (en) * | 2017-10-16 | 2019-04-25 | Performance Phenomics Inc. | Methods and apparatus for using brain imaging to predict performance |
| WO2019102901A1 (en) * | 2017-11-27 | 2019-05-31 | 株式会社国際電気通信基礎技術研究所 | Intracerebral network activity estimation system, intracerebral network activity estimation method, intracerebral network activity estimation program, and learned brain activity estimation model |
-
2019
- 2019-07-22 CN CN201910660196.XA patent/CN112274144A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006125960A2 (en) * | 2005-05-25 | 2006-11-30 | The Babraham Institute | Signal processing, transmission, data storage and representation |
| CN101972148A (en) * | 2010-11-19 | 2011-02-16 | 哈尔滨工业大学 | Disturbance elimination method of near infrared brain function detection based on empirical mode decomposition |
| JP2015112418A (en) * | 2013-12-13 | 2015-06-22 | 株式会社島津製作所 | Brain function measuring device and data processor for brain function measurement |
| CN104182645A (en) * | 2014-09-01 | 2014-12-03 | 黑龙江省计算中心 | Empirical mode decomposition and sliding time window weighted least square method based brain-computer interface extraction method |
| US20170079538A1 (en) * | 2015-09-17 | 2017-03-23 | National Central University | Method for Identifying Images of Brain Function and System Thereof |
| WO2017104914A1 (en) * | 2015-12-14 | 2017-06-22 | (의료)길의료재단 | Fmri method capable of reflecting only t2* change components without time epoch information on baseline state data |
| CN106580248A (en) * | 2016-11-03 | 2017-04-26 | 中国科学院自动化研究所 | Neurovascular coupling analytical method based on electroencephalogram and functional near infrared spectroscopy technology |
| WO2018081980A1 (en) * | 2016-11-03 | 2018-05-11 | 中国科学院自动化研究所 | Neurovascular coupling analytical method based on electroencephalogram and functional near infrared spectroscopy technology |
| WO2019077410A1 (en) * | 2017-10-16 | 2019-04-25 | Performance Phenomics Inc. | Methods and apparatus for using brain imaging to predict performance |
| WO2019102901A1 (en) * | 2017-11-27 | 2019-05-31 | 株式会社国際電気通信基礎技術研究所 | Intracerebral network activity estimation system, intracerebral network activity estimation method, intracerebral network activity estimation program, and learned brain activity estimation model |
| CN108685577A (en) * | 2018-06-12 | 2018-10-23 | 国家康复辅具研究中心 | A kind of brain function rehabilitation efficacy apparatus for evaluating and method |
| CN109567818A (en) * | 2018-11-20 | 2019-04-05 | 苏州大学 | The recognition methods that a variety of walking step states adjustment based on hemoglobin information is intended to |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113571142A (en) * | 2021-06-07 | 2021-10-29 | 四川大学华西医院 | Mental image integration system |
| CN117156072A (en) * | 2023-11-01 | 2023-12-01 | 慧创科仪(北京)科技有限公司 | Device for processing near infrared data of multiple persons, processing equipment and storage medium |
| CN117156072B (en) * | 2023-11-01 | 2024-02-13 | 慧创科仪(北京)科技有限公司 | Device for processing near infrared data of multiple persons, processing equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Brihadiswaran et al. | EEG-based processing and classification methodologies for autism spectrum disorder: A review | |
| Sun et al. | Multi-label ECG signal classification based on ensemble classifier | |
| CN111310570B (en) | Electroencephalogram signal emotion recognition method and system based on VMD and WPD | |
| CN113274011A (en) | Brain function monitoring and management method integrating electroencephalogram and functional near infrared spectrum technology | |
| Agyeman et al. | Classification Techniques for Arrhythmia Patterns Using Convolutional Neural Networks and Internet of Things (IoT) Devices | |
| CN112274144A (en) | Method and device for processing near-infrared brain function imaging data and storage medium | |
| Liao et al. | Classify autism and control based on deep learning and community structure on resting-state fMRI | |
| CN114947883A (en) | Time-frequency domain information fusion deep learning electroencephalogram noise reduction method | |
| Ansari et al. | A deep shared multi-scale inception network enables accurate neonatal quiet sleep detection with limited EEG channels | |
| CN115281685A (en) | Sleep stage identification method and device based on anomaly detection and computer readable storage medium | |
| Sahu et al. | Scz-scan: An automated schizophrenia detection system from electroencephalogram signals | |
| Kumar et al. | Review on compressive sensing algorithms for ECG signal for IoT based deep learning framework | |
| Narmada et al. | A novel adaptive artifacts wavelet Denoising for EEG artifacts removal using deep learning with Meta-heuristic approach | |
| Banerjee et al. | A new real-time lossless data compression algorithm for ECG and PPG signals | |
| Singhal et al. | GSMD-SRST: Group Sparse Mode Decomposition and Superlet Transform Based Technique for Multi-Level Classification of Cardiac Arrhythmia | |
| CN112274145A (en) | Method and device for processing near-infrared brain function imaging data and storage medium | |
| Lee et al. | Data-driven data augmentation for motor imagery brain-computer interface | |
| CN116035593B (en) | Electrocerebral noise reduction method based on generation countermeasure type parallel neural network | |
| CN111700592A (en) | Method and system for acquiring epilepsia electroencephalogram automatic classification model and classification system | |
| CN111798455B (en) | Thyroid nodule real-time segmentation method based on full convolution dense cavity network | |
| CN116912084A (en) | Neuroimaging data processing method and device, electronic equipment and storage medium | |
| CN115670480A (en) | Biological characteristic analysis method and device, electronic equipment and storage medium | |
| Liu et al. | Aggregating intrinsic information to enhance BCI performance through federated learning | |
| Ghosh et al. | Epileptic-seizure onset detection using PARAFAC model with cross-wavelet transformation on multi-channel EEG | |
| CN112274159A (en) | Compressed domain electrocardiosignal quality evaluation method based on improved band-pass filter |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210129 |