CN111402212A - Extraction method of dynamic connection activity mode of maritime brain function network - Google Patents
Extraction method of dynamic connection activity mode of maritime brain function network Download PDFInfo
- Publication number
- CN111402212A CN111402212A CN202010144112.XA CN202010144112A CN111402212A CN 111402212 A CN111402212 A CN 111402212A CN 202010144112 A CN202010144112 A CN 202010144112A CN 111402212 A CN111402212 A CN 111402212A
- Authority
- CN
- China
- Prior art keywords
- dynamic
- equal
- tested
- brain function
- function connection
- 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.)
- Granted
Links
- 230000003925 brain function Effects 0.000 title claims abstract description 77
- 230000000694 effects Effects 0.000 title claims abstract description 14
- 238000000605 extraction Methods 0.000 title description 2
- 230000006870 function Effects 0.000 claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 70
- 239000013598 vector Substances 0.000 claims abstract description 39
- 239000011159 matrix material Substances 0.000 claims abstract description 35
- 230000008569 process Effects 0.000 claims abstract description 32
- 230000000284 resting effect Effects 0.000 claims abstract description 22
- 210000004556 brain Anatomy 0.000 claims abstract description 14
- 238000002599 functional magnetic resonance imaging Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 9
- 238000012880 independent component analysis Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 230000009977 dual effect Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000004886 head movement Effects 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 238000012887 quadratic function Methods 0.000 claims description 2
- 241000287196 Asthenes Species 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 7
- 230000001537 neural effect Effects 0.000 abstract description 5
- 238000011160 research Methods 0.000 abstract description 5
- XMQFTWRPUQYINF-UHFFFAOYSA-N bensulfuron-methyl Chemical compound COC(=O)C1=CC=CC=C1CS(=O)(=O)NC(=O)NC1=NC(OC)=CC(OC)=N1 XMQFTWRPUQYINF-UHFFFAOYSA-N 0.000 abstract description 2
- 230000009323 psychological health Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008035 nerve activity Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000010490 psychological well-being Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000008925 spontaneous activity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000003936 working memory Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses a method for extracting a dynamic connection activity mode of a maritime brain function network, which comprises the following steps: step 1: collecting resting state functional magnetic resonance imaging data of brains of a marine person to be tested and a non-marine person to be tested; step 2: preprocessing acquired data; and step 3: obtaining a plurality of groups of resting brain function networks of levels and individual levels and corresponding time processes thereof; and 4, step 4: calculating a dynamic function connection matrix and a corresponding dynamic function connection vector between each tested corresponding brain function network in the data of the marine member and the non-marine member; and 5: and extracting the special brain function connection mode of the mariner hidden in the dynamic function connection matrix from the dynamic function connection vector. The method is helpful for acquiring the specific brain function connection mode of the maritime staff professional population according to the dynamics; the sailor dynamic brain function connection mode extracted by the invention can provide a basis for further research and analysis on sailor neural activity rules and occupational brain plasticity.
Description
Technical Field
The invention relates to the technical field of medical imaging image processing, in particular to a method for extracting a dynamic connection activity mode of a maritime officer brain function network.
Background
As a special professional group, marine working conditions of sea staffs are greatly different from land environments, and the sea staffs are easily influenced by a plurality of complex factors such as natural environments, working environments and the like, so that the psychological badness of the staffs is caused. The psychological health badness not only affects the physical and psychological health of the seaman, but also causes great potential safety hazard to the navigation operation. Therefore, it is important to find out and dredge the seaman with mental sub-health condition in advance. In recent years, the psychological health of the seaman has received more and more attention from society, especially from the shipping industry. However, to our knowledge, there are currently few objective quantitative methods to assess the psychological well-being of the mariner. The traditional evaluation system for the psychological health of the mariners mainly adopts a questionnaire mode, such as a symptom self-evaluation scale, and the like, and the mode is easily influenced by the incompleteness of questionnaire design and subjectivity of an evaluator to be evaluated when answering questions, so that the evaluation result is inaccurate.
Among many medical image analysis techniques, functional mri is a method for revealing brain nerve activity from a functional perspective, and has the advantages of non-invasiveness, non-radioactivity, high spatial and temporal resolution, and the like, and particularly, the functional mri based on blood oxygen level dependence is most widely used clinically. The resting brain function connection can be researched through the spontaneous activity of the neurons by resting functional magnetic resonance imaging, so that the resting brain function connection method is more suitable for revealing the brain function neural activity rule of a maritime population.
However, the current research is mainly focused on the aspect of static functional connection, the brain is a complex structure, the functional connection between different brain areas changes dynamically with time, and for a special professional group, the abnormal dynamic change is often reflected in the abnormal corresponding brain functional connection. The invention aims to extract a special dynamic brain function connection mode of a maritime officer occupational population through a certain algorithm based on dynamic function connection, and further research characteristics of the maritime officer brain function connection mode on the basis, thereby providing a basis for exploring brain plasticity and neural activity specificity of the maritime officer occupational population.
Disclosure of Invention
The invention aims to provide a method for extracting a dynamic connection activity mode of a marine brain function network, which is characterized in that a plurality of resting brain function networks and corresponding time processes thereof in marine brain function magnetic resonance data are extracted by a time cascade group independent component analysis method, then a time sliding window method is used for calculating a dynamic function connection matrix and a corresponding dynamic function connection vector between every tested brain function networks, finally an affine propagation clustering algorithm is used for carrying out clustering analysis on all dynamic function connection vector sets, and a special dynamic brain function connection mode of a marine is extracted, so that a data base is provided for further subsequent analysis.
In order to achieve the purpose, the invention provides a method for extracting a dynamic connection activity mode of a maritime brain function network, which comprises the following steps:
step 1: collecting resting state functional magnetic resonance imaging data of brains of a marine person to be tested and a non-marine person to be tested;
step 2: preprocessing acquired marine and non-marine resting state functional magnetic resonance imaging data, wherein the preprocessing operation comprises four steps of time layer correction, head movement correction, space standardization and space smoothing;
and step 3: according to the preprocessed resting state functional magnetic resonance imaging data of the marine workers and the non-marine workers, a plurality of groups of resting state brain function networks of the level and the level of the individual and corresponding time processes are respectively obtained by using a time cascade group independent component analysis method and a space-time dual regression mode;
and 4, step 4: calculating a dynamic function connection matrix and a corresponding dynamic function connection vector between each tested corresponding brain function network in the data of the sailors and the non-sailors by using a sliding time window method;
and 5: and extracting a special brain function connection mode of the mariners hidden in the dynamic function connection matrix from the dynamic function connection vector by using an affine propagation clustering algorithm.
The method for extracting the dynamic connection activity mode of the maritime brain function network comprises the following steps of:
step 3.1, assuming that the group data comprises K testees, and each tester comprises T time points and V voxels after pretreatment; independent component analysis of the tested level of the group is carried out in a time cascade mode, and the following model is obtained:
(X1；X2；…；XK)＝MS (1)
where M denotes a group mixing matrix of KT × V order, and S ═ S1，s2，…，sN) ' represents a source signal matrix of N × V order, each row represents a component, N is the number of brain function networks corresponding to each tested object;
solving the model in a constraint optimization mode:
maximization: j(s)i)＝{E[G(si)]-E[G(v)]}2(2)
Constrained to: h(s)i)＝E[si]2-1＝0
Wherein s isiRepresents the output component, J(s)i) A control function representing independence of the measurement output components; e (-) represents the desired operation; g (-) is a non-quadratic function, v is a Gaussian random variable; constraint of equation h(s)i) Solving the optimization problem in a convex area;
step 3.2, selecting an interested resting brain function network and a time process thereof from the components obtained by calculation in the step 3.1, and obtaining the brain function network corresponding to each tested in the group and the time process thereof in a space-time dual regression mode; for the test i (i ═ 1, 2.., K), the following is indicated:
Mi＝Xipinv(S),Si＝pinv(Mi)Xi(3)
wherein, XiMatrix of observations representing order T × V, MiRepresents T × NiThe mixing matrix of the order is then,
represents Ni× V, each row representing an independent component of the test i,
is a column vector of size V × 1.
The method for extracting the dynamic connection activity mode of the maritime brain function network comprises the following steps of:
step 4.1, obtaining N brain function networks corresponding to each tested object through step 3 and time process T thereof1、T2……TNAdopting a sliding time window correlation analysis method, sliding the window width W and the step length 1 on the time process, and recording the time process of the nth brain function network under the jth time window as
(N is more than or equal to 1 and less than or equal to N, j is more than or equal to 1 and less than or equal to T-W + 1); then, calculating the Pearson correlation coefficient between every two brain function network time processes corresponding to the tested brain function networks to obtain T-W +1 dynamic function connection matrixes, wherein the dynamic function connection matrixes form a tested dynamic function connection matrix set DFCMS ═ { DFCM1，DFCM2，...，DFCMj，...，DFCMT-W+1}；
The Pearson correlation coefficient between every two brain function network time processes refers to the x and y time processes of the brain function network under the jth sliding window
And
the pearson correlation coefficient between them, the formula of which is as follows:
in the formula (I), the compound is shown in the specification,
is composed of
And
the covariance of (a) of (b),
are respectively as
J is more than or equal to 1 and less than or equal to T-W +1, x is more than or equal to 1 and less than or equal to N, and y is more than or equal to 1 and less than or equal to N;
dynamic functional connection matrix DFCMjThe dynamic function connection matrix is a dynamic function connection matrix formed by Pearson correlation coefficients between every two brain function network time processes under the jth sliding window, and is specifically expressed as follows:
wherein j is more than or equal to 1 and less than or equal to T-W +1, u is more than or equal to 1 and less than or equal to N, and v is more than or equal to 1 and less than or equal to N;
step 4.2, for each tested object, calculating a dynamic function connection vector set, wherein the specific method comprises the following steps: dynamic function connection matrix DFCM in dynamic function connection matrix set DFCMSj(j is more than or equal to 1 and less than or equal to T-W +1), and dividing the DFCM into rowsjThe upper triangular elements are stretched into a line to obtain a dynamic function connection vector DFCVj(j is more than or equal to 1 and less than or equal to T-W + 1); each column vector having a size of
Cascading the T-W +1 column vectors from small to large according to window time points to form a dynamic function connection vector set DFCVS [ DFCV ]1，DFCV2，…，DFCVj，…，DFCVM-W+1]A size of (T-W +1) × N;
wherein, DFCVjThe motion function connection vector under the jth sliding window is specifically expressed as:
wherein j is more than or equal to 1 and less than or equal to T-W +1, u is more than or equal to 1 and less than or equal to N, and v is more than or equal to 1 and less than or equal to N.
The method for extracting the dynamic connection activity mode of the maritime brain function network comprises the following steps of:
step 5.1, merging all tested dynamic function connection vector sets according to columns to form clustering samples, wherein each sample is a dynamic function connection vector corresponding to a tested sample; generating Q initial class centers by adopting a method based on an automatic target generation process;
step 5.2, clustering all tested dynamic function connection vector samples by adopting an affine propagation clustering algorithm according to the initial class centers obtained in the previous step to obtain Q classes;
step 5.3, respectively calculating the corresponding relation between the tested marine member and the non-marine member comparison group of the marine members, wherein the corresponding relation is expressed as the maximum correlation coefficient between the dynamic function connection modes; then analyzing the difference and specificity between corresponding dynamic functional modes;
and 5.4, respectively calculating the number of the dynamic function connection matrixes belonging to the category in each tested person for each category in the tested person and the non-surveyor control group, analyzing the difference and specificity between the corresponding dynamic function connection modes, and further deducing the specific dynamic brain function connection mode of the tested person.
Compared with the prior art, the invention has the following beneficial effects:
the method for dynamic functional connection is introduced, and is beneficial to acquiring a specific brain functional connection mode of a maritime staff professional group according to the dynamic property; according to the method, the accuracy and the efficiency of extracting the dynamic brain function connection mode are improved by combining the group independent component analysis, the sliding time window correlation, the affine propagation clustering and the like; the sailor dynamic brain function connection mode extracted by the invention can provide a basis for further research and analysis on sailor neural activity rules and occupational brain plasticity.
Drawings
FIG. 1 is a flow chart of the method for extracting the dynamic connection activity pattern of the maritime brain function network according to the present invention.
Detailed Description
The invention will be further described by the following specific examples in conjunction with the drawings, which are provided for illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, a method for extracting a brain function network dynamic connection activity pattern of a marine member, the method comprises the following steps:
step 1, respectively collecting brain resting state functional magnetic resonance data of a marine member tested group and a normal non-marine member control group, wherein the number of two groups of samples is 88, and 176 tested groups are totally tested. During data acquisition, the tested brain is required to be kept awake and is laid down in the magnetic resonance instrument. The number of time points for each test corresponding to functional magnetic resonance data is 215.
And 2, preprocessing the two groups of acquired resting state functional magnetic resonance data, wherein the preprocessing comprises four steps of time layer correction, head movement correction, space standardization and space smoothing. The preprocessing of all data is done by DPARSF software.
And 3, obtaining a dynamic function connection matrix and a dynamic function connection vector corresponding to each tested object by adopting a group independent component analysis and sliding time window analysis mode according to the preprocessed resting state function magnetic resonance data.
Step 3.1, calculating the interested brain function network corresponding to each tested brain function network in the group and the time process thereof, wherein the specific method comprises the following steps: according to the preprocessed resting state functional magnetic resonance data, nine resting state brain function networks and time sequences thereof which are interested are obtained through time cascading group independent component analysis and calculation, wherein the nine resting state brain function networks comprise a default network, a visual network, two side visual networks, an auditory network, a sensory-motor network, an execution control network, a highlight network, a working memory network and an attention network, and brain function networks corresponding to each tested object in the group and time process information thereof are obtained through a space-time double regression mode, and the length of a time process is M215 TRs.
Step 3.2, calculateEach tested object in the group corresponds to a dynamic function connection matrix set among nine brain function networks, and the specific method is as follows: adopting sliding window method, and using window width of 20TRs and step length of 1TR to make nine brain function networks correspond to time process T1、T2……T9Sliding upwards, and recording the time course of the nth brain function network under the jth time window as
(1. ltoreq. n.ltoreq.9; 1. ltoreq. j.ltoreq.T-W + 1. ltoreq.196). Then, the Pearson correlation coefficient between every two corresponding nine brain function network time processes of the tested object is calculated to obtain 196 dynamic function connection matrixes, and the dynamic function connection matrixes form a tested dynamic function connection matrix set DFCMS (DFCM) { DFCM1，DFCM2，...，DFCMj，...，DFCM196}。
Further, the Pearson correlation coefficient between every two brain function network time processes specifically refers to the X and y time processes of the brain function network under the jth sliding window
And
the pearson correlation coefficient between them, the formula of which is as follows:
in the formula (I), the compound is shown in the specification,
is composed of
And
the covariance of (a) of (b),
are respectively as
The variance of j is more than or equal to 1 and less than or equal to 196, x is more than or equal to 1 and less than or equal to 9, and y is more than or equal to 1 and less than or equal to 9.
Further, a dynamic function connection matrix DFCMjThe dynamic function connection matrix is a dynamic function connection matrix formed by Pearson correlation coefficients between every two brain function network time processes under the jth sliding window, and is specifically expressed as follows:
wherein j is more than or equal to 1 and less than or equal to 196, u is more than or equal to 1 and less than or equal to 9, and v is more than or equal to 1 and less than or equal to 9.
Step 3.3, calculating a dynamic function connection vector set between the nine brain function networks corresponding to each tested object in the group, wherein the specific method comprises the following steps: dynamic function connection matrix DFCM in dynamic function connection matrix set DFCMSj(j is more than or equal to 1 and less than or equal to 196), and dividing the DFCM into rowsjThe upper triangular elements are stretched into a line to obtain a dynamic function connection vector DFCVjJ is more than or equal to 1 and less than or equal to 196, the size of each column vector is 36 × 1, 196 column vectors are cascaded from small to large according to window time points to form a dynamic function connection vector set DFCVS (DFCV) [ < DFCV ]1,DFCV2,…,DFCVj,…,DFCV196]And size 196 × 36.
Wherein, DFCVjThe motion function connection vector under the jth sliding window is specifically expressed as:
similarly, j is 1. ltoreq. 196, u is 1. ltoreq. 9, and v is 1. ltoreq. 9.
And 4, performing cluster analysis on all tested dynamic function connection vector sets by using an affine propagation clustering algorithm.
And 4.1, combining the two tested dynamic function connection vector sets according to columns to form clustering samples, wherein each sample is a dynamic function connection column vector corresponding to the tested.
And 4.2, clustering each group of tested dynamic function connection strength column vector samples by using an affine propagation clustering algorithm to obtain 4 categories and 6 categories respectively.
And 5, extracting a dynamic brain function connection mode corresponding to the marine population according to the clustering analysis result.
And 5.1, respectively calculating the corresponding relation between the tested marine member modes and the non-marine member control groups of the marine members, wherein the corresponding relation is expressed as the maximum correlation coefficient between the dynamic function connection modes. The differences and specificities between the corresponding dynamic functional patterns were then analyzed.
And 5.2, respectively calculating the number of the dynamic function connection matrixes belonging to the category in each tested person for each category in the tested person and the non-surveyor control group, analyzing the difference and specificity between the corresponding dynamic function connection modes, and further deducing the specific dynamic brain function connection mode of the tested person.
In conclusion, the dynamic function connection method is introduced, and is helpful for acquiring the specific brain function connection mode of the maritime staff professional population according to the dynamics; according to the method, the accuracy and the efficiency of extracting the dynamic brain function connection mode are improved by combining the group independent component analysis, the sliding time window correlation, the affine propagation clustering and the like; the sailor dynamic brain function connection mode extracted by the invention can provide a basis for further research and analysis on sailor neural activity rules and occupational brain plasticity.
While the present invention has been described in detail with reference to the preferred embodiments, it should be understood that the above description should not be taken as limiting the invention. Various modifications and alterations to this invention will become apparent to those skilled in the art upon reading the foregoing description. Accordingly, the scope of the invention should be determined from the following claims.
Claims (4)
1. A method for extracting a dynamic connection activity mode of a maritime brain function network is characterized by comprising the following steps:
step 1: collecting resting state functional magnetic resonance imaging data of brains of a marine person to be tested and a non-marine person to be tested;
step 2: preprocessing acquired marine and non-marine resting state functional magnetic resonance imaging data, wherein the preprocessing operation comprises four steps of time layer correction, head movement correction, space standardization and space smoothing;
and step 3: according to the preprocessed resting state functional magnetic resonance imaging data of the marine workers and the non-marine workers, a plurality of groups of resting state brain function networks of the level and the level of the individual and corresponding time processes are respectively obtained by using a time cascade group independent component analysis method and a space-time dual regression mode;
and 4, step 4: calculating a dynamic function connection matrix and a corresponding dynamic function connection vector between each tested corresponding brain function network in the data of the sailors and the non-sailors by using a sliding time window method;
and 5: and extracting a special brain function connection mode of the mariners hidden in the dynamic function connection matrix from the dynamic function connection vector by using an affine propagation clustering algorithm.
2. The method for extracting the brain function network dynamic connection activity pattern of the marine member as claimed in claim 1, wherein the step 3 comprises the steps of:
step 3.1, assuming that the group data comprises K testees, and each tester comprises T time points and V voxels after pretreatment; independent component analysis of the tested level of the group is carried out in a time cascade mode, and the following model is obtained:
(X1；X2；…；XK)＝MS (1)
where M denotes a group mixing matrix of KT × V order, and S ═ S1，s2，…，sN) ' represents a source signal matrix of N × V order, each row represents a component, N is the number of brain function networks corresponding to each tested object;
solving the model in a constraint optimization mode:
maximization: j(s)i)＝{E[G(si)]-E[G(v)]}2(2)
Constrained to: h(s)i)＝E[si]2-1＝0
Wherein s isiRepresents the output component, J(s)i) A control function representing independence of the measurement output components; e (-) represents the desired operation; g (-) is a non-quadratic function, v is a Gaussian random variable; constraint of equation h(s)i) Solving the optimization problem in a convex area;
step 3.2, selecting an interested resting brain function network and a time process thereof from the components obtained by calculation in the step 3.1, and obtaining the brain function network corresponding to each tested in the group and the time process thereof in a space-time dual regression mode; for the test i (i ═ 1, 2.., K), the following is indicated:
Mi＝Xipinv(S)，Si＝pinv(Mi)Xi(3)
wherein, XiMatrix of observations representing order T × V, MiRepresents T × NiThe mixing matrix of the order is then,
represents Ni× V, each row representing an independent component of the test i,
is a column vector of size V × 1.
3. The method for extracting the dynamic connection activity pattern of the brain function network of the marine member as claimed in claim 1, wherein the step 4 comprises the steps of:
step 4.1, obtaining N brain function networks corresponding to each tested object through step 3 and time process T thereof1、T2……TNAdopting a sliding time window correlation analysis method, sliding the window width W and the step length 1 on the time process, and recording the time process of the nth brain function network under the jth time window as
Then, calculating the Pearson correlation coefficient between every two brain function network time processes corresponding to the tested brain function networks to obtain T-W +1 dynamic function connection matrixes, wherein the dynamic function connection matrixes form a tested dynamic function connection matrix set DFCMS ═ { DFCM1，DFCM2，...，DFCMj，...，DFCMT-W+1}；
The Pearson correlation coefficient between every two brain function network time processes refers to the x and y time processes of the brain function network under the jth sliding window
And
the pearson correlation coefficient between them, the formula of which is as follows:
in the formula (I), the compound is shown in the specification,
is composed of
And
the covariance of (a) of (b),
are respectively as
The variance of j is more than or equal to 1 and less than or equal to T-W +1, x is more than or equal to 1 and less than or equal to N,1≤y≤N；
dynamic functional connection matrix DFCMjThe dynamic function connection matrix is a dynamic function connection matrix formed by Pearson correlation coefficients between every two brain function network time processes under the jth sliding window, and is specifically expressed as follows:
wherein j is more than or equal to 1 and less than or equal to T-W +1, u is more than or equal to 1 and less than or equal to N, and v is more than or equal to 1 and less than or equal to N;
step 4.2, for each tested object, calculating a dynamic function connection vector set, wherein the specific method comprises the following steps: dynamic function connection matrix DFCM in dynamic function connection matrix set DFCMSj(j is more than or equal to 1 and less than or equal to T-W +1), and dividing the DFCM into rowsjThe upper triangular elements are stretched into a line to obtain a dynamic function connection vector DFCVj(j is more than or equal to 1 and less than or equal to T-W + 1); each column vector having a size of
Cascading the T-W +1 column vectors from small to large according to window time points to form a dynamic function connection vector set DFCVS [ DFCV ]1，DFCV2，…，DFCVj，…，DFCVM-W+1]A size of (T-W +1) × N;
wherein, DFCVjThe motion function connection vector under the jth sliding window is specifically expressed as:
wherein j is more than or equal to 1 and less than or equal to T-W +1, u is more than or equal to 1 and less than or equal to N, and v is more than or equal to 1 and less than or equal to N.
4. The method for extracting the active pattern of the dynamic connection of the brain function network of the marine member as claimed in claim 1, wherein the step 5 comprises the steps of:
step 5.1, merging all tested dynamic function connection vector sets according to columns to form clustering samples, wherein each sample is a dynamic function connection vector corresponding to a tested sample; generating Q initial class centers by adopting a method based on an automatic target generation process;
step 5.2, clustering all tested dynamic function connection vector samples by adopting an affine propagation clustering algorithm according to the initial class centers obtained in the previous step to obtain Q classes;
step 5.3, respectively calculating the corresponding relation between the tested marine member and the non-marine member comparison group of the marine members, wherein the corresponding relation is expressed as the maximum correlation coefficient between the dynamic function connection modes; then analyzing the difference and specificity between corresponding dynamic functional modes;
and 5.4, respectively calculating the number of the dynamic function connection matrixes belonging to the category in each tested person for each category in the tested person and the non-surveyor control group, analyzing the difference and specificity between the corresponding dynamic function connection modes, and further deducing the specific dynamic brain function connection mode of the tested person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010144112.XA CN111402212B (en) | 2020-03-04 | 2020-03-04 | Extraction method of dynamic connection activity mode of sea person brain function network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010144112.XA CN111402212B (en) | 2020-03-04 | 2020-03-04 | Extraction method of dynamic connection activity mode of sea person brain function network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111402212A true CN111402212A (en) | 2020-07-10 |
| CN111402212B CN111402212B (en) | 2023-11-14 |
Family
ID=71428523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010144112.XA Active CN111402212B (en) | 2020-03-04 | 2020-03-04 | Extraction method of dynamic connection activity mode of sea person brain function network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111402212B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109316188A (en) * | 2018-09-30 | 2019-02-12 | 上海海事大学 | A kind of extracting method of migraine brain function connection mode |
| CN113509148A (en) * | 2021-04-28 | 2021-10-19 | 东北大学 | Schizophrenia detection system based on mixed high-order brain network |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160196649A1 (en) * | 2015-01-06 | 2016-07-07 | Siemens Healthcare Gmbh | Method for determining an intracortical working state of a functional network in the brain |
| CN106204581A (en) * | 2016-07-08 | 2016-12-07 | 西安交通大学 | Based PC A and the dynamic brain function connection mode decomposition method of K mean cluster |
| CN109316188A (en) * | 2018-09-30 | 2019-02-12 | 上海海事大学 | A kind of extracting method of migraine brain function connection mode |
| US20190231230A1 (en) * | 2018-01-30 | 2019-08-01 | Soochow University | Cerebral function state evaluation device based on brain hemoglobin information |
| CN110232332A (en) * | 2019-05-23 | 2019-09-13 | 中国人民解放军国防科技大学 | Extraction and brain state classification method and system for dynamic function connection local linear embedded features |
| CN110265148A (en) * | 2019-06-20 | 2019-09-20 | 上海海事大学 | A kind of dynamic function pattern learning method that fMRI brain network mechanism inspires |
| CN110598793A (en) * | 2019-09-12 | 2019-12-20 | 常州大学 | Brain function network feature classification method |
-
2020
- 2020-03-04 CN CN202010144112.XA patent/CN111402212B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160196649A1 (en) * | 2015-01-06 | 2016-07-07 | Siemens Healthcare Gmbh | Method for determining an intracortical working state of a functional network in the brain |
| CN106204581A (en) * | 2016-07-08 | 2016-12-07 | 西安交通大学 | Based PC A and the dynamic brain function connection mode decomposition method of K mean cluster |
| US20190231230A1 (en) * | 2018-01-30 | 2019-08-01 | Soochow University | Cerebral function state evaluation device based on brain hemoglobin information |
| CN109316188A (en) * | 2018-09-30 | 2019-02-12 | 上海海事大学 | A kind of extracting method of migraine brain function connection mode |
| CN110232332A (en) * | 2019-05-23 | 2019-09-13 | 中国人民解放军国防科技大学 | Extraction and brain state classification method and system for dynamic function connection local linear embedded features |
| CN110265148A (en) * | 2019-06-20 | 2019-09-20 | 上海海事大学 | A kind of dynamic function pattern learning method that fMRI brain network mechanism inspires |
| CN110598793A (en) * | 2019-09-12 | 2019-12-20 | 常州大学 | Brain function network feature classification method |
Non-Patent Citations (2)
| Title |
|---|
| 高剑奇等: "fMRI低频振幅比在海员心理评估方面的比较分析", 《磁共振成像》 * |
| 高剑奇等: "基于fMRI的人脑功能可塑性研究――以海员职业为例", 《中国科技论文》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109316188A (en) * | 2018-09-30 | 2019-02-12 | 上海海事大学 | A kind of extracting method of migraine brain function connection mode |
| CN113509148A (en) * | 2021-04-28 | 2021-10-19 | 东北大学 | Schizophrenia detection system based on mixed high-order brain network |
| CN113509148B (en) * | 2021-04-28 | 2022-04-22 | 东北大学 | Schizophrenia detection system based on mixed high-order brain network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111402212B (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kübler et al. | SubsMatch 2.0: Scanpath comparison and classification based on subsequence frequencies | |
| LaConte et al. | The evaluation of preprocessing choices in single-subject BOLD fMRI using NPAIRS performance metrics | |
| Agrawal et al. | Pixels to voxels: modeling visual representation in the human brain | |
| Cribben et al. | Dynamic connectivity regression: determining state-related changes in brain connectivity | |
| Yang et al. | Spatiotemporal differentiation of myocardial infarctions | |
| CN110265148B (en) | Dynamic functional mode learning method inspired by fMRI brain network mechanism | |
| Ahmed et al. | Single volume image generator and deep learning-based ASD classification | |
| Carlson et al. | An introduction to time-resolved decoding analysis for M/EEG | |
| CN109993230B (en) | TSK fuzzy system modeling method for brain function magnetic resonance image classification | |
| Hanson et al. | High-resolution imaging of the fusiform face area (FFA) using multivariate non-linear classifiers shows diagnosticity for non-face categories | |
| CN113096814A (en) | Alzheimer disease classification prediction method based on multi-classifier fusion | |
| CN111402212A (en) | Extraction method of dynamic connection activity mode of maritime brain function network | |
| Pfister et al. | Robustifying independent component analysis by adjusting for group-wise stationary noise | |
| CN110991422A (en) | Rolling bearing fault diagnosis method based on multi-element time-shifting multi-scale permutation entropy | |
| CN110192860B (en) | Brain imaging intelligent test analysis method and system for network information cognition | |
| CN110801228B (en) | Brain effect connection measurement method based on neural network prediction | |
| Zhang et al. | Blood vessel segmentation in fundus images based on improved loss function | |
| Buchsbaum et al. | Recency, repetition, and the multidimensional basis of recognition memory | |
| CN115659144A (en) | Sub-health personnel classification method, system and equipment based on fMRI multi-band analysis | |
| CN115337000A (en) | Machine learning method for evaluating brain aging caused by diseases based on brain structure images | |
| CN116028858A (en) | Pre-labeled self-supervision neural network learning heart beat classification method and system | |
| Cho et al. | Space-time modeling of intensive binary time series eye-tracking data using a generalized additive logistic regression model. | |
| Ingle et al. | Advancing ASD Diagnostic Classification with Features of Continuous Wavelet Transform of fMRIand Machine Learning Algorithms | |
| CN115240014B (en) | Medical image classification system based on residual error neural network | |
| Busch et al. | Dissociation of reliability, predictability, and heritability in fine-and coarse-scale functional connectomes during development |
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 |