CN101788656A - Method for recognizing function response signal under function nuclear magnetic resonance scan - Google Patents
Method for recognizing function response signal under function nuclear magnetic resonance scan Download PDFInfo
- Publication number
- CN101788656A CN101788656A CN201010103595A CN201010103595A CN101788656A CN 101788656 A CN101788656 A CN 101788656A CN 201010103595 A CN201010103595 A CN 201010103595A CN 201010103595 A CN201010103595 A CN 201010103595A CN 101788656 A CN101788656 A CN 101788656A
- Authority
- CN
- China
- Prior art keywords
- data
- signal
- function
- task
- component
- 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
Images
Landscapes
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention relates to a method for recognizing a function response signal under function nuclear magnetic resonance scan, comprising the following steps of: (1) obtaining task-state data and resting-state data by utilizing a nuclear magnetic resonance apparatus, processing the data in space and time by utilizing a function nuclear magnetic resonance analysis software SPM (statistical parametric mapping) to obtain a data set; (2)reducing the dimensionality of the task-state data and the resting-state data by utilizing a current principal component analysis PCA method, conserving main information, i.e. conserving the eigenvectors of information energy of over 90 percent of the data, reestablishing data, and then respectively extracting independent components of the two kinds of data including a machine noise signal component, a non-neurogenic physiological noise component and a neurogenic function signal response component by utilizing an independent component analysis ICA method in current time domain; (3) finding out the range of the function signal component by carrying out corresponding traversal among independent components of the two kinds of data to obtain a data set containing the function signal component; and (4) carrying out spectral analysis on every signal in the data set, eliminating components without obvious energy peak values in frequency domain, and selecting a principal component from rest components which is the principal function respond signal.
Description
Technical field
The present invention relates to the extraction of function nuclear magnetic resonance (fMRI) signal, the discriminating method of particularly a kind of function nuclear magnetic resonance (fMRI) scanning response signal under function belongs to technical fields such as Flame Image Process and spectrum analysis.
Background technology
Function nuclear magnetic resonance (fMRI) signal sensitivity is very high, in the gatherer process of temporal image, the physiological signal that experimenter's small head is moving, heartbeat, eye movement and some incoherent muscular movements cause also is mingled in the fMRI signal, has constituted the noise signal in the brain function signal.Want to extract the function response signal under the outside stimulus, these noise signals and brain function signal must be separated.The method that extensively adopts is to utilize the Hemodynamics response function (HRF) of blood oxygen saturation (BOLD) signal at present, this method relies on the existing fixed model and to the hypothesis of signal distributions, be difficult to the difference between the discovery individuality, to the also not enough robust of the examination of NOT-function signal.The method that has also developed data-driven in recent years successively obtains the function response signal, and (the independent component fractal method with the Martin proposition is the most typical, see Martin J.M., Scott M., Greg G.B.et.al, Analysis of fMRI Data by Blind Separation into Independent SpatialComponents, Human Brain Mapping, 1998,6:160-188), but method itself can only decomposite each unordered signal content, and brain function signal wherein can only be distinguished by the shape of composition ripple.Given this, these methods have been applicable to exemplary functions response signal waveform data more, as the experimental data under the tile designs, and seem powerless for the experimental data under the nearest application incident relevant design more and more widely.
Summary of the invention
For overcoming the deficiency of prior art, how to disobey the pattern type, the function signal composition in abstraction function nuclear magnetic resonance (fMRI) signal.A gordian technique difficult problem relates to: how to merge huge task attitude data and tranquillization attitude data 1.; 2. how under no typical waveform situation, to screen the function signal composition.
The invention provides the discriminating method of a kind of function nuclear magnetic resonance (fMRI) scanning response signal under function, technical scheme is as follows: a kind of discriminating method of function response signal under function nuclear magnetic resonance scan is characterized in that:
(1) utilizes nuclear magnetic resonance analyser to obtain task attitude and tranquillization attitude data, utilize function nuclear magnetic resonance spectroscopy software SPM that task attitude and tranquillization attitude data are carried out pre-service on the room and time then, obtain data set;
(2) utilize existing principal component analytical method PCA, the dimension of reduction task attitude data and tranquillization attitude data, keep main information, promptly keep formation task attitude and the tranquillization attitude data proper vector of 90% above information energy separately, rebuild task attitude and tranquillization attitude data; Utilize the independent component analysis method ICA on the existing time domain then, extract two kinds of data independent component separately respectively, comprise machine noise signal content, non-neuropathic physiological noise composition and nerve function signal response component;
(3) by between each independent component of two kinds of data, doing the method for relevant traversal, in task attitude data component, find out the scope of function signal composition, obtain comprising the set of signals of function signal composition;
(4) each signal in the set of signals is carried out spectrum analysis, reject the composition that on the frequency domain space, does not have remarkable energy peak, choose first composition in the residual components, be the major function response signal.
Following concrete steps can be adopted in above-mentioned (2), (3), (4):
The first step is used principal component analytical method PCA, and the variable of task attitude data and tranquillization attitude data is reassembled into one group of new irrelevant mutually generalized variable respectively;
(1) calculates two kinds of data matrix covariance matrix S separately;
(2) calculate the eigenwert of the proper vector of each auto-covariance matrix S, choose the front feature by big to little ordering, keeps the information of two kinds of data more than separately 〉=90% according to eigenwert;
(3) two kinds of data of projection are to the new space of being made up of the vector of character pair separately, the realization data compression;
Second step, carry out independent component analysis ICA, earlier two kinds of data are carried out centralization and whitening pretreatment separately, solve from the optimization of albefaction sample and to separate mixed matrix, obtain independent base vector separately, be independent signal composition on the time domain, actual measurement to time-domain signal be the linear combination of these independent components; Task attitude data and tranquillization attitude data are carried out above process respectively, set and keep 25 compositions respectively, the new signal that comprises the main information of noise, non-nervous function physiological signal and nervous function signal obtains the independent component set of two class data, is designated as SE respectively
i(t) (i=1,2 ..., 25) and SR
i(t) (i=1,2 ..., 25);
Decomposing the tranquillization attitude independent component SE of coming out
i(t) and task attitude independent component SR
i(t) related coefficient d is calculated in combination in twos between
Ij
Wherein, i=1,2 ..., 25; J=1,2 ..., 25; SE
i(t) be task attitude data independent components, SE
i(t) be the mean value of this independent component on time shaft; SR
j(t) be tranquillization attitude data independent components, SR
jBe the mean value of this independent component on time shaft.Select preceding 3 independent components of task attitude data by following formula:
The 3rd step, by observing spectrogram, the noise of choosing, non-nervous function physiological signal and 3 task attitudes of nervous function signal data independent component are carried out spectrum analysis, rejecting does not have the composition of remarkable energy peak on the frequency domain space, choose first composition in the residual components, promptly select tacticly according to second one step process, satisfying for the 3rd step, first signal of score value energy requirement is arranged is the major function response signal.All the other compositions are the composition that contains residue function response signal energy, according to practical application request, do auxiliary the use.
Advantage of the present invention and remarkable result:
(1) the inventive method can combine task attitude data and the tranquillization attitude data under function nuclear magnetic resonance (fMRI) scanning, under the condition without any priori, extracts neururgic function signal composition, need not prior model;
(2),, compare the related coefficient d between two types of data heterogeneities by the basal signal characteristic of tranquillization attitude data owing to task attitude data and tranquillization attitude data in conjunction with same individuality
IjSize (i=1,2 ..., 25; J=1,2 ..., 25), can screen and contain the function signal energy, thereby not need to screen it by the waveform characteristic of function signal itself than higher composition.Make this technology can be widely used in the experimental data of non-tile designs, be not limited to the data analysis of tile designs;
(3) because task attitude data have reflected the different modalities that same individuality is current with tranquillization attitude data from different angles, the original method (based on the method for model and the method for employing single type signal) that relatively is compared between them can embody neururgic individual difference more; In addition, also can better eliminate The noise by spectral performance to the screening of composition in the method.The function response signal that extracts can embody individual instances more.
Description of drawings
Fig. 1 is the inventive method process flow diagram;
Fig. 2 is that a certain individuality calculates acquisition related coefficient d according to Fig. 1 flow process
IjPreceding 3 compositions after the ordering;
Fig. 3 is the spectrogram of each signal correspondence among Fig. 2;
Fig. 4 is that the application performance of the function response signal of the whole bag of tricks extraction compares.
Embodiment
(Chinese Facial Expression Video System CFEVS) stimulates down the experimenter, scanning acquisition task attitude data, the tranquillization of scanning acquisition afterwards attitude data in Chinese facial expression video system.Utilize fMRI analysis software SPM that data are carried out pre-service on the room and time, comprise a normal moveout correction, space criteriaization, Gauss's smothing filtering, low frequency noise is removed in time standardization and high-pass filtering, after the operation, obtains data set.Utilize principal component analysis (PCA) PCA (Tipping M, BishopC.Mixtures of probabilistic principal component analyzers.NeuralComputation, 1999,11:443-482) dimension of reduction task attitude data and tranquillization attitude data keeps main information; Utilize the independent component analysis (ICA) on the time domain to extract each 25 independent component of two kinds of data respectively then; By between the independent component of two kinds of data, doing the method for relevant traversal, find out the scope of function signal composition again, obtain comprising the set of signals of function signal composition, as shown in Figure 1; Each signal in the set of signals is carried out spectrum analysis, its spectrogram as shown in Figure 2, its transverse axis and the longitudinal axis are represented the energy under frequency and the respective frequencies respectively.According to the derivation of formula (2), first pickup electrode among Fig. 2 might comprise the function signal composition of a large amount of nervous activity features, also might be the noise composition.First width of cloth figure of Fig. 3 has shown the spectrogram of this signal, from the spectrogram of this signal, the energy of each frequency content is uneven distribution, can get rid of the possibility that this signal is a noise signal, thinks that this signal is the function signal composition that has comprised a large amount of nervous activity features.Second signal among Fig. 2, in relevant traversal, also very little with the related coefficient absolute value of each independent component of tranquillization attitude, second width of cloth figure is the spectrogram of this signal among Fig. 3, as seen from the figure, the energy distribution of this each frequency content of signal is evenly distributed, and may be to cause because mix more noise, for the signal guaranteeing to gather is the function signal composition, we reject it.The frequency spectrum of the 3rd signal also is uneven distribution, and as seen, this signal contains part residue function response signal energy, can continue to employ to do and assist a ruler in governing a country application.
In order further to analyze the validity of the function signal that is extracted, can by checking the recognition capability of dysfunction individuality under the same task be verified extracting function signal as feature.Collect 13 Depression in women patients and 9 healthy persons, repeat said process, obtain each individual function response signal,, enter Bayes classifier, observe classifying quality as feature.In order to verify performance, the function signal that has also adopted other two typical methods to obtain is respectively as recognition feature.They are respectively 1) utilize function signal that Martin obtains for the analytical approach of representative as characteristic of division (Martin J.M., Scott M., Greg G.B.et.al, Analysis of fMRI Data by Blind Separation intoIndependent Spatial Components, Human Brain Mapping, 1998,6:160-188); 2) utilize Hemodynamics response function (HRF) to optimize the function signal of acquisition as characteristic of division (Cynthia H.Y.Fu, JanainaMourao-Miranda, Sergi G.Costafreda et.al.Pattern Classification of Sad Facial Processing:Toward the Development of Neurobiological Markers in Depression.BiologicalPsychiatry, 2008,63:656-662).We use whole accuracy rate, and patient's accuracy rate and healthy person accuracy rate are estimated classification performance, classification results such as Fig. 4.Method one is to utilize the function signal of this method as characteristic of division in Fig. 4 form; Method two is to utilize function signal that Martin obtains for the analytical approach of representative as characteristic of division (data of incident related experiment do not have the typical functions signal waveform can be for reference, so this way is to the inefficacy of this batch experimental data); Method three is to utilize Hemodynamics response function (HRF) to optimize the function signal of acquisition as characteristic of division.
As seen from Figure 4, though the inventive method and based on the method for prior model done same thing (as the table in method three), all be to extract the function signal composition relevant in the brain with nervous activity, but the method that the present invention proposes has but obtained classification results relatively preferably without any the participation of prior model.Result's superiority may come from, and has broken away from model, by the comparison to the polymorphic signal of individuality own, can well embody individual specificity, also can eliminate The noise preferably simultaneously.Data in the literary composition are the data of incident relevant design experiment, but not the data of tile designs experiment.The advantage of this stimulation design is single stimulation is come respectively, can better show the response process of brain to stimulating, but meanwhile, also increased the difficulty of data analysis, method two in the table is difficult to distinguish that from waveform which signal content is the function signal composition, therefore can't finish identification mission.
Claims (2)
1. the discriminating method of a function response signal under function nuclear magnetic resonance scan is characterized in that:
(1) utilizes nuclear magnetic resonance analyser to obtain task attitude and tranquillization attitude data, utilize function nuclear magnetic resonance spectroscopy software SPM that task attitude and tranquillization attitude data are carried out pre-service on the room and time then, obtain data set;
(2) utilize existing principal component analytical method PCA, the dimension of reduction task attitude data and tranquillization attitude data, keep main information, promptly keep formation task attitude and the tranquillization attitude data proper vector of 90% above information energy separately, rebuild two kinds of data of task attitude and tranquillization attitude; Utilize the independent component analysis method ICA on the existing time domain then, extract two kinds of data independent component separately respectively, comprise machine noise signal content, non-neuropathic physiological noise composition and nerve function signal response component;
(3) by between each independent component of two kinds of data, doing the method for relevant traversal, in task attitude data component, find out the scope of function signal composition, obtain comprising the set of signals of function signal composition;
(4) each signal in the set of signals is carried out spectrum analysis, reject the composition that on the frequency domain space, does not have remarkable energy peak, choose first composition in the residual components, be the major function response signal.
2. according to the discriminating method of the described function response signal under function nuclear magnetic resonance scan of claim 1, it is characterized in that: (2), (3), (4) concrete steps are:
The first step is used principal component analytical method PCA, and the variable of task attitude data and tranquillization attitude data is reassembled into one group of new irrelevant mutually generalized variable respectively;
(1) calculates two kinds of data matrix covariance matrix S separately;
(2) calculate the eigenwert of the proper vector of each auto-covariance matrix S, choose the front feature by big to little ordering, keeps the information of two kinds of data more than separately 〉=90% according to eigenwert;
(3) two kinds of data of projection are to the new space of being made up of the vector of character pair separately, the realization data compression;
Second step, carry out independent component analysis ICA, earlier two kinds of data are carried out centralization and whitening pretreatment separately, solve from the optimization of albefaction sample and to separate mixed matrix, obtain independent base vector separately, be independent signal composition on the time domain, actual measurement to time-domain signal be the linear combination of these independent components; Task attitude data and tranquillization attitude data are carried out above process respectively, set and keep 25 compositions respectively, the new signal that comprises the main information of noise, non-nervous function physiological signal and nervous function signal obtains the independent component set of two class data, is designated as SE respectively
i(t) (i=1,2 ..., 25) and SR
i(t) (i=1,2 ..., 25);
Decomposing the tranquillization attitude independent component SE of coming out
i(t) and task attitude independent component SR
i(t) related coefficient d is calculated in combination in twos between
Ij
Wherein, i=1,2 ..., 25; J=1,2 ..., 25; SE
i(t) be task attitude data independent components, SE
i(t) be the mean value of this independent component on time shaft; SR
j(t) be tranquillization attitude data independent components, SR
jBe the mean value of this independent component on time shaft.Select preceding 3 independent components of task attitude data by following formula:
The 3rd step, by observing spectrogram, the noise of choosing, non-nervous function physiological signal and 3 task attitudes of nervous function signal data independent component are carried out spectrum analysis, rejecting does not have the composition of remarkable energy peak on the frequency domain space, choose first composition in the residual components, promptly select tacticly according to second one step process, satisfying for the 3rd step, first signal of score value energy requirement is arranged is the major function response signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201010103595 CN101788656B (en) | 2010-01-29 | 2010-01-29 | Method for recognizing function response signal under function nuclear magnetic resonance scan |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201010103595 CN101788656B (en) | 2010-01-29 | 2010-01-29 | Method for recognizing function response signal under function nuclear magnetic resonance scan |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101788656A true CN101788656A (en) | 2010-07-28 |
CN101788656B CN101788656B (en) | 2013-06-05 |
Family
ID=42531939
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201010103595 Expired - Fee Related CN101788656B (en) | 2010-01-29 | 2010-01-29 | Method for recognizing function response signal under function nuclear magnetic resonance scan |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101788656B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102509282A (en) * | 2011-09-26 | 2012-06-20 | 东南大学 | Efficiency connection analysis method fused with structural connection for each brain area |
CN104459809A (en) * | 2014-10-30 | 2015-03-25 | 吉林大学 | Full-wave nuclear magnetic resonance signal denoising method based on independent component analysis |
CN104644173A (en) * | 2015-01-14 | 2015-05-27 | 北京工业大学 | Depression risk three-grade early warning method and depression risk three-grade early warning system |
CN105044794A (en) * | 2015-06-25 | 2015-11-11 | 中国石油大学(北京) | Nuclear magnetic resonance echo data compression method and device |
CN107132315A (en) * | 2017-05-12 | 2017-09-05 | 盐城工学院 | Signal recognition method, device and volatile organic matter detection device |
CN108700532A (en) * | 2016-02-12 | 2018-10-23 | 布鲁克碧奥斯平公司 | Via the component in the solid mixture of time domain NMR spectroscopy rapid qualitative chemicals |
WO2020215748A1 (en) * | 2019-04-23 | 2020-10-29 | 国网冀北电力有限公司计量中心 | Method for testing task execution capability of electrical energy meter, and device |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6759848B2 (en) * | 2002-05-17 | 2004-07-06 | Siemens Aktiengesellschaft | Magnetic resonance method and apparatus for spatially resolved presentation of change in the functional activities of a brain |
CN100348152C (en) * | 2005-11-29 | 2007-11-14 | 东南大学 | Method for eliminating functional magnetic resonance data noise based on independent component space relativity |
-
2010
- 2010-01-29 CN CN 201010103595 patent/CN101788656B/en not_active Expired - Fee Related
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102509282A (en) * | 2011-09-26 | 2012-06-20 | 东南大学 | Efficiency connection analysis method fused with structural connection for each brain area |
CN102509282B (en) * | 2011-09-26 | 2014-06-25 | 东南大学 | Efficiency connection analysis method fused with structural connection for each brain area |
CN104459809A (en) * | 2014-10-30 | 2015-03-25 | 吉林大学 | Full-wave nuclear magnetic resonance signal denoising method based on independent component analysis |
CN104644173A (en) * | 2015-01-14 | 2015-05-27 | 北京工业大学 | Depression risk three-grade early warning method and depression risk three-grade early warning system |
CN105044794A (en) * | 2015-06-25 | 2015-11-11 | 中国石油大学(北京) | Nuclear magnetic resonance echo data compression method and device |
CN108700532A (en) * | 2016-02-12 | 2018-10-23 | 布鲁克碧奥斯平公司 | Via the component in the solid mixture of time domain NMR spectroscopy rapid qualitative chemicals |
CN107132315A (en) * | 2017-05-12 | 2017-09-05 | 盐城工学院 | Signal recognition method, device and volatile organic matter detection device |
WO2020215748A1 (en) * | 2019-04-23 | 2020-10-29 | 国网冀北电力有限公司计量中心 | Method for testing task execution capability of electrical energy meter, and device |
Also Published As
Publication number | Publication date |
---|---|
CN101788656B (en) | 2013-06-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101788656B (en) | Method for recognizing function response signal under function nuclear magnetic resonance scan | |
CN102715911B (en) | Brain electric features based emotional state recognition method | |
Kachenoura et al. | ICA: a potential tool for BCI systems | |
CN105956624B (en) | Mental imagery brain electricity classification method based on empty time-frequency optimization feature rarefaction representation | |
La Rocca et al. | EEG biometrics for individual recognition in resting state with closed eyes | |
CN104715261A (en) | fMRI dynamic brain function sub-network construction and parallel SVM weighted recognition method | |
CN107981997B (en) | A kind of method for controlling intelligent wheelchair and system based on human brain motion intention | |
CN101706561B (en) | Clustering method for functional magnetic resonance images | |
CN106264499A (en) | A kind of quantization cardiorespiratory system interactive analysis method | |
CN104182042A (en) | BCI (brain-computer interface) method for multi-modal signals | |
CN109173063A (en) | A kind of the transcranial magnetic stimulation system and transcranial magnetic stimulation method of 3D scanning | |
CN114027857B (en) | Method for measuring exercise capacity based on electroencephalogram signals | |
CN107595281A (en) | Utilize the action purpose sorting technique of EEG NIRS fusion features | |
CN101433460B (en) | Spatial filtering method of lower limb imaginary action potential | |
CN108209909A (en) | Bimodulus spy's nerve signal feature selection approach based on action intention task | |
Hoya et al. | Classification of single trial EEG signals by a combined principal+ independent component analysis and probabilistic neural network approach | |
Elsawy et al. | A principal component analysis ensemble classifier for P300 speller applications | |
CN112861629B (en) | Multi-window distinguishing typical pattern matching method and brain-computer interface application | |
CN106175698B (en) | Sleep cycle detection device in sleep state analysis | |
Kołodziej et al. | Comparison of EEG signal preprocessing methods for SSVEP recognition | |
CN107595295B (en) | A kind of lower extremity movement resistive state recognition methods based on brain hemoglobin information | |
Maiorana et al. | EEG-based biometric recognition using EigenBrains | |
CN113780162A (en) | Motor imagery electroencephalogram decoding method combined with multi-period and multi-frequency band CSP algorithm | |
CN112617824B (en) | Ice drug addict detection system based on multichannel fNIRS signals | |
Billinger et al. | Automatic frequency band selection for BCIs with ERDS difference maps |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130605 Termination date: 20140129 |