CN102509123A - Brain functional magnetic resonance image classification method based on complex network - Google Patents

Abstract

The invention relates to a brain functional magnetic resonance image classification method based on a complex network, which comprises the following steps: pre-processing training sample images and test sample images, carrying out region segmentation, and extracting an average time sequence from each region; calculating the partial correlation coefficient among the average time sequences, carrying out matrix binarization on the partial correlation coefficient to obtain a complex network model, and calculating the feature path length, cost and clustering degree of the complex network model to respectively obtain network features of the training sample images and the test sample images; training to obtain an adaboost classifier; and by using the adaboost classifier obtained by training, classifying the test sample images. By using information in the brain functional magnetic resonance images as much as possible, the method can accurately classify the brain functional magnetic resonance images.

Description

A kind of brain function MRI sorting technique based on complex network

Technical field

The invention belongs to technical field of image processing, be specifically related to a kind of brain function MRI sorting technique based on complex network.

Background technology

(functional Magnetic Resonance Imaging, fMRI) with its high-spatial and temporal resolution, characteristics such as non-intrusion type are obtaining widespread use aspect the sacred disease diagnoses and treatment to functional mri.FMRI refers generally to rely on (blood oxygen level-dependent based on blood oxygen level; BOLD) magnetic resonance imaging, it changes through the magnetic resonance signal of measuring composition variations such as the cerebral blood flow that caused by nervous activity and brain blood oxygen and causing reacts cerebration.Brain is the system of a complicacy, and corresponding variation can take place the MRI of brain when being upset conditioned disjunction experience pathology.Utilizing image classification method, calculate the possibility size that brain function MRI has certain attribute, perhaps differentiate the category attribute of image automatically, is an important application of computer-aided analysis.

Traditional functions MRI sorting technique mainly contains area-of-interest (ROI) mode and two kinds of sorting techniques of voxel (voxel) mode.The sorting technique of area-of-interest mode is divided into a plurality of target areas with sample and target, and in view of the above target is classified according to the priori of object construction; The sorting technique of voxel mode adopts complicated non-linear registration, to realize the accurate correspondence between individuality to greatest extent, then with each mikey (voxel) of image as classification foundation.These the two kinds of methods all internal organizational structure of hypothetical target and sample are one to one.The former thinks that the image-region of priori is present in the middle of each target image, and can accurately cut apart; The latter supposes that the voxel behind the non-linear registration is one to one.Yet such hypothesis is also unreasonable under many circumstances.The brain function MRI of people under different conditions can receive the interference of many-sided factor, and traditional sorting technique is not according to the build-in attribute of brain brain function MRI to be classified, and therefore all can cause the decline of classification performance.

Summary of the invention

The technical matters that (one) will solve

In order to overcome the deficiency of prior art, technical matters to be solved by this invention is the brain function MRI sorting technique that a kind of classification accuracy of design is high, extensive performance is strong.

(2) technical scheme

For realizing above-mentioned purpose, the present invention proposes a kind of brain function MRI sorting technique based on complex network, may further comprise the steps:

Step Sa: training sample image and test sample image are carried out pre-service, carry out the brain differentiation then and cut, and extract sequence averaging time in each brain district;

Step Sb: calculate the partial correlation coefficient between each of sequence averaging time, obtain the partial correlation coefficient matrix;

Step Sc:, obtain complex network model with said partial correlation coefficient matrix binaryzation;

Step Sd: calculate characteristic path, cost and the cluster degree of this complex network model characteristic as the functional MRI image;

Step Se: utilize the characteristic of the network parameter of training sample image, train a self-adaptation to improve (adaboost) sorter as the training sample image in the characteristic of this functional MRI image;

Step Sf: utilize this self-adaptation that trains to improve (adaboost) sorter test sample image is classified.

(3) beneficial effect

The present invention is directed to the brain function MRI classification problem, through making up accuracy and the stability that methods such as brain network model, computational grid characteristic parameter, training self-adaptation raising (adaboost) sorter have effectively improved image classification.

The present invention can utilize information as much as possible in the brain function MRI; The brain network parameter can be from reacting the activity of brain in essence; Remedied the deficiency that the traditional classification method can not embody the cerebration build-in attribute, can classify to brain function MRI accurately.

Description of drawings

Fig. 1 is a method flow diagram of classifying based on the brain function MRI of complex network provided by the invention;

Fig. 2 uses sorting technique according to the invention (method A) contrast existing sorting technique based on local feature (method B), the correlation curve of classification experimenter's operating characteristic (ROC) according to the embodiment of the invention.

Embodiment

For making the object of the invention, technical scheme and advantage clearer, below in conjunction with specific embodiment, and with reference to accompanying drawing, to further explain of the present invention.

Brain function MRI classification based on complex network is a kind of brand-new brain function MRI sorting technique.This method is at first set up complicated brain network model, calculates the characteristic path and the cluster degree of brain network, in order to characterize the pictures different pattern; Utilize this characteristic path and cluster degree to train a self-adaptation to improve (adaboost) sorter then; Utilizing this self-adaptation that trains to improve (adaboost) sorter at last classifies to test sample image.

With reference to Fig. 1, according to a kind of human brain function magnetic resonance imaging image classification method of the present invention, can confirm the classification of test sample image according to training sample image, the practical implementation step is following:

Step Sa carries out pre-service to training sample image and test sample image, carries out the brain differentiation then and cuts, and extract sequence averaging time in each brain district;

1. the pre-service of brain function MRI

Because various The noise in the magnetic resonance imaging process, tested individual self exists yardstick and locational difference, is necessary very much before analyzing data, data to be done certain pre-service.In the data of whole experiment were obtained, main noise information source has: (1) physics head was moving; (2) interlayer difference sweep time in the image; (3) unevenness of exterior magnetic field etc.The pretreated common step of brain function MRI has: section alignment sweep time, image sequence alignment, associating registration, standardization (or claiming homogenization), space smoothing filtering and time smoothing filtering etc.

2. brain function MRI cuts apart

Adopt international structure tag template (AAL), full brain is divided into 90 brain districts.The structure tag template is a most widely used brain stay in place form of brain function MRI research field.

3. extract sequence averaging time in each brain district

Data according to pretreated brain function MRI; Extraction is contained in time series Y (the matrix dimension D * N) of inner each voxel activation value on different time points in corresponding brain district; Wherein D is contained in the inner voxel number of spheroid, and N counts the time.Said activation value is meant that the blood oxygen level of each voxel on different time points relies on (BOLD) intensity.

Step Sb: calculate the partial correlation coefficient between average each time series.This step Sb specifically comprises the steps:

1. calculate the covariance coefficient between average time series

The time series in each brain district that extracts according to step Sa is calculated the covariance matrix S between each of sequence, each element s of S averaging time _{I, j}Be the covariance coefficient between i and j the time series,

$s_{i,j}=\frac{1}{M}\underset{t=1}{\overset{M}{\mathrm{\Σ}}}(x_i\left(t\right)-\stackrel{\‾}{x_i})(x_j\left(t\right)-\stackrel{\‾}{x_j})$

Wherein, M is the time point number, x _i(t) (i=1 ..., M) be i time series,

Be i seasonal effect in time series mean value, Be j seasonal effect in time series mean value.

2. calculate the partial correlation coefficient between average time series

According to the covariance matrix of coefficients S between time series (matrix dimensionality is 90 * 90), the partial correlation coefficient matrix R (matrix dimensionality is 90 * 90) between the computing time sequence, each element r of R _{I, j}For:

$r_{i,j}=-\frac{s_{i,j}^{-1}}{\sqrt{s_{i,i}^{-1}{s}_{j,j}^{-1}}}$

Wherein,

is { i, j} element of the inverse matrix of covariance matrix S (matrix dimensionality is 90 * 90).

3. partial correlation coefficient is carried out the Fisher conversion

According to partial correlation coefficient matrix R (matrix dimensionality is 90 * 90), calculate partial correlation coefficient matrix F (matrix dimensionality is 90 * 90), each element f of F through the Fisher conversion _IjFor:

$f_{i,j}=\frac{1}{2}\left(\frac{1+r_{i,j}}{1-r_{i,j}}\right),$

Wherein, f _IjBe { i, j} element, r through the partial correlation coefficient matrix F (matrix dimensionality is 90 * 90) after the Fisher conversion _Ij{ i, j} element for partial correlation coefficient matrix R (matrix dimensionality is 90 * 90).

Step Sc:, obtain complex network model with partial correlation coefficient matrix binaryzation;

Setting threshold T ', order is 1 through the value more than or equal to T ' in the partial correlation coefficient matrix F (matrix dimensionality is 90 * 90) after the Fisher conversion, is 0 less than the value of T ', obtains complex network model.1 expression has connection between two brain districts in the matrix after the binaryzation, and promptly the limit between two nodes exists in the network, and 0 expression does not connect between two brain districts, does not promptly have the limit between two nodes in the network.The method of selection of threshold is: make the quantity in esse limit in the network be the limit that possibly exist in the network quantity

wherein N be the number of node in the network) 1/10th.The process of binaryzation can be described as order

$w_{i,j}=\left\{\begin{array}{c}1,\left|f_{i,j}\right|\&GreaterEqual;T^{\&prime;}\\ 0,\left|f_{i,j}\right|<T^{\&prime;}\end{array}\right.,$

Wherein, w _Ij{ i, j} element, f for the network after the binaryzation _IjFor through the partial correlation coefficient matrix F (matrix dimensionality is 90 * 90) of Fisher conversion the i, j} element, T ' are the threshold value of choosing, || be the absolute calculation symbol.

Step Sd: calculate characteristic path, cost and the cluster degree of this complex network model characteristic as the functional MRI image;

According to complex network model, calculate characteristic path, cost and the cluster degree of this complex network model, as the characteristic of functional MRI image.

The characteristic path provides the optimal path of another node of information arrival of a certain node in the network.We can use any two node i in the characteristic path matrix description network, the characteristic path l of j _IjNetwork average characteristics path L has described the mean value of the characteristic path of any two nodes in the network, promptly

$L=\frac{1}{N(N-1)}\underset{i,j\&Element;V,i\&NotEqual;j}{\mathrm{\&Sigma;}}{l}_{\mathrm{ij}}$

Wherein, N is the number of node in the network, the brain district of promptly cutting apart several 90; l _IjBe node i, the characteristic path between the j, V is the set of all nodes in the network.

Cost is an important parameter of tolerance network character, is used for weighing the required overall cost of paying of building network.Computing method are with the quantity in esse all limits in the network quantity than the limit that possibly exist at most in the last network, that is:

$K=\frac{\frac{\mathrm{\&Sigma;}{K}_i}{2}}{\frac{N(N-1)}{2}}=\frac{1}{N(N-1)}\mathrm{\&Sigma;}{K}_i,$

Wherein, N is the number of node in the network, K _iBe the quantity on the limit that is connected to node i in the network, K is the cost of network.

The cluster degree is another key character of tolerance network character, and the adjacent node that is used for measuring a certain node is neighbours' possibility each other.The cluster degree C of a certain node i _iThe number and the ratio of all possible limit number between them on the value limit that equals to exist between its adjacent node, promptly

$C_i=\frac{e_i}{\frac{k_i(k_i-1)}{2}}=\frac{2e_i}{k_i(k_i-1)}$

Wherein, e _iThe limit number that exists between the adjoint point of expression node i, k _iThe number of the adjoint point of expression node i,

Just represent the limit number that possibly exist between the adjoint point of node i.

Step Se: utilize the characteristic of the network parameter of training sample image, train a self-adaptation to improve (adaboost) sorter as the training sample image in the characteristic of this functional MRI image.

After obtaining the characteristic of training sample image; At first with characteristic path, cost and cluster degree as three linear classifiers; Form a new self-adaptation with the weighted sum of these three linear classifiers and improve (adaboost) sorter; The weight of initial each sorter is made as

(m is the number of sample image); Self-adaptation improves (adaboost) sorter is adjusted three linear classifiers gradually in training process weight, and the self-adaptation that obtains an optimum at last improves (adaboost) sorter.The practical implementation step is following:

To given sample (x ₁, y ₁) ..., (x _m, y _m), x wherein _i∈ X, y _i∈ Y=(1,1), X are the network characterization of training sample image, and Y is an image category, and the weight of at first setting the initialization sorter does Carry out T time iteration afterwards, iterative process is following:

Variable t is increased to T since 1, and each iteration is at first calculated each characteristic h _tThe error in classification ε that training sample image is classified and obtained _t, calculate new sample weights then,

${\mathrm{\&alpha;}}_t=\frac{1}{2}\ln \left(\frac{1-{\mathrm{\&epsiv;}}_t}{{\mathrm{\&epsiv;}}_t}\right),$

At last, upgrade the weight of each linear classifier,

$D_{t+1}\left(i\right)=\frac{D_t\left(i\right)}{Z_t}\left\{\begin{array}{c}{e}^{-{\mathrm{\&alpha;}}_t},h_t\left(x_i\right)=y_i\\ e^{{\mathrm{\&alpha;}}_t},h_t\left(x_i\right)\&NotEqual;y_i\end{array}\right.,$

Z wherein _tBe normalized factor.

Obtain optimum self-adaptation after the loop ends and improve (adaboost) sorter:

$H\left(x\right)=\mathrm{sign}\left(\underset{t=1}{\overset{T}{\mathrm{\&Sigma;}}}{\mathrm{\&alpha;}}_t{h}_t\left(x\right)\right).$

Step Sf: the optimum self-adaptation of utilizing training to obtain improves (adaboost) sorter test sample image is classified.

Test sample book is imported optimum self-adaptation raising (adaboost) sorter that above-mentioned steps obtains, test sample image is classified, classification results is through classification accuracy rate, True Positive Rate and false positive rate output.

The effect of the brain function MRI sorting technique based on complex network of the present invention can be able to explanation through real brain function magnetic resonance brain imaging data:

(1) True Data experimentation

For showing effect of the present invention, adopt the True Data collection to test in embodiments, totally 39 are tried to have participated in experiment, 20 men, 19 woman.Seen form 1 by examination age bracket and clinical dementia rating information.T2* weighting gtadient echo planar imaging is adopted in experiment, and (Echo-Planar Imaging, EPI) sequence is obtained BOLD fMRI tranquillization data behind the acupuncture stimulation.

Employing statistical parameter figure (SPM) software ( Http:// www.fil.ion.ucl.ac.uk/spm/) data are carried out pre-service, comprise section alignment sweep time, image sequence alignment, associating registration, standardization (or claiming homogenization), space smoothing filtering.Use the method for the invention (method A) contrast existing sorting technique (method B) based on local feature; Obtain experimenter's operating characteristic (ROC) curve and the TG-AUC (AUC) thereof of sorting technique, and with ROC curve and the AUC tolerance as the sorter performance.

Form 1 is by examination information

(2) experimental result

The classification ROC curve of two kinds of methods shows in Fig. 2 respectively on true experiment data set; Wherein, True Positive Rate among Fig. 2 is meant and correctly is judged to positive number percent by the standard that this screening is tested that false positive rate is meant actual negative and is judged to positive number percent by error by the standard that this screening is tested actual positive.As shown in Figure 2, the ROC curve of method A is higher than method B in most of threshold range; AUC value contrast situation: the AUC value of method A is 0.85, and the AUC value of method B is 0.78.TG-AUC (AUC) can be measured overall classification performance, posterior probability and ordering performance, and the AUC value is big more, and then the overall performance of this sorting technique is good more.Thus, method A effect is better than method B.

Experimental result explanation, the brain function MRI sorting technique based on complex network of the present invention has improved the classification performance of brain function MRI effectively.

The above; Be merely the embodiment among the present invention, but protection scope of the present invention is not limited thereto, anyly is familiar with this technological people in the technical scope that the present invention disclosed; Can understand conversion or the replacement expected, all should be encompassed within the protection domain of claims of the present invention.

Claims (8)

1. the brain function MRI sorting technique based on complex network is characterized in that, may further comprise the steps:

Step Sa: training sample image and test sample image are carried out pre-service, carry out the brain differentiation then and cut, and extract sequence averaging time in each brain district;

Step Sb: calculate the partial correlation coefficient between each of sequence averaging time, obtain the partial correlation coefficient matrix;

Step Sc:, obtain complex network model with said partial correlation coefficient matrix binaryzation;

Step Sd: calculate characteristic path, cost and the cluster degree of this complex network model characteristic as the functional MRI image;

Step Se: utilize the characteristic of the network parameter of training sample image, train a self-adaptation to improve (adaboost) sorter as the training sample image in the characteristic of this functional MRI image;

Step Sf: utilize this self-adaptation that trains to improve (adaboost) sorter test sample image is classified.

2. the brain function MRI sorting technique based on complex network as claimed in claim 1; It is characterized in that; Said training sample image and test sample image are carried out pre-service; Be when keeping the brain function image detail, use brain function image and standard form to carry out the pre-service of affine registration mapping mode, and improve the signal to noise ratio (S/N ratio) of brain function image.

3. the brain function MRI sorting technique based on complex network as claimed in claim 1 is characterized in that, the step of said extraction brain district sequence averaging time is:

At first according to standard brain stay in place form full brain is divided into 90 brain districts, extracts the activation value of inner each voxel in each brain district on different time points respectively, the activation value with each voxel averages again, obtains brain district sequence averaging time.

4. the brain function MRI sorting technique based on complex network as claimed in claim 1 is characterized in that, the method for calculating the partial correlation coefficient between each of sequence is averaging time:

At first calculate the covariance matrix S between each of sequence, this covariance matrix dimension is 90 * 90, each element s of S averaging time _{I, j}Be the covariance coefficient between i and j the time series,

$s_{i,j}=\frac{1}{M}\underset{t=1}{\overset{M}{\mathrm{\&Sigma;}}}(x_i\left(t\right)-\stackrel{\&OverBar;}{x_i})(x_j\left(t\right)-\stackrel{\&OverBar;}{x_j}),$

Wherein, M is the time point number, x _i(t) (i=1 ..., M) be i time series,

Be i seasonal effect in time series mean value,

Be j seasonal effect in time series mean value.

Then, calculate the partial correlation coefficient matrix R between average time series, the dimension of this partial correlation coefficient matrix R is 90 * 90, each element r of R _{I, j}For:

$r_{i,j}=-\frac{s_{i,j}^{-1}}{\sqrt{s_{i,i}^{-1}{s}_{j,j}^{-1}}};$

Wherein,

is { i, j} element of the inverse matrix of covariance matrix S;

At last, partial correlation coefficient is carried out the Fisher conversion, obtaining through the partial correlation coefficient matrix dimensionality after this conversion of partial correlation coefficient matrix F after the Fisher conversion is 90 * 90.

5. the brain function MRI sorting technique based on complex network as claimed in claim 1 is characterized in that, said said partial correlation coefficient matrix binaryzation is obtained the step of complex network model, comprising:

Selected threshold will be passed through the partial correlation coefficient matrix F binaryzation of Fisher conversion; Partial correlation coefficient matrix dimensionality after this conversion is 90 * 90; Between two brain districts of 1 expression connection is arranged after the binaryzation; Be that the limit between two nodes exists in the network, 0 expression does not connect between two brain districts, does not promptly have the limit between two nodes in the network;

The method of selection of threshold is: make the quantity of selecting for use this threshold value to carry out in esse limit in the network after the binaryzation be the limit that possibly exist in the network quantity 1/10th.

6. the brain function MRI sorting technique based on complex network as claimed in claim 1, the step of the characteristic path of wherein said this complex network model of calculating is:

With any two node i in the characteristic path matrix description network, the characteristic path l of j _Ij, network average characteristics path L has described the mean value of the characteristic path of any two nodes in the network, promptly

$L=\frac{1}{N(N-1)}\underset{i,j\&Element;V,i\&NotEqual;j}{\mathrm{\&Sigma;}}{l}_{\mathrm{ij}}$

Wherein, N is the number of node in the network, the brain district of promptly cutting apart several 90; l _IjBe node i, the characteristic path between the j, V is the set of all nodes in the network.

7. the brain function MRI sorting technique based on complex network as claimed in claim 1, the step of the cost of wherein said this complex network model of calculating is:

With the quantity in esse all limits in the network quantity, that is: than the limit that possibly exist at most in the last network

$K=\frac{\frac{\mathrm{\&Sigma;}{K}_i}{2}}{\frac{N(N-1)}{2}}=\frac{1}{N(N-1)}\mathrm{\&Sigma;}{K}_i,$

Wherein, N is the number of node in the network, K _iQuantity for the limit that is connected to node i in the network.

8. the brain function MRI sorting technique based on complex network as claimed in claim 1, the step of the cluster degree of wherein said this complex network model of calculating is:

The cluster degree C of a certain node i _iThe number and the ratio of all possible limit number between them on the value limit that equals to exist between its adjacent node, promptly

$C_i=\frac{e_i}{\frac{k_i(k_i-1)}{2}}=\frac{2e_i}{k_i(k_i-1)}$

Wherein, e _iThe limit number that exists between the adjoint point of expression node i, k _iThe number of the adjoint point of expression node i,

Just represent the limit number that possibly exist between the adjoint point of node i.

Images