CN106127769A - A kind of brain Forecasting Methodology in age connecting network based on brain - Google Patents

A kind of brain Forecasting Methodology in age connecting network based on brain Download PDF

Info

Publication number
CN106127769A
CN106127769A CN201610478697.2A CN201610478697A CN106127769A CN 106127769 A CN106127769 A CN 106127769A CN 201610478697 A CN201610478697 A CN 201610478697A CN 106127769 A CN106127769 A CN 106127769A
Authority
CN
China
Prior art keywords
brain
network
node
limit
age
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201610478697.2A
Other languages
Chinese (zh)
Inventor
张道强
路子祥
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN201610478697.2A priority Critical patent/CN106127769A/en
Publication of CN106127769A publication Critical patent/CN106127769A/en
Pending legal-status Critical Current

Links

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
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • 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)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (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 kind of brain Forecasting Methodology in age connecting network based on brain.First described method comprises the steps:, from brain image, abstraction function connects network；Secondly, the cluster coefficients feature as node of network node is calculated；Then, use the weight of LASSO opposite side to carry out feature selection, reject the limit without identification；Then, the feature of aggregators and there is the feature on limit of identification as fusion feature；Support vector regression (support vector regression, SVR) is finally used to estimate brain age.The invention provides a kind of effective extraction feature, the brain Forecasting Methodology in age connecting network based on brain that regression effect is good.

Description

A kind of brain Forecasting Methodology in age connecting network based on brain
Technical field
The invention discloses a kind of brain Forecasting Methodology in age connecting network based on brain, the invention belongs to medical image and calculating The crossing domain of machine science, relates to the technical field of digital image analysis and pattern recognition.
Background technology
In the last few years, neuroimaging technology develops rapidly, mainly includes structure NMR (Nuclear Magnetic Resonance)-imaging (structural Magnetic resonance imaging, structural MRI), diffusion tensor (diffusion tensor Imaging, DTI), function NMR (Nuclear Magnetic Resonance)-imaging (functional MRI, fMRI), electroencephalogram (electro- Encephalogram, EEG) and magneticencephalogram (magnetoencephalography, MEG).Based on fMRI, EEG and MEG image In, people can obtain function and connect network, for reflecting the dissection connection mode of Different brain region.
Brain network model is the simple expression to brain system.In brain connects network, node is generally defined as nerve Unit or area-of-interest, and limit is defined as the connection mode between them.At present, the research of brain connection analysis of network is broadly divided into Two aspects: one is to lay particular emphasis on the test driving ad hoc hypothesis, as to small-world network and hippocampal network etc.；Two is that emphasis is put Complete based on individual prediction and classification based on machine learning method.Rule are obtained owing to can automatically analyze from data Restraining, and unknown data is predicted by assimilated equations, method based on machine learning has become as a recent studies on focus.But by In the complexity of brain self, and the sample usually got is considerably less, which results in brain and connects dividing of network Analysis is a problem the most challenging.
Brain age, refer to the age of brain.Brain age and actual age have different implications, research to find, the mankind are at healthy shape Brain age under state is approximately equal to self actual age, suffers from the crowd of nervous system disease for some, its brain age Can be more than self actual age, those growths occur that its brain age of crowd of obstacle is then less than self actual age.Logical Spend the prediction human brain age, itself and actual age are contrasted, can detect whether brain accelerated ageing and nerve degeneration occurs The early symptom of property disease, it is the most necessary for therefore constructing a kind of brain forecast model in age that can effectively predict the human brain age 's.
The present invention, based on problem above, proposes a kind of brain Forecasting Methodology in age connecting network based on brain.Achieve the company of requiring mental skill Demonstrate, while connecing network Accurate Prediction brain age, the effectiveness that various features merges.
Summary of the invention
The present invention is to connect network based on brain, the method inventing a brain age prediction.
The concrete technical scheme of the present invention includes following step:
Step one: construct brain from brain image data and connect network；
Step 2: connect network from brain and extract the cluster coefficients of node as node diagnostic；
Step 3: connect network to extract and select from brain and there is the limit weight of identification as limit feature；
Step 4: merge the node diagnostic in first two steps and limit feature as fusion feature；
Step 5: use support vector regression to estimate brain age fusion feature.
In described step one, to the initial data collected, we use Data Processing Assistant for Resting-State fMRI (DPARSF) carries out time adjustment (slice timing) of cutting into slices, head dynamic(al) correction (motion And the standard pretreatment process such as spatial regularization (spatial normalization) correlation),.The most each object The Naokong corresponding to fMRI image between be divided into 90 according to Automated Anatomical Labeling (AAL) template Ge Nao district (summit in each brain district corresponding diagram), calculate each brain district average time sequence and brain interval Pearson correlation coefficient is as the bonding strength in brain interval.Thus obtain the functional connection network of brain.
In described step 2, we extract the cluster coefficients of node as node diagnostic from brain connection network.First, We use the method for thresholding, are converted into by the function having the right connection network and have no right network.Given function connects network (square Battle array) and G=[w (i, j)] ∈ Rn×nWith threshold value T, use formula below thresholding connect network:
w ( i , j ) = 0 i f w ( i , j ) < T 1 o t h e r w i s e - - - ( 1 )
Wherein, n represents the number of area-of-interest (region-of-interest, ROI).
Then, we calculate and have no right the cluster coefficients of each node in network.We provide the definition of cluster coefficients.
Definition 1: cluster coefficients
Having no right non-directed graph G for given one, the cluster coefficients computing formula of the i-th node in G is as follows:
C i = 2 &times; E i k i &times; ( k i - 1 ) - - - ( 2 )
Wherein kiRepresent the number of the abutment points of i-th node, EiRepresent the k of i-th nodeiExist between individual abutment points Limit number.
From formula (2) it can be seen that the connection between the abutment points of a point is the tightst, the value of cluster coefficients is more High.In the functional network of disease of brain patient, cluster coefficients can well reflect single area-of-interest (region-of- Interest, ROI) exception.
In described step 3, we extract the weight on limit from brain connection network and select the limit power with identification Recast is limit feature.Lasso algorithm is used to select the limit weight with identification the weight on the limit extracted.Lasso returns Estimation rarefaction representation coefficient w is returned to can be described as follows:
w ^ = arg m i n | | y - A w | | 2 2 + &lambda; | | w | | 1 - - - ( 3 )
It is that the feature in the initial data corresponding to 0 is removed by the coefficient matrix w intermediate value tried to achieve.Obtain one through spy Levy the eigenmatrix of the relatively low-dimensional after selection.
In described step 4, the feature picked out in step 2 and step 3 is carried out linear fusion obtain one new Feature.Specifically it is calculated as follows, if the eigenmatrix of node isThe eigenmatrix on limit isThen Eigenmatrix after fusion isWherein, n represents that number of samples, c represent the spy of node Levying number, e represents the Characteristic Number on limit.
In described step 5, support vector regression SVR is used to estimate brain age to step 4 obtains fusion feature.
The present invention uses above technical scheme compared with prior art, has the following advantages and beneficial effect:
(1) method merging multiple features that the present invention proposes is carried out after making full use of manifold advantage and being merged Regression forecasting, achieves and well predicts the outcome；
(2) existing brain network research focuses on how to divide the brain network of different people according to certain division rule mostly Class, and this clearly demarcated purpose is to do regression forecasting, obtain is a successive value, has more the meaning analyzing reference.
Accompanying drawing explanation
Fig. 1 is the frame diagram of the method for the invention.
Fig. 2 is the physiological age of the embodiment of the present invention and estimates brain corresponding diagram in age.
Detailed description of the invention
Select middle-aged and elderly people 40 example of health below, in conjunction with Fig. 1, said method of the present invention is specifically described.Wherein, The age of subjects, sex are as shown in table 1 below.Because sample number is less, leaving-one method is used to carry out cross validation in an experiment.Tool For body, in each experiment, choosing a sample as test sample, remaining sample is as training sample.Final knot Fruit is to be calculated by the average result of all experiments.
Table 1 subjects's Information Statistics table
Quantity Male/female ratio The range of age Age average/standard deviation
Tested sample 40 18/22 65～90 75.6/6.4
The overall procedure of the present invention is as shown in Figure 1.Concrete implementation process comprises five steps:
Step one is to build brain to connect network.Firstly, it is necessary to collect some brain image numbers comprising clinical variable Value Data According to.Then, to the initial data collected, use Data Processing Assistant for Resting-State FMRI (DPARSF) carries out time adjustment (slice timing) of cutting into slices, head dynamic(al) correction (motion correlation), and sky Between the standard pretreatment process such as regularization (spatial normalization).Corresponding to the fMRI image of the most each object Naokong between be divided into (each brain district pair of 90 Ge Nao districts according to Automated Anatomical Labeling (AAL) template Should a summit in figure), calculate each brain district average time sequence and the interval Pearson correlation coefficient of brain as brain Interval bonding strength.Thus obtain the functional connection network of brain.It should be noted that this brain network is a diagonal angle The symmetrical matrix of 1 it is all on line.
Step 2 is to extract the cluster coefficients of node.To the full Weight network that connects obtained in step one first by public affairs Formula (1) thresholding connects network, less than threshold value, weight in network is set to 0, is set to 1 more than or equal to threshold value.Thus will Brain network of having the right is converted into and haves no right brain network.Then, use formula (2) to calculate and have no right the cluster system of each node in brain network Number.Obtain a matrix comprising node diagnosticIn matrix A, often row represents a sample, each column generation The cluster coefficients of one node of table.In Setup Experiments, the threshold value in formula (1) is set to 0.6.
Step 3 is to extract and select the weight on limit.The symmetrical full Weight network that connects obtained in step one is carried out Conversion, pulls into the vector of a 90* (90-1)/2=4005 dimension by the network of this 90*90, and the information that this vector is comprised is The weighted value on the limit of network.Then, the formula (3) of Lasso algorithm is used to select the limit with identification.Obtain one to comprise The matrix of limit featureIn matrix B, often row represents a sample, and each column represents one and has identification Limit weight.In Setup Experiments, the parameter lambda in formula (3) is set to 0.7.
Step 4 is aggregators feature and limit feature.The matrix B that the matrix A obtaining step 2 and step 3 obtain is entered Row merges, if the eigenmatrix of node isThe eigenmatrix on limit isThen merge After eigenmatrix be
Step 5 uses support vector regression SVR the eigenmatrix C obtained in step 4 to be carried out regression analysis, to melt Eigenmatrix C is as independent variable in conjunction, and the age, as dependent variable, carries out regression analysis, estimates brain age.
It is computed, the correlation coefficient value between prediction brain age that fusion method proposed by the invention draws and true brain age Being 0.8899, root-mean-square error value is 3.1340.
Above in conjunction with accompanying drawing, embodiments of the present invention are explained in detail, but the present invention is not limited to above-mentioned enforcement Mode, in the ken that those of ordinary skill in the art are possessed, it is also possible on the premise of without departing from present inventive concept Make a variety of changes.

Claims (6)

1. connect a brain Forecasting Methodology in age for network based on brain, its feature comprises the steps:
(1) from brain image, construct brain connect network；
(2) extraction node diagnostic network is connected from brain；
(3) extract from brain connection network and select limit feature；
(4) the two kinds of features extracted in step (1), (2) are carried out linear fusion；
(5) use support vector regression (Support vector regression, SVR) that age brain is carried out regression forecasting.
The method of a kind of brain prediction in age connecting network based on brain the most according to claim 1, it is characterised in that described step Suddenly, in (1), from brain image, construct brain connect network.Its implementation includes:
(21) to the initial data collected, we use Data Processing Assistant for Resting- State fMRI (DPARSF) carries out time adjustment (slice timing) of cutting into slices, head dynamic(al) correction (motion And the standard pretreatment process such as spatial regularization (spatial normalization) correlation),；
(22) according to Automated Anatomical Labeling (AAL) template by corresponding to the fMRI image of each object Naokong between be divided into 90 Ge Nao districts (summit in each brain district corresponding diagram)；
(23) calculate each brain district average time sequence and the interval Pearson correlation coefficient of brain as the interval connection of brain Intensity (limit being in figure).
The method of a kind of brain prediction in age connecting network based on brain the most according to claim 1, it is characterised in that described step Suddenly in (2), connecting from brain and extract node diagnostic network, its implementation includes:
(31) first thresholding function connects network, sets threshold value T, is set to 0, more than or equal to threshold value T less than threshold value T It is set to 1；
(32) for the connection network after thresholding, the cluster coefficients of node is calculated.
The most according to claim 3 connection from brain extracts node diagnostic network, it is characterised in that described step (32) In, calculating the cluster coefficients of node, its implementation includes:
(41) for having no right without term diagram G, the computing formula of the cluster coefficients of the i-th node in G is as follows:
C i = 2 &times; E i k i &times; ( k i - 1 )
Wherein, kiRepresent the number of the abutment points of i-th node, EiRepresent the k of i-th nodeiThe limit existed between individual abutment points Number；
(42) brain of each sample is connected its cluster coefficients of network calculations, as the feature of node.
The method of a kind of brain prediction in age connecting network based on brain the most according to claim 1, it is characterised in that described step Suddenly in (3), connecting from brain and extract network and select limit feature, its implementation includes:
(51) network is connected for brain, first can simply obtain the limit in network, limit is pulled into vector and preserves its weight letter Breath；
(52) Lasso algorithms selection is used to have most the limit of identification, as the feature on limit.
The method of a kind of brain prediction in age connecting network based on brain the most according to claim 1, it is characterised in that described step Suddenly in (4), the two kinds of features extracted in step (1), (2) being carried out linear fusion, its implementation includes:
(61) merging the characteristic line of the feature on the limit extracted and node.Might as well set the eigenmatrix of node asThe eigenmatrix on limit isEigenmatrix after then merging is Wherein, n represents that number of samples, c represent the Characteristic Number of node, and e represents the Characteristic Number on limit.
CN201610478697.2A 2016-06-22 2016-06-22 A kind of brain Forecasting Methodology in age connecting network based on brain Pending CN106127769A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610478697.2A CN106127769A (en) 2016-06-22 2016-06-22 A kind of brain Forecasting Methodology in age connecting network based on brain

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610478697.2A CN106127769A (en) 2016-06-22 2016-06-22 A kind of brain Forecasting Methodology in age connecting network based on brain

Publications (1)

Publication Number Publication Date
CN106127769A true CN106127769A (en) 2016-11-16

Family

ID=57266676

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610478697.2A Pending CN106127769A (en) 2016-06-22 2016-06-22 A kind of brain Forecasting Methodology in age connecting network based on brain

Country Status (1)

Country Link
CN (1) CN106127769A (en)

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106780475A (en) * 2016-12-27 2017-05-31 北京市计算中心 A kind of image processing method and device based on histopathologic slide's image organizational region
CN107507162A (en) * 2017-06-29 2017-12-22 南京航空航天大学 A kind of Genotyping methods based on multi-modal brain image
CN108960341A (en) * 2018-07-23 2018-12-07 安徽师范大学 A kind of structured features selection method towards brain network
CN109344889A (en) * 2018-09-19 2019-02-15 深圳大学 A kind of cerebral disease classification method, device and user terminal
CN110097968A (en) * 2019-03-27 2019-08-06 中国科学院自动化研究所 Baby's brain age prediction technique, system based on tranquillization state functional magnetic resonance imaging
CN110101384A (en) * 2019-04-22 2019-08-09 自然资源部第一海洋研究所 Functional network analysis system and analysis method for complex network
CN110298479A (en) * 2019-05-20 2019-10-01 北京航空航天大学 A kind of brain volume atrophy prediction technique based on brain function network
CN110473171A (en) * 2019-07-18 2019-11-19 上海联影智能医疗科技有限公司 Brain age detection method, computer equipment and storage medium
CN110547772A (en) * 2019-09-25 2019-12-10 北京师范大学 Individual age prediction method based on brain signal complexity
CN110664400A (en) * 2019-09-20 2020-01-10 清华大学 Electroencephalogram characteristic potential tracing method based on degree information
CN111973180A (en) * 2020-09-03 2020-11-24 北京航空航天大学 Brain structure imaging system and method based on MEG and EEG fusion
CN113378898A (en) * 2021-05-28 2021-09-10 南通大学 Brain age prediction method based on relative entropy loss function convolution neural network
CN115736946A (en) * 2022-10-08 2023-03-07 浙江柔灵科技有限公司 Brain age calculation method based on electroencephalogram signals
CN117158890A (en) * 2023-04-04 2023-12-05 深圳市中医院 Brain age prediction method and related device based on segmented brain age model
CN117788897A (en) * 2023-12-20 2024-03-29 首都医科大学附属北京友谊医院 Brain age prediction method, device, equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102783936A (en) * 2011-05-16 2012-11-21 常州环视高科电子科技有限公司 Method and system for determining brain state
CN103383717A (en) * 2013-06-26 2013-11-06 北京理工大学 Senile dementia computer-aided diagnosis method based on three-dimensional nuclear magnetic resonance structure images
CN105046709A (en) * 2015-07-14 2015-11-11 华南理工大学 Nuclear magnetic resonance imaging based brain age analysis method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102783936A (en) * 2011-05-16 2012-11-21 常州环视高科电子科技有限公司 Method and system for determining brain state
CN103383717A (en) * 2013-06-26 2013-11-06 北京理工大学 Senile dementia computer-aided diagnosis method based on three-dimensional nuclear magnetic resonance structure images
CN105046709A (en) * 2015-07-14 2015-11-11 华南理工大学 Nuclear magnetic resonance imaging based brain age analysis method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
CHONG-YAW WEE 等: "《Identification of MCI individuals using structural and functional connectivity networks》", 《NEUROIMAGE》 *
MASSIMILIANO ZANIN 等: "《Optimizing Functional Network Representation of Multivariate Time Series》", 《SCIRNTIFIC REPORTS》 *
YAN CHAO-GAN 等: "《DPARSF: a MATLAB toolbox for "pipeline" data analysis of resting-state fMRI》", 《FRONTIERS IN SYSTEMS NEUROSCIENCE》 *

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106780475A (en) * 2016-12-27 2017-05-31 北京市计算中心 A kind of image processing method and device based on histopathologic slide's image organizational region
CN107507162A (en) * 2017-06-29 2017-12-22 南京航空航天大学 A kind of Genotyping methods based on multi-modal brain image
CN108960341A (en) * 2018-07-23 2018-12-07 安徽师范大学 A kind of structured features selection method towards brain network
CN108960341B (en) * 2018-07-23 2022-03-01 安徽师范大学 Brain network-oriented structural feature selection method
CN109344889A (en) * 2018-09-19 2019-02-15 深圳大学 A kind of cerebral disease classification method, device and user terminal
CN110097968A (en) * 2019-03-27 2019-08-06 中国科学院自动化研究所 Baby's brain age prediction technique, system based on tranquillization state functional magnetic resonance imaging
CN110101384A (en) * 2019-04-22 2019-08-09 自然资源部第一海洋研究所 Functional network analysis system and analysis method for complex network
CN110298479B (en) * 2019-05-20 2021-09-03 北京航空航天大学 Brain volume atrophy prediction method based on brain function network
CN110298479A (en) * 2019-05-20 2019-10-01 北京航空航天大学 A kind of brain volume atrophy prediction technique based on brain function network
CN110473171A (en) * 2019-07-18 2019-11-19 上海联影智能医疗科技有限公司 Brain age detection method, computer equipment and storage medium
CN110664400A (en) * 2019-09-20 2020-01-10 清华大学 Electroencephalogram characteristic potential tracing method based on degree information
CN110547772A (en) * 2019-09-25 2019-12-10 北京师范大学 Individual age prediction method based on brain signal complexity
CN111973180B (en) * 2020-09-03 2021-09-17 北京航空航天大学 Brain structure imaging system and method based on MEG and EEG fusion
CN111973180A (en) * 2020-09-03 2020-11-24 北京航空航天大学 Brain structure imaging system and method based on MEG and EEG fusion
CN113378898A (en) * 2021-05-28 2021-09-10 南通大学 Brain age prediction method based on relative entropy loss function convolution neural network
CN115736946A (en) * 2022-10-08 2023-03-07 浙江柔灵科技有限公司 Brain age calculation method based on electroencephalogram signals
CN117158890A (en) * 2023-04-04 2023-12-05 深圳市中医院 Brain age prediction method and related device based on segmented brain age model
CN117788897A (en) * 2023-12-20 2024-03-29 首都医科大学附属北京友谊医院 Brain age prediction method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN106127769A (en) A kind of brain Forecasting Methodology in age connecting network based on brain
CN113616184B (en) Brain network modeling and individual prediction method based on multi-mode magnetic resonance image
CN113040715B (en) Human brain function network classification method based on convolutional neural network
CN105046709B (en) A kind of brain age analysis method based on nuclear magnetic resonance image
YİĞİT et al. Applying deep learning models to structural MRI for stage prediction of Alzheimer's disease
CN110598793B (en) Brain function network feature classification method
CN111009324B (en) Auxiliary diagnosis system and method for mild cognitive impairment through multi-feature analysis of brain network
CN113610808B (en) Group brain map individuation method, system and equipment based on individual brain connection diagram
CN109509552A (en) A kind of mental disease automatic distinguishing method of the multi-level features fusion based on function connects network
CN109508644A (en) Facial paralysis grade assessment system based on the analysis of deep video data
CN113440149B (en) ECG signal classification method based on twelve-lead electrocardiograph data two-dimensional multi-input residual neural network
CN103646183A (en) Intelligent alzheimer disease discriminant analysis method based on artificial neural network and multi-modal MRI (Magnetic Resonance Imaging)
CN112614126B (en) Magnetic resonance image brain region dividing method, system and device based on machine learning
CN104636580A (en) Health monitoring mobile phone based on human face
CN112002428A (en) Whole brain individualized brain function map construction method taking independent component network as reference
CN112233086B (en) fMRI data classification and identification method and device based on brain region functional connection
CN117172294B (en) Method, system, equipment and storage medium for constructing sparse brain network
CN111523617B (en) Epilepsy detection system based on white matter fusion characteristic diagram and residual error attention network
CN115272295A (en) Dynamic brain function network analysis method and system based on time domain-space domain combined state
CN102508184A (en) Brain function active region detection method based on moving average time series models
Thomas et al. Artificial neural network for diagnosing autism spectrum disorder
CN107256408B (en) Method for searching key path of brain function network
CN113096127A (en) System and method for generating brain network evolution model
CN107092925B (en) Cerebral function magnetic resonance imaging blind source separation method based on SIM algorithm in groups
Ingalhalikar et al. Identifying sub-populations via unsupervised cluster analysis on multi-edge similarity graphs

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20161116

WD01 Invention patent application deemed withdrawn after publication