CN114159043A - Brain function network abnormal brain node data detection method based on Qcut algorithm - Google Patents
Brain function network abnormal brain node data detection method based on Qcut algorithm Download PDFInfo
- Publication number
- CN114159043A CN114159043A CN202111556333.9A CN202111556333A CN114159043A CN 114159043 A CN114159043 A CN 114159043A CN 202111556333 A CN202111556333 A CN 202111556333A CN 114159043 A CN114159043 A CN 114159043A
- Authority
- CN
- China
- Prior art keywords
- brain
- community
- node
- nodes
- function network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 114
- 230000003925 brain function Effects 0.000 title claims abstract description 40
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 24
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000002599 functional magnetic resonance imaging Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 16
- 231100000915 pathological change Toxicity 0.000 claims description 7
- 230000036285 pathological change Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 2
- 210000003484 anatomy Anatomy 0.000 claims description 2
- 239000008280 blood Substances 0.000 claims description 2
- 210000004369 blood Anatomy 0.000 claims description 2
- 238000009499 grossing Methods 0.000 claims description 2
- 230000004886 head movement Effects 0.000 claims description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 2
- 230000003902 lesion Effects 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 208000020401 Depressive disease Diseases 0.000 description 1
- 210000004227 basal ganglia Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 210000004326 gyrus cinguli Anatomy 0.000 description 1
- 210000001320 hippocampus Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 208000024714 major depressive disease Diseases 0.000 description 1
- 208000011736 mal de Debarquement Diseases 0.000 description 1
- 230000001936 parietal effect Effects 0.000 description 1
- 230000002360 prefrontal effect Effects 0.000 description 1
- 230000002739 subcortical effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4058—Detecting, measuring or recording for evaluating the nervous system for evaluating the central nervous system
- A61B5/4064—Evaluating the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Neurology (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Psychology (AREA)
- Educational Technology (AREA)
- Social Psychology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Developmental Disabilities (AREA)
- Signal Processing (AREA)
- High Energy & Nuclear Physics (AREA)
- Hospice & Palliative Care (AREA)
- Radiology & Medical Imaging (AREA)
- Child & Adolescent Psychology (AREA)
- Neurosurgery (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses a brain function network abnormal brain node data detection method based on a Qcut algorithm, which comprises the following steps of 1, preprocessing collected functional magnetic resonance imaging data of a testee; step 2, dividing the whole brain structure of the testee and constructing a brain function network; step 3, realizing community division of the brain function detection network based on the Qcut algorithm; and 4, carrying out community detection on the brain function network and detecting the abnormal condition of the brain nodes by adopting the Jacobi index. Compared with the prior art, the invention has the beneficial effects that: 1) the community structure stability of the obtained brain function network is high; 2) meanwhile, the brain is finely divided by adopting the brain network group atlas, the brain is divided into 246 brain nodes, the detection result of the obtained abnormal brain nodes is more accurate, and the method has high reliability.
Description
Technical Field
The invention relates to the technical field of cognitive neuroscience and machine learning, in particular to a method for detecting abnormal brain nodes of a brain functional network.
Background
Despite the great efforts made to treat depression, the increasing growth of society has led to an increase in the pressure of life of people, so that the incidence of depression has increased year by year. Therefore, greater emphasis should be placed on exploring a diagnosis of depression. In order to confirm the brain node abnormal condition of the depression patient, the Qcut algorithm based on the modularity is applied to the functional magnetic resonance imaging to detect the stable community structure of the brain function network, and the community structure of the brain network and the number of each community can be rapidly detected by the algorithm, so that the obtained result is more reliable.
The Qcut algorithm can be applied to not only social networks but also biological networks, and has good applicability. The Qcut algorithm is parameter-free, has high running speed and can quickly divide a brain function network. Therefore, the time cost is saved, and the accuracy of the experimental result is improved.
Disclosure of Invention
The invention aims to provide a brain function network abnormal brain node data detection method based on a Qcut algorithm.
The invention is realized by the following technical scheme:
a brain function network abnormal data detection method based on a Qcut algorithm specifically comprises the following steps:
wherein, XiRepresenting a time series of brain nodes i, XjRepresenting a time series of brain nodes j.
Representing the average time series of brain nodes i,
represents the average time series of brain nodes j;
the modularity is defined as follows:
wherein k represents the total number of communities obtained by dividing the brain function network, and e represents a symmetric matrix k x k, eiiRepresenting the ratio of the number of actually connected edges to the number of fully connected edges, a, in a community ii＝∑jeijThe sum of values representing all communities of community i connected to others, eijRepresenting the ratio of the number of actually connected edges of the community i and the community j to the total number of edges;
after determining the optimal community structures of the brain function networks of normal persons and depression patients respectively, the Jacobian index is used for detecting abnormal brain nodes, and for the brain node i, the Jacobian index JI is calculated by the following formula:
wherein A isiRepresenting the brain network of a normal personAll members of the community to which node i belongs in the network, BiRepresents all members of the community to which node i belongs in the brain network of the depression patient; the value range of the Jacka index JI is 0 to 1, and the smaller the value of JI is, the larger the difference between the environments of the brain node in the community structure of normal people and the community structure of depression patients is, the brain node may have certain pathological changes, cannot execute the original function and is classified into brain node communities with other functions; otherwise, the brain node is similar to the environment of the community structure of the normal person and the community structure of the depression patient, the original function of the brain node is basically reserved, and detection data containing pathological changes are not found.
Compared with the prior art, the invention has the following beneficial effects:
1) the community structure stability of the obtained brain function network is high;
2) meanwhile, the brain is finely divided by adopting the brain network group atlas, the brain is divided into 246 brain nodes, the detection result of the obtained abnormal brain nodes is more accurate, and the method has high reliability.
Drawings
FIG. 1 is an overall flow chart of a method for detecting abnormal brain node data in a brain functional network based on a Qcut algorithm according to the present invention;
fig. 2 shows the result of community division of the brain function network. (A) Dividing communities of normal people; (B) cohort divisions of depression patients;
FIG. 3 is a community in which abnormal brain node data is located.
Detailed Description
The technical solution of the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, it is an overall flowchart of a method for detecting abnormal brain node data in a brain functional network based on a Qcut algorithm according to the present invention. The method specifically comprises the following steps:
The data preprocessing in this step, specifically, preprocessing the data by using the SPM12 toolkit in Matlab software, includes the following steps:
step 1.1, removing the first 5 time points of each tested sample, and avoiding the influence caused by unstable scanning signals of a nuclear magnetic instrument at the beginning;
step 1.2, correcting time layers to ensure that scanned tested layers are obtained at the same time;
step 1.3, performing head movement correction, wherein in the acquisition process of fMRI data, although the head to be tested is fixed, the head to be tested inevitably moves due to physiological factors such as respiration and blood, parameters for registering time sequence images and reference images thereof are determined through a head correction function, and each frame image in an experimental sequence is aligned with the reference image of the sequence on the basis;
step 1.4, registering, namely converting corresponding points of the functional image and the structural image to achieve spatial consistency;
step 1.5, space standardization, namely, carrying out space standardization processing on different brain images, and explaining space positions by standardization processing according to differences of the tested brain on an anatomical structure;
and step 1.6, smoothing so as to effectively reduce image noise and improve the detection capability of the function activation data.
wherein, XiRepresenting a time series of brain nodes i, XjRepresenting a time series of brain nodes j.
Representing the average time series of brain nodes i,
representing the average time series of brain nodes j. r isijHas a value range of [ -1,1 [)]If the value of the pearson correlation is greater than 0, the relation between the brain nodes is positive correlation; if the value of the pearson correlation is less than 0, the relation between the brain nodes is negative correlation; if the value of the pearson correlation is equal to 0, no correlation relationship exists between the brain nodes.
And 3, realizing the community division of the functional brain function detection network based on the Qcut algorithm, namely quickly determining the community structure of the brain network and the number of each community. The method specifically comprises the following steps: a variable for measuring the quality of a brain function network is defined by a Qcut algorithm, called modularity, and the expression is as follows:
wherein k represents the total number of communities obtained by dividing the brain function network, and e represents a symmetric matrix k x k, eiiRepresenting the ratio of the number of actually connected edges to the number of fully connected edges, a, in a community ii＝∑jeijThe sum of values representing all communities to which the first community i is connected, eijThe ratio of the number of edges actually connected to the community i and the community j to the total number of edges is shown.
Q ranges from 0 to 1 and has: if Q is 0, the constructed brain function network is not considered to have a good community structure. If Q is 1, the constructed brain function network has a better community structure. However, in the actually constructed brain function network, the value of Q is generally between 0.3 and 0.8. Selecting the most stable community structure by combining standard mutual information and information variable quantity as indexes for measuring community stability;
suppose AiIs all members of the community to which the brain node i belongs in the brain network of the normal person, and BiAre all members of the community to which brain node i belongs in the brain network of depression patients. A. theiAnd BiThe environments of communities in which the brain nodes i are located in different groups are respectively shown, and abnormal nodes can be found by judging the difference of the environments of all the brain nodes. The difference of the environments of all brain nodes is calculated by adopting a Jacobian index, and for a brain node i, the calculation mode of the difference value is as follows:
the jacarat index JI ranges from 0 to 1. The smaller the value of JI, the larger the difference between the environment of the brain node in the community structure of the normal person and the environment of the community structure of the depression patient, which indicates that the brain node may be affected by a certain disease and cannot perform the original function, so that the brain node is classified into brain communities with other functions. On the contrary, when the value of JI is larger, the relative similarity of the environment of the brain node in the community structure of normal people and the community structure of depression patients is shown, and the brain node basically keeps the original function and has no pathological changes.
Calculating the Jacobian index of each brain node, selecting the brain nodes 15% before the Jacobian distance value, and observing that the brain nodes are in a community environment with the difference degree of more than 0.95 after suffering from depression, the community environment is greatly changed, and certain pathological changes possibly exist.
As shown in fig. 2, a community division structure based on the Qcut algorithm and obtained by combining information variation and standard mutual information is shown, where a is a brain function network division result of a normal person, and B is a brain function network division result of a depression patient, where the brain function network of the normal person is divided into 7 communities, the minimum community includes 7 brain nodes, and the maximum community includes 56 brain nodes; while the brain function network of depression is divided into 14 communities, the smallest community comprises 2 brain nodes and the largest community comprises 42 brain nodes. It is reasonable to see that the number of communities of depression is larger than that of normal people, because the brain function network of the depression patient has some abnormal conditions, which leads to the increase of the number of communities.
The specific embodiments of the present invention are described below:
for example, an embodiment of the present invention uses two sets of sample data, one set being MDD patients (18 females, 7 males, mean age 50.7 + -10.5, age range 24-65 years) and the other set being normal (20 females, 8 males, mean age 49.8 + -11.1, age range 25-65 years). All subjects were performed with written informed consent. All the tested subjects will get corresponding reward after the experiment.
Firstly, according to the specific problems of cognitive neuroscience, recruiting a subject to be tested, carrying out an experiment and completing data acquisition; and then, carrying out primary processing on the data by using a preprocessing technology, and carrying out brain node division on the whole brain structure by using a brain network group map to divide the whole brain structure into 246 brain nodes. Fig. 3 is a schematic diagram of an abnormal brain node. Including prefrontal gyrus, orbital gyrus, temporo sulcus, parietal lobule, anterior cuneiform, central gyrus, ligulate gyrus, cingulate gyrus, hippocampus, basal ganglia, etc. Numerals 1-13 indicate the community number where each abnormal brain node is located.
Claims (6)
1. A brain function network abnormal data detection method based on a Qcut algorithm is characterized by comprising the following steps:
step 1, preprocessing the acquired functional magnetic resonance imaging data of a testee;
step 2, dividing the whole brain structure of the testee by using a brain network group map with 210 cortex and 36 sub-cortex sub-regions, extracting a time sequence of each brain node, and calculating the correlation between any brain nodes by adopting Pearson correlation, wherein a specific formula is as follows:
wherein, XiRepresenting a time series of brain nodes i, XjA time series of brain nodes j is represented,
representing the average time series of brain nodes i,
represents the average time series of brain nodes j;
step 3, realizing community division for detecting the brain function network based on the Qcut algorithm, wherein the community structure of the brain network and the number of each community are determined, and the method specifically comprises the following steps:
the modularity is defined as follows:
wherein k represents the total number of communities obtained by dividing the brain function network, and e represents a symmetric matrix k x k, eiiRepresenting the ratio of the number of actually connected edges to the number of fully connected edges, a, in a community ii＝∑jeijThe sum of values representing all communities of community i connected to others, eijRepresenting the ratio of the number of actually connected edges of the community i and the community j to the total number of edges;
step 4, carrying out community detection on the brain function network, and selecting the most stable community structure by combining standard mutual information and information variable quantity as indexes for measuring community stability;
after determining the optimal community structures of the brain function networks of normal persons and depression patients respectively, the Jacobian index is used for detecting abnormal brain nodes, and for the brain node i, the Jacobian index JI is calculated by the following formula:
wherein A isiAll members of the community to which node i belongs in the brain network of the normal person, BiRepresents all members of the community to which node i belongs in the brain network of the depression patient; the value range of the Jacka index JI is 0 to 1, and the smaller the value of JI is, the larger the difference between the environments of the brain node in the community structure of normal people and the community structure of depression patients is, the brain node may have certain pathological changes, cannot execute the original function and is classified into brain node communities with other functions; otherwise, the brain node is similar to the environment of the community structure of the normal person and the community structure of the depression patient, the original function of the brain node is basically reserved, and detection data containing pathological changes are not found.
2. The method for detecting brain function network abnormal data based on the Qcut algorithm as claimed in claim 1, wherein the step 1 further comprises the following processes:
step 1.1, removing the first 5 time points of each tested sample, and avoiding the influence caused by unstable scanning signals of a nuclear magnetic instrument at the beginning;
step 1.2, correcting time layers to ensure that scanned tested layers are obtained at the same time;
step 1.3, performing head movement correction, wherein in the acquisition process of fMRI data, although the head of a tested person is fixed, the head of the tested person inevitably moves due to physiological factors such as respiration and blood, parameters for registering time sequence images and reference images thereof are determined through a head correction function, and each frame image in an experimental sequence is aligned with the reference image of the sequence on the basis;
step 1.4, registering, namely converting corresponding points of the functional image and the structural image to achieve spatial consistency;
step 1.5, space standardization, namely, carrying out space standardization processing on different brain images, and explaining space positions by standardization processing according to differences of the tested brain on an anatomical structure;
and step 1.6, smoothing so as to effectively reduce image noise and improve the detection capability of the function activation data.
3. The method for detecting brain function network abnormal data based on the Qcut algorithm as claimed in claim 1, wherein:
q ranges from 0 to 1 and has: if Q is 0, the constructed brain function network is not considered to have a good community structure; if Q is 1, the constructed brain function network has a better community structure.
4. The method for Qcut algorithm-based brain function network anomaly data detection as claimed in claim 1, wherein r isijHas a value range of [ -1,1 [)]If the value of the pearson correlation is greater than 0, the relation between the brain nodes is positive correlation; if the value of the pearson correlation is less than 0, the relation between the brain nodes is negative correlation; if the value of the pearson correlation is equal to 0, no correlation relationship exists between the brain nodes.
5. The method for detecting brain function network abnormal data based on the Qcut algorithm as claimed in claim 1, wherein the information variation represents a loss value, and the larger the loss value is, the more unstable the community structure is; the standard mutual information is used for measuring the stability of the community structure, the value of the standard mutual information is in direct proportion to the stability of the community, and the larger the value is, the more stable the community structure is.
6. The method for detecting brain function network abnormal data based on the Qcut algorithm as claimed in claim 1, wherein the jacobian index JI ranges from 0 to 1, and the smaller the value of JI, the greater the difference between the environment of the brain node in the community structure of the normal person and the environment of the community structure of the depression patient, which indicates that the brain node may have a certain lesion and cannot execute the original function, so the brain node is classified into the brain node communities with other functions; otherwise, the comparison of the environments of the brain node in the community structure of the normal person and the community structure of the depression patient is similar, the original function of the brain node is basically reserved, and detection data containing pathological changes are not found.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111556333.9A CN114159043A (en) | 2021-12-17 | 2021-12-17 | Brain function network abnormal brain node data detection method based on Qcut algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111556333.9A CN114159043A (en) | 2021-12-17 | 2021-12-17 | Brain function network abnormal brain node data detection method based on Qcut algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114159043A true CN114159043A (en) | 2022-03-11 |
Family
ID=80487329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111556333.9A Pending CN114159043A (en) | 2021-12-17 | 2021-12-17 | Brain function network abnormal brain node data detection method based on Qcut algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114159043A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117731A (en) * | 2015-07-17 | 2015-12-02 | 常州大学 | Community partition method of brain functional network |
| CN105595961A (en) * | 2015-12-21 | 2016-05-25 | 天津大学 | Alzheimer's disease detecting system and method based on electroencephalogram signals |
| CN107967686A (en) * | 2017-12-27 | 2018-04-27 | 电子科技大学 | A kind of epilepsy identification device for combining dynamic brain network and long memory network in short-term |
| CN108257144A (en) * | 2018-01-25 | 2018-07-06 | 深圳市商汤科技有限公司 | Stingy drawing method, device, equipment, storage medium and program based on neural network |
| US10034645B1 (en) * | 2017-04-13 | 2018-07-31 | The Board Of Trustees Of The Leland Stanford Junior University | Systems and methods for detecting complex networks in MRI image data |
| CN109730678A (en) * | 2019-01-28 | 2019-05-10 | 常州大学 | A kind of multilayer cerebral function network module division methods |
| CN110365006A (en) * | 2019-04-26 | 2019-10-22 | 太原理工大学 | A kind of sub-area division method based on nwbbo algorithm |
| CN111127441A (en) * | 2019-12-25 | 2020-05-08 | 兰州大学 | Multi-modal brain image depression recognition method and system based on graph node embedding |
| CN111753947A (en) * | 2020-06-08 | 2020-10-09 | 深圳大学 | Resting brain network construction method, device, equipment and computer storage medium |
| CN112750465A (en) * | 2020-12-29 | 2021-05-04 | 昆山杜克大学 | Cloud language ability evaluation system and wearable recording terminal |
-
2021
- 2021-12-17 CN CN202111556333.9A patent/CN114159043A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117731A (en) * | 2015-07-17 | 2015-12-02 | 常州大学 | Community partition method of brain functional network |
| CN105595961A (en) * | 2015-12-21 | 2016-05-25 | 天津大学 | Alzheimer's disease detecting system and method based on electroencephalogram signals |
| US10034645B1 (en) * | 2017-04-13 | 2018-07-31 | The Board Of Trustees Of The Leland Stanford Junior University | Systems and methods for detecting complex networks in MRI image data |
| CN107967686A (en) * | 2017-12-27 | 2018-04-27 | 电子科技大学 | A kind of epilepsy identification device for combining dynamic brain network and long memory network in short-term |
| CN108257144A (en) * | 2018-01-25 | 2018-07-06 | 深圳市商汤科技有限公司 | Stingy drawing method, device, equipment, storage medium and program based on neural network |
| CN109730678A (en) * | 2019-01-28 | 2019-05-10 | 常州大学 | A kind of multilayer cerebral function network module division methods |
| CN110365006A (en) * | 2019-04-26 | 2019-10-22 | 太原理工大学 | A kind of sub-area division method based on nwbbo algorithm |
| CN111127441A (en) * | 2019-12-25 | 2020-05-08 | 兰州大学 | Multi-modal brain image depression recognition method and system based on graph node embedding |
| CN111753947A (en) * | 2020-06-08 | 2020-10-09 | 深圳大学 | Resting brain network construction method, device, equipment and computer storage medium |
| CN112750465A (en) * | 2020-12-29 | 2021-05-04 | 昆山杜克大学 | Cloud language ability evaluation system and wearable recording terminal |
Non-Patent Citations (2)
| Title |
|---|
| RUAN, JH等: "Identifying network communities with a high resolution", PHYSICAL REVIEW, vol. 77, 1 January 2008 (2008-01-01) * |
| 赵君霞: "复杂网络在中医临床知识发现中的应用研究", 中国优秀硕士学位论文全文数据库, 15 November 2009 (2009-11-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522894B (en) | Method for detecting dynamic covariation of fMRI brain network | |
| WO2006060727A2 (en) | System and method for eeg imaging of cerebral activity using electrode sets | |
| CN113768519B (en) | Method for analyzing consciousness level of patient based on deep learning and resting state electroencephalogram data | |
| CN111739647B (en) | Magnetic resonance image-based bipolar disorder suicide risk prediction method and related device | |
| CN114332011A (en) | Medical image processing system, device and computer readable storage medium | |
| CN110211671B (en) | Thresholding method based on weight distribution | |
| CN113576491A (en) | Method and system for automatically analyzing frequency domain characteristics and brain network based on resting EEG | |
| CN115311309A (en) | Method and system for identifying and extracting focus of nuclear magnetic resonance image | |
| CN112348785A (en) | Epileptic focus positioning method and system | |
| CN113017597A (en) | Dynamic high-order brain network analysis method | |
| CN113052800B (en) | Alzheimer disease image analysis method and device | |
| CN110689029A (en) | Method for determining sparsity of fMRI brain function connection network | |
| CN117137488B (en) | Auxiliary identification method for depression symptoms based on electroencephalogram data and facial expression images | |
| CN103006215A (en) | Brain functional region positioning method based on local smoothing regressions | |
| CN114159043A (en) | Brain function network abnormal brain node data detection method based on Qcut algorithm | |
| CN114926396B (en) | Mental disorder magnetic resonance image preliminary screening model construction method | |
| CN115659144A (en) | Sub-health personnel classification method, system and equipment based on fMRI multi-band analysis | |
| CN114723937A (en) | Method and system for classifying blood vessel surrounding gaps based on nuclear magnetic resonance image | |
| Elyounssi et al. | Uncovering and mitigating bias in large, automated MRI analyses of brain development | |
| CN110647870B (en) | Method for calculating approximate entropy of resting state fMRI data based on sliding window | |
| CN113317790A (en) | Method for searching neurobiological markers of autism in children based on persistent coherence | |
| CN112132790A (en) | DAC-GAN model construction method and application in mammary gland MR image | |
| CN115251889B (en) | Method for describing characteristics of dynamic connection network of functional magnetic resonance image | |
| CN117649403B (en) | Video-derived facial blood flow pulsation quantitative evaluation method, device and equipment for migraine | |
| CN113598791B (en) | Consciousness disturbance classification method based on time-space convolution neural network used by resting state electroencephalogram |
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 |